EUVIMEDEUVIMED entdecken
Crossref

Speech-based differentiation of unipolar and bipolar depression across scripted reading and interview questions

Rongrong Zhong, Yuezhou Zhang, Xiaohui Wu, Lvchun Cui, Jiansen Lin, Xue Lv, Jiayue Chen, Shen Tse Chen, Yue Yu, Amos Folarin, Richard Dobson, Jun Chen und 1 weitere

Journal of Affective Disorders · 2027-01 · 417 · 122675

DOI: 10.1016/j.jad.2026.122675 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2027-01. Verfasst von Rongrong Zhong und 12 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Research Center & Division of Mood Disorders, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, Chi…. Hauptthemen laut MEDLINE: Bipolar Disorder, Reading, Interview, Psychological, Speech. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Differentiating bipolar depression (BPD) from unipolar depression (UPD) remains clinically challenging. We examined whether acoustic and linguistic speech features could support this distinction and whether their informativeness varied across scripted reading and interview questions. METHODS: This study included 109 healthy controls (HCs), 52 patients with UPD, and 53 patients with BPD experiencing depressive episodes. Participants completed a scripted reading task and an interview-based speech task comprising 16 questions. Acoustic features were extracted from all audio recordings, and linguistic features were derived from interview transcripts. Group differences were examined using robust analysis of covariance with global false discovery rate correction. Two-level stacking models with fold-wise sex adjustment of acoustic features evaluated classification performance and importance of speech features and interview-based speech elicitation prompts. RESULTS: Multiple acoustic and linguistic features showed significant group differences in interview responses, whereas no acoustic features differed significantly during scripted reading. The best-performing models achieved F1 scores of 0.6655 for three-class classification (HC, UPD and BPD) and 0.6430 for binary classification (UPD and BPD). Within interview-based speech, statistical and machine learning analyses identified Average Pause Duration, Phonation Ratio, and quantity-related expressions as particularly informative features. Two interview questions about (hypo-)manic experiences contributed most to differentiating BPD from UPD. CONCLUSIONS: Acoustic and linguistic speech features may help differentiate BPD from UPD during depressive episodes, with their informativeness varying across speech tasks and interview questions. Our findings suggest that targeted interview-based speech assessment may have potential as a non-invasive adjunct to conventional clinical evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bipolar DisorderReadingInterview, PsychologicalSpeechDepressive DisorderMajor Depressive DisorderHumansFemaleMaleAdultDiagnosis, DifferentialMiddle AgedSpeech AcousticsMachine Learning

Stichwörter der Autor:innen

Bipolar depressionDiagnosisMachine learningSpeechUnipolar depression

Autor:innen und Institutionen

  • Clinical Research Center & Division of Mood Disorders, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Department of Biostatistics & Health Informatics, Institute of Psy…
  • Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, United Kingdom.
  • Clinical Research Center & Division of Mood Disorders, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Clinical Research Center & Division of Mood Disorders, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China; College of Psychiatry and Clinical Psychology, Shanghai Jiao Tong…
  • Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, United Kingdom; Institute of Health Informatics, University College London, London, United K…
  • Clinical Research Center & Division of Mood Disorders, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China. Electronic address: doctorcj2010@gmail.com.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhong, R., Zhang, Y., Wu, X., Cui, L., Lin, J., Lv, X., Chen, J., Chen, S. T., Yu, Y., Folarin, A., Dobson, R., Chen, J., & Fang, Y. (2027). Speech-based differentiation of unipolar and bipolar depression across scripted reading and interview questions. Journal of Affective Disorders, 417, 122675. https://doi.org/10.1016/j.jad.2026.122675

Vancouver

Zhong R, Zhang Y, Wu X, Cui L, Lin J, Lv X, et al. Speech-based differentiation of unipolar and bipolar depression across scripted reading and interview questions. Journal of Affective Disorders. 2027;417:122675. doi:10.1016/j.jad.2026.122675

BibTeX
@article{Zhong2027,
  author = {Zhong, Rongrong and Zhang, Yuezhou and Wu, Xiaohui and Cui, Lvchun and Lin, Jiansen and Lv, Xue and Chen, Jiayue and Chen, Shen Tse and Yu, Yue and Folarin, Amos and Dobson, Richard and Chen, Jun and Fang, Yiru},
  title = {Speech-based differentiation of unipolar and bipolar depression across scripted reading and interview questions},
  journal = {Journal of Affective Disorders},
  year = {2027},
  volume = {417},
  pages = {122675},
  doi = {10.1016/j.jad.2026.122675}
}
Kostenlos starten →