Measuring physician adherence with gout quality indicators: a role for natural language processing

Monitoring and Management of Uric Acid Therapy in Gout and Chronic Kidney Disease: A Single-Center Retrospective Study

Background Gout commonly coexists with chronic kidney disease (CKD) due to reduced renal excretion of uric acid (UA). Guidelines recommend regular monitoring and dose adjustment of urate-lowering therapy (ULT), but the rate of adherence to these guidelines is not well established. Our study aimed to determine adherence to ULT guidelines in gout patients at our institution. In particular, we sought to assess the effect of CKD as well as other comorbidities on the prevalence of ULT guideline adherence. Methods We conducted a retrospective cohort study of 5,985 gout patients at our institution initiated on allopurinol between 2015 and 2020. Inclusion criteria were age over 18, a gout diagnosis, and a new allopurinol prescription. The primary outcome was UA monitoring within six months of therapy initiation. A secondary outcome was the prevalence of dose adjustments made by providers in response to a UA level above target. Results Only 48.3% (n = 2,889) of patients had UA levels monitored within six months. CKD stage did not significantly impact monitoring rates (p = 0.059). In patients with elevated UA levels (>6 mg/dL), 54.3% (n = 1,011) of patients had no dosage adjustments. Conclusions Significant gaps exist in adherence to ULT guidelines; nearly half of patients did not undergo recommended UA monitoring. Over half of patients with elevated uric levels did not have dosage adjustments. CKD stage did not affect the likelihood of UA monitoring or dose changes in persons with elevated UA levels.

Advancing rheumatology with natural language processing: insights and prospects from a systematic review

Objectives

Natural language processing (NLP) and large language models (LLMs) have emerged as powerful tools in healthcare, offering advanced methods for analysing unstructured clinical texts. This systematic review aims to evaluate the current applications of NLP and LLMs in rheumatology, focusing on their potential to improve disease detection, diagnosis and patient management.

Methods

We screened seven databases. We included original research articles that evaluated the performance of NLP models in rheumatology. Data extraction and risk of bias assessment were performed independently by two reviewers, following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies was used to evaluate the risk of bias.

Results

Of 1491 articles initially identified, 35 studies met the inclusion criteria. These studies utilized various data types, including electronic medical records and clinical notes, and employed models like Bidirectional Encoder Representations from Transformers and Generative Pre-trained Transformers. High accuracy was observed in detecting conditions such as RA, SpAs and gout. The use of NLP also showed promise in managing diseases and predicting flares.

Conclusion

NLP showed significant potential in enhancing rheumatology by improving diagnostic accuracy and personalizing patient care. While applications in detecting diseases like RA and gout are well developed, further research is needed to extend these technologies to rarer and more complex clinical conditions. Overcoming current limitations through targeted research is essential for fully realizing NLP's potential in clinical practice.

Serum Urate Monitoring Among Older Adults With Gout: Initiating Urate-Lowering Therapy in Ontario, Canada

OBJECTIVE

To assess the proportion of, and factors associated with, older adults with gout receiving a serum urate (SUA) test after starting urate-lowering therapy (ULT).

METHODS

We performed a population-based retrospective cohort study in Ontario, Canada in patients ages ≥66 years with gout, newly dispensed ULT between 2010 and 2019. We characterized patients with SUA testing within 6 and 12 months after ULT dispensation. Multilevel logistic regression clustered by ULT prescriber evaluated the factors associated with SUA monitoring within 6 months.

RESULTS

We included 44,438 patients with a mean ± SD age of 76.0 ± 7.3 years and 64.4% male. Family physicians prescribed 79.1% of all ULTs. SUA testing was lowest in 2010 (56.4% at 6 months) and rose over time to 71.3% in 2019 (P < 0.0001). Compared with rheumatologists, family physicians (odds ratio [OR] 0.26 [95% confidence interval (95% CI) 0.23-0.29]), internists (OR 0.34 [95% CI 0.29-0.39]), nephrologists (OR 0.37 [95% CI 0.30-0.45]), and other specialties (OR 0.25 [95% CI 0.21-0.29]) were less likely to test SUA, as were male physicians (OR 0.87 [95% CI 0.83-0.91]). Patient factors associated with lower odds of SUA monitoring included rural residence (OR 0.81 [95% CI 0.77-0.86]), lower socioeconomic status (OR 0.91 [95% CI 0.85-0.97]), and patient comorbidities. Chronic kidney disease, hypertension, diabetes mellitus, and coprescription of colchicine/oral corticosteroids (OR 1.31 [95% CI 1.23-1.40]) were correlated with increased SUA testing.

CONCLUSION

SUA testing is suboptimal among older adults with gout initiating ULT but is improving over time. ULT prescriber, patient, and prescription characteristics were correlated with SUA testing.

Measuring pain care quality in the Veterans Health Administration primary care setting

ABSTRACT

The lack of a reliable approach to assess quality of pain care hinders quality improvement initiatives. Rule-based natural language processing algorithms were used to extract pain care quality (PCQ) indicators from documents of Veterans Health Administration primary care providers for veterans diagnosed within the past year with musculoskeletal disorders with moderate-to-severe pain intensity across 2 time periods 2013 to 2014 (fiscal year [FY] 2013) and 2017 to 2018 (FY 2017). Patterns of documentation of PCQ indicators for 64,444 veterans and 124,408 unique visits (FY 2013) and 63,427 veterans and 146,507 visits (FY 2017) are described. The most commonly documented PCQ indicators in each cohort were presence of pain, etiology or source, and site of pain (greater than 90% of progress notes), while least commonly documented were sensation, what makes pain better or worse, and pain's impact on function (documented in fewer than 50%). A PCQ indicator score (maximum = 12) was calculated for each visit in FY 2013 (mean = 7.8, SD = 1.9) and FY 2017 (mean = 8.3, SD = 2.3) by adding one point for every indicator documented. Standardized Cronbach alpha for total PCQ scores was 0.74 in the most recent data (FY 2017). The mean PCQ indicator scores across patient characteristics and types of healthcare facilities were highly stable. Estimates of the frequency of documentation of PCQ indicators have face validity and encourage further evaluation of the reliability, validity, and utility of the measure. A reliable measure of PCQ fills an important scientific knowledge and practice gap.

Application of Artificial Intelligence in Community-Based Primary Health Care: Systematic Scoping Review and Critical Appraisal

BACKGROUND

Research on the integration of artificial intelligence (AI) into community-based primary health care (CBPHC) has highlighted several advantages and disadvantages in practice regarding, for example, facilitating diagnosis and disease management, as well as doubts concerning the unintended harmful effects of this integration. However, there is a lack of evidence about a comprehensive knowledge synthesis that could shed light on AI systems tested or implemented in CBPHC.

OBJECTIVE

We intended to identify and evaluate published studies that have tested or implemented AI in CBPHC settings.

METHODS

We conducted a systematic scoping review informed by an earlier study and the Joanna Briggs Institute (JBI) scoping review framework and reported the findings according to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analysis-Scoping Reviews) reporting guidelines. An information specialist performed a comprehensive search from the date of inception until February 2020, in seven bibliographic databases: Cochrane Library, MEDLINE, EMBASE, Web of Science, Cumulative Index to Nursing and Allied Health Literature (CINAHL), ScienceDirect, and IEEE Xplore. The selected studies considered all populations who provide and receive care in CBPHC settings, AI interventions that had been implemented, tested, or both, and assessed outcomes related to patients, health care providers, or CBPHC systems. Risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Two authors independently screened the titles and abstracts of the identified records, read the selected full texts, and extracted data from the included studies using a validated extraction form. Disagreements were resolved by consensus, and if this was not possible, the opinion of a third reviewer was sought. A third reviewer also validated all the extracted data.

RESULTS

We retrieved 22,113 documents. After the removal of duplicates, 16,870 documents were screened, and 90 peer-reviewed publications met our inclusion criteria. Machine learning (ML) (41/90, 45%), natural language processing (NLP) (24/90, 27%), and expert systems (17/90, 19%) were the most commonly studied AI interventions. These were primarily implemented for diagnosis, detection, or surveillance purposes. Neural networks (ie, convolutional neural networks and abductive networks) demonstrated the highest accuracy, considering the given database for the given clinical task. The risk of bias in diagnosis or prognosis studies was the lowest in the participant category (4/49, 4%) and the highest in the outcome category (22/49, 45%).

CONCLUSIONS

We observed variabilities in reporting the participants, types of AI methods, analyses, and outcomes, and highlighted the large gap in the effective development and implementation of AI in CBPHC. Further studies are needed to efficiently guide the development and implementation of AI interventions in CBPHC settings.

Social and Behavioral Determinants of Health in the Era of Artificial Intelligence with Electronic Health Records: A Scoping Review

Background. There is growing evidence that social and behavioral determinants of health (SBDH) play a substantial effect in a wide range of health outcomes. Electronic health records (EHRs) have been widely employed to conduct observational studies in the age of artificial intelligence (AI). However, there has been limited review into how to make the most of SBDH information from EHRs using AI approaches.Methods. A systematic search was conducted in six databases to find relevant peer-reviewed publications that had recently been published. Relevance was determined by screening and evaluating the articles. Based on selected relevant studies, a methodological analysis of AI algorithms leveraging SBDH information in EHR data was provided.Results. Our synthesis was driven by an analysis of SBDH categories, the relationship between SBDH and healthcare-related statuses, natural language processing (NLP) approaches for extracting SBDH from clinical notes, and predictive models using SBDH for health outcomes.Discussion. The associations between SBDH and health outcomes are complicated and diverse; several pathways may be involved. Using NLP technology to support the extraction of SBDH and other clinical ideas simplifies the identification and extraction of essential concepts from clinical data, efficiently unlocks unstructured data, and aids in the resolution of unstructured data-related issues.Conclusion. Despite known associations between SBDH and diseases, SBDH factors are rarely investigated as interventions to improve patient outcomes. Gaining knowledge about SBDH and how SBDH data can be collected from EHRs using NLP approaches and predictive models improves the chances of influencing health policy change for patient wellness, ultimately promoting health and health equity.

Development of Quality Indicators for the Care of Women with Abnormal Uterine Bleeding by Primary Care Providers in the Veterans Health Administration

BACKGROUND

Abnormal uterine bleeding (AUB) is a common women's health complaint. However, the quality of primary care (PC) management of AUB is unknown. Our objective was to develop quality indicators for Veterans Health Administration (VA) PC assessment and management of AUB.

METHODS

We drafted candidate indicators based on comprehensive review of the scientific literature, including published consensus guidelines. Then, we convened a national panel of nine experts including PC providers, obstetrician-gynecologists, VA policy stakeholders, and quality measurement experts, and used a modified Delphi panel process. First, panelists individually rated 19 candidate indicators, using 9-point scales, on three metrics: consistency with established guidelines, importance to women's health, and reliability of measurement from VA electronic health records. Panelists then discussed the indicators. Finally, panelists re-rated revised indicators using the same metrics. Indicators were selected if final median ratings were ≥7 on each 9-point scale, without dispersion in ratings.

RESULTS

Eighteen indicators were selected. Three focused on assessing need for emergency care (e.g., profuse bleeding or pregnancy). Three addressed ascertaining key aspects of the medical history (e.g., endometrial cancer risk). Two addressed performing a physical examination (e.g., pelvic examination). Six addressed indications for diagnostic studies and specialty care referrals, (e.g., transvaginal ultrasound examination). Four addressed initiation of treatment and counseling (e.g., hormone therapy).

CONCLUSIONS

We developed quality indicators for PC assessment and management of AUB that span reproductive and postmenopausal life phases. Applying these indicators in VA and other health systems with integrated electronic health records can assess need for, and effects of, AUB quality improvement programs.

Monitoring of Urate-Lowering Therapy Among US Veterans Following the 2012 American College of Rheumatology Guidelines for Management of Gout

BACKGROUND

With the prevalence of and hospitalizations for gout increasing, optimizing care for patients with gout is imperative. The 2012 American College of Rheumatology gout guidelines emphasize that timely monitoring is key to achieving serum urate (SUA) goals. Few studies have examined this metric following the 2012 update, and to our knowledge, none have examined a veteran population.

OBJECTIVE

To evaluate adherence to urate-lowering therapy (ULT) monitoring guidelines in a veteran population.

METHODS

This is a single-center, multisite, retrospective chart review of US veterans receiving ULT for gout within the VA (Veterans Affairs) Tennessee Valley Healthcare System from January 1, 2013, to June 30, 2015. The primary end point was percentage of patients with a SUA within 6 months of initial xanthine oxidase inhibitor prescription. Secondary end points included percentage of patients with SUA <6 mg/dL and percentage of patients with uptitration following SUA above goal.

RESULTS

A total of 601 patients met inclusion criteria for the study; after application of exclusion criteria, 505 were analyzed. Of these, 295 patients (58%) did not have a SUA drawn within 6 months, and 162 patients (32%) reached the end of the study period without SUA measured. Of 226 patients with SUA above goal on initial check, 64 (28%) had timely dose adjustment, whereas 143 patients (63%) had no adjustment. A total of 161 patients (32%) had a SUA at goal within the study period.

CONCLUSIONS

Rates of ULT monitoring at a major VA medical center were suboptimal, and improved adherence to guideline recommendations is needed.

Aspiring to Unintended Consequences of Natural Language Processing: A Review of Recent Developments in Clinical and Consumer-Generated Text Processing

OBJECTIVES

This paper reviews work over the past two years in Natural Language Processing (NLP) applied to clinical and consumer-generated texts.

METHODS

We included any application or methodological publication that leverages text to facilitate healthcare and address the health-related needs of consumers and populations.

RESULTS

Many important developments in clinical text processing, both foundational and task-oriented, were addressed in community- wide evaluations and discussed in corresponding special issues that are referenced in this review. These focused issues and in-depth reviews of several other active research areas, such as pharmacovigilance and summarization, allowed us to discuss in greater depth disease modeling and predictive analytics using clinical texts, and text analysis in social media for healthcare quality assessment, trends towards online interventions based on rapid analysis of health-related posts, and consumer health question answering, among other issues.

CONCLUSIONS

Our analysis shows that although clinical NLP continues to advance towards practical applications and more NLP methods are used in large-scale live health information applications, more needs to be done to make NLP use in clinical applications a routine widespread reality. Progress in clinical NLP is mirrored by developments in social media text analysis: the research is moving from capturing trends to addressing individual health-related posts, thus showing potential to become a tool for precision medicine and a valuable addition to the standard healthcare quality evaluation tools.

Self-reported quality care for knee osteoarthritis: comparisons across Denmark, Norway, Portugal and the UK

Objectives

To assess and compare patient perceived quality of osteoarthritis (OA) management in primary healthcare in Denmark, Norway, Portugal and the UK.

Methods

Participants consulting with clinical signs and symptoms of knee OA were identified in 30 general practices and invited to complete a cross-sectional survey including quality indicators (QI) for OA care. A QI was considered as eligible if the participant had checked ‘Yes’ or ‘No’, and as achieved if the participant had checked ‘Yes’ to the indicator. The median percentage (with IQR and range) of eligible QIs achieved by country was determined and compared in negative binominal regression analysis. Achievement of individual QIs by country was determined and compared using logistic regression analyses.

Results

A total of 354 participants self-reported QI achievement. The median percentage of eligible QIs achieved (checked ‘Yes’) was 48% (IQR 28%, 64%; range 0–100%) for the total sample with relatively similar medians across three of four countries. Achievement rates on individual QIs showed a large variation ranging from 11% (referral to services for losing weight) to 67% (information about the importance of exercise) with significant differences in achievement rates between the countries.

Conclusions

The results indicated a potential for improvement in OA care in all four countries, but for somewhat different aspects of OA care. By exploring these differences and comparing healthcare services, ideas may be generated on how the quality might be improved across nations. Larger studies are needed to confirm and further explore the findings.