← Back to VOLUME 15, ISSUE 4, APRIL 2026
This work is licensed under a Creative Commons Attribution 4.0 International License.
Postpartum Depression Risk Prediction Model: Leveraging Machine Learning for Early Detection and Preventive Care
π 10 viewsπ₯ 0 downloads
Abstract: Postpartum depression (PPD) is one of the most common and underdiagnosed psychiatric disorder to affect women after giving birth. It not only impacts the mental well-being of the mother but also infant health and development. Despite its seriousness, early detection and treatment remain challenging in the majority of healthcare systems due to the subjective symptoms and the stigma of mental health.
In this project, we applied machine learning to develop a predictive model that can assess whether a woman is at risk for PPD based on clinical, psychological, and lifestyle variables. The dataset contains 1,500 records, of which 1,200 are used for training purposes and 300 for testing purposes. It has variables such as mother's age, number of children, marriage status, history of mental illness, hormone level, stress level, sleeping habits, mode of delivery, and week postpartum.
Two models were used and compared: Logistic Regression and Random Forest Classifier. The Random Forest model achieved a remarkable test accuracy of 100%, but Logistic Regression achieved an accuracy of approximately 81%, a more interpretable and generalizable baseline. The models were measured using standard metrics such as accuracy, precision, recall, F1-score, and confusion matrix.
In order to cross-verify against overfitting, the Random Forest model's excellent accuracy, a 5-fold cross-validation has been performed. The Random Forest model itself had an extremely high mean accuracy of 99.83%, indicating a good generalization ability. Importance analysis of features also indicated that support systems, stress levels, and hormone levels were among the most significant predictor variables.
This work also shows promise for machine learning as a complementary diagnostic tool for postpartum menal health screening, providing clinicians and public health practitioners data-informed guidance to actively identify and support at-risk individuals.
Keywords: Maternal mental health, New born & Mother care, Postnatal health, Lactational Amenorrhea Method (LAM), Postpartum recovery support.
In this project, we applied machine learning to develop a predictive model that can assess whether a woman is at risk for PPD based on clinical, psychological, and lifestyle variables. The dataset contains 1,500 records, of which 1,200 are used for training purposes and 300 for testing purposes. It has variables such as mother's age, number of children, marriage status, history of mental illness, hormone level, stress level, sleeping habits, mode of delivery, and week postpartum.
Two models were used and compared: Logistic Regression and Random Forest Classifier. The Random Forest model achieved a remarkable test accuracy of 100%, but Logistic Regression achieved an accuracy of approximately 81%, a more interpretable and generalizable baseline. The models were measured using standard metrics such as accuracy, precision, recall, F1-score, and confusion matrix.
In order to cross-verify against overfitting, the Random Forest model's excellent accuracy, a 5-fold cross-validation has been performed. The Random Forest model itself had an extremely high mean accuracy of 99.83%, indicating a good generalization ability. Importance analysis of features also indicated that support systems, stress levels, and hormone levels were among the most significant predictor variables.
This work also shows promise for machine learning as a complementary diagnostic tool for postpartum menal health screening, providing clinicians and public health practitioners data-informed guidance to actively identify and support at-risk individuals.
Keywords: Maternal mental health, New born & Mother care, Postnatal health, Lactational Amenorrhea Method (LAM), Postpartum recovery support.
How to Cite:
[1] Tanish Shingade, Abhinav Ragam, Shriddhar Patil, Nikhil Nikam, Prof. Smita Chunamari, βPostpartum Depression Risk Prediction Model: Leveraging Machine Learning for Early Detection and Preventive Care,β International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), DOI: 10.17148/IJARCCE.2026.154279
This work is licensed under a Creative Commons Attribution 4.0 International License.