An interpretable machine learning modeling method for the effect of manual acupuncture manipulations on subcutaneous muscle tissue.
10.13703/j.0255-2930.20250117-0002
- Author:
Wenqi ZHANG
1
;
Yanan ZHANG
2
;
Yan SHEN
2
;
Chun SUN
2
;
Jie CHEN
3
;
Yuhe WEI
1
;
Jian KANG
1
;
Ziyi CHEN
1
;
Jingqi YANG
1
;
Jingwen YANG
4
;
Chong SU
1
Author Information
1. School of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China.
2. First Teaching Hospital of Tianjin University of TCM; National Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion.
3. Integrated Department of TCM, Zhongguancun Hospital, Beijing.
4. School of Acupuncture-Moxibustion and Tuina, Beijing University of CM.
- Publication Type:Journal Article
- Keywords:
acupuncture;
dynamic time warping barycenter averaging algorithm;
interpretability;
machine learning;
quantitative models
- MeSH:
Humans;
Acupuncture Therapy/methods*;
Machine Learning;
Male;
Adult;
Female;
Subcutaneous Tissue/diagnostic imaging*;
Young Adult
- From:
Chinese Acupuncture & Moxibustion
2025;45(10):1371-1382
- CountryChina
- Language:Chinese
-
Abstract:
OBJECTIVE:To investigate the effect of manual acupuncture manipulations (MAMs) on subcutaneous muscle tissue, by developing quantitative models of "lifting and thrusting" and "twisting and rotating", based on machine learning techniques.
METHODS:A depth camera was used to capture the acupuncture operator's hand movements during "lifting and thrusting" and "twisting and rotating" of needle. Simultaneously, the ultrasound imaging was employed to record the muscle tissue responses of the participants. Amplitude and angular features were extracted from the movement data of operators, and muscle fascicle slope features were derived from the data of ultrasound images. The dynamic time warping barycenter averaging algorithm was adopted to align the dual-source data. Various machine learning techniques were applied to build quantitative models, and the performance of each model was compared. The most optimal model was further analyzed for its interpretability.
RESULTS:Among the quantitative models built for the two types of MAMs, the random forest model demonstrated the best performance. For the quantitative model of the "lifting and thrusting" technique, the coefficient of determination (R2) was 0.825. For the "twisting and rotating" technique, R2 reached 0.872.
CONCLUSION:Machine learning can be used to effectively develop the models and quantify the effects of MAMs on subcutaneous muscle tissue. It provides a new perspective to understand the mechanism of acupuncture therapy and lays a foundation for optimizing acupuncture technology and designing personalized treatment regimen in the future.
