Construction of interpretable predictive model of acupuncture for methadone reduction in patients undergoing methadone maintenance treatment based on machine learning and SHAP.
10.13703/j.0255-2930.20250110-0002
- Author:
Baochao FAN
1
;
Qiao ZHANG
1
;
Chen CHEN
2
;
Yiming CHEN
1
;
Peiming ZHANG
3
;
Liming LU
1
Author Information
1. Clinical Medical College of Acupuncture-Moxibustion and Rehabilitation, Big Data Laboratory of Acupuncture-Moxibustion Research Center, Guangzhou University of CM, Guangzhou 511400, Guangdong Province, China.
2. Jiangsu Medical Vocational College.
3. Clinical Medical College of Acupuncture-Moxibustion and Rehabilitation, Big Data Laboratory of Acupuncture-Moxibustion Research Center, Guangzhou University of CM, Guangzhou 511400, Guangdong Province, China; Eighth Clinical Medical College of Guangzhou University of CM; Foshan TCM Hospital.
- Publication Type:Journal Article
- Keywords:
acupuncture;
machine learning;
methadone maintenance treatment;
model interpretation;
predictive model
- MeSH:
Humans;
Methadone/therapeutic use*;
Acupuncture Therapy;
Adult;
Female;
Male;
Machine Learning;
Middle Aged;
Opiate Substitution Treatment;
Young Adult
- From:
Chinese Acupuncture & Moxibustion
2025;45(10):1363-1370
- CountryChina
- Language:Chinese
-
Abstract:
OBJECTIVE:To construct a predictive model for the reduction in methadone maintenance treatment (MMT) and evaluate the effects of different interventions and other clinical factors on methadone reduction using Shapley additive explanations (SHAP).
METHODS:Two clinical trials of acupuncture for methadone reduction in MMT patients were analyzed, and the baseline data, MMT related information, intervention measures, the data related to dose-reduction outcomes were collected. The predictive model was constructed by means of 6 machine learning algorithms including support vector machine (SVM), K-nearest neighbors (KNN), logistic regression (LR), Naive Bayes (NB), random forest (RF) and categorical-boosting (CatBoost), and 2 integration methods, blending-ensemble method (Blending) and Stacking-ensemble method (Stacking). SHAP was employed for the interpretability analysis of the optimal model.
RESULTS:A total of 251 MMT patients were included, 128 cases in the acupuncture group and 123 cases in the non-acupuncture group. CatBoost and Stacking performed optimally in the test set. CatBoost obtained an accuracy of 0.780 0±0.060 8, a precision of 0.500 0±0.120 0, a recall of 0.818 2±0.140 2, F1 score of 0.620 7±0.114 0, and receiver operating characteristic-area under curve (ROC-AUC) of 0.857 8±0.140 2 for the subjects. In MMT patients with acupuncture as an adjunctive therapy, the top 5 important features for methadone reduction, included intervention measures, body mass index (BMI), the duration of MMT, the history of opioid use and occupation; and SHAP values were 1.25, 0.36, 0.21, 0.19 and 0.12, respectively. The SHAP feature dependence plot showed that BMI, MMT duration and the history of opioid use presented a nonlinear negative correlation with the reduction effect.
CONCLUSION:In acupuncture as adjunctive therapy for methadone reduction, the clinical factors should be considered comprehensively; and the interpretable predictive model provides a scientific basis for it, which is conducive to the improvement of clinical strategy of acupuncture for methadone reduction and the development of personalized reduction scheme.
