Abstract 347: Artificial Intelligence for Targeted and Personalized Prediction of Sudden Cardiac Death in the General Population: A Machine Learning Study Based on Electronic Health Records

• Published in: Circulation (New York, N.Y.) Vol. 148; no. Suppl_1; p. A347
• Main Authors: Youssfi, Younes, Bougouin, Wulfran, BEGANTON, Frankie, Empana, Jean-Philippe, Chopin, Nicolas, Jouven, Xavier
• Format: Journal Article
• Language: English
• Published: Hagerstown, MD Lippincott Williams & Wilkins 07.11.2023
• Subjects: Sudden cardiac death; Artificial Intelligence; Prediction model
• DOI: 10.1161/circ.148.suppl_1.347
• ISSN: 0009-7322

Background: Identification of subjects from the general population with an increased risk of Sudden Cardiac Death (SCD) remains highly challenging, particularly at an individual level. Methods: Every case of SCD + 18 y.o. that occurred since 2011 in Paris and its inner suburbs was prospectively included in the Paris Sudden Death Expertise Center (SDEC) registry (6.7M inhabitants). SCD cases were matched by age, sex, and residence area with a control group (70000) sampled from the general population. All data from the French National Health Insurance database (SNDS) were collected: prescribed drugs, examinations and diagnoses that occurred up to 10 y. before the event, including cardiovascular and non-cardiovascular variables (10000). We provide a detailed explanation of the prediction at the individual level. For each subject, we computed the Shapley scores from the supervised learning model (CatBoost) to evaluate the contribution of variables to its predicted risk. The model used was derived from 12338 SCD cases and matched controls cohort (2011-15) and validated on 11620 cases cohort (2016-20). Results: A total of 23958 equations have been built with personalized variables and coefficients, achieving an AUC of 0.80 in the derivation cohort (with a PPV=77%, sensitivity=68%). One example is shown below, with an individual predicted risk of SCD at 3 months (89.3%), and the most important factors that increase (red) or decrease (blue) the risk of SCD. Conclusions: For the first time, we provide a personalized prediction model of SCD, which explains the predicted risk at the individual level. These findings offer a new step toward personalized prevention and global public health interventions