Abstract 14337: Identification of New Clinical Phenotypes of Sudden Cardiac Death Using Artificial Intelligence

Abstract

Introduction: Current classifications of Sudden Cardiac Death (SCD) are based on cardiovascular (CV) conditions and risk factors, and frequently fail to explain numerous SCD cases. Hypothesis: a data-driven machine learning approach could identify new clinical phenotypes of SCD in the general population, using a wide range of CV and non-CV variables. Methods: All case of SCD over 18y that occurred between 2011-15 in Paris and suburbs were included in the Paris Sudden Death Expertise Center. Data from the French National Health Insurance database that occurred up to 10y before SCD were collected (drugs, examinations,diagnosis). We performed a non-supervised statistical approach to identify relevant clinical phenotypes of SCD, using clustering and dimension reduction methods. A validation was performed between 2016-20. Results: 12,651 SCD subjects were included. Mean age was 68y, and 61% were men. The clustering analysis identified 8 distinct clusters of SCD, with homogeneous characteristics. 3 clusters were already well known: a group mainly composed of aged women (3,307, 38% men, 81y), one with mainly CV diseases (3,638, 74% men, 74y) and one of young subjects with very few comorbidities (2,645, 65%men, 54 y). 4 non-CV clusters were identified: a group with psychiatric and/or neurologic disorders (862), a group with chronic or acute pulmonary diseases (688) and a group with malignant neoplasms of different sites and related drugs (518), and a group with kidney diseases (279). The last group was composed of subjects with characteristics related to social deprivation (alcohol related disorder, hepatitis, HIV, etc) (252).The same 8 clusters were identified in the validation cohort (11,485). Conclusions: By extending far beyond CV pathology, our approach provides for the first time a global picture of SCD, revealing the involvement of extra CV medical fields that might eventually lead to discover new pathways and help identifying high risk subjects.