Publications

ABSTRACT Background – Severe aortic stenosis (AS) and mitral regurgitation (MR) are frequently undertreated and characterized by persistent sex, racial and ethnic, socioeconomic, and geographic disparities despite effective valve therapies. Whether automated electronic clinician notification (ECN) alerts improve the evaluation and treatment of AS and MR across health systems is unknown. Objective – To evaluate … Continued

ABSTRACT Background: Despite increased awareness of its clinical consequences, personalized risk stratification in patients with moderateaortic stenosis (AS) remains ambiguous. We studied predictors of progression and clinical outcomes in moderate AS to improverisk stratification and add to the existing literature. Methods: Data collected through the Tempus Next care pathway intelligence platform at our tertiary referral … Continued

Abstract Background – Aortic stenosis (AS) and mitral regurgitation (MR) are common cardiac conditions associated with significant morbidity and mortality if left untreated. Despite the availability of effective therapies, many patients with severe AS and MR do not receive timely interventions, with disparities particularly affecting minority populations, women, and those in rural areas. Methods – … Continued

Abstract Background – Many medications are associated with long QTc (LQT). Current LQT predictors have limited generalizability and/or modest performance. Objective – To compare performance of machine learning-enabled approaches to drug-induced LQT prediction with current risk scores, including Tisdale and RISQ-PATH. Methods – We identified patients who began QTc-prolongers (QTdrugs) and had follow-up 12-lead ECGs … Continued

BACKGROUND/AIMS Severe aortic stenosis (AS) and mitral regurgitation (MR) are common valvular heart disease conditions associated with significant morbidity and mortality if not identified and treated in a timely fashion. Despite the availability of effective transcatheter and surgical therapies, many patients, especially those from minority, female, and rural populations, do not receive timely referral or … Continued

Abstract Low ejection fraction (EF), an indicator of impaired heart function, often goes undiagnosed and can lead to avoidable heart failure and arrhythmias. We developed and externally validated a deep learning model for detecting low EF from 12-lead electrocardiograms. The model achieved 85.8% sensitivity and 83.0% specificity on an independent validation cohort, with consistent results … Continued

Abstract Background: Despite increased awareness of its clinical consequences, personalized risk stratification in patients with moderate aortic stenosis (AS) remains ambiguous. We studied predictors of progression and clinical outcomes in moderate AS to improve risk stratification and add to the existing literature. Methods: Data collected through the Tempus Next care pathway intelligence platform at our … Continued

Background – Identifying the set of patients with a particular disease diagnosis across electronic health records (EHRs), referred to as a phenotype, is an important step in clinical research and applications. However, this task is often challenging, where incomplete data can render definitive classifications impossible. We propose a probabilistic approach to phenotyping based on Bayesian … Continued

Background – Underutilization of guideline-recommended Implantable Cardioverter Defibrillators (GR-ICD) to reduce sudden cardiac arrest (SCA) has been observed. We deployed electronic health record (EHR) notifications to doctors of patients at risk of SCA that had not yet been referred for a follow up (FU) echocardiogram (ECHO), with the hypothesis that this would result in patients … Continued

Background – We studied race-based (blacks, B vs. whites, W) trends in access to appropriate care for patients with severe aortic stenosis (SAS) and severe mitral regurgitation (SMR) at a tertiary care center from April 2019 to January 2024. Methods – In February 2020, we implemented echocardiogram (echo) – driven EHR notifications nudging clinicians to … Continued