Impact of electronic health record clinical decision support on diabetes care: a randomized trial

Technology-supported shared decision-making in chronic conditions: A systematic review of randomized controlled trials

OBJECTIVES

To describe the role of patients with a chronic disease, healthcare professionals (HCPs) and technology in shared decision making (SDM) and the use of clinical decision support systems (CDSSs), and to evaluate the effectiveness of SDM and CDSSs interventions.

METHODS

Randomized controlled studies published between 2011 and 2021 were identified and screened independently by two reviewers, followed by data extraction and analysis. SDM elements and interactive styles were identified to shape the roles of patients, HCPs and technology.

RESULTS

Forty-three articles were identified and reported on 21 SDM-studies, 15 CDSS-studies, 2 studies containing both an SDM-tool and a CDSS, and 5 studies with other decision support components. SDM elements were mostly identified in SDM-tools and interactions styles were least common in the other decision support components.

CONCLUSIONS

Patients within the included RCTs mainly received information from SDM-tools and occasionally CDSSs when it concerns treatment strategies. HCPs provide and clarify information using SDM-tools and CDSSs. Technology provides interactions, which can support more active SDM. SDM-tools mostly showed evidence for positive effects on SDM outcomes, while CDSSs mostly demonstrated positive effects on clinical outcomes.

PRACTICE IMPLICATIONS

Technology-supported SDM has potential to optimize SDM when patients, HCPs and technology collaborate well together.

The Development of the Municipal Registry of People with Diabetes in Porto Alegre, Brazil

Background/Objective: Diabetes registries that enhance surveillance and improve medical care are uncommon in low- and middle-income countries, where most of the diabetes burden lies. We aimed to describe the methodological and technical aspects adopted in the development of a municipal registry of people with diabetes using local and national Brazilian National Health System databases. Methods: We obtained data between July 2018 and June 2021 based on eight databases covering primary care, specialty and emergency consultations, medication dispensing, outpatient exam management, hospitalizations, and deaths. We identified diabetes using the International Classification of Disease (ICD), International Classification of Primary Care (ICPC), medications for diabetes, hospital codes for the treatment of diabetes complications, and exams for diabetes management. Results: After data processing and database merging using deterministic and probabilistic linkage, we identified 73,185 people with diabetes. Considering that 1.33 million people live in Porto Alegre, the registry captured 5.5% of the population. Conclusions: With additional data processing, the registry can reveal information on the treatment and outcomes of people with diabetes who are receiving publicly financed care in Porto Alegre. It will provide metrics for epidemiologic surveillance, such as the incidence, prevalence, rates, and trends of complications and causes of mortality; identify inadequacies; and provide information. It will enable healthcare providers to monitor the quality of care, identify inadequacies, and provide feedback as needed.

Machine learning for healthcare that matters: Reorienting from technical novelty to equitable impact

Despite significant technical advances in machine learning (ML) over the past several years, the tangible impact of this technology in healthcare has been limited. This is due not only to the particular complexities of healthcare, but also due to structural issues in the machine learning for healthcare (MLHC) community which broadly reward technical novelty over tangible, equitable impact. We structure our work as a healthcare-focused echo of the 2012 paper "Machine Learning that Matters", which highlighted such structural issues in the ML community at large, and offered a series of clearly defined "Impact Challenges" to which the field should orient itself. Drawing on the expertise of a diverse and international group of authors, we engage in a narrative review and examine issues in the research background environment, training processes, evaluation metrics, and deployment protocols which act to limit the real-world applicability of MLHC. Broadly, we seek to distinguish between machine learning ON healthcare data and machine learning FOR healthcare-the former of which sees healthcare as merely a source of interesting technical challenges, and the latter of which regards ML as a tool in service of meeting tangible clinical needs. We offer specific recommendations for a series of stakeholders in the field, from ML researchers and clinicians, to the institutions in which they work, and the governments which regulate their data access.

A CKD Clinical Decision Support System: A Cluster Randomized Clinical Trial in Primary Care Clinics

Rationale & Objective

The study aimed to develop, implement, and evaluate a clinical decision support (CDS) system for chronic kidney disease (CKD) in a primary care setting, with the goal of improving CKD care in adults.

Study Design

This was a cluster randomized trial.

Setting & Participants

A total of 32 Midwestern primary care clinics were randomly assigned to either receive usual care or CKD-CDS intervention. Between April 2019 and March 2020, we enrolled 6,420 patients aged 18-75 years with laboratory-defined glomerular filtration rate categories of CKD Stage G3 and G4, and 1 or more of 6 CKD care gaps: absence of a CKD diagnosis, suboptimal blood pressure or glycated hemoglobin levels, indication for angiotensin-converting enzyme inhibitor or angiotensin receptor blocker but not prescribed, a nonsteroidal anti-inflammatory agent on the active medication list, or indication for a nephrology referral.

Intervention

The CKD-CDS provided personalized suggestions for CKD care improvement opportunities directed to both patients and clinicians at primary care encounters.

Outcomes

We assessed the proportion of patients meeting each of 6 CKD-CDS quality metrics representing care gap resolution after 18 months.

Results

The adjusted proportions of patients meeting quality metrics in CKD-CDS versus usual care were as follows: CKD diagnosis documented (26.6% vs 21.8%; risk ratio [RR], 1.17; 95% CI, 0.91-1.51); angiotensin-converting enzyme inhibitor or angiotensin receptor blocker prescribed (15.9% vs 16.1%; RR, 0.95; 95% CI, 0.76-1.18); blood pressure control (20.4% vs 20.2%; RR, 0.98; 95% CI, 0.84-1.15); glycated hemoglobin level control (21.4% vs 22.1%; RR, 1.00; 95% CI, 0.80-1.24); nonsteroidal anti-inflammatory agent not on the active medication list (51.5% vs 50.4%; RR, 1.03; 95% CI, 0.90-1.17); and referral or visit to a nephrologist (38.7% vs 36.1%; RR, 1.02; 95% CI, 0.79-1.32).

Limitations

We encountered an overall reduction in expected primary care encounters and obstacles to point-of-care CKD-CDS utilization because of the coronavirus disease 2019 pandemic.

Conclusions

The CKD-CDS intervention did not lead to a significant improvement in CKD quality metrics. The challenges to CDS use during the coronavirus disease 2019 pandemic likely influenced these results.

Funding

National Institute of Diabetes and Digestive and Kidney Diseases (R18DK118463).

Trial Registration

clinicaltrials.gov Identifier: NCT03890588.

Decision aids for people facing health treatment or screening decisions

BACKGROUND

Patient decision aids are interventions designed to support people making health decisions. At a minimum, patient decision aids make the decision explicit, provide evidence-based information about the options and associated benefits/harms, and help clarify personal values for features of options. This is an update of a Cochrane review that was first published in 2003 and last updated in 2017.

OBJECTIVES

To assess the effects of patient decision aids in adults considering treatment or screening decisions using an integrated knowledge translation approach.

SEARCH METHODS

We conducted the updated search for the period of 2015 (last search date) to March 2022 in CENTRAL, MEDLINE, Embase, PsycINFO, EBSCO, and grey literature. The cumulative search covers database origins to March 2022.

SELECTION CRITERIA

We included published randomized controlled trials comparing patient decision aids to usual care. Usual care was defined as general information, risk assessment, clinical practice guideline summaries for health consumers, placebo intervention (e.g. information on another topic), or no intervention.

DATA COLLECTION AND ANALYSIS

Two authors independently screened citations for inclusion, extracted intervention and outcome data, and assessed risk of bias using the Cochrane risk of bias tool. Primary outcomes, based on the International Patient Decision Aid Standards (IPDAS), were attributes related to the choice made (informed values-based choice congruence) and the decision-making process, such as knowledge, accurate risk perceptions, feeling informed, clear values, participation in decision-making, and adverse events. Secondary outcomes were choice, confidence in decision-making, adherence to the chosen option, preference-linked health outcomes, and impact on the healthcare system (e.g. consultation length). We pooled results using mean differences (MDs) and risk ratios (RRs) with 95% confidence intervals (CIs), applying a random-effects model. We conducted a subgroup analysis of 105 studies that were included in the previous review version compared to those published since that update (n = 104 studies). We used Grading of Recommendations Assessment, Development, and Evaluation (GRADE) to assess the certainty of the evidence.

MAIN RESULTS

This update added 104 new studies for a total of 209 studies involving 107,698 participants. The patient decision aids focused on 71 different decisions. The most common decisions were about cardiovascular treatments (n = 22 studies), cancer screening (n = 17 studies colorectal, 15 prostate, 12 breast), cancer treatments (e.g. 15 breast, 11 prostate), mental health treatments (n = 10 studies), and joint replacement surgery (n = 9 studies). When assessing risk of bias in the included studies, we rated two items as mostly unclear (selective reporting: 100 studies; blinding of participants/personnel: 161 studies), due to inadequate reporting. Of the 209 included studies, 34 had at least one item rated as high risk of bias. There was moderate-certainty evidence that patient decision aids probably increase the congruence between informed values and care choices compared to usual care (RR 1.75, 95% CI 1.44 to 2.13; 21 studies, 9377 participants). Regarding attributes related to the decision-making process and compared to usual care, there was high-certainty evidence that patient decision aids result in improved participants' knowledge (MD 11.90/100, 95% CI 10.60 to 13.19; 107 studies, 25,492 participants), accuracy of risk perceptions (RR 1.94, 95% CI 1.61 to 2.34; 25 studies, 7796 participants), and decreased decisional conflict related to feeling uninformed (MD -10.02, 95% CI -12.31 to -7.74; 58 studies, 12,104 participants), indecision about personal values (MD -7.86, 95% CI -9.69 to -6.02; 55 studies, 11,880 participants), and proportion of people who were passive in decision-making (clinician-controlled) (RR 0.72, 95% CI 0.59 to 0.88; 21 studies, 4348 participants). For adverse outcomes, there was high-certainty evidence that there was no difference in decision regret between the patient decision aid and usual care groups (MD -1.23, 95% CI -3.05 to 0.59; 22 studies, 3707 participants). Of note, there was no difference in the length of consultation when patient decision aids were used in preparation for the consultation (MD -2.97 minutes, 95% CI -7.84 to 1.90; 5 studies, 420 participants). When patient decision aids were used during the consultation with the clinician, the length of consultation was 1.5 minutes longer (MD 1.50 minutes, 95% CI 0.79 to 2.20; 8 studies, 2702 participants). We found the same direction of effect when we compared results for patient decision aid studies reported in the previous update compared to studies conducted since 2015.

AUTHORS' CONCLUSIONS

Compared to usual care, across a wide variety of decisions, patient decision aids probably helped more adults reach informed values-congruent choices. They led to large increases in knowledge, accurate risk perceptions, and an active role in decision-making. Our updated review also found that patient decision aids increased patients' feeling informed and clear about their personal values. There was no difference in decision regret between people using decision aids versus those receiving usual care. Further studies are needed to assess the impact of patient decision aids on adherence and downstream effects on cost and resource use.

Protocol of a patient randomized clinical trial to improve medication adherence in primary care

BACKGROUND

Enhanced awareness of poor medication adherence could improve patient care. This article describes the original and adapted protocols of a randomized trial to improve medication adherence for cardiometabolic conditions.

METHODS

The original protocol entailed a cluster randomized trial of 28 primary care clinics allocated to either (i) medication adherence enhanced chronic disease care clinical decision support (eCDC-CDS) integrated within the electronic health record (EHR) or (ii) usual care (non-enhanced CDC-CDS). Enhancements comprised (a) electronic interfaces printed for patients and clinicians at primary care encounters that encouraged discussion about specific medication adherence issues that were identified, and (b) pharmacist phone outreach. Study subjects were individuals who at an index visit were aged 18-74 years and not at evidence-based care goals for hypertension (HTN), diabetes mellitus (DM), or lipid management, along with low medication adherence (proportion of days covered [PDC] <80%) for a corresponding medication. The primary study outcomes were improved medication adherence and clinical outcomes (BP and A1C) at 12 months. Protocol adaptation became imperative in response to major implementation challenges: (a) the availability of EHR system-wide PDC calculations that superseded our ability to limit PDC adherence information solely to intervention clinics; (b) the unforeseen closure of pharmacies committed to conducting the pharmacist outreach; and (c) disruptions and clinic closures due to the Covid-19 pandemic.

CONCLUSION

This manuscript details the protocol of a study to assess whether enhanced awareness of medication adherence issues in primary care settings could improve patient outcomes. The need for protocol adaptation arose in response to multiple implementation challenges.

Applications of Clinical Decision Support Systems in Diabetes Care: Scoping Review

BACKGROUND

Providing comprehensive and individualized diabetes care remains a significant challenge in the face of the increasing complexity of diabetes management and a lack of specialized endocrinologists to support diabetes care. Clinical decision support systems (CDSSs) are progressively being used to improve diabetes care, while many health care providers lack awareness and knowledge about CDSSs in diabetes care. A comprehensive analysis of the applications of CDSSs in diabetes care is still lacking.

OBJECTIVE

This review aimed to summarize the research landscape, clinical applications, and impact on both patients and physicians of CDSSs in diabetes care.

METHODS

We conducted a scoping review following the Arksey and O'Malley framework. A search was conducted in 7 electronic databases to identify the clinical applications of CDSSs in diabetes care up to June 30, 2022. Additional searches were conducted for conference abstracts from the period of 2021-2022. Two researchers independently performed the screening and data charting processes.

RESULTS

Of 11,569 retrieved studies, 85 (0.7%) were included for analysis. Research interest is growing in this field, with 45 (53%) of the 85 studies published in the past 5 years. Among the 58 (68%) out of 85 studies disclosing the underlying decision-making mechanism, most CDSSs (44/58, 76%) were knowledge based, while the number of non-knowledge-based systems has been increasing in recent years. Among the 81 (95%) out of 85 studies disclosing application scenarios, the majority of CDSSs were used for treatment recommendation (63/81, 78%). Among the 39 (46%) out of 85 studies disclosing physician user types, primary care physicians (20/39, 51%) were the most common, followed by endocrinologists (15/39, 39%) and nonendocrinology specialists (8/39, 21%). CDSSs significantly improved patients' blood glucose, blood pressure, and lipid profiles in 71% (45/63), 67% (12/18), and 38% (8/21) of the studies, respectively, with no increase in the risk of hypoglycemia.

CONCLUSIONS

CDSSs are both effective and safe in improving diabetes care, implying that they could be a potentially reliable assistant in diabetes care, especially for physicians with limited experience and patients with limited access to medical resources.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.37766/inplasy2022.9.0061.

Universal health coverage in China part 2: addressing challenges and recommendations

This report analyses the underlying causes of China's achievements and gaps in universal health coverage over the past 2 decades and proposes policy recommendations for advancing universal health coverage by 2030. Although strong political commitment and targeted financial investment have produced positive outcomes in reproductive, maternal, newborn, and child health and infectious diseases, a fragmented and hospital-centric delivery system, rising health-care costs, shallow benefit coverage of health insurance schemes, and little integration of health in all policies have restricted China's ability to effectively prevent and control chronic disease and provide adequate financial risk protection, especially for lower-income households. Here, we used a health system conceptual framework and we propose a set of feasible policy recommendations that draw from international experiences and first-hand knowledge of China's unique institutional landscape. Our six recommendations are: instituting a primary care-focused integrated delivery system that restructures provider incentives and accountability mechanisms to prioritise prevention; leveraging digital tools to support health behaviour change; modernising information campaigns; improving financial protection through insurance reforms; promoting a health in all policy; and developing a domestic monitoring framework with refined tracer indicators that reflects China's disease burden.

Harnessing the power of clinical decision support systems: challenges and opportunities

Clinical decision support systems (CDSSs) are increasingly integrated into healthcare settings to improve patient outcomes, reduce medical errors and enhance clinical efficiency by providing clinicians with evidence-based recommendations at the point of care. However, the adoption and optimisation of these systems remain a challenge. This review aims to provide an overview of the current state of CDSS, discussing their development, implementation, benefits, limitations and future directions. We also explore the potential for enhancing their effectiveness and provide an outlook for future developments in this field. There are several challenges in CDSS implementation, including data privacy concerns, system integration and clinician acceptance. While CDSS have demonstrated significant potential, their adoption and optimisation remain a challenge.

Does Clinical Decision Support Increase Appropriate Medication Prescribing for Cardiovascular Risk Reduction?

PURPOSE

To assess the impact of a clinical decision support (CDS) system's recommendations on prescribing patterns targeting cardiovascular disease (CVD) when the recommendations are prioritized in order from greatest to least benefit toward overall CVD risk reduction.

METHODS

Secondary analysis of trial data from September 20, 2018, to March 15, 2020, where 70 community health center clinics were cluster-randomized to the CDS intervention (42 clinics; 8 organizations) or control group (28 clinics; 7 organizations). Included patients were medication-naïve and aged 40 to 75 years with ≥1 uncontrolled cardiovascular disease risk factor, with known diabetes or cardiovascular disease, or ≥10% 10-year reversible CVD risk.

RESULTS

Among eligible encounters with 29,771 patients, the probability of prescribing a medication targeting hypertension was greater at intervention clinic encounters when CDS was used (34.9% [95% CI, 31.5 to 38.3]) versus dismissed (29.6% [95% CI, 26.7 to 32.6]; P < .001), but not when compared with control clinic encounters (34.9% [95% CI, 31.1 to 38.7]; P = .998). Prescribing for dyslipidemia was significantly higher at intervention encounters where the CDS system was used (11.3% [95% CI, 9.3 to 13.3]) compared with dismissed (7.7% [95% CI, 6.1 to 9.3]; P = .003) and to control encounters (8.7% [95% CI, 7.0 to 10.4]; P = .044); smoking cessation medication showed a similar pattern. Except for dyslipidemia, prescribing rates increased according to their prioritization.

CONCLUSIONS

Use of this CDS system was associated with significantly higher prescribing targeting most cardiovascular risk factors. These results highlight how displaying prioritized actions to reduce reversible CVD risk could improve risk management.

TRIAL REGISTRATION

ClinicalTrials.gov, NCT03001713, https://clinicaltrials.gov/.

Evaluation of a Digital Decision Support System to Integrate Type 2 Diabetes Mellitus and Periodontitis Care: Case-Vignette Study in Simulated Environments

BACKGROUND

As highlighted by the recent World Health Organization Oral Health Resolution, there is an urgent need to better integrate primary and oral health care. Despite evidence and guidelines substantiating the relevance of integrating type 2 diabetes mellitus (T2DM) and periodontitis care, the fragmentation of primary and oral health care persists.

OBJECTIVE

This paper reports on the evaluation of a prototype digital decision support system (DSS) that was developed to enhance the integration of T2DM and periodontitis care.

METHODS

The effects of the prototype DSS were assessed in web-based simulated environments, using 2 different sets of case vignettes in combination with evaluation surveys among 202 general dental practitioners (GDPs) and 206 general practitioners (GPs). Each participant evaluated 3 vignettes, one of which, chosen at random, was assisted by the DSS. Logistic regression analyses were conducted at the participant and case levels.

RESULTS

Under DSS assistance, GPs had 8.3 (95% CI 4.32-16.03) times higher odds of recommending a GDP visit. There was no significant impact of DSS assistance on GP advice about common risk factors for T2DM and periodontal disease. GDPs had 4.3 (95% CI 2.08-9.04) times higher odds of recommending a GP visit, 1.6 (95% CI 1.03-2.33) times higher odds of giving advice on disease correlations, and 3.2 (95% CI 1.63-6.35) times higher odds of asking patients about their glycated hemoglobin value.

CONCLUSIONS

The findings of this study provide a proof of concept for a digital DSS to integrate T2DM and periodontal care. Future updating and testing is warranted to continuously enhance the functionalities of the DSS in terms of interoperability with various types of data sources and diagnostic devices; incorporation of other (oral) health dimensions; application in various settings, including via telemedicine; and further customization of end-user interfaces.

Effects of Non-monetary Incentives in Physician Groups-A Systematic Review

Objectives: Healthcare expenditures in western countries have been rising for many years. This leads many countries to develop and test new reimbursement systems. A systematic review about monetary incentives in group settings indicated that a sole focus on monetary aspects does not necessarily result in better care at lower costs. Hence, this systematic review aims to describe the effects of non- monetary incentives in physician groups. Methods: We searched the databases MEDLINE (PubMed), The Cochrane Library, CINAHL, PsycINFO, EconLit, and ISI Web of Science. Grey literature search, reference lists, and authors' personal collection provided additional sources. Results: Overall, we included 36 studies. We identified 4 categories of interventions related to non-monetary incentives. In particular, the category of decision support achieved promising results. However, design features vary among different decision support systems. To enable effective design, we provide an overview of the features applied by the studies included. Conclusions: Not every type of non-monetary incentive has a positive impact on quality of care in physician group settings. Thus, creating awareness among decision-makers regarding this matter and extending research on this topic can contribute to preventing implementation of ineffective incentives, and consequently, allocate resources towards tools that add value.

Feasibility study of a clinical decision support system for polymedicated patients in primary care

Age-related changes in pharmacokinetics and pharmacodynamics, multimorbidity, frailty, and cognitive impairment represent challenges for drug treatments. Moreover, older adults are commonly exposed to polypharmacy, leading to increased risk of drug interactions and related adverse events, and higher costs for the healthcare systems. Thus, the complex task of prescribing medications to older polymedicated patients encourages the use of Clinical Decision Support Systems (CDSS). This paper evaluates the CDSS miniQ for identifying potentially inappropriate prescribing in poly-medicated older adults and assesses the usability and acceptability of the system in health care professionals, patients, and caregivers. The results of the study demonstrate that the miniQ system was useful for Primary Care physicians in significantly improving prescription, thereby reducing potentially inappropriate medication prescriptions for elderly patients. Additionally, the system was found to be beneficial for patients and their caregivers in understanding their medications, as well as usable and acceptable among healthcare professionals, patients, and caregivers, highlighting the potential to improve the prescription process and reduce errors, and enhancing the quality of care for elderly patients with polypharmacy, reducing adverse drug events, and improving medication management.

Quality improvement strategies for diabetes care: Effects on outcomes for adults living with diabetes

BACKGROUND

There is a large body of evidence evaluating quality improvement (QI) programmes to improve care for adults living with diabetes. These programmes are often comprised of multiple QI strategies, which may be implemented in various combinations. Decision-makers planning to implement or evaluate a new QI programme, or both, need reliable evidence on the relative effectiveness of different QI strategies (individually and in combination) for different patient populations.

OBJECTIVES

To update existing systematic reviews of diabetes QI programmes and apply novel meta-analytical techniques to estimate the effectiveness of QI strategies (individually and in combination) on diabetes quality of care.

SEARCH METHODS

We searched databases (CENTRAL, MEDLINE, Embase and CINAHL) and trials registers (ClinicalTrials.gov and WHO ICTRP) to 4 June 2019. We conducted a top-up search to 23 September 2021; we screened these search results and 42 studies meeting our eligibility criteria are available in the awaiting classification section.

SELECTION CRITERIA

We included randomised trials that assessed a QI programme to improve care in outpatient settings for people living with diabetes. QI programmes needed to evaluate at least one system- or provider-targeted QI strategy alone or in combination with a patient-targeted strategy. - System-targeted: case management (CM); team changes (TC); electronic patient registry (EPR); facilitated relay of clinical information (FR); continuous quality improvement (CQI). - Provider-targeted: audit and feedback (AF); clinician education (CE); clinician reminders (CR); financial incentives (FI). - Patient-targeted: patient education (PE); promotion of self-management (PSM); patient reminders (PR). Patient-targeted QI strategies needed to occur with a minimum of one provider or system-targeted strategy.

DATA COLLECTION AND ANALYSIS

We dual-screened search results and abstracted data on study design, study population and QI strategies. We assessed the impact of the programmes on 13 measures of diabetes care, including: glycaemic control (e.g. mean glycated haemoglobin (HbA1c)); cardiovascular risk factor management (e.g. mean systolic blood pressure (SBP), low-density lipoprotein cholesterol (LDL-C), proportion of people living with diabetes that quit smoking or receiving cardiovascular medications); and screening/prevention of microvascular complications (e.g. proportion of patients receiving retinopathy or foot screening); and harms (e.g. proportion of patients experiencing adverse hypoglycaemia or hyperglycaemia). We modelled the association of each QI strategy with outcomes using a series of hierarchical multivariable meta-regression models in a Bayesian framework. The previous version of this review identified that different strategies were more or less effective depending on baseline levels of outcomes. To explore this further, we extended the main additive model for continuous outcomes (HbA1c, SBP and LDL-C) to include an interaction term between each strategy and average baseline risk for each study (baseline thresholds were based on a data-driven approach; we used the median of all baseline values reported in the trials). Based on model diagnostics, the baseline interaction models for HbA1c, SBP and LDL-C performed better than the main model and are therefore presented as the primary analyses for these outcomes. Based on the model results, we qualitatively ordered each QI strategy within three tiers (Top, Middle, Bottom) based on its magnitude of effect relative to the other QI strategies, where 'Top' indicates that the QI strategy was likely one of the most effective strategies for that specific outcome. Secondary analyses explored the sensitivity of results to choices in model specification and priors.  Additional information about the methods and results of the review are available as Appendices in an online repository. This review will be maintained as a living systematic review; we will update our syntheses as more data become available.

MAIN RESULTS

We identified 553 trials (428 patient-randomised and 125 cluster-randomised trials), including a total of 412,161 participants. Of the included studies, 66% involved people living with type 2 diabetes only. Participants were 50% female and the median age of participants was 58.4 years. The mean duration of follow-up was 12.5 months. HbA1c was the commonest reported outcome; screening outcomes and outcomes related to cardiovascular medications, smoking and harms were reported infrequently. The most frequently evaluated QI strategies across all study arms were PE, PSM and CM, while the least frequently evaluated QI strategies included AF, FI and CQI. Our confidence in the evidence is limited due to a lack of information on how studies were conducted.  Four QI strategies (CM, TC, PE, PSM) were consistently identified as 'Top' across the majority of outcomes. All QI strategies were ranked as 'Top' for at least one key outcome. The majority of effects of individual QI strategies were modest, but when used in combination could result in meaningful population-level improvements across the majority of outcomes. The median number of QI strategies in multicomponent QI programmes was three.  Combinations of the three most effective QI strategies were estimated to lead to the below effects:  - PR + PSM + CE: decrease in HbA1c by 0.41% (credibility interval (CrI) -0.61 to -0.22) when baseline HbA1c < 8.3%; - CM + PE + EPR: decrease in HbA1c by 0.62% (CrI -0.84 to -0.39) when baseline HbA1c > 8.3%;  - PE + TC + PSM: reduction in SBP by 2.14 mmHg (CrI -3.80 to -0.52) when baseline SBP < 136 mmHg; - CM + TC + PSM: reduction in SBP by 4.39 mmHg (CrI -6.20 to -2.56) when baseline SBP > 136 mmHg;  - TC + PE + CM: LDL-C lowering of 5.73 mg/dL (CrI -7.93 to -3.61) when baseline LDL < 107 mg/dL; - TC + CM + CR: LDL-C lowering by 5.52 mg/dL (CrI -9.24 to -1.89) when baseline LDL > 107 mg/dL. Assuming a baseline screening rate of 50%, the three most effective QI strategies were estimated to lead to an absolute improvement of 33% in retinopathy screening (PE + PR + TC) and 38% absolute increase in foot screening (PE + TC + Other).

AUTHORS' CONCLUSIONS

There is a significant body of evidence about QI programmes to improve the management of diabetes. Multicomponent QI programmes for diabetes care (comprised of effective QI strategies) may achieve meaningful population-level improvements across the majority of outcomes. For health system decision-makers, the evidence summarised in this review can be used to identify strategies to include in QI programmes. For researchers, this synthesis identifies higher-priority QI strategies to examine in further research regarding how to optimise their evaluation and effects. We will maintain this as a living systematic review.

Predicting Visit Cost of Obstructive Sleep Apnea Using Electronic Healthcare Records With Transformer

BACKGROUND

Obstructive sleep apnea (OSA) is growing increasingly prevalent in many countries as obesity rises. Sufficient, effective treatment of OSA entails high social and financial costs for healthcare.

OBJECTIVE

For treatment purposes, predicting OSA patients' visit expenses for the coming year is crucial. Reliable estimates enable healthcare decision-makers to perform careful fiscal management and budget well for effective distribution of resources to hospitals. The challenges created by scarcity of high-quality patient data are exacerbated by the fact that just a third of those data from OSA patients can be used to train analytics models: only OSA patients with more than 365 days of follow-up are relevant for predicting a year's expenditures.

METHODS AND PROCEDURES

The authors propose a translational engineering method applying two Transformer models, one for augmenting the input via data from shorter visit histories and the other predicting the costs by considering both the material thus enriched and cases with more than a year's follow-up. This method effectively adapts state-of-the-art Transformer models to create practical cost prediction solutions that can be implemented in OSA management, potentially enhancing patient care and resource allocation.

RESULTS

The two-model solution permits putting the limited body of OSA patient data to productive use. Relative to a single-Transformer solution using only a third of the high-quality patient data, the solution with two models improved the prediction performance's [Formula: see text] from 88.8% to 97.5%. Even using baseline models with the model-augmented data improved the [Formula: see text] considerably, from 61.6% to 81.9%.

CONCLUSION

The proposed method makes prediction with the most of the available high-quality data by carefully exploiting details, which are not directly relevant for answering the question of the next year's likely expenditure. Clinical and Translational Impact Statement: Public Health- Lack of high-quality source data hinders data-driven analytics-based research in healthcare. The paper presents a method that couples data augmentation and prediction in cases of scant healthcare data.

Partner-developed electronic health record tools to facilitate social risk-informed care planning

OBJECTIVE

Increased social risk data collection in health care settings presents new opportunities to apply this information to improve patient outcomes. Clinical decision support (CDS) tools can support these applications. We conducted a participatory engagement process to develop electronic health record (EHR)-based CDS tools to facilitate social risk-informed care plan adjustments in community health centers (CHCs).

MATERIALS AND METHODS

We identified potential care plan adaptations through systematic reviews of hypertension and diabetes clinical guidelines. The results were used to inform an engagement process in which CHC staff and patients provided feedback on potential adjustments identified in the guideline reviews and on tool form and functions that could help CHC teams implement these suggested adjustments for patients with social risks.

RESULTS

Partners universally prioritized tools for social risk screening and documentation. Additional high-priority content included adjusting medication costs and changing follow-up plans based on reported social risks. Most content recommendations reflected partners' interests in encouraging provider-patient dialogue about care plan adaptations specific to patients' social needs. Partners recommended CDS tool functions such as alerts and shortcuts to facilitate and efficiently document social risk-informed care plan adjustments.

DISCUSSION AND CONCLUSION

CDS tools were designed to support CHC providers and staff to more consistently tailor care based on information about patients' social context and thereby enhance patients' ability to adhere to care plans. While such adjustments occur on an ad hoc basis in many care settings, these are among the first tools designed both to systematize and document these activities.

Adoption of shared decision-making and clinical decision support for reducing cardiovascular disease risk in community health centers

Objective

Electronic health record (EHR)-based shared decision-making (SDM) and clinical decision support (CDS) systems can improve cardiovascular disease (CVD) care quality and risk factor management. Use of the CV Wizard system showed a beneficial effect on high-risk community health center (CHC) patients' CVD risk within an effectiveness trial, but system adoption was low overall. We assessed which multi-level characteristics were associated with system use.

Materials and Methods

Analyses included 80 195 encounters with 17 931 patients with high CVD risk and/or uncontrolled risk factors at 42 clinics in September 2018-March 2020. Data came from the CV Wizard repository and EHR data, and a survey of 44 clinic providers. Adjusted, mixed-effects multivariate Poisson regression analyses assessed factors associated with system use. We included clinic- and provider-level clustering as random effects to account for nested data.

Results

Likelihood of system use was significantly higher in encounters with patients with higher CVD risk and at longer encounters, and lower when providers were >10 minutes behind schedule, among other factors. Survey participants reported generally high satisfaction with the system but were less likely to use it when there were time constraints or when rooming staff did not print the system output for the provider.

Discussion

CHC providers prioritize using this system for patients with the greatest CVD risk, when time permits, and when rooming staff make the information readily available. CHCs' financial constraints create substantial challenges to addressing barriers to improved system use, with health equity implications.

Conclusion

Research is needed on improving SDM and CDS adoption in CHCs.

Trial Registration

ClinicalTrials.gov, NCT03001713, https://clinicaltrials.gov/.

Ontologies Applied in Clinical Decision Support System Rules: Systematic Review

BACKGROUND

Clinical decision support systems (CDSSs) are important for the quality and safety of health care delivery. Although CDSS rules guide CDSS behavior, they are not routinely shared and reused.

OBJECTIVE

Ontologies have the potential to promote the reuse of CDSS rules. Therefore, we systematically screened the literature to elaborate on the current status of ontologies applied in CDSS rules, such as rule management, which uses captured CDSS rule usage data and user feedback data to tailor CDSS services to be more accurate, and maintenance, which updates CDSS rules. Through this systematic literature review, we aim to identify the frontiers of ontologies used in CDSS rules.

METHODS

The literature search was focused on the intersection of ontologies; clinical decision support; and rules in PubMed, the Association for Computing Machinery (ACM) Digital Library, and the Nursing & Allied Health Database. Grounded theory and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines were followed. One author initiated the screening and literature review, while 2 authors validated the processes and results independently. The inclusion and exclusion criteria were developed and refined iteratively.

RESULTS

CDSSs were primarily used to manage chronic conditions, alerts for medication prescriptions, reminders for immunizations and preventive services, diagnoses, and treatment recommendations among 81 included publications. The CDSS rules were presented in Semantic Web Rule Language, Jess, or Jena formats. Despite the fact that ontologies have been used to provide medical knowledge, CDSS rules, and terminologies, they have not been used in CDSS rule management or to facilitate the reuse of CDSS rules.

CONCLUSIONS

Ontologies have been used to organize and represent medical knowledge, controlled vocabularies, and the content of CDSS rules. So far, there has been little reuse of CDSS rules. More work is needed to improve the reusability and interoperability of CDSS rules. This review identified and described the ontologies that, despite their limitations, enable Semantic Web technologies and their applications in CDSS rules.

Chronic disease IMPACT (chronic disease early detection and improved management in primary care project): An Australian stepped wedge cluster randomised trial

Background

Interrelated chronic vascular diseases (chronic kidney disease (CKD), type 2 diabetes (T2D) and cardiovascular disease (CVD)) are common with high morbidity and mortality. This study aimed to assess if an electronic-technology-based quality improvement intervention in primary care could improve detection and management of people with and at risk of these diseases.

Methods

Stepped-wedge trial with practices randomised to commence intervention in one of five 16-week periods. Intervention included (1) electronic-technology tool extracting data from general practice electronic medical records and generating graphs and lists for audit; (2) education regarding chronic disease and the electronic-technology tool; (3) assistance with quality improvement audit plan development, benchmarking, monitoring and support. De-identified data analysis using R 3.5.1 conducted using Bayesian generalised linear mixed model with practice and time-specific random intercepts.

Results

At baseline, eight included practices had 37,946 active patients (attending practice ≥3 times within 2 years) aged ≥18 years. Intervention was associated with increased OR (95% CI) for: kidney health checks (estimated glomerular filtration rate, urine albumin:creatinine ratio (uACR) and blood pressure) in those at risk 1.34 (1.26-1.42); coded diagnosis of CKD 1.18 (1.09-1.27); T2D diagnostic testing (fasting glucose or HbA1c) in those at risk 1.15 (1.08-1.23); uACR in patients with T2D 1.78 (1.56-2.05). Documented eye checks within recommended frequency in patients with T2D decreased 0.85 (0.77-0.96). There were no significant changes in other assessed variables.

Conclusions

This electronic-technology-based intervention in primary care has potential to help translate guidelines into practice but requires further refining to achieve widespread improvements across the interrelated chronic vascular diseases.

A randomized controlled trial of an intervention to reduce stigma toward people with opioid use disorder among primary care clinicians

BACKGROUND

Many primary care clinicians (PCCs) hold stigma toward people with opioid use disorder (OUD), which may be a barrier to care. Few interventions exist to address PCC stigma toward people with OUD. This study examined whether an online training incorporating patient narratives reduced PCCs' stigma toward people with OUD (primary) and increased intentions to treat people with OUD compared to an attention-control training (secondary).

METHODS

PCCs from 15 primary care clinics were invited to complete a 30 min online training for an electronic health record-embedded clinical decision support (CDS) tool that alerts PCCs to screen, diagnose, and treat people with OUD. PCCs were randomized to receive a stigma-reduction version of the training with patient narrative videos or a control training without patient narratives and were blinded to group assignment. Immediately after the training, PCCs completed surveys of stigma towards people with OUD and intentions and willingness to treat OUD. CDS tool use was monitored for 6 months. Analyses included independent samples t-tests, Pearson correlations, and logistic regression.

RESULTS

A total of 162 PCCs were randomized; 88 PCCs (58% female; 68% white) completed the training (Stigma = 48; Control = 40) and were included in analyses. There was no significant difference between intervention and control groups for stigma (t = - 0.48, p = .64, Cohen's d = - 0.11), intention to get waivered (t = 1.11, p = .27, d = 0.26), or intention to prescribe buprenorphine if a waiver were no longer required (t = 0.90, p = 0.37, d = 0.21). PCCs who reported greater stigma reported lower intentions both to get waivered (r = - 0.25, p = 0.03) and to prescribe buprenorphine with no waiver (r = - 0.25, p = 0.03). Intervention group and self-reported stigma were not significantly related to CDS tool use.

CONCLUSIONS

Stigma toward people with OUD may require more robust intervention than this brief training was able to accomplish. However, stigma was related to lower intentions to treat people with OUD, suggesting stigma acts as a barrier to care. Future work should identify effective interventions to reduce stigma among PCCs.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04867382. Registered 30 April 2021-Retrospectively registered, https://clinicaltrials.gov/ct2/show/NCT04867382.

Clinician perceptions of a clinical decision support system to reduce cardiovascular risk among prediabetes patients in a predominantly rural healthcare system

Background

The early detection and management of uncontrolled cardiovascular risk factors among prediabetes patients can prevent cardiovascular disease (CVD). Prediabetes increases the risk of CVD, which is a leading cause of death in the United States. CVD clinical decision support (CDS) in primary care settings has the potential to reduce cardiovascular risk in patients with prediabetes while potentially saving clinicians time. The objective of this study is to understand primary care clinician (PCC) perceptions of a CDS system designed to reduce CVD risk in adults with prediabetes.

Methods

We administered pre-CDS implementation (6/30/2016 to 8/25/2016) (n = 183, 61% response rate) and post-CDS implementation (6/12/2019 to 8/7/2019) (n = 131, 44.5% response rate) independent cross-sectional electronic surveys to PCCs at 36 randomized primary care clinics participating in a federally funded study of a CVD risk reduction CDS tool. Surveys assessed PCC demographics, experiences in delivering prediabetes care, perceptions of CDS impact on shared decision making, perception of CDS impact on control of major CVD risk factors, and overall perceptions of the CDS tool when managing cardiovascular risk.

Results

We found few significant differences when comparing pre- and post-implementation responses across CDS intervention and usual care (UC) clinics. A majority of PCCs felt well-prepared to discuss CVD risk factor control with patients both pre- and post-implementation. About 73% of PCCs at CDS intervention clinics agreed that the CDS helped improve risk control, 68% reported the CDS added value to patient clinic visits, and 72% reported they would recommend use of this CDS system to colleagues. However, most PCCs disagreed that the CDS saves time talking about preventing diabetes or CVD, and most PCCs also did not find the clinical domains useful, nor did PCCs believe that the clinical domains were useful in getting patients to take action. Finally, only about 38% reported they were satisfied with the CDS.

Conclusions

These results improve our understanding of CDS user experience and can be used to guide iterative improvement of the CDS. While most PCCs agreed the CDS improves CVD and diabetes risk factor control, they were generally not satisfied with the CDS. Moreover, only 40–50% agreed that specific suggestions on clinical domains helped patients to take action. In spite of this, an overwhelming majority reported they would recommend the CDS to colleagues, pointing for the need to improve upon the current CDS.

Trial registration: NCT02759055 03/05/2016.

Bolstering the Business Case for Adoption of Shared Decision-Making Systems in Primary Care: Randomized Controlled Trial

BACKGROUND

Limited budgets may often constrain the ability of health care delivery systems to adopt shared decision-making (SDM) systems designed to improve clinical encounters with patients and quality of care.

OBJECTIVE

This study aimed to assess the impact of an SDM system shown to improve diabetes and cardiovascular patient outcomes on factors affecting revenue generation in primary care clinics.

METHODS

As part of a large multisite clinic randomized controlled trial (RCT), we explored the differences in 1 care system between clinics randomized to use an SDM intervention (n=8) versus control clinics (n=9) regarding the (1) likelihood of diagnostic coding for cardiometabolic conditions using the 10th Revision of the International Classification of Diseases (ICD-10) and (2) current procedural terminology (CPT) billing codes.

RESULTS

At all 24,138 encounters with care gaps targeted by the SDM system, the proportion assigned high-complexity CPT codes for level of service 5 was significantly higher at the intervention clinics (6.1%) compared to that in the control clinics (2.9%), with P<.001 and adjusted odds ratio (OR) 1.64 (95% CI 1.02-2.61). This was consistently observed across the following specific care gaps: diabetes with glycated hemoglobin A_1c (HbA_1c)>8% (n=8463), 7.2% vs 3.4%, P<.001, and adjusted OR 1.93 (95% CI 1.01-3.67); blood pressure above goal (n=8515), 6.5% vs 3.7%, P<.001, and adjusted OR 1.42 (95% CI 0.72-2.79); suboptimal statin management (n=17,765), 5.8% vs 3%, P<.001, and adjusted OR 1.41 (95% CI 0.76-2.61); tobacco dependency (n=7449), 7.5% vs. 3.4%, P<.001, and adjusted OR 2.14 (95% CI 1.31-3.51); BMI >30 kg/m² (n=19,838), 6.2% vs 2.9%, P<.001, and adjusted OR 1.45 (95% CI 0.75-2.8). Compared to control clinics, intervention clinics assigned ICD-10 diagnosis codes more often for observed cardiometabolic conditions with care gaps, although the difference did not reach statistical significance.

CONCLUSIONS

In this randomized study, use of a clinically effective SDM system at encounters with care gaps significantly increased the proportion of encounters assigned high-complexity (level 5) CPT codes, and it was associated with a nonsignificant increase in assigning ICD-10 codes for observed cardiometabolic conditions.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02451670; https://clinicaltrials.gov/ct2/show/NCT02451670.

Design, effectiveness, and economic outcomes of contemporary chronic disease clinical decision support systems: a systematic review and meta-analysis

Objectives

Electronic health record-based clinical decision support (CDS) has the potential to improve health outcomes. This systematic review investigates the design, effectiveness, and economic outcomes of CDS targeting several common chronic diseases.

Material and Methods

We conducted a search in PubMed (Medline), EBSCOHOST (CINAHL, APA PsychInfo, EconLit), and Web of Science. We limited the search to studies from 2011 to 2021. Studies were included if the CDS was electronic health record-based and targeted one or more of the following chronic diseases: cardiovascular disease, diabetes, chronic kidney disease, hypertension, and hypercholesterolemia. Studies with effectiveness or economic outcomes were considered for inclusion, and a meta-analysis was conducted.

Results

The review included 76 studies with effectiveness outcomes and 9 with economic outcomes. Of the effectiveness studies, 63% described a positive outcome that favored the CDS intervention group. However, meta-analysis demonstrated that effect sizes were heterogenous and small, with limited clinical and statistical significance. Of the economic studies, most full economic evaluations (n = 5) used a modeled analysis approach. Cost-effectiveness of CDS varied widely between studies, with an estimated incremental cost-effectiveness ratio ranging between USD$2192 to USD$151 955 per QALY.

Conclusion

We summarize contemporary chronic disease CDS designs and evaluation results. The effectiveness and cost-effectiveness results for CDS interventions are highly heterogeneous, likely due to differences in implementation context and evaluation methodology. Improved quality of reporting, particularly from modeled economic evaluations, would assist decision makers to better interpret and utilize results from these primary research studies.

Registration

PROSPERO (CRD42020203716)

Evaluating a Prototype Clinical Decision Support Tool for Chronic Pain Treatment in Primary Care

OBJECTIVES

 The Chronic Pain Treatment Tracker (Tx Tracker) is a prototype decision support tool to aid primary care clinicians when caring for patients with chronic noncancer pain. This study evaluated clinicians' perceived utility of Tx Tracker in meeting information needs and identifying treatment options, and preferences for visual design.

METHODS

 We conducted 12 semi-structured interviews with primary care clinicians from four health systems in Indiana. The interviews were conducted in two waves, with prototype and interview guide revisions after the first six interviews. The interviews included exploration of Tx Tracker using a think-aloud approach and a clinical scenario. Clinicians were presented with a patient scenario and asked to use Tx Tracker to make a treatment recommendation. Last, participants answered several evaluation questions. Detailed field notes were collected, coded, and thematically analyzed by four analysts.

RESULTS

 We identified several themes: the need for clinicians to be presented with a comprehensive patient history, the usefulness of Tx Tracker in patient discussions about treatment planning, potential usefulness of Tx Tracker for patients with high uncertainty or risk, potential usefulness of Tx Tracker in aggregating scattered information, variability in expectations about workflows, skepticism about underlying electronic health record data quality, interest in using Tx Tracker to annotate or update information, interest in using Tx Tracker to translate information to clinical action, desire for interface with visual cues for risks, warnings, or treatment options, and desire for interactive functionality.

CONCLUSION

 Tools like Tx Tracker, by aggregating key information about past, current, and potential future treatments, may help clinicians collaborate with their patients in choosing the best pain treatments. Still, the use and usefulness of Tx Tracker likely relies on continued improvement of its functionality, accurate and complete underlying data, and tailored integration with varying workflows, care team roles, and user preferences.

Clinical Decision Support for Newborn Weight Loss: A Randomized Controlled Trial

BACKGROUND AND OBJECTIVE

The Newborn Weight Tool (NEWT) can inform newborn feeding decisions and might reduce health care utilization by preventing excess weight loss. Clinical decision support (CDS) displaying NEWT might facilitate its use. Our study's objective is to determine the effect of CDS displaying NEWT on feeding and health care utilization.

METHODS

At an hospital involved in NEWT development, we randomly assigned 2682 healthy infants born ≥36 weeks gestation in 2018-2019 either to CDS displaying NEWT with an electronic flag if most recent weight was ≥75th weight loss centile or to a control of usual care with NEWT accessed at clinician discretion. Our primary outcome was feeding type concordant with weight loss, defined as exclusive breastfeeding for those not flagged, exclusive breastfeeding or supplementation for those flagged once, and supplementation for those flagged more than once. Secondary outcomes included inpatient and outpatient utilization in the first 30 days. We used χ2 and Student's t tests to compare intervention infants with control and to compare trial infants with those born in 2017.

RESULTS

Feeding was concordant with for 1854 (74.5%) trial infants and did not differ between randomized groups (P = .65); concordant feeding was higher for all trial infants than for infants born in 2017 (64.4%; P < .0005). Readmission occurred for 51 (3.8%) CDS infants and 45 (3.4%) control infants (P = .56). Among the 60% of trial infants with outpatient records available, there were 3.5 ± 1.7 visits with no differences between randomized groups (P = .10).

CONCLUSIONS

At an hospital involved in NEWT development, CDS displaying NEWT did not alter either feeding or health care utilization compared with discretionary NEWT access.

Functional IT Complementarity and Hospital Performance in the United States: A Longitudinal Investigation

For healthcare practitioners and policymakers, one of the most challenging problems is understanding how to implement health information technology (HIT) applications in a way that yields the most positive impacts on quality and cost of care. We identify four clinical HIT functions which we label as order entry and management (OEM), decision support (DS), electronic clinical documentation (ECD), and results viewing (RV). We view OEM and DS as primary clinical functions and ECD and RV as support clinical functions. Our results show that no single combination of applications uniformly improves clinical and experiential quality and reduces cost for all hospitals. Thus, managers must assess which HIT interactions improve which performance metric under which conditions. Our results suggest that synergies can be realized when these systems are implemented simultaneously. Additionally, synergies can occur when support HIT is implemented before primary HIT and irrespective of the order in which primary HITs are implemented. Practitioners should also be aware that the synergistic effects of HITs and their impact on cost and quality are different for chronic and acute diseases. Our key message to top managers is to prioritize different combinations of HIT contingent on the performance variables they are targeting for their hospitals but also to realize that technology may not impact all outcomes.

The Impact of Electronic Health Records and Meaningful Use on Inpatient Quality

ABSTRACT

It is unclear if national investments of the HITECH Act have resulted in significant improvements in care processes and outcomes by making "Meaningful Use (MU)" of Electronic Health Record (EHR) systems. The objective of this study is to determine the impact of EHRs and MU on inpatient quality. We used inpatient hospitalization data, American Hospital Association annual survey, and the Centers for Medicare and Medicaid Services attestation records to study the impact of EHRs on inpatient quality composite scores. Agency for Healthcare Research and Quality Inpatient Quality Indicator (IQI) software version 5.0 was used to compute the hospital-level risk-adjusted standardized rates for IQI indicators and composite scores. After adjusting for confounding factors, EHRs that attested to MU had a positive impact on IQI 90 and IQI 91 composite scores with an 8% decrease in composites for mortality for selected procedures and 18% decrease in composites for mortality for selected conditions. Meaningful Use attestation may be an important driver related to inpatient quality. Health care leaders may need to focus on quality improvement initiatives and advanced analytics to better leverage their EHRs to improve IQI 90 composite score for mortality for selected procedures, because we observed a lesser impact on IQI 90 compared with IQI 91.

Effect of Clinical Decision Support on Cardiovascular Risk Among Adults With Bipolar Disorder, Schizoaffective Disorder, or Schizophrenia: A Cluster Randomized Clinical Trial

IMPORTANCE

Adults with schizophrenia, schizoaffective disorder, or bipolar disorder, collectively termed serious mental illness (SMI), have shortened life spans compared with people without SMI. The leading cause of death is cardiovascular (CV) disease.

OBJECTIVE

To assess whether a clinical decision support (CDS) system aimed at primary care clinicians improves CV health for adult primary care patients with SMI.

DESIGN, SETTING, AND PARTICIPANTS

In this cluster randomized clinical trial conducted from March 2, 2016, to September 19, 2018, restricted randomization assigned 76 primary care clinics in 3 Midwestern health care systems to receive or not receive a CDS system aimed at improving CV health among patients with SMI. Eligible clinics had at least 20 patients with SMI; clinicians and their adult patients with SMI with at least 1 modifiable CV risk factor not at the goal set by the American College of Cardiology/American Heart Association guidelines were included. Statistical analysis was conducted on an intention-to-treat basis from January 10, 2019, to December 29, 2021.

INTERVENTION

The CDS system assessed modifiable CV risk factors and provided personalized treatment recommendations to clinicians and patients.

MAIN OUTCOMES AND MEASURES

Patient-level change in total modifiable CV risk over 12 months, summed from individual modifiable risk factors (smoking, body mass index, low-density lipoprotein cholesterol level, systolic blood pressure, and hemoglobin A1c level).

RESULTS

A total of 80 clinics were randomized; 4 clinics were excluded for having fewer than 20 eligible patients, leaving 42 intervention clinics and 34 control clinics. A total of 8937 patients with SMI (4922 women [55.1%]; mean [SD] age, 48.4 [13.5] years) were enrolled. There was a 4% lower rate of increase in total modifiable CV risk among intervention patients relative to control patients (relative rate ratio [RR], 0.96; 95% CI, 0.94-0.98). The intervention favored patients who were 18 to 29 years of age (RR, 0.89; 95% CI, 0.81-0.98) or 50 to 59 years of age (RR, 0.93; 95% CI, 0.90-0.96), Black (RR, 0.93; 95% CI, 0.88-0.98), or White (RR, 0.96; 95% CI, 0.94-0.98). Men (RR, 0.96; 95% CI, 0.94-0.99) and women (RR, 0.95; 95% CI, 0.92-0.97), as well as patients with any SMI subtype (bipolar disorder: RR, 0.96; 95% CI, 0.94-0.99; schizoaffective disorder: RR, 0.94; 95% CI, 0.90-0.98; schizophrenia: RR, 0.92; 95% CI, 0.85-0.99) also benefited from the intervention. Despite treatment effects favoring the intervention, there were no significant differences in individual modifiable risk factors.

CONCLUSIONS AND RELEVANCE

This CDS intervention resulted in a rate of change in total modifiable CV risk that was 4% lower among intervention patients compared with control patients. Results were driven by the cumulative effects of incremental and mostly nonsignificant changes in individual modifiable risk factors. These findings emphasize the value of using CDS to prompt early primary care intervention for adults with SMI.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT02451670.

Clinical Decision Support with or without Shared Decision Making to Improve Preventive Cancer Care: A Cluster-Randomized Trial

BACKGROUND

Innovative interventions are needed to address gaps in preventive cancer care, especially in rural areas. This study evaluated the impact of clinical decision support (CDS) with and without shared decision making (SDM) on cancer-screening completion.

METHODS

In this 3-arm, parallel-group, cluster-randomized trial conducted at a predominantly rural medical group, 34 primary care clinics were randomized to clinical decision support (CDS), CDS plus shared decision making (CDS+SDM), or usual care (UC). The CDS applied web-based clinical algorithms identifying patients overdue for United States Preventive Services Task Force-recommended preventive cancer care and presented evidence-based recommendations to patients and providers on printouts and on the electronic health record interface. Patients in the CDS+SDM clinic also received shared decision-making tools (SDMTs). The primary outcome was a composite indicator of the proportion of patients overdue for breast, cervical, or colorectal cancer screening at index who were up to date on these 1 y later.

RESULTS

From August 1, 2018, to March 15, 2019, 69,405 patients aged 21 to 74 y had visits at study clinics and 25,198 were overdue for 1 or more cancer screening tests at an index visit. At 12-mo follow-up, 9,543 of these (37.9%) were up to date on the composite endpoint. The adjusted, model-derived percentage of patients up to date was 36.5% (95% confidence interval [CI]: 34.0-39.1) in the UC group, 38.1% (95% CI: 35.5-40.9) in the CDS group, and 34.4% (95% CI: 31.8-37.2) in the CDS+SDM group. For all comparisons, the screening rates were higher than UC in the CDS group and lower than UC in the CDS+SDM group, although these differences did not reach statistical significance.

CONCLUSION

The CDS did not significantly increase cancer-screening rates. Exploratory analyses suggest a deeper understanding of how SDM and CDS interact to affect cancer prevention decisions is needed. Trial registration: ClinicalTrials.gov ID: NCT02986230, December 6, 2016.

Effect of Clinical Decision Support at Community Health Centers on the Risk of Cardiovascular Disease: A Cluster Randomized Clinical Trial

IMPORTANCE

Management of cardiovascular disease (CVD) risk in socioeconomically vulnerable patients is suboptimal; better risk factor control could improve CVD outcomes.

OBJECTIVE

To evaluate the impact of a clinical decision support system (CDSS) targeting CVD risk in community health centers (CHCs).

DESIGN, SETTING, AND PARTICIPANTS

This cluster randomized clinical trial included 70 CHC clinics randomized to an intervention group (42 clinics; 8 organizations) or a control group that received no intervention (28 clinics; 7 organizations) from September 20, 2018, to March 15, 2020. Randomization was by CHC organization accounting for organization size. Patients aged 40 to 75 years with (1) diabetes or atherosclerotic CVD and at least 1 uncontrolled major risk factor for CVD or (2) total reversible CVD risk of at least 10% were the population targeted by the CDSS intervention.

INTERVENTIONS

A point-of-care CDSS displaying real-time CVD risk factor control data and personalized, prioritized evidence-based care recommendations.

MAIN OUTCOMES AND MEASURES

One-year change in total CVD risk and reversible CVD risk (ie, the reduction in 10-year CVD risk that was considered achievable if 6 key risk factors reached evidence-based levels of control).

RESULTS

Among the 18 578 eligible patients (9490 [51.1%] women; mean [SD] age, 58.7 [8.8] years), patients seen in control clinics (n = 7419) had higher mean (SD) baseline CVD risk (16.6% [12.8%]) than patients seen in intervention clinics (n = 11 159) (15.6% [12.3%]; P < .001); baseline reversible CVD risk was similarly higher among patients seen in control clinics. The CDSS was used at 19.8% of 91 988 eligible intervention clinic encounters. No population-level reduction in CVD risk was seen in patients in control or intervention clinics; mean reversible risk improved significantly more among patients in control (-0.1% [95% CI, -0.3% to -0.02%]) than intervention clinics (0.4% [95% CI, 0.3% to 0.5%]; P < .001). However, when the CDSS was used, both risk measures decreased more among patients with high baseline risk in intervention than control clinics; notably, mean reversible risk decreased by an absolute 4.4% (95% CI, -5.2% to -3.7%) among patients in intervention clinics compared with 2.7% (95% CI, -3.4% to -1.9%) among patients in control clinics (P = .001).

CONCLUSIONS AND RELEVANCE

The CDSS had low use rates and failed to improve CVD risk in the overall population but appeared to have a benefit on CVD risk when it was consistently used for patients with high baseline risk treated in CHCs. Despite some limitations, these results provide preliminary evidence that this technology has the potential to improve clinical care in socioeconomically vulnerable patients with high CVD risk.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT03001713.

Assessing the implementation of a clinical decision support tool in primary care for diabetes prevention: a qualitative interview study using the Consolidated Framework for Implementation Science

BACKGROUND

In this paper we describe the use of the Consolidated Framework for Implementation Research (CFIR) to study implementation of a web-based, point-of-care, EHR-linked clinical decision support (CDS) tool designed to identify and provide care recommendations for adults with prediabetes (Pre-D CDS).

METHODS

As part of a large NIH-funded clinic-randomized trial, we identified a convenience sample of interview participants from 22 primary care clinics in Minnesota, North Dakota, and Wisconsin that were randomly allocated to receive or not receive a web-based EHR-integrated prediabetes CDS intervention. Participants included 11 clinicians, 6 rooming staff, and 7 nurse or clinic managers recruited by study staff to participate in telephone interviews conducted by an expert in qualitative methods. Interviews were recorded and transcribed, and data analysis was conducted using a constructivist version of grounded theory.

RESULTS

Implementing a prediabetes CDS tool into primary care clinics was useful and well received. The intervention was integrated with clinic workflows, supported primary care clinicians in clearly communicating prediabetes risk and management options with patients, and in identifying actionable care opportunities. The main barriers to CDS use were time and competing priorities. Finally, while the implementation process worked well, opportunities remain in engaging the care team more broadly in CDS use.

CONCLUSIONS

The use of CDS tools for engaging patients and providers in care improvement opportunities for prediabetes is a promising and potentially effective strategy in primary care settings. A workflow that incorporates the whole care team in the use of such tools may optimize the implementation of CDS tools like these in primary care settings. Trial registration Name of the registry: Clinicaltrial.gov.

TRIAL REGISTRATION NUMBER

NCT02759055. Date of registration: 05/03/2016. URL of trial registry record: https://clinicaltrials.gov/ct2/show/NCT02759055 Prospectively registered.

Primary care clinicians' opinions before and after implementation of cancer screening and prevention clinical decision support in a clinic cluster-randomized control trial: a survey research study

BACKGROUND

Electronic health record (EHR)-linked clinical decision support (CDS) may impact primary care clinicians' (PCCs') clinical care opinions. As part of a clinic cluster-randomized control trial (RCT) testing a cancer prevention and screening CDS system with patient and PCC printouts (with or without shared decision-making tools [SDMT]) for patients due for breast, cervical, colorectal, and lung cancer screening and/or human papillomavirus (HPV) vaccination compared to usual care (UC), we surveyed PCCs at study clinics pre- and post-CDS implementation. Our primary aim was to learn if PCCs' opinions changed over time within study arms. Secondary aims including examining whether PCCs' opinions in study arms differed both pre- and post-implementation, and gauging PCCs' opinions on the CDS in the two intervention arms.

METHODS

This study was conducted within a healthcare system serving an upper Midwestern population. We administered pre-implementation (11/2/2017-1/24/2018) and post-implementation (2/2/2020-4/9/2020) cross-sectional electronic surveys to PCCs practicing within a RCT arm: UC; CDS; or CDS + SDMT. Bivariate analyses compared responses between study arms at both time periods and longitudinally within study arms.

RESULTS

Pre-implementation (53%, n = 166) and post-implementation (57%, n = 172) response rates were similar. No significant differences in PCC responses were seen between study arms on cancer prevention and screening questions pre-implementation, with few significant differences found between study arms post-implementation. However, significantly fewer intervention arm clinic PCCs reported being very comfortable with discussing breast cancer screening options with patients compared to UC post-implementation, as well as compared to the same intervention arms pre-implementation. Other significant differences were noted within arms longitudinally. For intervention arms, these differences related to CDS areas like EHR alerts, risk calculators, and ordering screening. Most intervention arm PCCs noted the CDS provided overdue screening alerts to which they were unaware. Few PCCs reported using the CDS, but most would recommend it to colleagues, expressed high CDS satisfaction rates, and thought patients liked the CDS's information and utility.

CONCLUSIONS

While appreciated by PCCs with high satisfaction rates, the CDS may lower PCCs' confidence regarding discussing patients' breast cancer screening options and may be used irregularly. Future research will evaluate the impact of the CDS on cancer prevention and screening rates.

TRIAL REGISTRATION

clinicaltrials.gov , NCT02986230, December 6, 2016.

A Clinical Decision Support System for Diabetes Patients with Deep Learning: Experience of a Taiwan Medical Center

Background: Diabetes mellitus (DM) is a major public health problem worldwide. It involves dysfunction of blood sugar regulation resulting from insulin resistance, inadequate insulin secretion, or excessive glucagon secretion. Methods: This study collated 971,401 drug usage records of 51,009 DM patients. These data include patient identification code, age, gender, outpatient visiting dates, visiting code, medication features (included items, doses, and frequencies of drugs), HbA1c results, and testing time. We apply a random forest (RF) model for feature selection and implement a regression model with the bidirectional long short-term memory (Bi-LSTM) deep learning architecture. Finally, we use the root mean square error (RMSE) as the evaluation index for the prediction model. Results: After data cleaning, the data included 8,729 male and 9,115 female cases. Metformin was the most important feature suggested by the RF model, followed by glimepiride, acarbose, pioglitazone, glibenclamide, gliclazide, repaglinide, nateglinide, sitagliptin, and vildagliptin. The model performed better with the past two seasons in the training data than with additional seasons. Further, the Bi-LSTM architecture model performed better than support vector machines (SVMs). Discussion & Conclusion: This study found that Bi-LSTM models is a well kernel in a CDSS which help physicians' decision-making, and the increasing the number of seasons will negative impact the performance. In addition, this study found that the most important drug is metformin, which is recommended as first-line treatment OHA in various situations for DM patients.

Persistent Cardiometabolic Health Gaps: Can Therapeutic Care Gaps Be Precisely Identified from Electronic Health Records

The objective of this study was to determine the strengths and limitations of using structured electronic health records (EHR) to identify and manage cardiometabolic (CM) health gaps. We used medication adherence measures derived from dispense data to attribute related therapeutic care gaps (i.e., no action to close health gaps) to patient- (i.e., failure to retrieve medication or low adherence) or clinician-related (i.e., failure to initiate/titrate medication) behavior. We illustrated how such data can be used to manage health and care gaps for blood pressure (BP), low-density lipoprotein cholesterol (LDL-C), and HbA1c for 240,582 Sutter Health primary care patients. Prevalence of health gaps was 44% for patients with hypertension, 33% with hyperlipidemia, and 57% with diabetes. Failure to retrieve medication was common; this patient-related care gap was highly associated with health gaps (odds ratios (OR): 1.23-1.76). Clinician-related therapeutic care gaps were common (16% for hypertension, and 40% and 27% for hyperlipidemia and diabetes, respectively), and strongly related to health gaps for hyperlipidemia (OR = 5.8; 95% CI: 5.6-6.0) and diabetes (OR = 5.7; 95% CI: 5.4-6.0). Additionally, a substantial minority of care gaps (9% to 21%) were uncertain, meaning we lacked evidence to attribute the gap to either patients or clinicians, hindering efforts to close the gaps.

Embedding electronic health records onto a knowledge network recognizes prodromal features of multiple sclerosis and predicts diagnosis

OBJECTIVE

Early identification of chronic diseases is a pillar of precision medicine as it can lead to improved outcomes, reduction of disease burden, and lower healthcare costs. Predictions of a patient's health trajectory have been improved through the application of machine learning approaches to electronic health records (EHRs). However, these methods have traditionally relied on "black box" algorithms that can process large amounts of data but are unable to incorporate domain knowledge, thus limiting their predictive and explanatory power. Here, we present a method for incorporating domain knowledge into clinical classifications by embedding individual patient data into a biomedical knowledge graph.

MATERIALS AND METHODS

A modified version of the Page rank algorithm was implemented to embed millions of deidentified EHRs into a biomedical knowledge graph (SPOKE). This resulted in high-dimensional, knowledge-guided patient health signatures (ie, SPOKEsigs) that were subsequently used as features in a random forest environment to classify patients at risk of developing a chronic disease.

RESULTS

Our model predicted disease status of 5752 subjects 3 years before being diagnosed with multiple sclerosis (MS) (AUC = 0.83). SPOKEsigs outperformed predictions using EHRs alone, and the biological drivers of the classifiers provided insight into the underpinnings of prodromal MS.

CONCLUSION

Using data from EHR as input, SPOKEsigs describe patients at both the clinical and biological levels. We provide a clinical use case for detecting MS up to 5 years prior to their documented diagnosis in the clinic and illustrate the biological features that distinguish the prodromal MS state.

Implementation of a multi-level community-clinical linkage intervention to improve glycemic control among south Asian patients with uncontrolled diabetes: study protocol of the DREAM initiative

BACKGROUND

A number of studies have identified patient-, provider-, and community-level barriers to effective diabetes management among South Asian Americans, who have a high prevalence of type 2 diabetes. However, no multi-level, integrated community health worker (CHW) models leveraging health information technology (HIT) have been developed to mitigate disease among this population. This paper describes the protocol for a multi-level, community-clinical linkage intervention to improve glycemic control among South Asians with uncontrolled diabetes.

METHODS

The study includes three components: 1) building the capacity of primary care practices (PCPs) to utilize electronic health record (EHR) registries to identify patients with uncontrolled diabetes; 2) delivery of a culturally- and linguistically-adapted CHW intervention to improve diabetes self-management; and 3) HIT-enabled linkage to culturally-relevant community resources. The CHW intervention component includes a randomized controlled trial consisting of group education sessions on diabetes management, physical activity, and diet/nutrition. South Asian individuals with type 2 diabetes are recruited from 20 PCPs throughout NYC and randomized at the individual level within each PCP site. A total of 886 individuals will be randomized into treatment or control groups; EHR data collection occurs at screening, 6-, 12-, and 18-month. We hypothesize that individuals receiving the multi-level diabetes management intervention will be 15% more likely than the control group to achieve ≥0.5% point reduction in hemoglobin A1c (HbA1c) at 6-months. Secondary outcomes include change in weight, body mass index, and LDL cholesterol; the increased use of community and social services; and increased health self-efficacy. Additionally, a cost-effectiveness analysis will focus on implementation and healthcare utilization costs to determine the incremental cost per person achieving an HbA1c change of ≥0.5%.

DISCUSSION

Final outcomes will provide evidence regarding the effectiveness of a multi-level, integrated EHR-CHW intervention, implemented in small PCP settings to promote diabetes control among an underserved South Asian population. The study leverages multisectoral partnerships, including the local health department, a healthcare payer, and EHR vendors. Study findings will have important implications for the translation of integrated evidence-based strategies to other minority communities and in under-resourced primary care settings.

TRIAL REGISTRATION

This study was registered with clinicaltrials.gov: NCT03333044 on November 6, 2017.

Developing a User-Centered Digital Clinical Decision Support App for Evidence-Based Medication Recommendations for Type 2 Diabetes Mellitus: Prototype User Testing and Validation Study

Background

Closing the gap between care recommended by evidence-based guidelines and care delivered in practice is an ongoing challenge across systems and delivery models. Clinical decision support systems (CDSSs) are widely deployed to augment clinicians in their complex decision-making processes. Despite published success stories, the poor usability of many CDSSs has contributed to fragmented workflows and alert fatigue.

Objective

This study aimed to validate the application of a user-centered design (UCD) process in the development of a standards-based medication recommender for type 2 diabetes mellitus in a simulated setting. The prototype app was evaluated for effectiveness, efficiency, and user satisfaction.

Methods

We conducted interviews with 8 clinical leaders with 8 rounds of iterative user testing with 2-8 prescribers in each round to inform app development. With the resulting prototype app, we conducted a validation study with 43 participants. The participants were assigned to one of two groups and completed a 2-hour remote user testing session. Both groups reviewed mock patient facts and ordered diabetes medications for the patients. The Traditional group used a mock electronic health record (EHR) for the review in Period 1 and used the prototype app in Period 2, while the Tool group used the prototype app during both time periods. The perceived cognitive load associated with task performance during each period was assessed with the National Aeronautics and Space Administration Task Load Index. Participants also completed the System Usability Scale (SUS) questionnaire and Kano Survey.

Results

Average SUS scores from the questionnaire, taken at the end of 5 of the 8 user testing sessions, ranged from 68-86. The results of the validation study are as follows: percent adherence to evidence-based guidelines was greater with the use of the prototype app than with the EHR across time periods with the Traditional group (prototype app mean 96.2 vs EHR mean 72.0, P<.001) and between groups during Period 1 (Tool group mean 92.6 vs Traditional group mean 72.0, P<.001). Task completion times did not differ between groups (P=.23), but the Tool group completed medication ordering more quickly in Period 2 (Period 1 mean 130.7 seconds vs Period 2 mean 107.7 seconds, P<.001). Based on an adjusted α level owing to violation of the assumption of homogeneity of variance (Ps>.03), there was no effect on screens viewed and on perceived cognitive load (all Ps>.14).

Conclusions

Through deployment of the UCD process, a point-of-care medication recommender app holds promise of improving adherence to evidence-based guidelines; in this case, those from the American Diabetes Association. Task-time performance suggests that with practice the T2DM app may support a more efficient ordering process for providers, and SUS scores indicate provider satisfaction with the app.

Patient Perceptions of Using Clinical Decision Support for Cancer Screening and Prevention: "I wouldn't have thought about getting screened without it."

PURPOSE

We sought to gain an understanding of cancer prevention and screening perspectives among patients exposed to a clinical decision support (CDS) tool because they were due or overdue for certain cancer screenings or prevention.

METHODS

Semi-structured qualitative interviews were conducted with 37 adult patients due or overdue for cancer prevention services in 10 primary care clinics within the same health system. Data were thematically segmented and coded using qualitative content analysis.

RESULTS

We identified three themes: 1) The CDS tool had more strengths than weaknesses, with areas for improvement; 2) Many facilitators and barriers to cancer prevention and screening exist; and 3) Discussions and decision-making varied by type of cancer prevention and screening. Almost all participants made positive comments regarding the CDS. Some participants learned new information, reporting the CDS helped them make a decision they otherwise would not have made. Participants who used the tool with their provider had higher self-reported rates of deciding to be screened than those who did not.

CONCLUSIONS

Learning about patients' perceptions of a CDS tool may increase understanding of how patient-tailored CDS impacts cancer screening and prevention rates. Participants found a personalized CDS tool for cancer screening and prevention in primary care useful and a welcome addition to their visit. However, many providers were not using the tool with eligible patients.

Using Electronic Health Record-Based Clinical Decision Support to Provide Social Risk-Informed Care in Community Health Centers: Protocol for the Design and Assessment of a Clinical Decision Support Tool

Background

Consistent and compelling evidence demonstrates that social and economic adversity has an impact on health outcomes. In response, many health care professional organizations recommend screening patients for experiences of social and economic adversity or social risks—for example, food, housing, and transportation insecurity—in the context of care. Guidance on how health care providers can act on documented social risk data to improve health outcomes is nascent. A strategy recommended by the National Academy of Medicine involves using social risk data to adapt care plans in ways that accommodate patients’ social risks.

Objective

This study’s aims are to develop electronic health record (EHR)–based clinical decision support (CDS) tools that suggest social risk–informed care plan adaptations for patients with diabetes or hypertension, assess tool adoption and its impact on selected clinical quality measures in community health centers, and examine perceptions of tool usability and impact on care quality.

Methods

A systematic scoping review and several stakeholder activities will be conducted to inform development of the CDS tools. The tools will be pilot-tested to obtain user input, and their content and form will be revised based on this input. A randomized quasi-experimental design will then be used to assess the impact of the revised tools. Eligible clinics will be randomized to a control group or potential intervention group; clinics will be recruited from the potential intervention group in random order until 6 are enrolled in the study. Intervention clinics will have access to the CDS tools in their EHR, will receive minimal implementation support, and will be followed for 18 months to evaluate tool adoption and the impact of tool use on patient blood pressure and glucose control.

Results

This study was funded in January 2020 by the National Institute on Minority Health and Health Disparities of the National Institutes of Health. Formative activities will take place from April 2020 to July 2021, the CDS tools will be developed between May 2021 and November 2022, the pilot study will be conducted from August 2021 to July 2022, and the main trial will occur from December 2022 to May 2024. Study data will be analyzed, and the results will be disseminated in 2024.

Conclusions

Patients’ social risk information must be presented to care teams in a way that facilitates social risk–informed care. To our knowledge, this study is the first to develop and test EHR-embedded CDS tools designed to support the provision of social risk–informed care. The study results will add a needed understanding of how to use social risk data to improve health outcomes and reduce disparities.

International Registered Report Identifier (IRRID)

PRR1-10.2196/31733

Pragmatic clinic randomized trial to improve chronic kidney disease care: Design and adaptation due to COVID disruptions

BACKGROUND

We describe a clinic-randomized trial to improve chronic kidney disease (CKD) care through a CKD-clinical decision support (CKD-CDS) intervention in primary care clinics and the challenges we encountered due to COVID-19 care disruption.

METHODS/DESIGN

Primary care clinics (N = 32) were randomized to usual care (UC) or to CKD-CDS. Between April 17, 2019 and March 14, 2020, more than 7000 patients had accrued for analysis by meeting study-eligibility criteria at an index office visit: age 18-75, laboratory criteria for stage 3 or 4 CKD (eGFR 15-59 mL/min/1.73 m2), and one or more opportunities algorithmically identified to improve CKD care such as blood pressure (BP) or glucose control, angiotensin converting enzyme inhibitor (ACEI) or angiotensin receptor blocker (ARB) use, discontinuance of a nonsteroidal anti-inflammatory drug (NSAID), or nephrology referral. At CKD-CDS clinics, CDS provided individualized treatment suggestions that were printed for patients and clinicians at the start of office encounters and were viewable within the electronic health record. By initial design, the impact of the CKD-CDS intervention on care gaps was to be assessed 12 months after the index date, but COVID-19 caused major disruptions to care delivery during the intervention period. In response to disruptions, the intervention was temporarily suspended while we expanded CDS use for telehealth encounters and programmed new criteria for displaying the CKD-CDS to intervention patients due to clinic closures and scheduling changes.

DISCUSSION

We describe a NIH-funded pragmatic trial of web-based EHR-integrated CKD-CDS and modifications necessary mid-study to complete the study as intended in the face of COVID-19 pandemic challenges.

The Impact of Guideline Integration into Electronic Medical Records on Outcomes for Patients with Diabetes: A Systematic Review

Optimal strategies for integration of clinical practice guidelines into electronic medical records and its impact on processes of care and clinical outcomes in diabetic patients are not well understood. A systematic review of CINAHL, MEDLINE, PubMed, and Cochrane Library databases in August 2016, November 2017, and June 2020 was conducted. Studies investigating integration of diabetes guidelines into ambulatory care electronic medical records reporting quantitative results were included. After screening 15,783 records, 21 articles were included. Lipid and blood pressure control consistently improved with guideline integration, but A1c control remained equivocal. Electronic guideline integration improved microvascular complication screening, vaccination, and documentation of cardiovascular risk factors, while medication prescription and blood pressure, lipid, and A1c documentation did not improve. Studies employing a combination of electronic record intervention strategies were associated with improvement in monitoring and attainment of guideline and screening targets. Thus, strategies employing combinations of interventions to incorporate guidelines into electronic records may improve processes of care and some clinical outcomes.

Imputing intracluster correlation coefficients from a posterior predictive distribution is a feasible method of dealing with unit of analysis errors in a meta-analysis of cluster RCTs

BACKGROUND

Incorporating cluster randomized trials (CRTs) into meta-analyses is challenging because appropriate standard errors of study estimates accounting for clustering are not always reported. Systematic reviews of CRTs often use a single constant external estimate of the intraclass correlation coefficient (ICC) to adjust study estimate standard errors and facilitate meta-analyses; an approach that fails to account for possible variation of ICCs among studies and the imprecision with which they are estimated. Using a large systematic review of the effects of diabetes quality improvement interventions, we investigated whether we could better account for ICC variation and uncertainty in meta-analyzed effect estimates by imputing missing ICCs from a posterior predictive distribution constructed from a database of relevant ICCs.

METHODS

We constructed a dataset of ICC estimates from applicable studies. For outcomes with two or more available ICC estimates, we constructed posterior predictive ICC distributions in a Bayesian framework. For a selected continuous outcome, glycosylated hemoglobin (HbA1c), we compared the impact of incorporating a single constant ICC versus imputing ICCs drawn from the posterior predictive distribution when estimating the effect of intervention components on post treatment mean in a case study of diabetes quality improvement trials.

RESULTS

Using internal and external ICC estimates, we were able to construct a database of 59 ICCs for 12 of the 13 review outcomes (range 1-10 per outcome) and estimate the posterior predictive ICC distribution for 11 review outcomes. Synthesized results were not markedly changed by our approach for HbA1c.

CONCLUSION

Building posterior predictive distributions to impute missing ICCs is a feasible approach to facilitate principled meta-analyses of cluster randomized trials using prior data. Further work is needed to establish whether the application of these methods leads to improved review inferences for different reviews based on different factors (e.g., proportion of CRTs and CRTs with missing ICCs, different outcomes, variation and precision of ICCs).

American Association of Clinical Endocrinology And Associazione Medici Endocrinologi Thyroid Nodule Algorithmic Tool

OBJECTIVE

The first edition of the American Association of Clinical Endocrinology/American College of Endocrinology/Associazione Medici Endocrinologi Guidelines for the Diagnosis and Management of Thyroid Nodules was published in 2006 and updated in 2010 and 2016. The American Association of Clinical Endocrinology/American College of Endocrinology/Associazione Medici Endocrinologi multidisciplinary thyroid nodules task force was charged with developing a novel interactive electronic algorithmic tool to evaluate thyroid nodules.

METHODS

The Thyroid Nodule App (termed TNAPP) was based on the updated 2016 clinical practice guideline recommendations while incorporating recent scientific evidence and avoiding unnecessary diagnostic procedures and surgical overtreatment. This manuscript describes the algorithmic tool development, its data requirements, and its basis for decision making. It provides links to the web-based algorithmic tool and a tutorial.

RESULTS

TNAPP and TI-RADS were cross-checked on 95 thyroid nodules with histology-proven diagnoses.

CONCLUSION

TNAPP is a novel interactive web-based tool that uses clinical, imaging, cytologic, and molecular marker data to guide clinical decision making to evaluate and manage thyroid nodules. It may be used as a heuristic tool for evaluating and managing patients with thyroid nodules. It can be adapted to create registries for solo practices, large multispecialty delivery systems, regional and national databases, and research consortiums. Prospective studies are underway to validate TNAPP to determine how it compares with other ultrasound-based classification systems and whether it can improve the care of patients with clinically significant thyroid nodules while reducing the substantial burden incurred by those who do not benefit from further evaluation and treatment.

French FastContext: A publicly accessible system for detecting negation, temporality and experiencer in French clinical notes

The context of medical conditions is an important feature to consider when processing clinical narratives. NegEx and its extension ConText became the most well-known rule-based systems that allow determining whether a medical condition is negated, historical or experienced by someone other than the patient in English clinical text. In this paper, we present a French adaptation and enrichment of FastContext which is the most recent, n-trie engine-based implementation of the ConText algorithm. We compiled an extensive list of French lexical cues by automatic and manual translation and enrichment. To evaluate French FastContext, we manually annotated the context of medical conditions present in two types of clinical narratives: (i)death certificates and (ii)electronic health records. Results show good performance across different context values on both types of clinical notes (on average 0.93 and 0.86 F1, respectively). Furthermore, French FastContext outperforms previously reported French systems for negation detection when compared on the same datasets and it is the first implementation of contextual temporality and experiencer identification reported for French. Finally, French FastContext has been implemented within the SIFR Annotator: a publicly accessible Web service to annotate French biomedical text data (http://bioportal.lirmm.fr/annotator). To our knowledge, this is the first implementation of a Web-based ConText-like system in a publicly accessible platform allowing non-natural-language-processing experts to both annotate and contextualize medical conditions in clinical notes.

Design and rationale of an intervention to improve cancer prevention using clinical decision support and shared decision making: A clinic-randomized trial

BACKGROUND

Despite decades of research the gap in primary and secondary cancer prevention services in the U. S. remains unacceptably wide. Innovative interventions are needed to address this persistent challenge. Electronic health records linked with Web-based clinical decision support may close this gap, especially if delivered to both patients and their providers.

OBJECTIVES

The Cancer Prevention Wizard (CPW) study is an implementation, clinic-randomized trial designed to achieve these aims: 1) assess impact of the Cancer Prevention Wizard-Clinical Decision Support (CPW-CDS) alone and CPW-CDS plus Shared Decision Making Tools (CPW + SDMTs) compared to usual care (UC) on tobacco cessation counseling and drugs, HPV vaccinations, and screening tests for breast, cervical, colorectal, or lung cancer; 2) assess cost of the CPW-CDS intervention; and 3) describe critical facilitators and barriers for CPW-CDS implementation, use, and clinical impact using a mixed-methods approach supported by the CFIR and RE-AIM frameworks.

METHODS

34 predominantly rural, primary care clinics were randomized to CPW-CDS, CPW + SMDTs, or UC. Between August 2018 and October 2020, primary care providers and their patients who met inclusion criteria in intervention clinics were exposed to the CPW-CDS with or without SDMTs. Study outcomes at 12 months post index visit include patients up to date on screening tests and HPV vaccinations, overall healthcare costs, and diagnostic codes and billing levels for cancer prevention services.

CONCLUSIONS

We will test in rural primary care settings whether CPW-CDS with or without SDMTs can improve delivery of primary and secondary cancer prevention services. The trial and analyses are ongoing with results expected in 2021.

Challenges involved in establishing a web-based clinical decision support tool in community health centers

Implementation lessons: Establishing a shared 'hub-and-spoke,' web-based clinical decision support system (CDSS) in an EHR shared by >600 community health centers incurred a myriad of challenges, which are summarized here to guide others seeking to use similar CDSS. Legal and compliance challenges involved ensuring secure data exchanges, determining which entity maintains data records, and deciding which data are sent to the CDSS. Technical challenges involved using lab data from multiple sources and improving the CDSS' cache routine performance in its new setting. Clinical implementation challenges involved identifying optimal strategies for generating data on CDSS use rates, modifying the CDSS functionality for obtaining clinician/staff feedback, and customizing the risk thresholds that trigger the CDSS for the new setting.

Guiding Glucose Management Discussions Among Adults With Type 2 Diabetes in General Practice: Development and Pretesting of a Clinical Decision Support Tool Prototype Embedded in an Electronic Medical Record

BACKGROUND

Managing type 2 diabetes (T2D) requires progressive lifestyle changes and, sometimes, pharmacological treatment intensification. General practitioners (GPs) are integral to this process but can find pharmacological treatment intensification challenging because of the complexity of continually emerging treatment options.

OBJECTIVE

This study aimed to use a co-design method to develop and pretest a clinical decision support (CDS) tool prototype (GlycASSIST) embedded within an electronic medical record, which uses evidence-based guidelines to provide GPs and people with T2D with recommendations for setting glycated hemoglobin (HbA1c) targets and intensifying treatment together in real time in consultations.

METHODS

The literature on T2D-related CDS tools informed the initial GlycASSIST design. A two-part co-design method was then used. Initial feedback was sought via interviews and focus groups with clinicians (4 GPs, 5 endocrinologists, and 3 diabetes educators) and 6 people with T2D. Following refinements, 8 GPs participated in mock consultations in which they had access to GlycASSIST. Six people with T2D viewed a similar mock consultation. Participants provided feedback on the functionality of GlycASSIST and its role in supporting shared decision making (SDM) and treatment intensification.

RESULTS

Clinicians and people with T2D believed that GlycASSIST could support SDM (although this was not always observed in the mock consultations) and individualized treatment intensification. They recommended that GlycASSIST includes less information while maintaining relevance and credibility and using graphs and colors to enhance visual appeal. Maintaining clinical autonomy was important to GPs, as they wanted the capacity to override GlycASSIST's recommendations when appropriate. Clinicians requested easier screen navigation and greater prescribing guidance and capabilities.

CONCLUSIONS

GlycASSIST was perceived to achieve its purpose of facilitating treatment intensification and was acceptable to people with T2D and GPs. The GlycASSIST prototype is being refined based on these findings to prepare for quantitative evaluation.