PRIME score for prediction of permanent pacemaker implantation after transcatheter aortic valve replacement.

OBJECTIVES: We sought to produce a simple scoring system that can be applied at clinical visits before transcatheter aortic valve replacement (TAVR) to stratify the risk of permanent pacemaker (PPM) after the procedure. BACKGROUND: Atrioventricular block is a known complication of TAVR. Current models for predicting the risk of PPM after TAVR are not designed to be applied clinically to assist with preprocedural planning. METHODS: Patients undergoing TAVR at the University of Colorado were split into a training cohort for the development of a predictive model, and a testing cohort for model validation. Stepwise and binary logistic regressions were performed on the training cohort to produce a predictive model. Beta coefficients from the binary logistic regression were used to create a simple scoring system for predicting the need for PPM implantation. Scores were then applied to the validation cohort to assess predictive accuracy. RESULTS: Patients undergoing TAVR from 2013 to 2019 were analyzed: with 483 included in the training cohort and 123 included in the validation cohort. The need for a pacemaker was associated with five preprocedure variables in the training cohort: PR interval > 200 ms, Right bundle branch block, valve-In-valve procedure, prior Myocardial infarction, and self-Expandable valve. The PRIME score was developed using these clinical features, and was highly accurate for predicting PPM in both the training and model validation cohorts (area under the curve 0.804 and 0.830 in the model training and validation cohorts, respectively). CONCLUSIONS: The PRIME score is a simple and accurate preprocedural tool for predicting the need for PPM implantation after TAVR.

Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data.

BACKGROUND: With cardiovascular disease increasing, substantial research has focused on the development of prediction tools. We compare deep learning and machine learning models to a baseline logistic regression using only 'known' risk factors in predicting incident myocardial infarction (MI) from harmonized EHR data. METHODS: Large-scale case-control study with outcome of 6-month incident MI, conducted using the top 800, from an initial 52 k procedures, diagnoses, and medications within the UCHealth system, harmonized to the Observational Medical Outcomes Partnership common data model, performed on 2.27 million patients. We compared several over- and under- sampling techniques to address the imbalance in the dataset. We compared regularized logistics regression, random forest, boosted gradient machines, and shallow and deep neural networks. A baseline model for comparison was a logistic regression using a limited set of 'known' risk factors for MI. Hyper-parameters were identified using 10-fold cross-validation. RESULTS: Twenty thousand Five hundred and ninety-one patients were diagnosed with MI compared with 2.25 million who did not. A deep neural network with random undersampling provided superior classification compared with other methods. However, the benefit of the deep neural network was only moderate, showing an F1 Score of 0.092 and AUC of 0.835, compared to a logistic regression model using only 'known' risk factors. Calibration for all models was poor despite adequate discrimination, due to overfitting from low frequency of the event of interest. CONCLUSIONS: Our study suggests that DNN may not offer substantial benefit when trained on harmonized data, compared to traditional methods using established risk factors for MI.

Frailty, Implantable Cardioverter Defibrillators, and Mortality: a Systematic Review.

BACKGROUND: Evidence for the benefit of implantable cardioverter defibrillators (ICD) in preventing sudden cardiac death (SCD) in older adults is mixed; age alone may not predict benefit. Frailty may help identify patients in whom an ICD does not improve overall mortality risk. METHODS: Structured search of PubMed, Embase, Web of Science, and Cochrane Central Register of Controlled Trials on 1/31/2019, without language restriction, with terms for ICD, frailty, and mortality. Frailty was defined broadly using any validated single component (e.g., walking speed, weight loss) or multi-component tool (e.g., cumulative deficit index). Each study was assessed for quality and risk of bias. RESULTS: We identified and screened 2649 titles, reviewed 280 abstracts, and extracted 71 articles. Nine articles, including two RCTs, one prospective cohort, and six retrospective cohort studies met all criteria. The most common reason for exclusion was a lack of frailty definition. Frailty definitions were heterogeneous, including cumulative deficit models, low weight, and walking speed. Follow-up time for mortality differed: from days to > 6 years. All studies indicated that mortality was higher amongst individuals identified as frail, regardless of definition. In one RCT, slow walkers did not benefit from ICD therapy after 3 years. A cohort of 83,792 Medicare beneficiaries in an ICD registry reported higher 1-year mortality following ICD in those with frailty or dementia. Four studies reported an association between being underweight and increased mortality following ICD placement. CONCLUSION: Existing literature suggests that individuals with frailty may not benefit from ICD placement for primary prevention of SCD.

Common Genetic Variant Risk Score Is Associated With Drug-Induced QT Prolongation and Torsade de Pointes Risk: A Pilot Study.

BACKGROUND: Drug-induced QT interval prolongation, a risk factor for life-threatening ventricular arrhythmias, is a potential side effect of many marketed and withdrawn medications. The contribution of common genetic variants previously associated with baseline QT interval to drug-induced QT prolongation and arrhythmias is not known. METHODS: We tested the hypothesis that a weighted combination of common genetic variants contributing to QT interval at baseline, identified through genome-wide association studies, can predict individual response to multiple QT-prolonging drugs. Genetic analysis of 22 subjects was performed in a secondary analysis of a randomized, double-blind, placebo-controlled, crossover trial of 3 QT-prolonging drugs with 15 time-matched QT and plasma drug concentration measurements. Subjects received single doses of dofetilide, quinidine, ranolazine, and placebo. The outcome was the correlation between a genetic QT score comprising 61 common genetic variants and the slope of an individual subject's drug-induced increase in heart rate-corrected QT (QTc) versus drug concentration. RESULTS: The genetic QT score was correlated with drug-induced QTc prolongation. Among white subjects, genetic QT score explained 30% of the variability in response to dofetilide (r=0.55; 95% confidence interval, 0.09-0.81; P=0.02), 23% in response to quinidine (r=0.48; 95% confidence interval, -0.03 to 0.79; P=0.06), and 27% in response to ranolazine (r=0.52; 95% confidence interval, 0.05-0.80; P=0.03). Furthermore, the genetic QT score was a significant predictor of drug-induced torsade de pointes in an independent sample of 216 cases compared with 771 controls (r2=12%, P=1×10-7). CONCLUSIONS: We demonstrate that a genetic QT score comprising 61 common genetic variants explains a significant proportion of the variability in drug-induced QT prolongation and is a significant predictor of drug-induced torsade de pointes. These findings highlight an opportunity for recent genetic discoveries to improve individualized risk-benefit assessment for pharmacological therapies. Replication of these findings in larger samples is needed to more precisely estimate variance explained and to establish the individual variants that drive these effects. CLINICAL TRIAL REGISTRATION: URL: http://www.clinicaltrials.gov. Unique identifier: NCT01873950.

SIRT2 induces the checkpoint kinase BubR1 to increase lifespan.

Mice overexpressing the mitotic checkpoint kinase gene BubR1 live longer, whereas mice hypomorphic for BubR1 (BubR1(H/H)) live shorter and show signs of accelerated aging. As wild-type mice age, BubR1 levels decline in many tissues, a process that is proposed to underlie normal aging and age-related diseases. Understanding why BubR1 declines with age and how to slow this process is therefore of considerable interest. The sirtuins (SIRT1-7) are a family of NAD(+)-dependent deacetylases that can delay age-related diseases. Here, we show that the loss of BubR1 levels with age is due to a decline in NAD(+) and the ability of SIRT2 to maintain lysine-668 of BubR1 in a deacetylated state, which is counteracted by the acetyltransferase CBP. Overexpression of SIRT2 or treatment of mice with the NAD(+) precursor nicotinamide mononucleotide (NMN) increases BubR1 abundance in vivo. Overexpression of SIRT2 in BubR1(H/H) animals increases median lifespan, with a greater effect in male mice. Together, these data indicate that further exploration of the potential of SIRT2 and NAD(+) to delay diseases of aging in mammals is warranted.

Measures of Body Size and Composition and Risk of Incident Atrial Fibrillation in Older People: The Cardiovascular Health Study.

Various anthropometric measures, including height, have been associated with atrial fibrillation (AF). This raises questions about the appropriateness of using ratio measures such as body mass index (BMI), which contains height squared in its denominator, in the evaluation of AF risk. Among older adults, the optimal anthropometric approach to risk stratification of AF remains uncertain. Anthropometric and bioelectrical impedance measures were obtained from 4,276 participants (mean age = 72.4 years) free of cardiovascular disease in the Cardiovascular Health Study. During follow-up (1989-2008), 1,050 cases of AF occurred. BMI showed a U-shaped association, whereas height, weight, waist circumference, hip circumference, fat mass, and fat-free mass were linearly related to incident AF. The strongest adjusted association occurred for height (per each 1-standard-deviation increment, hazard ratio = 1.38, 95% confidence interval: 1.25, 1.51), which exceeded all other measures, including weight (hazard ratio = 1.21, 95% confidence interval: 1.13, 1.29). Combined assessment of log-transformed weight and height showed regression coefficients that departed from the 1 to -2 ratio inherent in BMI, indicating a loss of predictive information. Risk estimates for AF tended to be stronger for hip circumference than for waist circumference and for fat-free mass than for fat mass, which was explained largely by height. These findings highlight the prominent role of body size and the inadequacy of BMI as determinants of AF in older adults.

Genetic variants related to height and risk of atrial fibrillation: the cardiovascular health study.

Increased height is a known independent risk factor for atrial fibrillation (AF). However, whether genetic determinants of height influence risk is uncertain. In this candidate gene study, we examined the association of 209 height-associated single-nucleotide polymorphisms (SNPs) with incident AF in 3,309 persons of European descent from the Cardiovascular Health Study, a prospective cohort study of older adults (aged ≥ 65 years) enrolled in 1989-1990. After a median follow-up period of 13.2 years, 879 participants developed incident AF. The height-associated SNPs together explained approximately 10% of the variation in height (P = 6.0 × 10(-8)). Using an unweighted genetic height score, we found a nonsignificant association with risk of AF (per allele, hazard ratio = 1.01, 95% confidence interval: 1.00, 1.02; P = 0.06). In weighted analyses, we found that genetically predicted height was strongly associated with AF risk (per 10 cm, hazard ratio = 1.30, 95% confidence interval: 1.03, 1.64; P = 0.03). Importantly, for all models, the inclusion of actual height completely attenuated the genetic height effect. Finally, we identified 1 nonsynonymous SNP (rs1046934) that was independently associated with AF and may warrant future study. In conclusion, we found that genetic determinants of height appear to increase the risk of AF, primarily via height itself. This approach of examining SNPs associated with an intermediate phenotype should be considered as a method for identifying novel genetic targets.

Circulating fibrosis biomarkers and risk of atrial fibrillation: The Cardiovascular Health Study (CHS).

BACKGROUND: Cardiac fibrosis is thought to play a central role in the pathogenesis of atrial fibrillation (AF). Retrospective studies have suggested that circulating fibrosis biomarkers are associated with AF, but prospective studies are limited. METHODS: We measured circulating levels of 2 fibrosis biomarkers, procollagen type III, N-terminal propeptide (PIIINP) and transforming growth factor ß1 among participants of the CHS, a population-based study of older Americans. We used Cox proportional hazards and competing risks models to examine adjusted risk of incident AF over a median follow-up of 8.8 years. RESULTS: Levels of PIIINP were assessed in 2,935 participants, of whom 767 developed AF. Compared with the median PIIINP level (4.45 µg/L), adjusted hazard ratios (95% CIs) were 0.85 (0.72-1.00) at the 10th percentile, 0.93 (0.88-0.99) at the 25th percentile, 1.04 (0.95-1.04) at the 75th percentile, and 1.07 (0.90-1.26) at the 90th. Transforming growth factor ß1 levels, assessed in 1,538 participants with 408 cases of incident AF, were not associated with AF risk. CONCLUSION: In older adults, PIIINP levels were associated with risk of incident AF in a complex manner, with an association that appeared to be positive up to median levels but with little relationship beyond that. Further studies are required to confirm and possibly delineate the mechanism for this relationship.

Evaluating the prescribing and monitoring of medications associated with QTc-prolongation in the ambulatory care setting.

RATIONALE: Little is known about the prescribing of medications with potential to cause QTc-prolongation in the ambulatory care settings. Understanding real-world prescribing of QTc-prolonging medications and actions taken to mitigate this risk will help guide strategies to optimize safety and appropriate prescribing among ambulatory patients. OBJECTIVE: To evaluate the frequency of clinician action taken to monitor and mitigate modifiable risk factors for QTc-prolongation when indicated. METHODS: This retrospective, cross-sectional study evaluated clinician action at the time of prescribing prespecified medications with potential to prolong QTc in adult patients in primary care. The index date was defined as the date the medication was ordered. Electronic health record (EHR) data were evaluated to assess patient, clinician and visit characteristics. Clinician action was determined if baseline or follow-up monitoring was ordered or if action was taken to mitigate modifiable risk factors (laboratory abnormalities or electrocardiogram [ECG] monitoring) within 48 h of prescribing a medication with QTc-prolonging risk. Descriptive statistics were used to describe current practice. RESULTS: A total of 399 prescriptions were prescribed to 386 patients, with a mean age of 51 ± 18 years, during March 2021 from a single-centre, multisite health system. Of these, 17 (4%) patients had a known history of QTc-prolongation, 170 (44%) did not have a documented history of QTc-prolongation and 199 (52%) had an unknown history (no ECG documented). Thirty-nine patients (10%) had at least one laboratory-related risk factor at the time of prescribing, specifically hypokalemia (16 patients), hypomagnesemia (8 patients) or hypocalcemia (19 patients). Of these 39 patients with laboratory risk factors, only 6 patients (15%) had their risk acknowledged or addressed by a clinician. Additionally, eight patients' most recent QTc was ≥500 ms and none had an ECG checked at the time the prescription was ordered. CONCLUSION: Despite national recommendations, medication monitoring and risk mitigation is infrequent when prescribing QTc-prolonging medications in the ambulatory care setting. These findings call for additional research to better understand this gap, including reasons for the gap and consequences on patient outcomes.

A polygenic risk score for the QT interval is an independent predictor of drug-induced QT prolongation.

Drug-induced QT prolongation (diLQTS), and subsequent risk of torsade de pointes, is a major concern with use of many medications, including for non-cardiac conditions. The possibility that genetic risk, in the form of polygenic risk scores (PGS), could be integrated into prediction of risk of diLQTS has great potential, although it is unknown how genetic risk is related to clinical risk factors as might be applied in clinical decision-making. In this study, we examined the PGS for QT interval in 2500 subjects exposed to a known QT-prolonging drug on prolongation of the QT interval over 500ms on subsequent ECG using electronic health record data. We found that the normalized QT PGS was higher in cases than controls (0.212±0.954 vs. -0.0270±1.003, P = 0.0002), with an unadjusted odds ratio of 1.34 (95%CI 1.17-1.53, P<0.001) for association with diLQTS. When included with age and clinical predictors of QT prolongation, we found that the PGS for QT interval provided independent risk prediction for diLQTS, in which the interaction for high-risk diagnosis or with certain high-risk medications (amiodarone, sotalol, and dofetilide) was not significant, indicating that genetic risk did not modify the effect of other risk factors on risk of diLQTS. We found that a high-risk cutoff (QT PGS ≥ 2 standard deviations above mean), but not a low-risk cutoff, was associated with risk of diLQTS after adjustment for clinical factors, and provided one method of integration based on the decision-tree framework. In conclusion, we found that PGS for QT interval is an independent predictor of diLQTS, but that in contrast to existing theories about repolarization reserve as a mechanism of increasing risk, the effect is independent of other clinical risk factors. More work is needed for external validation in clinical decision-making, as well as defining the mechanism through which genes that increase QT interval are associated with risk of diLQTS.

Development and validation of the Atri-Risk Conduction Index risk score to predict risk of atrial fibrillation after typical atrial flutter ablation.

BACKGROUND: Identification of patients at risk for atrial fibrillation (AF) after typical atrial flutter (tAFL) ablation is important to guide monitoring and treatment. OBJECTIVE: The purpose of this study was to create and validate a risk score to predict AF after tAFL ablation METHODS: We identified patients who underwent tAFL ablation with no AF history between 2017 and 2022 and randomly allocated to derivation and validation cohorts. We collected clinical variables and measured conduction parameters in sinus rhythm on an electrophysiology recording system (CardioLab, GE Healthcare). Univariate and multivariate logistic regressions (LogR) were used to evaluate association with AF development. RESULTS: A total of 242 consecutive patients (81% male; mean age 66 ± 11 years) were divided into derivation (n =142) and validation (n = 100) cohorts. Forty-two percent developed AF over median follow-up of 330 days. In multivariate LogR (derivation cohort), proximal to distal coronary sinus time (pCS-dCS) ≥70 ms (odds ratio [OR] 16.7; 95% confidence interval [CI] 5.6-49), pCS time ≥36 ms (OR 4.5; 95% CI 1.5-13), and CHADS2-VASc score ≥3 (OR 4.3; 95% CI 1.6-11.8) were independently associated with new AF during follow-up. The Atri-Risk Conduction Index (ARCI) score was created with 0 as minimal and 4 as high-risk using pCS-dCS ≥70 ms = 2 points; pCS ≥36 ms = 1 point; and CHADS2-VASc score ≥3 = 1 point. In the validation cohort, 0% of patients with ARCI score = 0 developed AF, whereas 89% of patients with ARCI score = 4 developed AF. CONCLUSION: We developed and validated a risk score using atrial conduction parameters and clinical risk factors to predict AF after tAFL ablation. It stratifies low-, moderate-, and high-risk patients and may be helpful in individualizing approaches to AF monitoring and anticoagulation.

Use of a noninvasive continuous monitoring device in the management of atrial fibrillation: a pilot study.

BACKGROUND: Outpatient ambulatory cardiac rhythm monitoring is a routine part of the management of patients with paroxysmal atrial fibrillation (AF). Current systems are limited by patient convenience and practicality. METHODS: We compared the Zio(®) Patch, a single-use, noninvasive waterproof long-term continuous monitoring patch, with a 24-hour Holter monitor in 74 consecutive patients with paroxysmal AF referred for Holter monitoring for detection of arrhythmias. RESULTS: The Zio(®) Patch was well tolerated, with a mean monitoring period of 10.8 ± 2.8 days (range 4-14 days). Over a 24-hour period, there was excellent agreement between the Zio(®) Patch and Holter for identifying AF events and estimating AF burden. Although there was no difference in AF burden estimated by the Zio(®) Patch and the Holter monitor, AF events were identified in 18 additional individuals, and the documented pattern of AF (persistent or paroxysmal) changed in 21 patients after Zio(®) Patch monitoring. Other clinically relevant cardiac events recorded on the Zio(®) Patch after the first 24 hours of monitoring, including symptomatic ventricular pauses, prompted referrals for pacemaker placement or changes in medications. As a result of the findings from the Zio(®) Patch, 28.4% of patients had a change in their clinical management. CONCLUSIONS: The Zio(®) Patch was well tolerated, and allowed significantly longer continuous monitoring than a Holter, resulting in an improvement in clinical accuracy, the detection of potentially malignant arrhythmias, and a meaningful change in clinical management. Further studies are necessary to examine the long-term impact of the use of the Zio(®) Patch in AF management.

Echocardiographic diastolic parameters and risk of atrial fibrillation: the Cardiovascular Health Study.

AIMS: Atrial fibrillation (AF) is the most common sustained arrhythmia in the elderly, and shares several risk factors with diastolic dysfunction, including hypertension and advanced age. The purpose of this study is to examine diastolic dysfunction as a risk for incident AF. METHODS AND RESULTS: We examined the association of echocardiographic parameters of diastolic function with the incidence of AF in 4480 participants enrolled in the Cardiovascular Health Study, an ongoing cohort of community-dwelling older adults from four US communities. Participants underwent baseline echocardiography in 1989-1990 and were followed for incident AF on routine follow-up and hospitalizations. After 50 941 person-years of follow-up (median follow-up time 12.1 years), 1219 participants developed AF. In multivariable-adjusted age-stratified Cox models, diastolic echocardiographic parameters were significantly associated with the risk of incident AF. The most significant parameters were the Doppler peak E-wave velocity and left atrial diameter, which demonstrated a positive nonlinear association [HR 1.5 (CI 1.3-1.9) and HR 1.7 (CI 1.4-2.1) for highest vs. lowest quintile, respectively], and Doppler A-wave velocity time integral, which displayed a U-shaped relationship with the risk of AF [HR 0.7 (CI 0.6-0.9) for middle vs. lowest quintile]. Each diastolic parameter displayed a significant association with adjusted NT-proBNP levels, although the nature of the association did not entirely parallel the risk of AF. Further cluster analysis revealed unique patterns of diastolic function that may identify patients at risk for AF. CONCLUSION: In a community-based population of older adults, echocardiographic measures of diastolic function are significantly associated with an increased risk of AF.

The impact of height on the risk of atrial fibrillation: the Cardiovascular Health Study.

AIMS: Atrial fibrillation (AF) is the most common sustained arrhythmia. Increased body size has been associated with AF, but the relationship is not well understood. In this study, we examined the effect of increased height on the risk of AF and explore potential mediators and implications for clinical practice. METHODS AND RESULTS: We examined data from 5860 individuals taking part in the Cardiovascular Health Study, a cohort study of older US adults followed for a median of 13.6 (women) and 10.3 years (men). Multivariate linear models and age-stratified Cox proportional hazards and risk models were used, with focus on the effect of height on both prevalent and incident AF. Among 684 (22.6%) and 568 (27.1%) incident cases in women and men, respectively, greater height was significantly associated with AF risk [hazard ratio (HR)(women) per 10 cm 1.32, confidence interval (CI) 1.16-1.50, P < 0.0001; HR(men) per 10 cm 1.26, CI 1.11-1.44, P < 0.0001]. The association was such that the incremental risk from sex was completely attenuated by the inclusion of height (for men, HR 1.48, CI 1.32-1.65, without height, and HR 0.94, CI 0.85-1.20, with height included). Inclusion of height in the Framingham model for incident AF improved discrimination. In sequential models, however, we found minimal attenuation of the risk estimates for AF with adjustment for left ventricular (LV) mass and left atrial (LA) dimension. The associations of LA and LV size measurements with AF risk were weakened when indexed to height. CONCLUSION: Independent from sex, increased height is significantly associated with the risk of AF.

A Discussion of the Contemporary Prediction Models for Atrial Fibrillation.

Atrial Fibrillation is a complex disease state with many environmental and genetic risk factors. While there are environmental factors that have been shown to increase an individual's risk of atrial fibrillation, it has become clear that atrial fibrillation has a genetic component that influences why some patients are at a higher risk of developing atrial fibrillation compared to others. This review will first discuss the clinical diagnosis of atrial fibrillation and the corresponding rhythm atrial flutter. We will then discuss how a patients' risk of stroke can be assessed by using other clinical co-morbidities. We will then review the clinical risk factors that can be used to help predict an individual patient's risk of atrial fibrillation. Many of the clinical risk factors have been used to create several different risk scoring methods that will be reviewed. We will then discuss how genetics can be used to identify individuals who are at higher risk for developing atrial fibrillation. We will discuss genome-wide association studies and other sequencing high-throughput sequencing studies. Finally, we will touch on how genetic variants derived from a genome-wide association studies can be used to calculate an individual's polygenic risk score for atrial fibrillation. An atrial fibrillation polygenic risk score can be used to identify patients at higher risk of developing atrial fibrillation and may allow for a reduction in some of the complications associated with atrial fibrillation such as cerebrovascular accidents and the development of heart failure. Finally, there is a brief discussion of how artificial intelligence models can be used to predict which patients will develop atrial fibrillation.

Profound First-Degree Atrioventricular Block in a High-Level Basketball Athlete.

First-degree atrioventricular (AV) block (PR interval >200 ms) is commonly observed among screening electrocardiogram (ECG) in athletes. Profound first-degree AV block (PR interval >400 ms) and Mobitz type I (Wenckebach) second-degree AV block are generally uncommon and often require further workup on a case-by-case basis, particularly when there is concern for a structural cardiac abnormality. In this case, we present an example of an asymptomatic profound first-degree AV block with Mobitz type I (Wenckebach) second-degree AV block. Transthoracic echocardiogram and stress echocardiogram were unremarkable and the patient was cleared to participate in sports without any restriction. Physicians managing athletes should be aware of ECG features that require additional evaluation and cardiology consultation.

Clinician challenges to evidence-based prescribing for heart failure and reduced ejection fraction: A qualitative evaluation.

BACKGROUND: Reasons for suboptimal prescribing for heart failure with reduced ejection fraction (HFrEF) have been identified, but it is unclear if they remain relevant with recent advances in healthcare delivery and technologies. This study aimed to identify and understand current clinician-perceived challenges to prescribing guideline-directed HFrEF medications. METHODS: We conducted content analysis methodology, including interviews and member-checking focus groups with primary care and cardiology clinicians. Interview guides were informed by the Cabana Framework. RESULTS: We conducted interviews with 33 clinicians (13 cardiology specialists, 22 physicians) and member checking with 10 of these. We identified four levels of challenges from the clinician perspective. Clinician level challenges included misconceptions about guideline recommendations, clinician assumptions (e.g., drug cost or affordability), and clinical inertia. Patient-clinician level challenges included misalignment of priorities and insufficient communication. Clinician-clinician level challenges were primarily between generalists and specialists, including lack of role clarity, competing priorities of providing focused versus holistic care, and contrasting confidence regarding safety of newer drugs. Policy and system/organisation level challenges included insufficient access to timely/reliable patient data, and unintended care gaps for medications without financially incentivized metrics. CONCLUSION: This study presents current challenges faced by cardiology and primary care which can be used to strategically design interventions to improve guideline-directed care for HFrEF. The findings support the persistence of many challenges and also sheds light on new challenges. New challenges identified include conflicting perspectives between generalists and specialists, hesitancy to prescribe newer medications due to safety concerns, and unintended consequences related to value-based reimbursement metrics for select medications.

Evaluation of Quantitative Decision-Making for Rhythm Management of Atrial Fibrillation Using Tabular Q-Learning.

Background Rhythm management is a complex decision for patients with atrial fibrillation (AF). Although clinical trials have identified subsets of patients who might benefit from a given rhythm-management strategy, for individual patients it is not always clear which strategy is expected to have the greatest mortality benefit or durability. Methods and Results In this investigation 52 547 patients with a new atrial fibrillation diagnosis between 2010 and 2020 were retrospectively identified. We applied a type of artificial intelligence called tabular Q-learning to identify the optimal initial rhythm-management strategy, based on a composite outcome of mortality, change in treatment, and sustainability of the given treatment, termed the reward function. We first applied an unsupervised learning algorithm using a variational autoencoder with K-means clustering to cluster atrial fibrillation patients into 8 distinct phenotypes. We then fit a Q-learning algorithm to predict the best outcome for each cluster. Although rate-control strategy was most frequently selected by treating providers, the outcome was superior for rhythm-control strategies across all clusters. Subjects in whom provider-selected treatment matched the Q-table recommendation had fewer total deaths (4 [8.5%] versus 473 [22.4%], odds ratio=0.32, P=0.02) and a greater reward (P=4.8×10-6). We then demonstrated application of dynamic learning by updating the Q-table prospectively using batch gradient descent, in which the optimal strategy in some clusters changed from cardioversion to ablation. Conclusions Tabular Q-learning provides a dynamic and interpretable approach to apply artificial intelligence to clinical decision-making for atrial fibrillation. Further work is needed to examine application of Q-learning prospectively in clinical patients.

A machine learning evaluation of patient characteristics associated with prescribing of guideline-directed medical therapy for heart failure.

Introduction/background: Patients with heart failure and reduced ejection fraction (HFrEF) are consistently underprescribed guideline-directed medications. Although many barriers to prescribing are known, identification of these barriers has relied on traditional a priori hypotheses or qualitative methods. Machine learning can overcome many limitations of traditional methods to capture complex relationships in data and lead to a more comprehensive understanding of the underpinnings driving underprescribing. Here, we used machine learning methods and routinely available electronic health record data to identify predictors of prescribing. Methods: We evaluated the predictive performance of machine learning algorithms to predict prescription of four types of medications for adults with HFrEF: angiotensin converting enzyme inhibitor/angiotensin receptor blocker (ACE/ARB), angiotensin receptor-neprilysin inhibitor (ARNI), evidence-based beta blocker (BB), or mineralocorticoid receptor antagonist (MRA). The models with the best predictive performance were used to identify the top 20 characteristics associated with prescribing each medication type. Shapley values were used to provide insight into the importance and direction of the predictor relationships with medication prescribing. Results: For 3,832 patients meeting the inclusion criteria, 70% were prescribed an ACE/ARB, 8% an ARNI, 75% a BB, and 40% an MRA. The best-predicting model for each medication type was a random forest (area under the curve: 0.788-0.821; Brier score: 0.063-0.185). Across all medications, top predictors of prescribing included prescription of other evidence-based medications and younger age. Unique to prescribing an ARNI, the top predictors included lack of diagnoses of chronic kidney disease, chronic obstructive pulmonary disease, or hypotension, as well as being in a relationship, nontobacco use, and alcohol use. Discussion/conclusions: We identified multiple predictors of prescribing for HFrEF medications that are being used to strategically design interventions to address barriers to prescribing and to inform further investigations. The machine learning approach used in this study to identify predictors of suboptimal prescribing can also be used by other health systems to identify and address locally relevant gaps and solutions to prescribing.