Abstract Introduction Patients at high risk of sudden cardiac death are treated with an implantable cardioverter-defibrillator (ICD). Patterns in physical behaviour may be prognostic for clinical deterioration. Deep embedded clustering (DEC) employs deep neural networks to learn compact and meaningful representations from high-dimensional data, on which an unsupervised clustering then operates. Purpose The objectives of this study were to use DEC to identify and describe behavioural profiles in a prospective ICD cohort and assess their risk of clinical outcomes. Methods Data from the multicenter, prospective SafeHeart study conducted at our 2 centers, was used. Patients received an implantable cardioverter defibrillator (ICD) between May 2021 and September 2022, who then wore wearable devices during 6 months that capture physical behaviour. Latent representations were extracted from the time-series behavioural data using a variational autoencoder, and used as input to an unsupervised machine learning algorithm (Figure 1). Kaplan-Meier survival curves were used to visualise the annual risk of appropriate ICD-therapy, and the composite of all ICD-therapy and death. Results A total of 272 patients (mean age of 63.1 ±10.2 years, 81% male) were eligible, with a total of 37478 days of behavioural data (138 ±47 days per patient). DEC identified five distinct behavioural profiles: Cluster A (n=70) had high activity levels, mainly at light-to-moderate intensity. Cluster B (n=51) showed above-average sleep efficiency. Cluster C (n=63) exhibited a high-intensity activity profile. Cluster D (n=42) had frequent waking episodes and poor sleep. Cluster E (n=46) had very low physical activity levels and an impaired sleep architecture. Significantly differences were observed between clusters A-E in ICD-therapy and mortality (log-rank p-value 0.04) (Figure 2). Clusters B and D exhibited a threefold decrease in the annual risk of appropriate ICD therapy compared to cluster E. Conclusion DEC reveals distinct behavioural profiles in a prospective ICD cohort, with their inherent risk on outcomes. Wearable accelerometer devices enable behavioural monitoring that may provide opportunities for improved personalised risk prediction in a notoriously heterogeneous high-risk patient population.Deep embedded clustering of behaviourEvent rates stratified for clusters

Deep embedded clustering of physical behaviour in patients with an implanted cardioverter-defibrillator identifies high and low risk profiles