Construction and validation of a predictive model for suicidal attempts in patients with mood disorders after discharge based on machine learning methods: A two-year follow-up study
Journal of Affective Disorders · 2026-07 · 405 · 121607
DOI: 10.1016/j.jad.2026.121607 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Journal of Affective Disorders, 2026-07. Verfasst von Yannan Deng und 9 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Key Laboratory of Intelligent Drug Research and Development for Mental Disorders, National Clinical Research Center for Mental Disorders, Nat…. Hauptthemen laut MEDLINE: Suicide, Attempted, Mood Disorders, Patient Discharge, Machine Learning. Die Arbeit nennt 47 Literaturangaben. Gefördert von: Beijing Municipal Administration of Hospitals.
Abstract (Originalsprache)
BACKGROUND: Suicide attempts (SA) in patients with mood disorders (MD) should be paid enough attention. Currently, there is a lack of relevant research on the prediction of SA of inpatients with MD in psychiatric wards after discharge. We tried to construct a SA prediction model for hospitalized patients within two years of discharge through a variety of machine learning algorithms, and verify the relevant performance of the model. METHODS: We followed up 1099 patients for two years, a total of 865 patients completed. In order to avoid the influence of redundant features, we used the LASSO regression method to reduce the dimension, and used eight machine learning algorithms to construct the SA prediction model. At the same time, we evaluated the machine learning model with the best stability based on sensitivity, AUC and FI scores. Then we used the local interpretation technique of SHapley Additive ExPlanations (SHAP) to analyze the contribution of each feature to SA within two years after discharge. RESULTS: We tried to analyze the prediction model based on the characteristics of LASSO regression. The SA prediction model constructed by random forest (RF) method showed good robustness (testing AUC = 0.770, training AUC = 0.944). SHAP interpretation technique found that SA occurred within 3 months was the most important feature, and previous NSSI was more indicative than previous SA and suicidal behavior (SB). CONCLUSION: The RF method can well construct a risk prediction model for SA in hospitalized MD patients within two years of discharge.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Beijing Key Laboratory of Intelligent Drug Research and Development for Mental Disorders, National Clinical Research Center for Mental Disorders, National Center for Mental Disorders, Beijing Anding Hospital, Capital Me…
- School of Software, Dalian University of Technology, Dalian, China.
- Department of Medical Psychology of Hainan Hospital, Chinese PLA General Hospital, Sanya, China.
Förderung
- Beijing Municipal Administration of Hospitals
Zitieren
APA
Deng, Y., Shen, H., Zhang, C., Han, J., Ye, Z., Zhao, G., Zhang, J., Zhao, X., Guo, T., & Liang, S. (2026). Construction and validation of a predictive model for suicidal attempts in patients with mood disorders after discharge based on machine learning methods: A two-year follow-up study. Journal of Affective Disorders, 405, 121607. https://doi.org/10.1016/j.jad.2026.121607
Vancouver
Deng Y, Shen H, Zhang C, Han J, Ye Z, Zhao G, et al. Construction and validation of a predictive model for suicidal attempts in patients with mood disorders after discharge based on machine learning methods: A two-year follow-up study. Journal of Affective Disorders. 2026;405:121607. doi:10.1016/j.jad.2026.121607
BibTeX
@article{Deng2026,
author = {Deng, Yannan and Shen, Haotian and Zhang, Chaoshi and Han, Jiali and Ye, Zifeng and Zhao, Guangwei and Zhang, Jinhe and Zhao, Xixi and Guo, Tong and Liang, Sixiang},
title = {Construction and validation of a predictive model for suicidal attempts in patients with mood disorders after discharge based on machine learning methods: A two-year follow-up study},
journal = {Journal of Affective Disorders},
year = {2026},
volume = {405},
pages = {121607},
doi = {10.1016/j.jad.2026.121607}
}
EUVIMED