Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The authors evaluated the minimum continuous wearable monitoring duration required to classify insomnia severity by benchmarking activity count and circadian-derived features across 2,305 participants in the longitudinal AURORA study. Establishing these temporal windows is critical for determining when passive digital phenotyping data becomes clinically actionable versus when it introduces observational noise. Across multiple follow-up intervals, predictive performance plateaued at approximately eight weeks of data collection—achieving a peak AUROC of 0.693 for identifying non-clinical insomnia—with temporal circadian patterns matching or outperforming raw activity volumes.
Digital phenotyping algorithms hit a strict data-collection floor for sleep pathology: wearable models require at least eight continuous weeks of sensor tracking before circadian features provide clinically meaningful insomnia discrimination.
Background: Wearable devices provide continuous, objective measures of daily activity and offer promise for assessing sleep disorders. However, the minimum monitoring duration needed to differentiate insomnia severity remains unclear. We investigated when wearable-derived behavioral features become informative for distinguishing Insomnia Severity Index (ISI) categories and examined the contribution of Activity Count (AC) and circadian-derived features. Methods: We analyzed wearable data from 2,305 participants in the Advancing Understanding of Recovery after Trauma (AURORA) study. Separate binary classifiers were developed for four ISI categories across six follow-up periods using AC and circadian-derived feature sets. Performance was evaluated using accuracy, F1-score, precision, recall, and AUROC. Results: Classification improved with longer monitoring. Across ISI categories, approximately eight weeks was the earliest time point at which wearable-derived features consistently achieved informative discrimination, with modest improvements thereafter. Participants without clinically significant insomnia were easiest to identify, reaching an AUROC of 0.693. Circadian-derived features performed comparably to, and in several cases better than, AC features, suggesting that the temporal organization of daily activity provides information beyond overall activity volume. Conclusions: Approximately eight weeks of longitudinal wearable monitoring may represent a practical minimum for differentiating ISI-defined insomnia categories. Longer monitoring provided only incremental improvements. Circadian behavioral features show promise as digital biomarkers for objective insomnia assessment.