Artificial intelligence-enabled prediction of chemotherapy-induced cardiotoxicity from baseline electrocardiograms.

Anthracyclines can cause cancer therapy-related cardiac dysfunction (CTRCD) that adversely affects prognosis. Despite guideline recommendations, only half of the patients undergo surveillance echocardiograms. An AI model detecting reduced left ventricular ejection fraction from 12-lead electrocardiograms (ECG) (AI-EF model) suggests ECG features reflect left ventricular pathophysiology. We hypothesized that AI could predict CTRCD from baseline ECG, leveraging the AI-EF model's insights, and developed the AI-CTRCD model using transfer learning on the AI-EF model. In 1011 anthracycline-treated patients, 8.7% experienced CTRCD. High AI-CTRCD scores indicated elevated CTRCD risk (hazard ratio (HR), 2.66; 95% CI 1.73-4.10; log-rank p < 0.001). This remained consistent after adjusting for risk factors (adjusted HR, 2.57; 95% CI 1.62-4.10; p < 0.001). AI-CTRCD score enhanced prediction beyond known factors (time-dependent AUC for 2 years: 0.78 with AI-CTRCD score vs. 0.74 without; p = 0.005). In conclusion, the AI model robustly stratified CTRCD risk from baseline ECG.

Assessment of patient characteristics influencing the complexity of leadless pacemaker implantation.

Background: The complexity of leadless pacemaker (LP) implantation varies widely. However, the predictive factors determining this difficulty are poorly understood. Objective: The purpose of this study was to evaluate the factors influencing LP implantation difficulty, specifically procedural time during right atrial (RA) and right ventricular (RV) manipulation, based on patient background, cardiac function, and anatomic characteristics. Methods: Analysis included LP implantation cases between 2017 and 2023, excluding the initial 3 implants performed by each operator. The relevance of patient background, cardiac function, and anatomic features on procedural and fluoroscopy times was evaluated. Results: Fifty-four patients (mean age 82.2 ± 10.0 years; 57.4% male) were included in the study. Median procedural and fluoroscopy time was 45.8 minutes and 16.0 minutes, respectively, with an average of 2.0 ± 1.4 device deployments. Univariate analysis showed associations between procedural time and older age, RA and RV diameter, and severity of tricuspid regurgitation (TR). After adjustment for physician and potential contributing factors, RV dilation (midventricular diameter ≥35 mm) and severe TR were identified as independent predictors of prolonged procedural time. Medical history exhibited no association with procedural time. Consistent results were observed in analyses using fluoroscopy time as the outcome. Conclusion: RV dilation and severe TR were associated with prolonged procedural time for LP implantation. Anatomic features obtained from preprocedural echocardiography could provide valuable insights into both the safety and efficiency of LP implantation, thereby enhancing tailored treatment strategies for patients undergoing pacemaker implantation.