
浏览全部资源
扫码关注微信
广州中医药大学针灸康复临床医学院,针灸研究中心大数据实验室,广东广州 511400
江苏医药职业学院
广州中医药大学第八临床医学院
佛山市中医院
✉陆丽明,教授。E-mail:lulimingleon@126.com
收稿:2025-01-10,
网络首发:2025-07-14,
纸质出版:2025-10-12
移动端阅览
范宝超, 张侨, 陈晨, 等. 基于机器学习与SHAP的针刺干预美沙酮维持患者美沙酮减量的可解释性预测模型构建研究[J]. 中国针灸, 2025,45(10):1363-1370.
FAN Baochao, ZHANG Qiao, CHEN Chen, et al. Construction of interpretable predictive model of acupuncture for methadone reduction in patients undergoing methadone maintenance treatment based on machine learning and SHAP[J]. Chinese Acupuncture & Moxibustion, 2025, 45(10): 1363-1370.
范宝超, 张侨, 陈晨, 等. 基于机器学习与SHAP的针刺干预美沙酮维持患者美沙酮减量的可解释性预测模型构建研究[J]. 中国针灸, 2025,45(10):1363-1370. DOI: 10.13703/j.0255-2930.20250110-0002.
FAN Baochao, ZHANG Qiao, CHEN Chen, et al. Construction of interpretable predictive model of acupuncture for methadone reduction in patients undergoing methadone maintenance treatment based on machine learning and SHAP[J]. Chinese Acupuncture & Moxibustion, 2025, 45(10): 1363-1370. DOI: 10.13703/j.0255-2930.20250110-0002.
目的:
2
建立一种美沙酮维持治疗(methadone maintenance treatment,MMT)减量预测模型,并采用沙普利加和解释(SHAP)方法评估不同干预措施及其他临床因素对美沙酮减量的影响。
方法:
2
对两项针刺干预MMT患者美沙酮减量的临床试验进行分析,收集患者的基线资料、MMT相关信息、干预方式、减量结局指标相关数据,采用支持向量机(SVM)、K最近邻(KNN)、逻辑回归(LR)、朴素贝叶斯(NB)、随机森林(RF)和CatBoost分类模型(CatBoost)6种机器学习算法和混合(Blending)、堆叠(Stacking)2种集成方法构建预测模型,并用SHAP方法对最优模型进行可解释性分析。
结果:
2
共251例MMT患者纳入研究,其中针刺组128例、非针刺组123例。CatBoost模型和Stacking集成方法在测试集上表现最优,CatBoost模型的准确率为0.780 0±0.060 8,精确率为0.500 0±0.120 0,召回率为0.818 2±0.140 2,F1分数为0.620 7±0.114 0,受试者工作特征曲线下面积(ROC-AUC)为0.857 8±0.140 2。影响针刺辅助MMT患者美沙酮减量的前5个重要特征为干预方式、体质量指数(BMI)、MMT时长、阿片类物质使用史和就业情况,其SHAP值分别为1.25、0.36、0.21、0.19和0.12。特征依赖图显示BMI、MMT时长和阿片类物质使用史与减量效果之间均呈现负相关。
结论:
2
可解释的预测模型为针刺辅助美沙酮减量治疗中需综合考虑临床因素提供了科学依据,有助于针刺临床美沙酮减量策略的改进和个性化减量方案的制定。
Objective
2
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
2
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
2
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
2
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.
0
浏览量
8
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621