Thomas Laurenceau

Aims: The vast majority of sudden cardiac death (SCD) cases occur in the general population with few known risk factors instead of just patients already identified to be at high risk, making the prediction of SCD very difficult. Therefore, a better screening tool should be developed to facilitate early identification. Methods and results: To estimate the risk of SCD, we trained and validated a machine learning model on electronic health record (EHR) data covering 17 172 359 drug prescriptions and 1 639 057 hospital diagnoses up to 5 years for cases and controls. Training was done on data obtained from a cohort of 12 338 SCD cases in Greater Paris and 12 338 controls from 2011 to 2015. We then validated the results on two external cohorts: a temporal cohort in the same area from 2016 and 2020 with 11 620 SCD cases and 11 620 controls and a geographical cohort from the University of Washington (Seattle, USA) with 892 SCD cases and 892 controls from 2013 to 2021. In the 5 years preceding the SCD, cardiovascular diagnoses were prevalent in only a few patients, scarce in many patients, and totally nonexistent for 25.7% of subjects. Our model achieved an area under the curve of 0.81 [95% confidence interval (CI), 0.80–0.82] and 0.66 (95% CI, 0.58–0.73) in the validation and geographical cohort, respectively. The prediction model discriminated SCD from the general population, especially in the highest decile, where the model detected 26% and 33% of all SCD in the Paris and Seattle datasets, respectively. Our prediction model was specific to SCD and was not predictive of myocardial infarction. In addition to classical cardiovascular risk factors, various non-cardiovascular drugs and diagnoses contributed to the prediction model. Conclusion: We propose a prediction model designed to identify individuals at high risk of SCD among the general population. When combined with EHR, this artificial intelligence model has the potential to assist in risk stratification and may help inform the prioritization of preventive strategies, contributing to more targeted use of cardiovascular health resources.

Aims: The rising popularity of endurance races underscores the need to explore the risks of sports-related sudden cardiac arrest (Sr-SCA). Although rare, Sr-SCA is significantly more prevalent in men than in women. The mechanisms underlying these sex differences remain unclear. We aimed to investigate the incidence rates, clinical characteristics, aetiologies, sex differences, and exercise performances among SCA cases during major endurance races in Paris over a 10-year period. Methods and results: We Analysed the Paris Sudden Death Expertise Centre Registry Data (Covering 2011–2024, excluding 2020). This included SCA cases from the half marathon, full marathon and 20 km Parisian race events. We calculated the incidence rates for men and women, with performance analyses focusing on acceleration patterns and the relative risk of SCA in the final kilometre. Among the 1.2 million participants, 17 SCA cases (88% male) were identified, yielding crude incidences of 16.9 and 5.7 per million for men and women, respectively. Sr-SCA was overrepresented in the final kilometres of short races. Men exhibited twice the acceleration rate that women did. Despite extensive medical investigations, no cause was identified in 47.1% of the cases, underscoring the idiopathic nature of Sr-SCA. After hospitalization, 88% (15/17) of the cases survived, all with excellent neurological outcomes [cerebral performance category (CPC) 1], except for one CPC 2. Conclusion: SCA incidences during endurance races are low, with male predominance, high survival rates, and a high proportion of unexplained cases. The male-specific acceleration in the final kilometre may suggest that physiological and behavioural factors influence SCA risk.