Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study
Abstract Objective Depression has emerged as a global public health concern with high incidence and disability rates, which are timely imperative to identify and intervene in clinical practice. The objective of this study was to explore the association between heart rate variability (HRV) and depres...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-12-01
|
| Series: | BMC Psychiatry |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12888-024-06384-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846112338813386752 |
|---|---|
| author | Min Yang Huiqin Zhang Minglan Yu Yunxuan Xu Bo Xiang Xiaopeng Yao |
| author_facet | Min Yang Huiqin Zhang Minglan Yu Yunxuan Xu Bo Xiang Xiaopeng Yao |
| author_sort | Min Yang |
| collection | DOAJ |
| description | Abstract Objective Depression has emerged as a global public health concern with high incidence and disability rates, which are timely imperative to identify and intervene in clinical practice. The objective of this study was to explore the association between heart rate variability (HRV) and depression, with the aim of establishing and validating machine learning models for the auxiliary diagnosis of depression. Methods The data of 465 outpatients from the Affiliated Hospital of Southwest Medical University were selected for the study. The study population was then randomly divided into training and test sets in a 7:3 ratio. Logistic regression (LR), support vector machine (SVM), random forest (RF) and eXtreme gradient boosting (XGBoost) algorithm models were used to construct risk prediction models in the training set, and the model performance was verified in the test set. The four models were evaluated by the area under the receiver operating characteristic curve (ROC), calibration curve and the decision curve analysis (DCA). Furthermore, we employed the SHapley Additive exPlanations (SHAP) method to illustrate the effects of the features attributed to the model. Results There were 237 people in the depressed group and 228 in the non-depressed group. In the training set (n = 325) and test set (n = 140), the area under of the curve(AUC) values of the XGBoost model are 0.92 [95% confidence interval (CI) 0.888,0.95] and 0.82 (95% CI 0.754,0.892)] respectively, which are higher than the other three models. The XGBoost model has excellent predictive efficacy and clinical utility. The SHAP method was ranked according to the importance of the degree of influence on the model, with age, heart rate, Standard deviation of the NN intervals (SDNN), two nonlinear parameters of HRV and sex considered to be the top 6 predictors. Conclusion We provided a feasibility study of HRV as a potential biomarker for depression. The proposed model based on HRV provides clinicians with a quantitative auxiliary diagnostic tool, which is assist to improving the accuracy and efficiency of depression diagnosis, and can also be utilized for the monitoring and prevention of depression. |
| format | Article |
| id | doaj-art-561725bfff354e53b2c8508ec3b6ee9d |
| institution | Kabale University |
| issn | 1471-244X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Psychiatry |
| spelling | doaj-art-561725bfff354e53b2c8508ec3b6ee9d2024-12-22T12:40:02ZengBMCBMC Psychiatry1471-244X2024-12-0124111510.1186/s12888-024-06384-wAuxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective studyMin Yang0Huiqin Zhang1Minglan Yu2Yunxuan Xu3Bo Xiang4Xiaopeng Yao5School of Public Health, Southwest Medical UniversitySchool of Public Health, Southwest Medical UniversityInstitute of cardiovascular research, Southwest Medical UniversitySchool of Computer Science and Technology, Southwest University of Science and TechnologyDepartment of Psychiatry, Fundamental and Clinical Research on Mental Disorders Key Laboratory of Luzhou, Medical Laboratory Center, Laboratory of Neurological Diseases & Brain Function, Affiliated Hospital of Southwest Medical UniversitySchool of Medical Information and Engineering, Southwest Medical UniversityAbstract Objective Depression has emerged as a global public health concern with high incidence and disability rates, which are timely imperative to identify and intervene in clinical practice. The objective of this study was to explore the association between heart rate variability (HRV) and depression, with the aim of establishing and validating machine learning models for the auxiliary diagnosis of depression. Methods The data of 465 outpatients from the Affiliated Hospital of Southwest Medical University were selected for the study. The study population was then randomly divided into training and test sets in a 7:3 ratio. Logistic regression (LR), support vector machine (SVM), random forest (RF) and eXtreme gradient boosting (XGBoost) algorithm models were used to construct risk prediction models in the training set, and the model performance was verified in the test set. The four models were evaluated by the area under the receiver operating characteristic curve (ROC), calibration curve and the decision curve analysis (DCA). Furthermore, we employed the SHapley Additive exPlanations (SHAP) method to illustrate the effects of the features attributed to the model. Results There were 237 people in the depressed group and 228 in the non-depressed group. In the training set (n = 325) and test set (n = 140), the area under of the curve(AUC) values of the XGBoost model are 0.92 [95% confidence interval (CI) 0.888,0.95] and 0.82 (95% CI 0.754,0.892)] respectively, which are higher than the other three models. The XGBoost model has excellent predictive efficacy and clinical utility. The SHAP method was ranked according to the importance of the degree of influence on the model, with age, heart rate, Standard deviation of the NN intervals (SDNN), two nonlinear parameters of HRV and sex considered to be the top 6 predictors. Conclusion We provided a feasibility study of HRV as a potential biomarker for depression. The proposed model based on HRV provides clinicians with a quantitative auxiliary diagnostic tool, which is assist to improving the accuracy and efficiency of depression diagnosis, and can also be utilized for the monitoring and prevention of depression.https://doi.org/10.1186/s12888-024-06384-wHeart rate variabilityDepressionCorrelationMachine learningPredictive model |
| spellingShingle | Min Yang Huiqin Zhang Minglan Yu Yunxuan Xu Bo Xiang Xiaopeng Yao Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study BMC Psychiatry Heart rate variability Depression Correlation Machine learning Predictive model |
| title | Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study |
| title_full | Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study |
| title_fullStr | Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study |
| title_full_unstemmed | Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study |
| title_short | Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study |
| title_sort | auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability a retrospective study |
| topic | Heart rate variability Depression Correlation Machine learning Predictive model |
| url | https://doi.org/10.1186/s12888-024-06384-w |
| work_keys_str_mv | AT minyang auxiliaryidentificationofdepressionpatientsusinginterpretablemachinelearningmodelsbasedonheartratevariabilityaretrospectivestudy AT huiqinzhang auxiliaryidentificationofdepressionpatientsusinginterpretablemachinelearningmodelsbasedonheartratevariabilityaretrospectivestudy AT minglanyu auxiliaryidentificationofdepressionpatientsusinginterpretablemachinelearningmodelsbasedonheartratevariabilityaretrospectivestudy AT yunxuanxu auxiliaryidentificationofdepressionpatientsusinginterpretablemachinelearningmodelsbasedonheartratevariabilityaretrospectivestudy AT boxiang auxiliaryidentificationofdepressionpatientsusinginterpretablemachinelearningmodelsbasedonheartratevariabilityaretrospectivestudy AT xiaopengyao auxiliaryidentificationofdepressionpatientsusinginterpretablemachinelearningmodelsbasedonheartratevariabilityaretrospectivestudy |