Publications by authors named "Michael A Rosenberg"
Article Synopsis
- Drug-induced QT prolongation (diLQTS) is a significant risk with various medications, and genetic factors like polygenic risk scores (PGS) may help predict this risk.
- Researchers analyzed data from 2,500 subjects using a known QT-prolonging drug and found that higher QT PGS was significantly associated with diLQTS risk, even when accounting for other clinical factors.
- The study concludes that while QT PGS can independently predict diLQTS risk, it does not modify the effects of existing clinical risk factors, indicating further research is needed for practical clinical applications.
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).
Article Synopsis
- The study examines how often clinicians take action to monitor or reduce risks associated with medications that can prolong QTc intervals in outpatient settings.
- It involved reviewing medical records of nearly 400 prescriptions and assessing whether clinicians addressed modifiable risk factors for QTc-prolongation within 48 hours of prescribing these medications.
- Results showed that although a significant portion of patients had potential laboratory-related risk factors, only a small percentage of those risks were acknowledged and acted upon by clinicians.
Article Synopsis
- * The review covers the clinical diagnosis of atrial fibrillation and stroke risk assessment, along with various clinical risk scoring methods to evaluate individual patient risk.
- * Additionally, it explores how genetic studies can identify high-risk individuals through polygenic risk scores and discusses the potential use of artificial intelligence in predicting atrial fibrillation development.
Article Synopsis
- First-degree atrioventricular (AV) block is often found in athletes during ECG screenings, especially when the PR interval exceeds 200 ms.
- Profound first-degree AV block (PR interval >400 ms) and Mobitz type I (Wenckebach) second-degree AV block are rarer and may need individual assessments, especially if there's concern about heart structure.
- In one case, an asymptomatic athlete with profound first-degree AV block and Mobitz type I was cleared for sports after normal echocardiograms, highlighting the importance for physicians to recognize when further evaluation is necessary.
Article Synopsis
- The study aimed to create an easy-to-use scoring system to assess the risk of needing a permanent pacemaker (PPM) after transcatheter aortic valve replacement (TAVR).
- Atrial block, a common issue related to TAVR, prompted the need for a more clinically applicable risk prediction model, as existing models weren't suitable for pre-procedure planning.
- The resulting PRIME score was developed using five key pre-procedure variables and demonstrated high accuracy in predicting PPM needs in both training and validation groups.
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 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.
View Article and Find Full Text PDFArticle Synopsis
- A study was conducted to identify challenges clinicians face when prescribing medications for heart failure with reduced ejection fraction (HFrEF), particularly in light of recent advancements in healthcare.
- Interviews with 33 clinicians revealed four levels of challenges: clinician-focused misconceptions, patient-clinician communication issues, conflicts between different types of healthcare providers, and systemic policy barriers.
- The findings highlight ongoing and new challenges—such as differing views between specialists and generalists, hesitance to use newer drugs due to safety concerns, and inadequate access to patient data—that need to be addressed to improve HFrEF treatment.
Article Synopsis
- The study analyzed data from over 52,000 patients diagnosed with atrial fibrillation between 2010 and 2020 to determine the best rhythm-management strategies for individuals.
- Researchers utilized a form of artificial intelligence called tabular Q-learning to predict optimal treatments based on outcomes such as mortality and treatment sustainability, while also clustering patients into distinct groups for better analysis.
- Findings revealed that rhythm-control strategies led to better outcomes than rate-control strategies, particularly when the treatment matched the Q-learning recommendations, indicating a promising method for improving clinical decision-making in atrial fibrillation management.
Article Synopsis
- The study focuses on drug-induced long-QT syndrome (diLQTS) in hospitalized patients, evaluating the use of machine learning to identify those at risk for better monitoring.
- Researchers aimed to balance the accuracy of complex deep learning models with the interpretability of simpler cluster analysis models to assess diLQTS risk among 35,639 patients treated with specific medications.
- Results indicated that certain medications, especially class III antiarrhythmics, heightened risk, with specific drugs like propofol and ondansetron showing varied risk levels based on patient health and conditions.
Article Synopsis
- Numerous studies on atrial fibrillation (AF) lack a one-size-fits-all strategy for rhythm management, often requiring a trial-and-error approach that can benefit from a clinical decision support system (CDSS) like QRhythm, which leverages AI to optimize recommendations based on patient-specific factors.
- QRhythm employs a two-stage machine learning model that first mimics expert clinician decisions and then refines its recommendations using reinforcement learning for better patient outcomes, such as reducing symptoms and hospitalizations.
- In a survey of 33 healthcare providers evaluating QRhythm, safety was rated the highest importance (4.7/5), followed by clinical integrity, highlighting the need for reliable and sensible automated guidance in managing AF.
Article Synopsis
- Unipolar electrograms (UniEGMs) are often used for localizing focal arrhythmias, but their effectiveness in ablation of deeper premature ventricular contractions (PVCs) is questionable.
- This study compared bipolar electrograms (BiEGMs) to UniEGMs in guiding the successful ablation of PVCs originating from both the right ventricular outflow tract (RVOT) and intramural outflow tracts.
- Results showed that BiEGMs provided a better identification of activation times, particularly for intramural PVCs, highlighting their superior role in successful ablation compared to UniEGMs.
Background: Management of chronic recurrent medical conditions (CRMCs), such as migraine headaches, chronic pain, and anxiety/depression, remains a major challenge for modern providers. Our team has developed an edge-based, semiautomated mobile health (mHealth) technology called iMTracker that employs the N-of-1 trial approach to allow self-management of CRMCs.
Objective: This study examines the patterns of adoption, identifies CRMCs that users selected for self-application, and explores barriers to use of the iMTracker app.
Objective: Nonvasodilatory beta blockers are associated with inferior cardiovascular event reduction compared with other antihypertensive classes, and there is uncertainty about first-line use of beta blockers for hypertension in guidelines. The third generation vasodilatory beta blocker nebivolol has unique beneficial effects on central and peripheral vasculature. Our objective was to compare longitudinal cardiovascular outcomes of hypertensive patients taking nebivolol with those taking the nonvasodilatory beta blockers metoprolol and atenolol.
View Article and Find Full Text PDFBackground: The identification of an appropriate rhythm management strategy for patients diagnosed with atrial fibrillation (AF) remains a major challenge for providers. Although clinical trials have identified subgroups of patients in whom a rate- or rhythm-control strategy might be indicated to improve outcomes, the wide range of presentations and risk factors among patients presenting with AF makes such approaches challenging. The strength of electronic health records is the ability to build in logic to guide management decisions, such that the system can automatically identify patients in whom a rhythm-control strategy is more likely and can promote efficient referrals to specialists.
View Article and Find Full Text PDFIncreased incidence of cavotricuspid isthmus atrial flutter following slow pathway ablation.
J Interv Card Electrophysiol
April 2022
Article Synopsis
- * A retrospective analysis of 544 patients’ ablation procedures over a decade revealed that patients undergoing atrioventricular nodal reentry tachycardia ablation had a significantly higher incidence of CTI-dependent flutter (4.97%) than those receiving other ablation types (0%).
- * The findings suggest a strong association between atrioventricular nodal reentry tachycardia ablation and the development of atrial
Article Synopsis
- Clinical decision support (CDS) alerts in electronic health records aim to reduce drug-induced long QT syndrome (diLQTS) risk by notifying providers when high-risk medications are prescribed.
- During a study period, these alerts were triggered 15,002 times; however, over half of the providers (51%) chose to override the alerts and prescribe the medications anyway.
- Factors like patient age and the availability of alternative medications influenced provider responses to the alerts, highlighting the need to balance adherence to CDS alerts with real patient outcomes like mortality rates.
Article Synopsis
- This study explores the use of machine learning algorithms to predict the risk of drug-induced QT prolongation using electronic health record (EHR) data, a condition that can lead to serious health issues.
- Researchers analyzed data from 35,639 inpatients who took medications that prolong the QT interval, finding that a deep neural network method showed the best accuracy in identifying patients at risk.
- The deep neural network achieved an F1 score of 0.404 and an AUC of 0.71, indicating it can reasonably predict who is most susceptible, highlighting the need for further validation in different healthcare settings.
Article Synopsis
- The concept of frailty helps explain why older adults have different disease risks, particularly related to cardiovascular health, but practical assessments of frailty are still limited.
- This pilot study looks at whether routine follow-ups of patients with cardiac implantable electronic devices (CIEDs) can be used to assess frailty effectively.
- Results indicated no significant difference in average daily activity between frail and non-frail patients, but those deemed frail showed greater variability in daily activity, suggesting this variance might be a more meaningful indicator of frailty or cognitive issues.
Article Synopsis
- The study compares deep learning and machine learning models to logistic regression for predicting myocardial infarction (MI) using electronic health record (EHR) data from nearly 2.3 million patients.
- Researchers conducted a large-scale case-control study to evaluate different sampling techniques and algorithms, including regularized logistic regression and deep neural networks, focusing on a subset of 800 relevant procedures and conditions.
- Results showed that while deep neural networks had slightly better classification performance, the improvement was minimal and traditional methods using established risk factors still performed comparably, indicating limited advantages of advanced techniques in this context.
Background: Remote monitoring (RM) of cardiac implantable electronic devices (CIEDs) is standard of care. However, it is underutilized. In July 2012, our institution began providing cell phone adapters (CPAs) to patients free of charge following CIED implantation to improve remote transmission (RT) adherence.
View Article and Find Full Text PDFImportance: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, and its early detection could lead to significant improvements in outcomes through the appropriate prescription of anticoagulation medication. Although a variety of methods exist for screening for AF, a targeted approach, which requires an efficient method for identifying patients at risk, would be preferred.
Objective: To examine machine learning approaches applied to electronic health record data that have been harmonized to the Observational Medical Outcomes Partnership Common Data Model for identifying risk of AF.