OBJECTIVE: To propose a machine learning-based method for predicting the trajectories during manual acupuncture manipulation (MAM), aiming to improve the precision and consistency of acupuncture practitioner' operation and provide the real-time suggestions on MAM error correction. METHODS: Computer vision technology was used to analyze the hand micromotion when holding needle during acupuncture, and provide a three-dimensional coordinate description method of the index finger joints of the holding hand. Focusing on the 4 typical motions of MAM, a machine learning-based MAM trajectory predictive model was designed. By integrating the changes of phalangeal joint angle and hand skeletal information of acupuncture practitioner, the motion trajectory of the index finger joint was predicted accurately. Besides, the roles of machine learning-based MAM trajectory predictive model in the skill transmission of acupuncture manipulation were verified by stratified randomized controlled trial. RESULTS: The performance of MAM trajectory predictive model, based on the long short-term memory network (LSTM), obtained the highest stability and precision, up to 98%. The learning effect was improved when the model applied to the skill transmission of acupuncture manipulation. CONCLUSION The machine learning-based MAM predictive model provides acupuncture practitioner with precise action prediction and feedback. It is valuable and significant for the inheritance and error correction of manual operation of acupuncture.
Humans ; Acupuncture Therapy/instrumentation* ; Machine Learning ; Adult ; Male ; Female

Menopausal syndromes are mostly based on kidney deficiency， which could be expalined that kidney governing essence storage and controlling innateness， so when the kidney water was deficient and the liver fail to nourish， then led to liver depression and transform into fire； deficiency of the kidney， loss of warmth of the spleen， and inability to transport and transform the water and dampness will easily lead to phlegm and fire； the decline of the kidney yin and loss of water and fire will easily cause the exuberance of heart fire. Therefore， clinical symptoms of hot flashes， insomnia， and palpitations are common due to phlegm， depressions， and fire. Based on this， at the beginning of the treatment， we should treat the symptoms firstly by resolving phlegm， relieving depression and clearing fire， and commonly use Huanglian Wendan Decoction （黄连温胆汤）， Yigan Powder （抑肝散）， Chaihu plus Longgu Muli Decoction （柴胡加龙骨牡蛎汤）， and Qingxin Zishen Decoction （清心滋肾饮）， etc. After improving the symptoms of hot flashes and sweating， irritability， dreaming and frightening， then we should give the prescriptions to tonify kidney yang and nourish kidney yin， in order to eliminate the pathogens and reinforce healthy qi， and to treat both the manifestations and the root cause， so that the symptoms of the patients can be better alleviated.

Objective:To evaluate the efficacy and safety of anti-human T lymphocyte porcine immunoglobulin (P-ATG) with recombinant human tumor necrosis factor-α receptor Ⅱ:IgG Fc fusion protein (rhTNFR∶Fc, Etanercept) on grade Ⅲ/Ⅳ acute graft-versus-host disease (aGVHD) after allogenic hematopoietic stem cell transplantation (allo-HSCT) .Methods:Thirty-five patients with Grade Ⅲ/Ⅳ aGVHD who received P-ATG with etanercept therapy after allo-HSCT were retrospectively analyzed. P-ATGs (5 mg·kg -1·d -1) were administrated for 3 to 5 days, and then 5mg/kg was sequentially administrated, QOD to BIW. Etanercepts were administrated 25 mg, twice a week (12.5 mg, BIW for pediatric patients) . Results:Among the 35 patients with grade Ⅲ/Ⅳ aGVHD, 21 were males and 14 females, with a median age of 10 (3-54) years. A total of 19 cases of acute myeloid leukemia, 13 of acute lymphoblastic leukemia, 1 of severe aplastic anemia, 1 of myelodysplastic syndrome, and 1 of mixed phenotypic acute leukemia were noted. The overall response (OR) rate of P-ATG with etanercept was 85.7% (30/35) , with complete response (CR) and partial response (PR) rates of 34.3% (12/35) and 51.4% (18/35) , respectively, on day 28. The OR rate of grade Ⅲ aGVHD group was higher than of grade IV aGVHD group [100% (19/19) vs. 68.8% (11/16) , P=0.004]. On day 56, the OR rate became 77.2% (27/35) , with CR and PR rates of 62.9% (22/35) and 14.3% (5/35) , respectively. The OR rate of grade Ⅲ aGVHD group was also higher than of grade Ⅳ aGVHD group [89.5% (17/19) vs. 62.5% (10/16) , P=0.009]. Thirty-five patients had no adverse effects such as fever, chills, and rash during the P-ATG infusion, and no obvious liver and kidney function damage was observed after treatment. The main treatment-related complication was infection. The reactivation rates of CMV and EBV were 77.1% (27/35) and 22.9% (8/35) , respectively, and the bacterial infection rate was 48.6% (17/35) . With a median follow-up time of 13 (1-55) months after HSCT, the 1-year and 2-year OS rates were (68.1±8.0) % and (64.3±8.4) % , respectively. The 1-year OS rate of grade Ⅲ aGVHD group was superior to grade Ⅳ aGVHD group [ (84.2±8.4) % vs. (47.6±13.1) % , χ2=3.38, P=0.05]. Conclusion:This study demonstrated that P-ATG with etanercept was effective and safe in treating grade Ⅲ-Ⅳ aGVHD after allo-HSCT.