Maximizing Large Language Model Utility in Cardiovascular Care: A Practical Guide.

Large language models (LLMs) have emerged as powerful tools in artificial intelligence, demonstrating remarkable capabilities in natural language processing and generation. In this article, we explore the potential applications of LLMs in enhancing cardiovascular care and research. We discuss how LLMs can be utilized to simplify complex medical information, improve patient-physician communication, and automate tasks such as summarizing medical articles and extracting key information. Additionally, we highlight the role of LLMs in categorizing and analyzing unstructured data, such as medical notes and test results, which could revolutionize data handling and interpretation in cardiovascular research. However, we also emphasize the limitations and challenges associated with LLMs, including potential biases, reasoning opacity, and the need for rigorous validation in medical contexts. This article provides a practical guide for cardiovascular professionals to understand and harness the power of LLMs while navigating their limitations. We conclude by discussing the future directions and implications of LLMs in transforming cardiovascular care and research.

Device-specific quality of life: Results from the ATLAS trial-Avoid Transvenous Leads in Appropriate Subjects.

AIM: Patient reported outcomes (PROs) provide important insights into patients' acceptance of their medical devices. ATLAS, a randomized, multi-center, open-label clinical trial, recently reported fewer perioperative complications in S-ICD compared to TV-ICD patients. This study reports PROs, including device-specific and generic quality of life (QOL) from the ATLAS trial. METHODS AND RESULTS: Device-specific QOL was the primary PRO using the Florida Patient Acceptance Survey (FPAS) at 1-and 6-months post-implantation. Secondary outcomes included generic QOL using the Medical Outcomes Survey (SF-36) pre-implant and 6-months post-implantation. FPAS and SF-36 were analyzed using ANCOVA. Pain measured using a Numeric Rating Scale, at 1-and 6-months, anesthetic, BMI and within/between differences were analyzed using descriptive statistics and mixed-effects linear models (MLM). Of the 503 patients randomized in ATLAS, 404 had complete FPAS data to include in this analysis. Participant characteristics were balanced. There were no significant differences between S-ICD and TV-ICD for FPAS or SF-36, across timepoints. Mean total FPAS scores increased from 73.73 (16.09) to 77.05 (16.13) and 74.43 (15.35) to 78.25 (15.88) for S-ICD and TV-ICD, respectively, (p <0.001). PROs suggested that both devices were associated with good QOL. CONCLUSION: Device-specific and generic QOL were similar between S-ICD and TV-ICD groups up to 6-months post-implantation indicating that regardless of device type, both groups reported good device specific QOL in ATLAS patients. S-ICD patients reported higher pain scores at implant, but pain decreased by 6 months. The findings offer evidence that can be included during shared decision-making. The inclusion of patient partners in ATLAS provided opportunity to measure PROs that were deemed important to patients.

Autopsy of all young sudden death cases is important to increase survival in family members left behind.

Sudden cardiac death (SCD) is an important public health problem worldwide, accounting for an estimated 6 to 20% of total mortality. A significant proportion of SCD is caused by inherited heart disease, especially among the young. An autopsy is crucial to establish a diagnosis of inherited heart disease, allowing for subsequent identification of family members who require cardiac evaluation. Autopsy of cases of unexplained sudden death in the young is recommended by both the European Society of Cardiology and the American Heart Association. Overall autopsy rates, however, have been declining in many countries across the globe and there is a lack of skilled trained pathologists able to carry out full autopsies. Recent studies show that not all cases of sudden death in the young are autopsied, likely due to financial, administrative, and organizational limitations as well as awareness among police, legal authorities, and physicians. Consequently, diagnoses of inherited heart disease are likely missed, along with the opportunity for treatment and prevention among surviving relatives. This article reviews the evidence for the role of autopsy in sudden death, how the cardiologist should interpret the autopsy-record and how this can be integrated and implemented in clinical practice. Finally, we identify areas for future research along with potential for healthcare reform aimed at increasing autopsy awareness and ultimately reducing mortality from SCD.

2024 HRS expert consensus statement on arrhythmias in the athlete: Evaluation, treatment, and return to play.

Youth and adult participation in sports continues to increase, and athletes may be diagnosed with potentially arrhythmogenic cardiac conditions. This international multidisciplinary document is intended to guide electrophysiologists, sports cardiologists, and associated health care team members in the diagnosis, treatment, and management of arrhythmic conditions in the athlete with the goal of facilitating return to sport and avoiding the harm caused by restriction. Expert, disease-specific risk assessment in the context of athlete symptoms and diagnoses is emphasized throughout the document. After appropriate risk assessment, management of arrhythmias geared toward return to play when possible is addressed. Other topics include shared decision-making and emergency action planning. The goal of this document is to provide evidence-based recommendations impacting all areas in the care of athletes with arrhythmic conditions. Areas in need of further study are also discussed.

Applying Artificial Intelligence for Phenotyping of Inherited Arrhythmia Syndromes.

Inherited arrhythmia disorders account for a significant proportion of sudden cardiac death, particularly among young individuals. Recent advances in our understanding of these syndromes have improved patient diagnosis and care, yet certain clinical gaps remain, particularly within case ascertainment, access to genetic testing and risk stratification. Artificial intelligence (AI), specifically machine learning and its subset deep learning, present promising solutions to these challenges. The capacity of AI to process vast amounts of patient data and identify disease patterns differentiates them from traditional methods, which are time and resource intensive. To date, AI models have demonstrated immense potential in condition detection (including asymptomatic/concealed disease) and genotype and phenotype identification, exceeding expert cardiologists in these tasks. Additionally, they have exhibited applicability for general population screening, improving case ascertainment in a set of conditions that are often asymptomatic such as left ventricular dysfunction. Third, models have displayed ability to improve testing protocols, as through model identification of disease and genotype, specific clinical testing (e.g. drug challenges or further diagnostic imaging) can be avoided, reducing health care expenses, speeding diagnosis, and possibly allowing for more incremental or targeted genetic testing approaches. These significant benefits warrant continued investigation of the field, particularly regarding the development and implementation of clinically applicable screening tools. This review summarizes key developments in the field, including studies in Long QT Syndrome, Brugada Syndrome, Hypertrophic Cardiomyopathy, and Arrhythmogenic Cardiomyopathies, and provides direction for effective future AI implementation in clinical practice.

An international multicenter cohort study on implantable cardioverter-defibrillators for the treatment of symptomatic children with catecholaminergic polymorphic ventricular tachycardia.

BACKGROUND: Catecholaminergic polymorphic ventricular tachycardia (CPVT) may cause sudden cardiac death (SCD) despite medical therapy. Therefore, implantable cardioverter-defibrillators (ICDs) are commonly advised. However, there are limited data on the outcomes of ICD use in children. OBJECTIVE: The purpose of this study was to compare the risk of arrhythmic events in pediatric patients with CPVT with and without ICD. METHODS: We compared the risk of SCD in patients with RYR2 (ryanodine receptor 2) variants and phenotype-positive symptomatic patients with CPVT with and without ICD who were younger than 19 years and had no history of sudden cardiac arrest at phenotype diagnosis. The primary outcome was SCD; secondary outcomes were composite end points of SCD, sudden cardiac arrest, or appropriate ICD shocks with or without arrhythmic syncope. RESULTS: The study included 235 patients, 73 with ICD (31.1%) and 162 without ICD (68.9%). Over a median follow-up of 8.0 years (interquartile range 4.3-13.4 years), SCD occurred in 7 patients (3.0%), of whom 4 (57.1%) were noncompliant with medications and none had an ICD. Patients with ICD had a higher risk of both secondary composite outcomes (without syncope: hazard ratio 5.85; 95% confidence interval 3.40-10.09; P < .0001; with syncope: hazard ratio 2.55; 95% confidence interval 1.50-4.34; P = .0005). Thirty-one patients with ICD (42.5%) experienced appropriate shocks, 18 (24.7%) inappropriate shocks, and 21 (28.8%) device-related complications. CONCLUSION: SCD events occurred only in the no ICD group and in those not on optimal medical therapy. Patients with ICD had a high risk of appropriate and inappropriate shocks, which may be reduced with appropriate device programming. Severe ICD complications were common, and risks vs benefits of ICDs need to be considered.

Deep Learning-Augmented ECG Analysis for Screening and Genotype Prediction of Congenital Long QT Syndrome.

Importance: Congenital long QT syndrome (LQTS) is associated with syncope, ventricular arrhythmias, and sudden death. Half of patients with LQTS have a normal or borderline-normal QT interval despite LQTS often being detected by QT prolongation on resting electrocardiography (ECG). Objective: To develop a deep learning-based neural network for identification of LQTS and differentiation of genotypes (LQTS1 and LQTS2) using 12-lead ECG. Design, Setting, and Participants: This diagnostic accuracy study used ECGs from patients with suspected inherited arrhythmia enrolled in the Hearts in Rhythm Organization Registry (HiRO) from August 2012 to December 2021. The internal dataset was derived at 2 sites and an external validation dataset at 4 sites within the HiRO Registry; an additional cross-sectional validation dataset was from the Montreal Heart Institute. The cohort with LQTS included probands and relatives with pathogenic or likely pathogenic variants in KCNQ1 or KCNH2 genes with normal or prolonged corrected QT (QTc) intervals. Exposures: Convolutional neural network (CNN) discrimination between LQTS1, LQTS2, and negative genetic test results. Main Outcomes and Measures: The main outcomes were area under the curve (AUC), F1 scores, and sensitivity for detecting LQTS and differentiating genotypes using a CNN method compared with QTc-based detection. Results: A total of 4521 ECGs from 990 patients (mean [SD] age, 42 [18] years; 589 [59.5%] female) were analyzed. External validation within the national registry (101 patients) demonstrated the CNN's high diagnostic capacity for LQTS detection (AUC, 0.93; 95% CI, 0.89-0.96) and genotype differentiation (AUC, 0.91; 95% CI, 0.86-0.96). This surpassed expert-measured QTc intervals in detecting LQTS (F1 score, 0.84 [95% CI, 0.78-0.90] vs 0.22 [95% CI, 0.13-0.31]; sensitivity, 0.90 [95% CI, 0.86-0.94] vs 0.36 [95% CI, 0.23-0.47]), including in patients with normal or borderline QTc intervals (F1 score, 0.70 [95% CI, 0.40-1.00]; sensitivity, 0.78 [95% CI, 0.53-0.95]). In further validation in a cross-sectional cohort (406 patients) of high-risk patients and genotype-negative controls, the CNN detected LQTS with an AUC of 0.81 (95% CI, 0.80-0.85), which was better than QTc interval-based detection (AUC, 0.74; 95% CI, 0.69-0.78). Conclusions and Relevance: The deep learning model improved detection of congenital LQTS from resting ECGs and allowed for differentiation between the 2 most common genetic subtypes. Broader validation over an unselected general population may support application of this model to patients with suspected LQTS.

Update on Cardiovascular Implantable Electronic Device Infections and Their Prevention, Diagnosis, and Management: A Scientific Statement From the American Heart Association: Endorsed by the International Society for Cardiovascular Infectious Diseases.

The American Heart Association sponsored the first iteration of a scientific statement that addressed all aspects of cardiovascular implantable electronic device infection in 2010. Major advances in the prevention, diagnosis, and management of these infections have occurred since then, necessitating a scientific statement update. An 11-member writing group was identified and included recognized experts in cardiology and infectious diseases, with a career focus on cardiovascular infections. The group initially met in October 2022 to develop a scientific statement that was drafted with front-line clinicians in mind and focused on providing updated clinical information to enhance outcomes of patients with cardiovascular implantable electronic device infection. The current scientific statement highlights recent advances in prevention, diagnosis, and management, and how they may be incorporated in the complex care of patients with cardiovascular implantable electronic device infection.

The Impact of Chronic Disease on the Corrected QT (QTc) Value in Women in a British Columbia First Nations Population.

BACKGROUND: Indigenous women have higher rates of chronic disease than Indigenous men and non-Indigenous women. Long QT syndrome (LQTS) can be inherited or acquired; the latter may occur with chronic disease. A prolonged corrected QT value (QTc) is an independent risk factor for ventricular arrhythmias and sudden death, but few studies have quantified the impact of chronic disease on the QTc. We assessed the association between chronic disease and QTc prolongation in a population of First Nations women previously ascertained to study a high rate of inherited LQTS due to a unique genetic (founder) variant in their community. METHODS: This substudy focusing on women expands on the original research where patients with clinical features of LQTS and their relatives were assessed for genetic variants discovered to affect the QTc. Medical records were retrospectively reviewed and chronic diseases documented. Using multivariate linear regression, adjusting for the effect of genetic variants, age, and QTc-prolonging medications, we evaluated the association between chronic disease and the QTc. RESULTS: In total, 275 women were included. After adjustments, a prolonged QTc was associated with coronary artery disease (26.5 ms, 95% confidence interval [CI] 9.0-44.1 ms; P = 0.003), conduction system disease (26.8 ms, 95% CI 2.2-51.4 ms; P = 0.033), rheumatoid arthritis (28.9 ms, 95% CI 12.7-45.1 ms; P = 0.001), and type 2 diabetes mellitus (17.9 ms, 95% CI 3.6-32.3 ms; P = 0.015). CONCLUSIONS: This quantification of the association between chronic disease and QTc prolongation in an Indigenous cohort provides insight into the nongenetic determinants of QTc prolongation. Corroboration in other populations will provide evidence for generalisability of these results.

Clinical Management of Brugada Syndrome: Commentary From the Experts.

Although there is consensus on the management of patients with Brugada Syndrome with high risk for sudden cardiac arrest, asymptomatic or intermediate-risk patients present clinical management challenges. This document explores the management opinions of experts throughout the world for patients with Brugada Syndrome who do not fit guideline recommendations. Four real-world clinical scenarios were presented with commentary from small expert groups for each case. All authors voted on case-specific questions to evaluate the level of consensus among the entire group in nuanced diagnostic and management decisions relevant to each case. Points of agreement, points of controversy, and gaps in knowledge are highlighted.

Statement from the Asia Summit: Current state of arrhythmia care in Asia.

On May 27, 2022, the Asia Pacific Heart Rhythm Society and the Heart Rhythm Society convened a meeting of leaders from different professional societies of healthcare providers committed to arrhythmia care from the Asia Pacific region. The overriding goals of the meeting were to discuss clinical and health policy issues that face each country for providing care for patients with electrophysiologic issues, share experiences and best practices, and discuss potential future solutions. Participants were asked to address a series of questions in preparation for the meeting. The format of the meeting was a series of individual country reports presented by the leaders from each of the professional societies followed by open discussion. The recorded presentations from the Asia Summit can be accessed at https://www.heartrhythm365.org/URL/asiasummit-22. Three major themes arose from the discussion. First, the major clinical problems faced by different countries vary. Although atrial fibrillation is common throughout the region, the most important issues also include more general issues such as hypertension, rheumatic heart disease, tobacco abuse, and management of potentially life-threatening problems such as sudden cardiac arrest or profound bradycardia. Second, there is significant variability in the access to advanced arrhythmia care throughout the region due to differences in workforce availability, resources, drug availability, and national health policies. Third, collaboration in the area already occurs between individual countries, but no systematic regional method for working together is present.

The 2023 Canadian Cardiovascular Society Clinical Practice Update on Management of the Patient With a Prolonged QT Interval.

A prolonged QT interval on the electrocardiogram is associated with an increased risk of the torsades de pointes form of ventricular arrhythmia resulting in syncope, sudden cardiac arrest or death, or misdiagnosis as a seizure disorder. The cause of QT prolongation can be congenital and inherited as an autosomal dominant variant, or it can be transient and acquired, often because of QT-prolonging drugs or electrolyte abnormalities. Automated measurement of the QT interval can be inaccurate, especially when the baseline electrocardiogram is abnormal, and manual verification is recommended. In this clinical practice update we provide practical tips about measurement of the QT interval, diagnosis, and management of congenital long QT syndrome and acquired prolongation of the QT interval. For congenital long QT syndrome, certain ß-adrenergic-blocking drugs are highly effective, and implantable defibrillators are infrequently required. Many commonly prescribed drugs such as antidepressants and antibiotics can prolong the QT interval, and recommendations are provided on their safe use.

The Prevalence and Characteristics of Arrhythmic Mitral Valve Prolapse in Patients With Unexplained Cardiac Arrest.

BACKGROUND: There is growing evidence that mitral valve prolapse (MVP) is associated with otherwise unexplained cardiac arrest (UCA). However, reports are hindered by the absence of a systematic ascertainment of alternative diagnoses. OBJECTIVES: This study reports the prevalence and characteristics of MVP in a large cohort of patients with UCA. METHODS: Patients were enrolled following an UCA, defined as cardiac arrest with no coronary artery disease, preserved left ventricular ejection fraction, and no apparent explanation on electrocardiogram. A comprehensive evaluation was performed, and patients were diagnosed with idiopathic ventricular fibrillation (IVF) if no cause was found. Echocardiography reports were reviewed for MVP. Patients with MVP were divided into 2 groups: those with IVF (AMVP) and those with an alternative diagnosis (nonarrhythmic MVP). Patient characteristics were then compared. The long-term outcomes of AMVP were reported. RESULTS: Among 571 with an initially UCA, 34 patients had MVP (6%). The prevalence of definite MVP was significantly higher in patients with IVF than those with an alternative diagnosis (24 of 366 [6.6%] vs 5 of 205 [2.4%]; P = 0.03). Bileaflet prolapse was significantly associated with AMVP (18 of 23 [78%] vs 1 of 8 [12.5%]; P = 0.001; OR: 25.2). The proportion of patients with AMVP who received appropriate implantable cardioverter-defibrillator therapies over a median follow-up of 42 months was 21.1% (4 of 19). CONCLUSIONS: MVP is associated with otherwise UCA (IVF), with a prevalence of 6.6%. Bileaflet prolapse appears to be a feature of AMVP, although future studies need to ascertain its independent association. A significant proportion of patients with AMVP received appropriate implantable cardioverter-defibrillator therapies during follow-up.

Rationale and Design of the Randomized Bayesian Multicenter COME-TAVI Trial in Patients With a New Onset Left Bundle Branch Block.

Patients with new-onset left bundle branch block (LBBB) after transcatheter aortic valve implantation (TAVI) are at risk of developing delayed high-degree atrioventricular block. Management of new-onset LBBB post-TAVI remains controversial. In the Comparison of a Clinical Monitoring Strategy Versus Electrophysiology-Guided Algorithmic Approach in Patients With a New LBBB After TAVI (COME-TAVI) trial, consenting patients with new-onset LBBB that persists on day 2 after TAVI, meeting exclusion/inclusion criteria, are randomized to an electrophysiological study (EPS)-guided approach or 30-day electrocardiographic monitoring. In the EPS-guided approach, patients with a His to ventricle (HV) interval ≥ 65 ms undergo permanent pacemaker implantation. Patients randomized to noninvasive monitoring receive a wearable continuous electrocardiographic recording and transmitting device for 30 days. Follow-up will be performed at 3, 6, and 12 months. The primary endpoint is a composite outcome designed to capture net clinical benefit. The endpoint incorporates major consequences of both strategies in patients with new-onset LBBB after TAVI, as follows: (i) sudden cardiac death; (ii) syncope; (iii) atrioventricular conduction disorder requiring a pacemaker (for a class I or IIa indication); and (iv) complications related to the pacemaker or EPS. The trial incorporates a Bayesian design with a noninformative prior, outcome-adaptive randomization (initially 1:1), and 2 prespecified interim analyses once 25% and 50% of the anticipated number of primary endpoints are reached. The trial is event-driven, with an anticipated upper limit of 452 patients required to reach 77 primary outcome events over 12 months of follow-up. In summary, the aim of this Bayesian multicentre randomized trial is to compare 2 management strategies in patients with new-onset LBBB post-TAVI-an EPS-guided approach vs noninvasive 30-day monitoring. Trial registration number: NCT03303612.

Les patients chez qui un bloc de branche gauche (BBG) est récemment apparu à la suite de l'implantation valvulaire aortique par cathéter (IVAC) présentent un risque de bloc auriculoventriculaire de haut degré tardif. La prise en charge d'un BBG récemment apparu après une IVAC demeure controversée. Dans le cadre de l'essai COME-TAVI (Comparison of a ClinicalMonitoring Strategy VersusElectrophysiology-Guided Algorithmic Approach in Patients With a New LBBB AfterTAVI, ou comparaison d'une stratégie de surveillance clinique, par rapport à une approche guidée par étude électrophysiologique et fondée sur un algorithme, chez des patients présentant un BBG d'apparition récente à la suite d'une IVAC), des patients qui présentent un BBG d'apparition récente persistant le 2e jour après une IVAC, qui répondent aux critères d'admissibilité et qui ont donné leur consentement sont répartis aléatoirement pour être suivis à l'aide d'une approche guidée par une étude électrophysiologique (EEP) ou faire l'objet d'une surveillance électrocardiographique d'une durée de 30 jours. Un stimulateur cardiaque est implanté chez les patients du groupe de l'EEP dont l'intervalle HV (temps de conduction dans le tronc du faisceau de His jusqu'aux ventricules) est ≥ 65 ms. Les patients du groupe de surveillance non invasive reçoivent un dispositif portable d'enregistrement et de transmission continue de données électrocardiographiques pour une période de 30 jours. Le suivi sera réalisé aux 3e, 6e et 12e mois. Le critère d'évaluation principal est un paramètre composite conçu afin de saisir le bienfait clinique net. Il comprend les conséquences majeures des deux stratégies chez les patients présentant un BBG d'apparition récente après une IVAC, comme suit : (i) mort subite d'origine cardiaque; (ii) syncope; (iii) trouble de la conduction auriculoventriculaire nécessitant la pose d'un stimulateur cardiaque (pour une indication de classe I ou IIa); et (iv) complications relatives au stimulateur cardiaque ou à l'EEP. L'essai intègre une conception bayésienne avec une répartition aléatoire (dans un rapport initial de 1:1) antérieure non informative adaptée aux résultats et deux analyses intermédiaires définies au préalable lorsque 25 % et 50 % du nombre anticipé des critères d'évaluation principaux seront atteints. L'essai est axé sur les événements, et la limite supérieure anticipée pour atteindre 77 événements relatifs aux critères d'évaluation principaux sur 12 mois de suivi est de 452 patients. En résumé, l'objectif de cet essai bayésien multicentrique à répartition aléatoire est de comparer deux stratégies de prise en charge de patients présentant un BBG d'apparition récente après une IVAC, soit une approche guidée par une EEP, par rapport à une surveillance non invasive de 30 jours. Trial registration number: NCT03303612.

Provocation testing in congenital long QT syndrome: A practical guide.

Congenital long QT syndrome (LQTS) is a hereditary cardiac channelopathy with an estimated prevalence of 1 in 2500. A prolonged resting QT interval corrected for heart rate (QTc interval) remains a key diagnostic component; however, the QTc value may be normal in up to 40% of patients with genotype-positive LQTS and borderline in a further 30%. Provocation of QTc prolongation and T-wave changes may be pivotal to unmasking the diagnosis and useful in predicting genotype. LQTS provocation testing involves assessment of repolarization during and after exercise, in response to changes in heart rate or autonomic tone, with patients with LQTS exhibiting a maladaptive repolarization response. We review the utility and strengths and limitations of 4 forms of provocation testing-stand-up test, exercise stress test, epinephrine challenge, and mental stress test-in diagnosing LQTS and provide some practical guidance for performing provocation testing. Ultimately, exercise testing, when feasible, is the most useful form of provocation testing when considering diagnostic sensitivity and specificity.