Comprehensive Symptom Prediction in Inpatients With Acute Psychiatric Disorders Using Wearable-Based Deep Learning Models: Development and Validation Study

Abstract

Background: Assessing the complex and multifaceted symptoms of patients with acute psychiatric disorders proves to besignificantly challenging for clinicians. Moreover, the staff in acute psychiatric wards face high work intensity and risk of burnout,yet research on the introduction of digital technologies in this field remains limited. The combination of continuous and objectivewearable sensor data acquired from patients with deep learning techniques holds the potential to overcome the limitations oftraditional psychiatric assessments and support clinical decision-making.Objective: This study aimed to develop and validate wearable-based deep learning models to comprehensively predict patientsymptoms across various acute psychiatric wards in South Korea.Methods: Participants diagnosed with schizophrenia and mood disorders were recruited from 4 wards across 3 hospitals andprospectively observed using wrist-worn wearable devices during their admission period. Trained raters conducted periodicclinical assessments using the Brief Psychiatric Rating Scale, Hamilton Anxiety Rating Scale, Montgomery-Asberg DepressionRating Scale, and Young Mania Rating Scale. Wearable devices collected patients'heart rate, accelerometer, and location data.Deep learning models were developed to predict psychiatric symptoms using 2 distinct approaches: single symptoms individually(Single) and multiple symptoms simultaneously via multitask learning (Multi). These models further addressed 2 problems:within-subject relative changes (Deterioration) and between-subject absolute severity (Score). Four configurations were consequentlydeveloped for each scale: Single-Deterioration, Single-Score, Multi-Deterioration, and Multi-Score. Data of participants recruitedbefore May 1, 2024, underwent cross-validation, and the resulting fine-tuned models were then externally validated using datafrom the remaining participants Results: Of the 244 enrolled participants, 191 (78.3%; 3954 person-days) were included in the final analysis after applying theexclusion criteria. The demographic and clinical characteristics of participants, as well as the distribution of sensor data, showedconsiderable variations across wards and hospitals. Data of 139 participants were used for cross-validation, while data of 52participants were used for external validation. The Single-Deterioration and Multi-Deterioration models achieved similar overallaccuracy values of 0.75 in cross-validation and 0.73 in external validation. The Single-Score and Multi-Score models attainedoverall R-2 values of 0.78 and 0.83 in cross-validation and 0.66 and 0.74 in external validation, respectively, with the Multi-Scoremodel demonstrating superior performance.Conclusions: Deep learning models based on wearable sensor data effectively classified symptom deterioration and predictedsymptom severity in participants in acute psychiatric wards. Despite lower computational costs, Multi models demonstratedequivalent or superior performance than Single models, suggesting that multitask learning is a promising approach forcomprehensive symptom prediction. However, significant variations were observed across wards, which presents a key challengefor developing clinical decision support systems in acute psychiatric wards. Future studies may benefit from recurring localvalidation or federated learning to address generalizability issues