Machine learning-based methods for predicting postpartum depression: A review

Postpartum depression (PPD) is a widespread mental illness after delivery, which has a substantial impact on the health of both mothers and infants. Machine learning (ML) has developed rapidly and plays a vital function in disease prediction. This article summarizes and reviews ML techniques used to predict PPD, aiming to investigate their potential for predicting the risk of PPD. We performed a bibliographic search on China National Knowledge Infrastructure (CNKI), China Science and Technology Journal Database (CQVIP), Web of Science and Google Scholar looking for studies aimed at the prediction of PPD using ML techniques. Of the 103 articles collected, 25 fulfilled the inclusion criteria. Supervised learning was the primary ML technique applied and the most prevalent ML models were gradient boosting, random forest, and support vector machine. Notably, the PPD prediction model based on gradient boosting has the best effect and the vast majority of studies have ended up in an area under the curve that exceeds 0. 7. All studies indicate that it is feasible to use ML techniques to predict PPD. We focused on the research of ML techniques used for PPD prediction, and did not delve into the medical knowledge related to PPD prediction. ML has great potential in the field of PPD prediction. Nevertheless, further research is needed to fully realize this prospect, including standardizing data collection, improving the robustness of feature selection, and encouraging interdisciplinary collaboration. This will help improve the stability and accuracy of the model and provide more personalized medical services for patients.

Authors

• Xiaobo Zhang Ant Group
• Jinyu Bao
• Jianzhong Ye
• Xiaoping Qiu
• Yi Pan

Keywords

• Machine learning
• Postpartum depression
• Influence factor
• Prediction models