Predicting acupuncture efficacy for major depressive disorder using baseline clinical variables: A machine learning study

Abstract

Acupuncture is a viable treatment option for major depressive disorder (MDD). However, its effectiveness varies among patients. This study aimed to develop a model to predict the efficacy of acupuncture therapy for MDD using machine learning and baseline clinical variables. A total of 124 patients with MDD from five research centers were included in our machine learning study. All patients underwent acupuncture treatment for 6 weeks and the efficacy of the treatment was evaluated using the Hamilton Depression Scale-17 (HAMD-17). The max-relevance and min-redundancy (mRMR) algorithm and Pearson correlation analysis were used for selecting 11 significant features from 26 baseline clinical variables for model training. We compared the performance of five machine learning models, including logistic regression, support vector machine, K-nearest neighbor, random forest, and XgBoost, in predicting the effect of acupuncture in relieving major depression. Among the five models, XgBoost performed the best with an area under the receiver operating characteristic curve (AUC) of 0.835, an accuracy of 0.730, a sensitivity of 0.670, a specificity of 0.774, and an F1 score of 0.751. The key predictive variables identified were anxiety score in the self-rating depression scale (SDS), the traditional Chinese medicine syndrome of deficiency in both heart and spleen, and body mass index (BMI). The study demonstrates that the developed model can help physicians predict the patients who will benefit from acupuncture treatment, which is of positive significance for improving the clinical efficacy of acupuncture on MDD.

Keywords: Acupuncture; Efficacy prediction; Machine learning; Major depressive disorder.