EUVIMEDEUVIMED entdecken
ValidierungsstudieFall-Kontroll-StudieOpen Access

A Smartphone-Based Acoustic Machine Learning Pipeline for Detecting Suicidal Ideation: Case-Control Model Development and Validation Study

Min Lyu, Lixin Tan, Jun Xiao, Heqing Huang, Fangjian Liu, Jiahui Qi, Tian Huang, Jinyu Lei, Zhihui Zhao, Tianxiang Jiang, Zhu Liu, Xueqian Wang und 2 weitere

JMIR Formative Research · 15.09.2026 · 10 · e92646-e92646

DOI: 10.2196/92646 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift JMIR Formative Research, online erschienen am 15.09.2026. Verfasst von Min Lyu und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Psychology, Army Medical University, No. 30 Gaotanyan Main Street, Shapingba District, Chongqing, 400038, China, +86-1662346085…. Hauptthemen laut MEDLINE: Machine Learning, Suicidal Ideation, Smartphone, Acoustics. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Suicidal ideation (SI) among university students is a growing public health concern. Self-report screening can be limited by concealment and delayed disclosure. We evaluated a leakage-resistant, proof-of-concept pipeline to detect SI from standardized smartphone-recorded speech.

Objective

This study aimed to extract acoustic markers from brief smartphone-based reading tasks and develop machine learning models for suicide risk prediction in university students, enabling low-cost, scalable early screening to support campus mental health services.

Methods

Questionnaire data and speech recordings were collected via a WeChat mini program. After screening and clinical confirmation, 96 participants (n=48, 50% with SI; n=48, 50% controls) were included. Age and sex were evaluated as potential confounders. Each participant read 16 standardized sentences. Acoustic features were extracted using openSMILE (version 3.0.2), yielding a 570D feature vector per utterance. To prevent leakage from multiple recordings per speaker, we used participant-level 5-fold cross-validation, assigning all recordings from each participant to a single fold. Seven machine learning algorithms were evaluated using area under the curve (AUC), accuracy, and F 1 -score.

Results

Acoustic-based models discriminated participants with SI from control participants. The SI group was significantly older than the control group ( P =.001). Random forest achieved an AUC of 0.813 (accuracy=0.748), and naive Bayes achieved an AUC of 0.806 (accuracy=0.757). Feature families related to pitch, mel-frequency cepstral coefficients, and harmonicity contributed to model performance.

Conclusions

Standardized read speech captured via smartphones shows preliminary feasibility for SI discrimination under a leakage-aware evaluation design. External validation and testing with more naturalistic speech are warranted.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningSuicidal IdeationSmartphoneAcousticsHumansFemaleMaleCase-Control StudiesAdultStudentsSurveys and QuestionnairesYoung AdultUniversities

Stichwörter der Autor:innen

AIartificial intelligencecross-validationmachine learningspeech acousticssuicidal ideationuniversity students

Autor:innen und Institutionen

  • Department of Medical Psychology, Army Medical University, No. 30 Gaotanyan Main Street, Shapingba District, Chongqing, 400038, China, +86-16623460852.
  • Mental Health Education and Counseling Center, Chongqing University, Chongqing, China.
  • Department of Cardiovascular Medicine, Chongqing Emergency Medical Center/The Fourth People's Hospital of Chongqing, Chongqing, China.
  • Department of Medical Psychology, First Affiliated Hospital of Army Medical University, Chongqing, China.
  • Faculty of Health and Wellness, City University of Macau, Macau, China.
  • College of Computer Science, Chongqing University, Chongqing, China.

Zitieren

APA

Lyu, M., Tan, L., Xiao, J., Huang, H., Liu, F., Qi, J., Huang, T., Lei, J., Zhao, Z., Jiang, T., Liu, Z., Wang, X., Zhong, J., & Feng, Z. (2026). A Smartphone-Based Acoustic Machine Learning Pipeline for Detecting Suicidal Ideation: Case-Control Model Development and Validation Study. JMIR Formative Research, 10, e92646-e92646. https://doi.org/10.2196/92646

Vancouver

Lyu M, Tan L, Xiao J, Huang H, Liu F, Qi J, et al. A Smartphone-Based Acoustic Machine Learning Pipeline for Detecting Suicidal Ideation: Case-Control Model Development and Validation Study. JMIR Formative Research. 2026;10:e92646-e92646. doi:10.2196/92646

BibTeX
@article{Lyu2026,
  author = {Lyu, Min and Tan, Lixin and Xiao, Jun and Huang, Heqing and Liu, Fangjian and Qi, Jiahui and Huang, Tian and Lei, Jinyu and Zhao, Zhihui and Jiang, Tianxiang and Liu, Zhu and Wang, Xueqian and Zhong, Jiang and Feng, Zhengzhi},
  title = {A Smartphone-Based Acoustic Machine Learning Pipeline for Detecting Suicidal Ideation: Case-Control Model Development and Validation Study},
  journal = {JMIR Formative Research},
  year = {2026},
  volume = {10},
  pages = {e92646--e92646},
  doi = {10.2196/92646}
}
Kostenlos starten →