A multisource clinical deep learning model for early identification of mental disorders in first-visit psychiatric patients
6 affiliations
- 1Department of Psychiatry, Heilongjiang Provincial Hospital
- 2Department of General Practice, Heilongjiang Provincial Hospital
- 3Department of Dentistry, Heilongjiang Provincial Hospital
- 4Department of Neurology, Heilongjiang Provincial Hospital
- 5Outpatient Comprehensive Clinic, Heilongjiang Provincial Hospital
- 6Discipline Inspection and Supervision Office, Heilongjiang Provincial Hospital
Abstract
Introduction: Mental disorders often present with overlapping symptoms at the first psychiatric visit, making early identification difficult. This study included 5802 first-visit psychiatric patients and developed a TUCH-FT for multi-label classification of mental disorders using demographic information, clinical history, and item-level Symptom Checklist-90 data. Final diagnostic labels were determined through longitudinal follow-up, treatment response, and psychiatric expert evaluation. The original FT-Transformer places heterogeneous clinical variables in a single sequence, which may weaken source-specific structures, inadequately represent unclear clinical histories, and fail to model directional cross-source interactions and hierarchical comorbidity relationships.
Methods: To overcome these limitations, this study proposes a three-branch clinical feature encoding method, an uncertainty-aware embedding method, a cross-group multi-head attention fusion mechanism, and a hierarchical multi-label classification method to address the challenges of heterogeneous clinical information, ambiguous clinical histories, the interaction of information from multiple sources, and the modelling of comorbidity relationships.
Results: TUCH-FT achieved a Macro-F1 of 0.803, Micro-F1 of 0.842, Macro-average precision of 0.838, Hamming loss of 0.095, and label ranking average precision of 0.876. In a temporally separated, same-centre validation cohort of 1, 272 patients, TUCH-FT demonstrated good calibration performance, with the lowest Brier score observed for psychotic disorders (0.072) and the highest for anxiety disorders (0.134), while expected calibration errors ranged from 0.031 to 0.067.
Discussion: Although the exact-match accuracy for complete diagnostic combinations was 60.8%, indicating some limitations in predicting co-occurring disorders, TUCH-FT may still provide a useful reference for differential assessment among first-visit psychiatric patients presenting with mood-related symptoms.
Related
- A clinical laboratory test-wide association scan of polygenic scores identifies biomarkers of psychiatric disorders
- Predicting One-Year Psychiatric Rehospitalization Using Natural Language Processing and Machine Learning Methods Based on Clinical Texts
- Revisiting Identification Thresholds of Specific Learning Disorders ( SLD ) in Gifted Children ( GC ). A Comparison of Three Groups: Twice‐Exceptional ( TE ) Children, GC Without SLD and Non‐ GC With SLD
- Microglia in Psychiatric Disorders: Stage-Dependent Roles and Therapeutic Implications
- Healthcare utilization and medical costs among adults with selected psychiatric disorders: a nationwide retrospective cohort study
BibTeX
@article{zhang2026multisource,
title = {{A multisource clinical deep learning model for early identification of mental disorders in first-visit psychiatric patients}},
author = {Yu Zhang and Zhan Gao and Wenyu Ge and Zhiyu Cao and Hongyan Zhu and Yuchao Ma and Weiwei Wang and Yuqing Song and Yu Li and Xiangna Zheng},
journal = {Frontiers in Psychiatry},
year = {2026},
month = oct,
doi = {10.3389/fpsyt.2026.1988768},
url = {https://www.frontiersin.org/articles/10.3389/fpsyt.2026.1988768/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A multisource clinical deep learning model for early identification of mental disorders in first-visit psychiatric patients
AU - Yu Zhang
AU - Zhan Gao
AU - Wenyu Ge
AU - Zhiyu Cao
AU - Hongyan Zhu
AU - Yuchao Ma
AU - Weiwei Wang
AU - Yuqing Song
AU - Yu Li
AU - Xiangna Zheng
PY - 2026
DA - 2026/10/28
JO - Frontiers in Psychiatry
DO - 10.3389/fpsyt.2026.1988768
UR - https://www.frontiersin.org/articles/10.3389/fpsyt.2026.1988768/full
AB - Introduction: Mental disorders often present with overlapping symptoms at the first psychiatric visit, making early identification difficult. This study included 5802 first-visit psychiatric patients and developed a TUCH-FT for multi-label classification of mental disorders using demographic information, clinical history, and item-level Symptom Checklist-90 data. Final diagnostic labels were determined through longitudinal follow-up, treatment response, and psychiatric expert evaluation. The original FT-Transformer places heterogeneous clinical variables in a single sequence, which may weaken source-specific structures, inadequately represent unclear clinical histories, and fail to model directional cross-source interactions and hierarchical comorbidity relationships. Methods: To overcome these limitations, this study proposes a three-branch clinical feature encoding method, an uncertainty-aware embedding method, a cross-group multi-head attention fusion mechanism, and a hierarchical multi-label classification method to address the challenges of heterogeneous clinical information, ambiguous clinical histories, the interaction of information from multiple sources, and the modelling of comorbidity relationships. Results: TUCH-FT achieved a Macro-F1 of 0.803, Micro-F1 of 0.842, Macro-average precision of 0.838, Hamming loss of 0.095, and label ranking average precision of 0.876. In a temporally separated, same-centre validation cohort of 1, 272 patients, TUCH-FT demonstrated good calibration performance, with the lowest Brier score observed for psychotic disorders (0.072) and the highest for anxiety disorders (0.134), while expected calibration errors ranged from 0.031 to 0.067. Discussion: Although the exact-match accuracy for complete diagnostic combinations was 60.8%, indicating some limitations in predicting co-occurring disorders, TUCH-FT may still provide a useful reference for differential assessment among first-visit psychiatric patients presenting with mood-related symptoms.
SN - 1664-0640
ER -