Uncertainty-Driven Anomaly Detection for Psychotic Relapse Using Smartwatches: Forecasting and Multi-Task Learning Fusion
For clinicians monitoring schizophrenia patients, this work provides a more accurate digital phenotyping approach for early relapse detection, though the improvement is incremental.
The paper develops two smartwatch-based frameworks for daily psychotic relapse detection, one using cardiac forecasting and the other fusing sleep, motion, and cardiac signals via multi-task learning, and combines them via late fusion. The fused model achieves an 8% relative improvement over the competition-winning baseline on the e-Prevention Grand Challenge dataset.
Digital phenotyping enables continuous passive monitoring of behavior and physiology, offering a promising paradigm for early detection of psychotic relapse. In this work, we develop and systematically study two smartwatch-based frameworks for daily relapse detection. The first forecasts cardiac dynamics and flags deviations between predicted and observed features as indicators of abnormality. The second adopts a multi-task formulation that fuses sleep with motion and cardiac-derived signals, learning time-aware embeddings and predicting measurement timing. Both pipelines use Transformer encoders and output a daily anomaly score, derived from predictive uncertainty estimated via an ensemble of multilayer perceptrons to improve robustness to real-world wearable variability. While each framework independently demonstrates strong predictive power, we show that they capture complementary physiological signatures. Consequently, we propose a late-fusion strategy that synergistically combines the anomaly signals from both architectures into a unified decision score. We benchmark our methodology on the 2nd e-Prevention Grand Challenge dataset, where our fused model achieves a 8% relative improvement over the competition-winning baseline. Our results, supported by extensive ablation studies, suggest that the integration of diverse digital phenotypes, cardiac, motion, and sleep, is essential for the high-fidelity detection of psychotic relapse in real-world settings.