Raikhelkar, J.

Abstract Aims Heart failure (HF), a major global health challenge, affects millions worldwide and poses substantial healthcare and economic burdens. It is estimated that a large proportion of those with early systolic dysfunction remain asymptomatic at a stage when guideline-directed medical therapies have been shown to prevent disease progression. To develop an artificial intelligence (AI) model capable of predicting abnormal left ventricular ejection fraction (EF) directly from static, non-gated, non-contrast chest computed tomography (CT) scans as a form of opportunistic screening, Methods and results Using a multi-institutional dataset of 34 058 paired non- contrast CT images and echocardiogram reports from two academic centres, we trained our model of classification for predicting left-ventricle ejection fraction (LVEF) categories: abnormal EF (EF < 50%) vs. normal on 25 948 studies. We validated the model on 8110 paired chest CT and echocardiogram results from a separate institution. The model achieved an area under the receiver operating characteristic (AUROC) curve of 0.786 on the hold-out test set and 0.762 on external validation to detect an abnormal EF (<50%). Beyond strong predictive performance, the AI model surpassed expert radiologists in both accuracy and efficiency and provided interpretable visualizations highlighting imaging features linked to reduced LVEF. Conclusion In this study, we developed and validated an AI model capable of predicting abnormal LVEF directly from static, non-gated, non-contrast chest CT scans, a novel application for an imaging modality typically used for unrelated indications as a form of opportunistic screening. This technology holds significant promise for early detection of systolic HF, reducing the diagnostic gap, and improving outcomes in asymptomatic HF patients.

Abstract BackgroundRe-allocation of resources during the COVID-19 pandemic has resulted in delays in care delivery to patients with cardiovascular disease and cancer. The ability of health care providers to provide optimal care in this setting has not been formally evaluated.ObjectivesTo assess the impact of COVID-19 resource re-allocation on scheduling, testing, elective procedures, telemedicine access, use of new COVID-19 therapies, and providers’ opinions on healthcare policies among oncology and cardiology practitioners.MethodsAn electronic survey was conducted by a cardio-oncology collaborative network through regional and state chapters of the American College of Cardiology , American Society of Clinical Oncology, and the International Cardio-Oncology Society. Descriptive statistics were reported by frequency and proportion for analyses, and stratified categorically by geographic region and specialty.Results1,415 providers (43 countries) participated: 986 cardiologists, 306 oncologists, and 118 trainees/internal medicine. 63% (195/306) of oncologists vs 92% (896/976) of cardiologists reported cancellations of treatments/elective procedures (p=0.01). 46% (442/970) of cardiologists and 25% (76/303) of oncologists modified the scope of their practice (p=<0.001). Academic physicians (74.5%) felt better supplied with personal protective equipment (PPE) vs non-academic (74.5% vs 67.2%; p=0.018). Telemedicine was less common in Europe 81% (74/91), and Latin America 64% (101/158), than the United States, 88% (950/1,097) (p=<0.001). 95% of all groups supported more active leadership from medical professional societies.ConclusionsThese results support initiatives to promote expanded coverage for telemedicine, increased access to PPE, better testing availability and involvement of medical professional societies to help with preparedness for future health care crisis.Appendix: Link to the Survey: https://www.surveymonkey.com/r/C8ZDYNW