Portal de Periódicos da CAPES

AI-based heart monitoring: the FIFPRO player pilot study

2024; Oxford University Press; Volume: 26; Issue: Supplement_1 Linguagem: Inglês

10.1093/europace/euae102.543

1532-2092

Daniel Corrochano-Diego, José María Lillo-Castellano, Vincent Gouttebarge, Patricia Gómez-Valiente, David Jiménez-Virumbrales, Manuel Marina‐Breysse, François De Guio,

Artificial Intelligence in Healthcare and Education

Abstract Background The implementation of remote global heart screening and monitoring services in professional players is essential as it allows: (1) efficient and rapid identification of cardiac abnormalities ensuring their safety and health; (2) standardizing the quality of medical heart checkups in low-resource regions to promote health equity; (3) prioritizing diversity in data collection to aid in the research and prevention of sudden cardiac death in sports. Purpose To demonstrate the feasibility of a global standardized heart screening program for professional footballers by leveraging an artificial intelligence platform to efficiently identify cardiac patterns from Holter’s records. In this study, we presented the most prevalent cardiac patterns, the patterns that prompted further assessment by the cardiologist, and an example of a typical research question exploring the effect of age on the prevalence of cardiac patterns. Methods The pilot study included 100 players from 9 different countries: Australia, Botswana, Bulgaria, Ghana, Greece, Indonesia, Panama, Spain and the UK. Holter data (Bittium Faros 180) were acquired in real-life monitoring from 24h to 48h including training sessions. Electrocardiograms were analyzed through an AI platform with a deep learning-based methodology to detect over 20 cardiac patterns. Medical team reviewed labels of detected cardiac patterns to validate and further train the AI algorithm. Thereafter cardiologists reviewed the cardiac patterns to determine whether further cardiac assessment was required. Results 145 sessions were recorded, with 100 players having one session and 45 players having two sessions. The mean age was 27.5 years (minimum 15, maximum 41), with 31 female players. The median duration of the Holter session was 25.1 hours. Table 1 presents the most frequently detected cardiac patterns: low density premature atrial complex, mild sinus bradycardia and low density premature ventricular complex in over 50% of the players. 18 players were identified with abnormalities requiring further study. 14 presented altered cardiac patterns (6 with negative T-waves, 5 with intraventricular conduction delay, 2 with QRS low voltage and 1 with P wave enlargement) and 3 presented premature ventricular complexes during exercise or high density. 1 was excluded because of inadequate clinical information. Regarding the effect of age, players with mild sinus bradycardia, premature ventricular complex, pause (2-3 seconds) or 2-degree atrioventricular block were found to be significantly older than players without those patterns (Figure 1). Conclusion This is the first global AI-based platform to obtain standardized heart screening program in professional athletes remotely. This study has been validated using diverse data from groups on 5 continents. This approach is beneficial to promote health equity in screening and monitoring of possible cardiomyopathies and channelopathies in order to prevent sudden cardiac death.Table 1Figure 1