Machine Learning Classification of Bipolar Disorder Across Mood States Using Natural Language Processing and Speech Analysis: Observational Study
Journal of Medical Internet Research · 2026-11-01 · 28 · e98094-e98094
DOI: 10.2196/98094 ↗At a glance
Beobachtungsstudie in Journal of Medical Internet Research, published online on 2026-11-01. Written by Yusei Yamaguchi and 10 co-authors. Institution: Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Institute of Science Tokyo, 1-5-45 Yushima, Bunkyo-…. Major MEDLINE topics: Bipolar Disorder, Machine Learning, Natural Language Processing, Affect. 54 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Bipolar disorder (BP) affects 1% to 3% of adults worldwide, with diagnostic delays averaging 6 years and high initial misdiagnosis rates. The absence of objective diagnostic measures contributes to clinical uncertainty and suboptimal outcomes.
Objective
This study aimed to (1) develop a machine learning model for BP diagnosis and mood state classification using linguistic and acoustic features, (2) identify features associated with different mood states by comparing each with healthy controls (HC), and (3) explore whether features distinguish between mood states within BP.
Methods
We analyzed data prospectively collected over 7 years from 61 patients with BP and 99 HC across Japan. Speech samples were collected via semistructured interviews over 1 to 5 visits and analyzed cross-sectionally, using aggregated or single-visit observations per participant rather than within-person longitudinal modeling. We extracted 6373 acoustic features (openSMILE 3.0, ComParE 2016) and 211 linguistic features. Least absolute shrinkage and selection operator (LASSO)–regularized logistic regression with nested cross-validation and age- and sex-matched undersampling was used. Mood states were classified as depressive state (DS; Hamilton Depression Rating Scale-17 [HAMD-17] ≥8, Young Mania Rating Scale [YMRS] ≤7), state with manic/mixed symptoms (MS/MX; YMRS ≥8), or euthymic state (ES; HAMD-17 ≤7, YMRS ≤7). Seven classification tasks included BP vs HC, each mood state vs HC, and interstate comparisons. Feature importance was validated via permutation testing ( P
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Institute of Science Tokyo, 1-5-45 Yushima, Bunkyo-ku, Tokyo, Japan.
- Faculty of Informatics, Shizuoka University, Chuo-ku, Hamamatsu, Shizuoka, Japan.
- Clinical and Translational Research Center, Keio University Hospital, Shinjuku-ku, Tokyo, Japan.
- Department of Neuropsychiatry, Keio University School of Medicine, Shinjuku-ku, Tokyo, Japan.
- Center for the Promotion of Interdisciplinary Research in Medicine and Life Science, School of Medicine, Keio University, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan, 81 3-5360-1524.
- Center for Brain Integration Research, Institute of Science Tokyo, Tokyo, Japan.
Cite
APA
Yamaguchi, Y., Kano, Y., Sugihara, G., Takemura, R., Nakamura, H., Shimizu, M., Iizuka, M., Kitazawa, M., Sento, A., Takahashi, H., & Kishimoto, T. (2026). Machine Learning Classification of Bipolar Disorder Across Mood States Using Natural Language Processing and Speech Analysis: Observational Study. Journal of Medical Internet Research, 28, e98094-e98094. https://doi.org/10.2196/98094
Vancouver
Yamaguchi Y, Kano Y, Sugihara G, Takemura R, Nakamura H, Shimizu M, et al. Machine Learning Classification of Bipolar Disorder Across Mood States Using Natural Language Processing and Speech Analysis: Observational Study. Journal of Medical Internet Research. 2026;28:e98094-e98094. doi:10.2196/98094
BibTeX
@article{Yamaguchi2026,
author = {Yamaguchi, Yusei and Kano, Yoshinobu and Sugihara, Genichi and Takemura, Ryo and Nakamura, Hironobu and Shimizu, Masaaki and Iizuka, Mari and Kitazawa, Momoko and Sento, Ayako and Takahashi, Hidehiko and Kishimoto, Taishiro},
title = {Machine Learning Classification of Bipolar Disorder Across Mood States Using Natural Language Processing and Speech Analysis: Observational Study},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e98094--e98094},
doi = {10.2196/98094}
}
EUVIMED