Alert-based computerized decision support for high-risk hospitalized patients with atrial fibrillation not prescribed anticoagulation: a randomized, controlled trial (AF-ALERT)

Clinical decision support systems to optimize adherence to anticoagulant guidelines in patients with atrial fibrillation: a systematic review and meta-analysis of randomized controlled trials

BACKGROUND

Clinical decision support systems (CDSS) have been utilized as a low-cost intervention to improve healthcare process measures. Thus, we aim to estimate CDSS efficacy to optimize adherence to oral anticoagulant guidelines in eligible patients with atrial fibrillation (AF).

METHODS

A systematic review and meta-analysis of randomized controlled trials (RCTs) retrieved from PubMed, WOS, SCOPUS, EMBASE, and CENTRAL through August 2023. We used RevMan V. 5.4 to pool dichotomous data using risk ratio (RR) with a 95% confidence interval (CI).

PROSPERO ID

CRD42023471806.

RESULTS

We included nine RCTs with a total of 25,573 patients. There was no significant difference, with the use of CDSS compared to routine care, in the number of patients prescribed anticoagulants (RR: 1.06, 95% CI [0.98, 1.14], P = 0.16), the number of patients prescribed antiplatelets (RR: 1.01 with 95% CI [0.97, 1.06], P = 0.59), all-cause mortality (RR: 1.19, 95% CI [0.31, 4.50], P = 0.80), major bleeding (RR: 0.84, 95% CI [0.21, 3.45], P = 0.81), and clinically relevant non-major bleeding (RR: 1.05, 95% CI [0.52, 2.16], P = 0.88). However, CDSS was significantly associated with reduced incidence of myocardial infarction (RR: 0.18, 95% CI [0.06, 0.54], P = 0.002) and cerebral or systemic embolic event (RR: 0.11, 95% CI [0.01, 0.83], P = 0.03).

CONCLUSION

We report no significant difference with the use of CDSS compared to routine care in anticoagulant or antiplatelet prescription in eligible patients with AF. CDSS was associated with a reduced incidence of myocardial infarction and cerebral or systemic embolic events.

Computerized clinical decision support to improve stroke prevention therapy in primary care management of atrial fibrillation: a cluster randomized trial

BACKGROUND

Despite guidelines supporting antithrombotic therapy use in atrial fibrillation (AF), under-prescribing persists. We assessed whether computerized clinical decision support (CDS) would enable guideline-based antithrombotic therapy for AF patients in primary care.

METHODS

This cluster randomized trial of CDS versus usual care (UC) recruited participants from primary care practices across Nova Scotia, following them for 12 months. The CDS tool calculated bleeding and stroke risk scores and provided recommendations for using oral anticoagulants (OAC) per Canadian guidelines.

RESULTS

From June 14, 2014 to December 15, 2016, 203 primary care providers (99 UC, 104 CDS) with access to high-speed Internet were recruited, enrolling 1,145 eligible patients (543 UC, 590 CDS) assigned to the same treatment arm as their provider. Patient mean age was 72.3 years; most were male (350, 64.5% UC, 351, 59.5% CDS) and from a rural area (298, 54.9% UC, 315, 53.4% CDS). At baseline, a higher than anticipated proportion of patients were receiving guideline-based OAC therapy (373, 68.7% UC, 442, 74.9% CDS; relative risk [RR] 0.97 (95% confidence interval [CI], 0.87-1.07; P = .511)). At 12 months, prescription data were available for 538 usual care and 570 CDS patients, and significantly more CDS patients were managed according to guidelines (415, 77.1% UC, 479, 84.0% CDS; RR 1.08 (95% CI, 1.01-1.15; P = .024)).

CONCLUSION

Notwithstanding high baseline rates, primary care provider access to the CDS over 12 months further optimized the prescribing of OAC therapy per national guidelines to AF patients potentially eligible to receive it. This suggests that CDS can be effective in improving clinical process of care.

TRIAL REGISTRATION

Clinical Trials NCT01927367. https://clinicaltrials.gov/ct2/show/NCT01927367?term=NCT01927367&draw=2&rank=1.

An interrupted time series study of electronic health record clinical decision support for providers caring for patients with atrial fibrillation at increased stroke risk

PURPOSE

To measure the effect of clinical decision support (CDS) on anticoagulation rates in patients with atrial fibrillation (AFib) or atrial flutter (AFlut) at high stroke risk and receiving care in outpatient settings, and to assess provider response to CDS.

METHODS

This observational, quasi-experimental, interrupted time series study utilized electronic health record data at a large integrated delivery network in Texas from April to November 2020. CDS consisted of an electronic Best Practice Advisory (BPA)/alert (Epic Systems Corporation, Verona, WI) with links to 2 AFib order sets displayed to providers in outpatient settings caring for non-anticoagulated patients with AFib and elevated CHA2DS2VASc scores. Weekly outpatient anticoagulation rates were assessed in patients with high stroke risk before and after implementation of CDS. Alert actions and acknowledgment reasons were evaluated descriptively.

RESULTS

Mean (SD) weekly counts of eligible patients were 8,917 (566) before and 8,881 (811) after implementation. Weekly anticoagulation rates increased during the pre-BPA study period (β1 = 0.07%; SE, 0.02%; P = 0.0062); however, there were no significant changes in the level (β2 = 0.60%; SE, 0.42%; P = 0.1651) or trend (β3 = -0.01%; SE, 0.05%; P = 0.8256) of anticoagulation rates associated with CDS implementation. In encounters with the BPA/alert displayed (n = 17,654), acknowledgment reasons were provided in 4,473 (25.3%) of the encounters, with prescribers most commonly citing bleeding risk (n = 1,327, 7.5%) and fall risk (n = 855, 4.8%).

CONCLUSION

There was a significant trend of increasing anticoagulation rates during the pre-BPA period, with no significant change in trend during the post-BPA period relative to the pre-BPA period.

Practical solutions for implementation of blood cholesterol guidelines in clinical practice

Underutilization of lipid-lowering therapy (LLT) and failure to attain guideline-recommended low-density lipoprotein cholesterol (LDL-C) goals are important quality gaps in cardiovascular risk optimization, especially among patients with atherosclerotic cardiovascular disease (ASCVD). Large database analyses demonstrate an unmet need for improved LDL-C measurement, and that nearly 75% of patients with ASCVD have an LDL-C level above guideline-recommended levels, and greater than 50% are not treated with statins or ezetimibe. Proposed solutions for overcoming these obstacles to optimal lipid management include provider- and patient-facing educational interventions, health information technology strategies, implementation of incentive-based care, advocacy efforts, and systems-based process innovations. While individual interventions may not be enough to overcome the totality of barriers to optimal LLT, comprehensive multifaceted approaches that address barriers at the provider, patient, and healthcare delivery level are likely to offer the greatest likelihood of success and improved patient outcomes.

Electronic alerts for ambulatory patients with atrial fibrillation not prescribed anticoagulation: A randomized, controlled trial (AF-ALERT2)

BACKGROUND

Despite widely available risk stratification tools, safe and effective anticoagulants, and guideline recommendations, anticoagulation for stroke prevention in atrial fibrillation (AF) is under-prescribed in ambulatory patients. To assess the impact of alert-based computerized decision support (CDS) on anticoagulation prescription in ambulatory patients with AF and high-risk for stroke, we conducted this randomized controlled trial.

METHODS

Patients with AF and CHA₂DS_2-VASc score ≥ 2 who were not prescribed anticoagulation and had a clinic visit at Brigham and Women's Hospital were enrolled. Patients were randomly allocated, according to Attending Physician of record, to intervention (alert-based CDS) versus control (no notification). The primary efficacy outcome was the frequency of anticoagulant prescription.

RESULTS

The CDS tool assigned 395 and 403 patients to the alert and control groups, respectively. Alert patients were more likely to be prescribed anticoagulation within 48 h of the clinic visit (15.4 % vs. 7.7 %, p < 0.001) and at 90 days (17.2 % vs. 9.9 %, p < 0.01). Direct oral anticoagulants were the predominantly prescribed form of anticoagulation. No significant differences were observed in stroke, TIA, or systemic embolic events (0 % vs. 0.8 %, p = 0.09), symptomatic VTE (0.5 % vs. 1 %, p = 0.43), all-cause mortality (2 % vs. 0.7 %, p = 0.12), or major adverse cardiovascular events (2.8 % vs. 2.5 %, p = 0.79) at 90 days.

CONCLUSIONS

An alert-based CDS strategy increased a primary efficacy outcome of anticoagulation in clinic patients with AF and high-risk for stroke who were not receiving anticoagulation at the time of the office visit. The study was likely underpowered to assess an impact on clinical outcomes.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier- NCT02958943.

BARRIERS TO GUIDELINE-DIRECTED ANTICOAGULATION IN PATIENTS WITH ATRIAL FIBRILLATION NEW APPROACHES TO AN OLD PROBLEM

Optimising guideline-directed anticoagulation in atrial fibrillation remains a perennial problem despite strong evidence for improved health outcomes with use of guideline-directed anticoagulation. Efforts to improve uptake have been hampered by barriers found at the level of the physician, patient, disease and choices of therapy. Clinician judgement is often clouded by factors such as therapeutic inertia, aversion to bleeding risk and implicit bias. For patients, negative pre-conceptions of therapy, impact of therapy on day-to-day life and the nocebo effect pose significant barriers. Both groups are impacted by poor education. Utility of a single pronged approach directed towards clinicians or patients have demonstrated variable success, with the highest impact appreciated in studies employing shared decision models. Further, there is emerging evidence for use of integrated models of care, which have shown improved efficacy in improving patient outcomes, as well as use of digital platforms such as mobile app-based interventions, which can be of aid to the clinician in improving patient adherence to anticoagulation with translated improved outcomes in clinical trials. Our narrative review article aims to investigate the physician and health system, patient, as well as drug therapy and disease barriers to uptake of guideline-directed anticoagulation in treatment of non-valvular atrial fibrillation.

Using a Clinical Decision Support System to Improve Anticoagulation in Patients with Nonvalve Atrial Fibrillation in China's Primary Care Settings: A Feasibility Study

BACKGROUND

To primarily investigate the effect of using a clinical decision support system (CDSS) in community health centers in Shanghai, China, on the proportion of patients prescribed guideline-directed antithrombotic therapy. This study also gauged the general practitioner (GP)'s acceptance of the CDSS who worked in the atrial fibrillation (AF) special consulting room of the CDSS group.

METHODS

This was a prospective cohort study that included a semistructured interview and a feasibility study for a cluster-randomized controlled trial. Eligible patients who sought medical care in the AF special consulting rooms in two community health centers in Shanghai, China, between April 1, 2020, and October 1, 2020, were enrolled, and their medical records from the enrollment date, up to October 1, 2021, were extracted. Based on whether the GPs in the AF special consulting rooms of the two sites used the CDSS or not, we classified the two sites as a software group and a control group. The CDSS could automatically assess the risks of stroke and bleeding and provide suggestions on treatment, follow-up, adjustment of anticoagulants or dosage, and other items. The primary outcome was the proportion of patients prescribed guideline-directed antithrombotic therapy. We also conducted a semistructured interview with the GP in the AF special consulting rooms of the software group regarding the acceptance of the CDSS and suggestions on the optimization of the CDSS and the study protocol of the cluster-randomized controlled trial in the future.

RESULTS

Eighty-four patients completed the follow-up. The mean age of these subjects was 75.71 years, the median time of clinical visits was six times per person, and the follow-up duration was 15 months. The basic demographics were similar between the two groups, except for age (t = 2.109, p = 0.038) and the HAS-BLED score (χ ² = 4.363, p = 0.037). The primary outcome in the software group was 8.071 times higher than that in the control group (adjusted odds ratio (OR) = 8.071, 95% confidence interval (2.570-25.344), p < 0.001). The frequency of consultation between groups was not significantly different (p = 0.981). It seemed that the incidence of adverse clinical events in the software group was lower than that in the control group. The main reason for dropouts in both groups was "following up in other hospitals." The GP in the AF special consulting rooms of the software group accepted the CDSS well.

CONCLUSIONS

The findings indicated that it was feasible to further promote the CDSS in the study among community health centers in China. The use of the CDSS might improve the proportion of patients prescribed guideline-directed antithrombotic therapy. The GP in the AF special consulting room of the software group showed a positive attitude toward the CDSS.

SUPPORT-AF IV: Supporting use of AC through provider prompting about oral anticoagulation therapy for AF clinical trial study protocol

Background

Six million Americans suffer from atrial fibrillation (AF), a heart rhythm abnormality that significantly increases the risk of stroke. AF is responsible for 15% of ischemic strokes, which lead to permanent disability in 60% of cases and death in up to 20%. Anticoagulation (AC) is the mainstay for stroke prevention in patients with AF. Despite guidelines recommending AC for patients, up to half of eligible patients are not on AC. Clinical decision support tools in the electronic health record (EHR) can help bridge the disparity in AC prescription for patients with AF.

Objective

To enhance and assess the effectiveness of our previous rule-based alert on AC initiation and persistence in a diverse patient population from UMass-Memorial Medical Center and University of Florida at Jacksonville.

Methods/Results

Using the EHR, we will track AC initiation and persistence. We will interview both patients and providers to determine a measure of satisfaction with AC management. We will track digital crumbs to better understand the alert’s mechanism of effect and further add enhancements. These enhancements will be used to refine the alert and aid in developing an implementation toolkit to facilitate use of the alert at other health systems.

Conclusion

If the number of AC starts, the likelihood of persisting on AC, and the frequency alert use are found to be higher among intervention vs control providers, we believe such findings will confirm our hypothesis on the effectiveness of our alert.

Association of Socioeconomic Disadvantage With Mortality and Readmissions Among Older Adults Hospitalized for Pulmonary Embolism in the United States

Background In the United States, hospitalizations for pulmonary embolism (PE) are increasing among older adults insured by Medicare. Although efforts to reduce health disparities have intensified, it remains unclear whether clinical outcomes differ between socioeconomically disadvantaged and nondisadvantaged Medicare beneficiaries hospitalized with PE. Methods and Results In this study, there were 53 386 Medicare fee-for-service beneficiaries age ≥65 years hospitalized for PE between October 2015 and January 2017. Of these, 5494 (10.3%) were socioeconomically disadvantaged and 47 892 (89.7%) were nondisadvantaged. Socioeconomically disadvantaged adults were of similar age as nondisadvantaged adults (77.1 versus 77.0), more likely to be female (68.5% versus 54.2%), and less likely to receive advanced therapies (11.0% versus 12.1%). After adjustment for demographics, 90-day all-cause mortality rates were similar between disadvantaged and nondisadvantaged adults. In contrast, 1-year mortality rates were higher among socioeconomically disadvantaged adults (hazard ratio [HR], 1.16; 95% CI, 1.10-1.22), although these differences were partially attenuated after additional adjustments for comorbidities and PE severity (HR, 1.09; 95% CI, 1.02-1.16). Risk-adjusted 30-day and 90-day all-cause readmission rates were substantially higher among socioeconomically disadvantaged patients (30-day HR, 1.14 [95% CI, 1.06-1.22]; 90-day HR, 1.18 [95% CI, 1.12-1.25]). In addition, 90-day readmissions attributed to PE, deep vein thrombosis, and/or bleeding were higher among socioeconomically disadvantaged patients (HR, 1.16; 95% CI, 1.02-1.32). Conclusions Socioeconomically disadvantaged older adults hospitalized with PE have higher 1-year mortality rates compared with their nondisadvantaged counterparts. Nearly 1 in 3 socioeconomically disadvantaged older adults was readmitted within 90 days of a hospitalization for PE. Targeted strategies are needed to improve transitional and ambulatory care for this vulnerable population.

Stroke risk factors and outcomes among hospitalized women with atrial fibrillation

Observational cohort analyses suggest that women with atrial fibrillation (AF) endure a greater burden of stroke. We conducted an analysis of an observational cohort study completed at our tertiary care medical center to assess sex-related differences in cardiovascular risk factors, prescription of antithrombotic therapy, and 90-day outcomes. We analyzed 5000 hospitalized patients with AF: 1888 women and 3112 men. Clinical characteristics of AF, risk of stroke and bleeding, prescription of antithrombotic therapy, and 90-day clinical outcomes, including stroke and all-cause mortality, were compared. We observed a 50% higher relative frequency of stroke in hospitalized women with AF compared with men. While the frequencies of prescription of antithrombotic therapy at discharge were similar, anticoagulation was omitted in 40% of women with AF. The 90-day frequencies of major adverse events and mortality were increased in hospitalized women with AF not prescribed antithrombotic therapy at discharge. Prescription of anticoagulation in women with AF at hospital discharge was associated with a 60% and 40% relative reduction in the odds of mortality and major adverse events at 90 days. In conclusion, women hospitalized with AF have a higher risk of stroke at 90 days compared with men. Anticoagulation at hospital discharge was omitted in 40% of women with AF, but when prescribed, was associated with a reduction in mortality and major adverse events at 90 days, respectively. We analyzed 5000 hospitalized patients with atrial fibrillation (AF) (1888 women and 3112 men) in an observational cohort study completed at our tertiary care medical center to assess sex-related differences in cardiovascular risk factors, prescription of antithrombotic therapy, and 90-day outcomes. We observed a 50% higher relative frequency of stroke in hospitalized women with AF compared with men. The 90-day frequencies of major adverse events and mortality were increased in hospitalized women with AF not prescribed antithrombotic therapy at discharge. Prescription of anticoagulation in women with AF at hospital discharge was associated with a 60% and 40% relative reduction in the odds of mortality and major adverse events at 90 days.

SUPPORT-AF III: supporting use of AC through provider prompting about oral anticoagulation therapy for AF

Only half of atrial fibrillation (AF) patients with elevated stroke risk receive anticoagulation (AC). Electronic health record (EHR) alerts have the potential to close the gap. We designed an outpatient EHR alert (linked to an order set for ordering AC, labs, and specialty referrals) that fired when cardiology and primary care providers (PCPs) saw AF patients not on AC. We assigned all untreated patients seen by cardiology providers and PCPs in the 8 months before and after the alert launch to pre- and post-launch intervention cohorts, respectively. Untreated AF patients seeing other types of providers became controls. We then compared the difference in AC starts between intervention and control patients post-launch to the same difference prelaunch (adjusting for covariates). We measured alert responsiveness as how often patients had at least one encounter with a provider, who interacted with the alert. The adjusted percentage of AC starts for the prelaunch cohort was 20% for intervention patients and 17% for controls (difference = 3%); post-launch, the percentage was 13% for both post-launch intervention and controls (difference = 0%). The difference in difference was - 3% (p value 0.63). For half of patients, at least one provider was responsive to our alert. Reasons for no AC commonly included relative contraindications (e.g. fall, gastrointestinal bleed). Our alert did not increase AC starts but responsiveness to it was high. Increasing AC starts will likely require education surrounding relative contraindications.

Current Drug Treatment Strategies for Atrial Fibrillation and TASK-1 Inhibition as an Emerging Novel Therapy Option

Atrial fibrillation (AF) is the most common sustained arrhythmia with a prevalence of up to 4% and an upwards trend due to demographic changes. It is associated with an increase in mortality and stroke incidences. While stroke risk can be significantly reduced through anticoagulant therapy, adequate treatment of other AF related symptoms remains an unmet medical need in many cases. Two main treatment strategies are available: rate control that modulates ventricular heart rate and prevents tachymyopathy as well as rhythm control that aims to restore and sustain sinus rhythm. Rate control can be achieved through drugs or ablation of the atrioventricular node, rendering the patient pacemaker-dependent. For rhythm control electrical cardioversion and pharmacological cardioversion can be used. While electrical cardioversion requires fasting and sedation of the patient, antiarrhythmic drugs have other limitations. Most antiarrhythmic drugs carry a risk for pro-arrhythmic effects and are contraindicated in patients with structural heart diseases. Furthermore, catheter ablation of pulmonary veins can be performed with its risk of intraprocedural complications and varying success. In recent years TASK-1 has been introduced as a new target for AF therapy. Upregulation of TASK-1 in AF patients contributes to prolongation of the action potential duration. In a porcine model of AF, TASK-1 inhibition by gene therapy or pharmacological compounds induced cardioversion to sinus rhythm. The DOxapram Conversion TO Sinus rhythm (DOCTOS)-Trial will reveal whether doxapram, a potent TASK-1 inhibitor, can be used for acute cardioversion of persistent and paroxysmal AF in patients, potentially leading to a new treatment option for AF.

An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records

Background

Secondary hypertension is a kind of hypertension with a definite etiology and may be cured. Patients with suspected secondary hypertension can benefit from timely detection and treatment and, conversely, will have a higher risk of morbidity and mortality than those with primary hypertension.

Objective

The aim of this study was to develop and validate machine learning (ML) prediction models of common etiologies in patients with suspected secondary hypertension.

Methods

The analyzed data set was retrospectively extracted from electronic medical records of patients discharged from Fuwai Hospital between January 1, 2016, and June 30, 2019. A total of 7532 unique patients were included and divided into 2 data sets by time: 6302 patients in 2016-2018 as the training data set for model building and 1230 patients in 2019 as the validation data set for further evaluation. Extreme Gradient Boosting (XGBoost) was adopted to develop 5 models to predict 4 etiologies of secondary hypertension and occurrence of any of them (named as composite outcome), including renovascular hypertension (RVH), primary aldosteronism (PA), thyroid dysfunction, and aortic stenosis. Both univariate logistic analysis and Gini Impurity were used for feature selection. Grid search and 10-fold cross-validation were used to select the optimal hyperparameters for each model.

Results

Validation of the composite outcome prediction model showed good performance with an area under the receiver-operating characteristic curve (AUC) of 0.924 in the validation data set, while the 4 prediction models of RVH, PA, thyroid dysfunction, and aortic stenosis achieved AUC of 0.938, 0.965, 0.959, and 0.946, respectively, in the validation data set. A total of 79 clinical indicators were identified in all and finally used in our prediction models. The result of subgroup analysis on the composite outcome prediction model demonstrated high discrimination with AUCs all higher than 0.890 among all age groups of adults.

Conclusions

The ML prediction models in this study showed good performance in detecting 4 etiologies of patients with suspected secondary hypertension; thus, they may potentially facilitate clinical diagnosis decision making of secondary hypertension in an intelligent way.

Big Data and Atrial Fibrillation: Current Understanding and New Opportunities

Atrial fibrillation (AF) is the most common arrhythmia with diverse etiology that remarkably relates to high morbidity and mortality. With the advancements in intensive clinical and basic research, the understanding of electrophysiological and pathophysiological mechanism, as well as treatment of AF have made huge progress. However, many unresolved issues remain, including the core mechanisms and key intervention targets. Big data approach has produced new insights into the improvement of the situation. A large amount of data have been accumulated in the field of AF research, thus using the big data to achieve prevention and precise treatment of AF may be the direction of future development. In this review, we will discuss the current understanding of big data and explore the potential applications of big data in AF research, including predictive models of disease processes, disease heterogeneity, drug safety and development, precision medicine, and the potential source for big data acquisition. Grapical abstract.

Registry of Arterial and Venous Thromboembolic Complications in Patients With COVID-19

Background

Cardiovascular complications, including myocardial infarction, ischemic stroke, and pulmonary embolism, represent an important source of adverse outcomes in coronavirus disease-2019 (COVID-19).

Objectives

To assess the frequency of arterial and venous thromboembolic disease, risk factors, prevention and management patterns, and outcomes in patients with COVID-19, the authors designed a multicenter, observational cohort study.

Methods

We analyzed a retrospective cohort of 1,114 patients with COVID-19 diagnosed through our Mass General Brigham integrated health network. The total cohort was analyzed by site of care: intensive care (n = 170); hospitalized nonintensive care (n = 229); and outpatient (n = 715). The primary study outcome was a composite of adjudicated major arterial or venous thromboembolism.

Results

Patients with COVID-19 were 22.3% Hispanic/Latinx and 44.2% non-White. Cardiovascular risk factors of hypertension (35.8%), hyperlipidemia (28.6%), and diabetes (18.0%) were common. Prophylactic anticoagulation was prescribed in 89.4% of patients with COVID-19 in the intensive care cohort and 84.7% of those in the hospitalized nonintensive care setting. Frequencies of major arterial or venous thromboembolism, major cardiovascular adverse events, and symptomatic venous thromboembolism were highest in the intensive care cohort (35.3%, 45.9%, and 27.0 %, respectively) followed by the hospitalized nonintensive care cohort (2.6%, 6.1%, and 2.2%, respectively) and the outpatient cohort (0% for all).

Conclusions

Major arterial or venous thromboembolism, major adverse cardiovascular events, and symptomatic venous thromboembolism occurred with high frequency in patients with COVID-19, especially in the intensive care setting, despite a high utilization rate of thromboprophylaxis.

Patients with perceived high-bleeding risk and computerized decision support for stroke prevention in atrial fibrillation: an AF-ALERT substudy : Piazza: outcomes of high-bleeding risk AF patients

A perceived increased risk of bleeding is one of the most frequent reasons for withholding anticoagulation for stroke prevention in atrial fibrillation (AF). We previously conducted a randomized controlled trial of alert-based computerized decision support to increase prescription of anticoagulation in hospitalized patients with AF. To determine the clinical characteristics and outcomes of those patients whose inpatient health care providers received a computer alert, we analyzed all 248 patients in the alert group. Patients for whom providers elected to omit anticoagulation and provided a rationale of a perceived high risk of bleeding were compared with those who were not designated as high-risk. Perceived high risk of bleeding was the most common reason (77%) for omitting anticoagulation. Median HAS-BLED scores were similar in these patients compared with those who were not deemed to have an increased bleeding risk (3 vs. 3, p = 0.44). Despite being categorized as too high-risk for bleeding to receive antithrombotic therapy at the time of the alert, nearly 12% of these patients were ultimately prescribed anticoagulation by 90 days. The frequency of major and clinically-relevant non-major bleeding was similar between the groups. The frequency of death, myocardial infarction, stroke, or systemic embolic event was similar in both groups (10.2% vs. 12.4%, p = 0.59). In conclusion, a perceived high risk of bleeding was the most common reason for omission of anticoagulation in patients with AF after a computerized alert. Perceived high risk of bleeding was not reflected in a higher HAS-BLED score.Clinical trial registration: ClinicalTrials.gov Identifier: NCT02339493 https://clinicaltrials.gov/ct2/show/NCT02339493 In a randomized controlled trial of computerized decision support to increase prescription of antithrombotic therapy in hospitalized patients with atrial fibrillation (AF), a perceived high risk of bleeding was the most common reason (77%) for omitting antithrombotic therapy after an on-screen alert. Median HAS-BLED scores were similar in these patients compared with those who were not deemed to have an increased bleeding risk (3 vs. 3, p = 0.44). Despite being categorized as too high-risk for bleeding to receive antithrombotic therapy for stroke prevention at the time of the alert, nearly 12% of these patients were ultimately prescribed anticoagulation over the ensuing 90 days.

Semantic computational analysis of anticoagulation use in atrial fibrillation from real world data

Atrial fibrillation (AF) is the most common arrhythmia and significantly increases stroke risk. This risk is effectively managed by oral anticoagulation. Recent studies using national registry data indicate increased use of anticoagulation resulting from changes in guidelines and the availability of newer drugs. The aim of this study is to develop and validate an open source risk scoring pipeline for free-text electronic health record data using natural language processing. AF patients discharged from 1^st January 2011 to 1^st October 2017 were identified from discharge summaries (N = 10,030, 64.6% male, average age 75.3 ± 12.3 years). A natural language processing pipeline was developed to identify risk factors in clinical text and calculate risk for ischaemic stroke (CHA₂DS₂-VASc) and bleeding (HAS-BLED). Scores were validated vs two independent experts for 40 patients. Automatic risk scores were in strong agreement with the two independent experts for CHA₂DS₂-VASc (average kappa 0.78 vs experts, compared to 0.85 between experts). Agreement was lower for HAS-BLED (average kappa 0.54 vs experts, compared to 0.74 between experts). In high-risk patients (CHA₂DS₂-VASc ≥2) OAC use has increased significantly over the last 7 years, driven by the availability of DOACs and the transitioning of patients from AP medication alone to OAC. Factors independently associated with OAC use included components of the CHA₂DS₂-VASc and HAS-BLED scores as well as discharging specialty and frailty. OAC use was highest in patients discharged under cardiology (69%). Electronic health record text can be used for automatic calculation of clinical risk scores at scale. Open source tools are available today for this task but require further validation. Analysis of routinely collected EHR data can replicate findings from large-scale curated registries.