Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort study

Abstract Background Vascular depression (VaDep) is a prevalent affective disorder in older adults that significantly impacts functional status and quality of life. Early identification and intervention are crucial but largely insufficient in clinical practice due to inconspicuous depressive symptoms...

Full description

Saved in:
Bibliographic Details
Main Authors: Ran Zhang, Tian Li, Fan Fan, Haoying He, Liuyi Lan, Dong Sun, Zhipeng Xu, Sisi Peng, Jing Cao, Juan Xu, Xiaoxiang Peng, Ming Lei, Hao Song, Junjian Zhang
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medicine
Subjects:
Online Access:https://doi.org/10.1186/s12916-025-04283-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343690947952640
author Ran Zhang
Tian Li
Fan Fan
Haoying He
Liuyi Lan
Dong Sun
Zhipeng Xu
Sisi Peng
Jing Cao
Juan Xu
Xiaoxiang Peng
Ming Lei
Hao Song
Junjian Zhang
author_facet Ran Zhang
Tian Li
Fan Fan
Haoying He
Liuyi Lan
Dong Sun
Zhipeng Xu
Sisi Peng
Jing Cao
Juan Xu
Xiaoxiang Peng
Ming Lei
Hao Song
Junjian Zhang
author_sort Ran Zhang
collection DOAJ
description Abstract Background Vascular depression (VaDep) is a prevalent affective disorder in older adults that significantly impacts functional status and quality of life. Early identification and intervention are crucial but largely insufficient in clinical practice due to inconspicuous depressive symptoms mostly, heterogeneous imaging manifestations, and the lack of definitive peripheral biomarkers. This study aimed to develop and validate an interpretable machine learning (ML) model for VaDep to serve as a clinical support tool. Methods This study included 602 participants from Wuhan in China divided into 236 VaDep patients and 366 controls for training and internal validation from July 2020 to October 2023. An independent dataset of 171 participants from surrounding areas was used for external validation. We collected clinical data, neuropsychological assessments, blood test results, and MRI scans to develop and refine ML models through cross-validation. Feature reduction was implemented to simplify the models without compromising their performance, with validation achieved through internal and external datasets. The SHapley Additive exPlanations method was used to enhance model interpretability. Results The Light Gradient Boosting Machine (LGBM) model outperformed from the selected 6 ML algorithms based on performance metrics. An optimized, interpretable LGBM model with 8 key features, including white matter hyperintensities score, age, vascular endothelial growth factor, interleukin-6, brain-derived neurotrophic factor, tumor necrosis factor-alpha levels, lacune counts, and serotonin level, demonstrated high diagnostic accuracy in both internal (AUROC = 0.937) and external (AUROC = 0.896) validations. The final model also achieved, and marginally exceeded, clinician-level diagnostic performance. Conclusions Our research established a consistent and explainable ML framework for identifying VaDep in older adults, utilizing comprehensive clinical data. The 8 characteristics identified in the final LGBM model provide new insights for further exploration of VaDep mechanisms and emphasize the need for enhanced focus on early identification and intervention in this vulnerable group. More attention needs to be paid to the affective health of older adults.
format Article
id doaj-art-fd80e5dec5d449459de60db9b97e8f68
institution Kabale University
issn 1741-7015
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medicine
spelling doaj-art-fd80e5dec5d449459de60db9b97e8f682025-08-20T03:42:53ZengBMCBMC Medicine1741-70152025-07-0123111710.1186/s12916-025-04283-9Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort studyRan Zhang0Tian Li1Fan Fan2Haoying He3Liuyi Lan4Dong Sun5Zhipeng Xu6Sisi Peng7Jing Cao8Juan Xu9Xiaoxiang Peng10Ming Lei11Hao Song12Junjian Zhang13Department of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neuropsychology, Zhongnan Hospital of Wuhan UniversityDepartment of Neuropsychology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Third People’s Hospital of Hubei ProvinceDepartment of Neurology, General Hospital of the Yangtze River ShippingDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityDepartment of Neurology, Zhongnan Hospital of Wuhan UniversityAbstract Background Vascular depression (VaDep) is a prevalent affective disorder in older adults that significantly impacts functional status and quality of life. Early identification and intervention are crucial but largely insufficient in clinical practice due to inconspicuous depressive symptoms mostly, heterogeneous imaging manifestations, and the lack of definitive peripheral biomarkers. This study aimed to develop and validate an interpretable machine learning (ML) model for VaDep to serve as a clinical support tool. Methods This study included 602 participants from Wuhan in China divided into 236 VaDep patients and 366 controls for training and internal validation from July 2020 to October 2023. An independent dataset of 171 participants from surrounding areas was used for external validation. We collected clinical data, neuropsychological assessments, blood test results, and MRI scans to develop and refine ML models through cross-validation. Feature reduction was implemented to simplify the models without compromising their performance, with validation achieved through internal and external datasets. The SHapley Additive exPlanations method was used to enhance model interpretability. Results The Light Gradient Boosting Machine (LGBM) model outperformed from the selected 6 ML algorithms based on performance metrics. An optimized, interpretable LGBM model with 8 key features, including white matter hyperintensities score, age, vascular endothelial growth factor, interleukin-6, brain-derived neurotrophic factor, tumor necrosis factor-alpha levels, lacune counts, and serotonin level, demonstrated high diagnostic accuracy in both internal (AUROC = 0.937) and external (AUROC = 0.896) validations. The final model also achieved, and marginally exceeded, clinician-level diagnostic performance. Conclusions Our research established a consistent and explainable ML framework for identifying VaDep in older adults, utilizing comprehensive clinical data. The 8 characteristics identified in the final LGBM model provide new insights for further exploration of VaDep mechanisms and emphasize the need for enhanced focus on early identification and intervention in this vulnerable group. More attention needs to be paid to the affective health of older adults.https://doi.org/10.1186/s12916-025-04283-9Vascular depressionLate-life depressionMachine learningLight Gradient Boosting MachineWhite matter hyperintensity
spellingShingle Ran Zhang
Tian Li
Fan Fan
Haoying He
Liuyi Lan
Dong Sun
Zhipeng Xu
Sisi Peng
Jing Cao
Juan Xu
Xiaoxiang Peng
Ming Lei
Hao Song
Junjian Zhang
Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort study
BMC Medicine
Vascular depression
Late-life depression
Machine learning
Light Gradient Boosting Machine
White matter hyperintensity
title Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort study
title_full Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort study
title_fullStr Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort study
title_full_unstemmed Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort study
title_short Identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults: a multicenter cohort study
title_sort identification and validation of an explainable machine learning model for vascular depression diagnosis in the older adults a multicenter cohort study
topic Vascular depression
Late-life depression
Machine learning
Light Gradient Boosting Machine
White matter hyperintensity
url https://doi.org/10.1186/s12916-025-04283-9
work_keys_str_mv AT ranzhang identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT tianli identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT fanfan identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT haoyinghe identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT liuyilan identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT dongsun identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT zhipengxu identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT sisipeng identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT jingcao identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT juanxu identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT xiaoxiangpeng identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT minglei identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT haosong identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy
AT junjianzhang identificationandvalidationofanexplainablemachinelearningmodelforvasculardepressiondiagnosisintheolderadultsamulticentercohortstudy