An optimization for postpartum depression risk assessment and preventive intervention strategy based machine learning approaches

Hao Liu; Anran Dai; Zhou Zhou; Xiaowen Xu; Kai Gao; Qiuwen Li; Shouyu Xu; Yunfei Feng; Chen Chen; Chun Ge; Yuanjun Lu; Jianjun Zou; Saiying Wang

doi:10.1016/j.jad.2023.02.028

An optimization for postpartum depression risk assessment and preventive intervention strategy based machine learning approaches

J Affect Disord. 2023 May 1:328:163-174. doi: 10.1016/j.jad.2023.02.028. Epub 2023 Feb 8.

Authors

Hao Liu¹, Anran Dai¹, Zhou Zhou², Xiaowen Xu³, Kai Gao⁴, Qiuwen Li⁴, Shouyu Xu⁴, Yunfei Feng⁴, Chen Chen⁵, Chun Ge⁵, Yuanjun Lu⁶, Jianjun Zou⁷, Saiying Wang⁸

Affiliations

¹ School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing 211198, China; Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210006, China.
² Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210006, China.
³ Office of Clinical Trials, Nanjing First Hospital, Nanjing Medical University, Nanjing 210006, China.
⁴ Department of Anesthesiology, Third Xiangya Hospital of Central South University, Changsha 410013, China.
⁵ Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210006, China; Department of Pharmacy, Nanjing First Hospital, China Pharmaceutical University, Nanjing 210006, China.
⁶ Research and Development Department, Hangzhou Million Happy Deer Co. Ltd, Hangzhou 310012, China.
⁷ Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210006, China; Department of Pharmacy, Nanjing First Hospital, China Pharmaceutical University, Nanjing 210006, China. Electronic address: zoujianjun100@126.com.
⁸ Department of Anesthesiology, Third Xiangya Hospital of Central South University, Changsha 410013, China. Electronic address: 1771303488@qq.com.

PMID: 36758872
DOI: 10.1016/j.jad.2023.02.028

Abstract

Background: Postpartum depression (PPD) is one of the most common psychiatric disorders for women after delivery. The establishment of an effective PPD prediction model helps to distinguish high-risk groups, and verifying whether such high-risk groups can benefit from drug intervention is very important for clinical guidance.

Methods: We collected data of parturients that underwent a cesarean delivery. The Control group was divided into a training cohort and a testing cohort. Six different ML models were constructed and we compared their prediction performance in the testing cohort. For model interpretation, we introduced SHapley Additive exPlanations (SHAP). Then, training cohort, ketamine group and dexmedetomidine (DEX) group were classified as high or low risk for PPD by the model. A 1:1 propensity score matching (PSM) was performed to compare the incidence of PPD between two groups in different risk cohorts.

Results: Extreme gradient enhancement (XGB) had the best recognition effect, with an area under the receiver operating characteristic curve (AUROC) of 0.789 (95 % CI 0.742-0.836) in the training cohort and 0.744 (95 % CI 0.655-0.823) in the testing cohort, respectively. A threshold of 21.5 % PPD risk probability was determined. After PSM, the results showed that the incidence of PPD in the two intervention groups was significantly different from the control group in the high-risk cohort (P < 0.001) but not in the low-risk cohort (P > 0.001).

Conclusion: Our study demonstrated that the XGB algorithm provided a more accurate in prediction of PPD risk, and it was beneficial to receive early intervention for the high-risk groups distinguished by the model.

Keywords: Dexmedetomidine; Ketamine; Machine learning; Postpartum depression; Prediction model; Risk threshold.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Cesarean Section / adverse effects
Depression, Postpartum* / epidemiology
Female
Humans
Machine Learning
Pregnancy
ROC Curve
Risk Assessment