%0 Journal Article
%T Multimodal Digital Phenotyping for Bipolar Disorder: Robust Mood-State Classification and Early Relapse Risk Monitoring
%A Rocco de Filippis
%A Abdullah Al Foysal
%J Open Access Library Journal
%V 12
%N 12
%P 1-19
%@ 2333-9721
%D 2025
%I Open Access Library
%R 10.4236/oalib.1114600
%X Bipolar disorder (BD) is characterized by recurrent transitions between manic, depressive, and euthymic states, yet continuous symptom monitoring remains a major clinical challenge. We present a multimodal digital phenotyping framework for fine-grained BD mood-state classification and relapse-risk monitoring using naturalistic facial video, voice audio, and phone-usage metadata. The proposed architecture employs modality-specific encoders with late-fusion logits to learn disentangled representations of affective, prosodic, and behavioural signals. Across a moderately imbalanced but clinically representative dataset, the model achieves near-perfect validation performance, including a 100% final accuracy and a strictly diagonal confusion matrix, indicating complete separation between euthymic, depressive, and manic classes. t-SNE visualizations show well-defined clusters at the embedding level for each individual modality and even tighter grouping in the fused representation, suggesting robust cross-modal alignment. An ablation analysis confirms that facial affect provides the strongest single-modality predictive signal (98.8% accuracy), while combining voice and facial features yields the highest bi-modal performance (99.0%), closely followed by the full multimodal system (98.5%). We further demonstrate a relapse-risk layer that transforms predicted mood probabilities into a continuous risk score, triggering alerts when a calibrated clinical threshold is crossed. Although the results are strong, we critically examine the possibility of data leakage and overfitting underlying ¡°perfect¡± validation learning curves. To ensure realistic clinical utility, we outline subject-wise evaluation, temporal blocking, calibration strategies, and privacy-preserving deployment considerations. Class proportions (euthymic ¡Ö 1000, depressive ¡Ö 534, manic ¡Ö 468) reflect real-world prevalence patterns rather than strict balance. Overall, our findings highlight the promise of low-burden multi-modal monitoring for BD while emphasizing the methodological rigor and safeguards required for real-world translation.<br />
%K Bipolar Disorder
%K Digital Phenotyping
%K Multimodal Learning
%K Face/Voice/Phone
%K Mood Classification
%K Relapse Prediction
%K T-SNE
%K Ablation
%U http://www.oalib.com/paper/6880095