In Frontiers in neurology
Background: The present study aimed to investigate the use of imaging biomarkers to predict the outcome of acupuncture in patients with migraine without aura (MwoA). Methods: Forty-one patients with MwoA received 4 weeks of acupuncture treatment and two brain imaging sessions at the Beijing Traditional Chinese Medicine Hospital affiliated with Capital Medical University. Patients kept a headache diary for 4 weeks before treatment and during acupuncture treatment. Responders were defined as those with at least a 50% reduction in the number of migraine days. The machine learning method was used to distinguish responders from non-responders based on pre-treatment brain gray matter (GM) volume. Longitudinal changes in GM predictive regions were also analyzed. Results: After 4 weeks of acupuncture, 19 patients were classified as responders. Based on 10-fold cross-validation for the selection of GM features, the linear support vector machine produced a classification model with 73% sensitivity, 85% specificity, and 83% accuracy. The area under the receiver operating characteristic curve was 0.7871. This classification model included 10 GM areas that were mainly distributed in the frontal, temporal, parietal, precuneus, and cuneus gyri. The reduction in the number of migraine days was correlated with baseline GM volume in the cuneus, parietal, and frontal gyri in all patients. Moreover, the left cuneus showed a longitudinal increase in GM volume in responders. Conclusion: The results suggest that pre-treatment brain structure could be a novel predictor of the outcome of acupuncture in the treatment of MwoA. Imaging features could be a useful tool for the prediction of acupuncture efficacy, which would enable the development of a personalized medicine strategy.
Yang Xue-Juan, Liu Lu, Xu Zi-Liang, Zhang Ya-Jie, Liu Da-Peng, Fishers Marc, Zhang Lan, Sun Jin-Bo, Liu Peng, Zeng Xiao, Wang Lin-Peng, Qin Wei
acupuncture, gray matter, machine learning, migraine, prediction