Computer vision-inspired contrastive learning for self-supervised anomaly detection in sensor-based remote healthcare monitoring

Sensor-based remote healthcare monitoring is a promising approach for timely detection of adverse health events such as falls or infections in people living with dementia (PLwD) in the home, and reducing preventable hospital admissions. Current anomaly detection approaches in the home setting are hindered by challenges such as noisy, multivariate data, unreliability of event annotations, and heterogeneity across home settings. Inspired by the simplicity and recent applications of contrastive learning in the field of computer vision, we propose a lightweight, self-supervised, negative sample-free approach to detect anomalous events using home activity changes in PLwD. We use the contrastive loss between hourly-aggregated daily sensor data and a lower temporal resolution augmentation, to extract a noise-robust, discriminative representation of daily activity. The daily difference in representation forms the anomaly score, which is compared to the household-personalized threshold, and alerts raised to a clinical monitoring team. Attention weights from the Transformer encoder and Layer-wise Relevance Propagation support explainability. We evaluated the models on accuracy and generalizability, given a target alert rate. Our model outperformed state-of-the-art algorithms in detecting agitation and fall events for three distinct patient cohorts, with 86%(SD=4%) average recall and 92%(SD=4%) generalizability, at a target alert rate of 7%. Our novel application of contrastive frameworks is domain-agnostic and can extract salient patterns from time-series data in other remote monitoring environments.