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

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.
Humans ; Acupuncture Therapy/methods* ; Machine Learning ; Male ; Adult ; Female ; Subcutaneous Tissue/diagnostic imaging* ; Young Adult

Hearing loss is the most prevalent disabling disease. Cochlear implantation（CI） serves as the primary intervention for severe to profound hearing loss. This consensus systematically explores the value of genetic diagnosis in the pre-operative assessment and efficacy prognosis for CI. Drawing upon domestic and international research and clinical experience, it proposes an evidence-based medicine three-tiered prognostic classification system（Favorable, Marginal, Poor）. The consensus focuses on common hereditary non-syndromic hearing loss（such as that caused by mutations in genes like GJB2, SLC26A4, OTOF, LOXHD1） and syndromic hereditary hearing loss（such as Jervell & Lange-Nielsen syndrome and Waardenburg syndrome）, which are closely associated with congenital hearing loss, analyzing the impact of their pathological mechanisms on CI outcomes. The consensus provides recommendations based on multiple round of expert discussion and voting. It emphasizes that genetic diagnosis can optimize patient selection, predict prognosis, guide post-operative rehabilitation, offer stratified management strategies for patients with different genotypes, and advance the application of precision medicine in the field of CI.
Humans ; Cochlear Implantation ; Prognosis ; Hearing Loss/surgery* ; Consensus ; Connexin 26 ; Mutation ; Sulfate Transporters ; Connexins/genetics*

Objective:To explore the effects of Undaria pinnatifida polysaccharides(UPPs)on depressive-like behavior,neurotransmitter content,oxidative stress,and the hypothalamus-pituitary-adrenal(HPA)axis in rats treated with chronic unpredictable mild stress(CUMS).Methods:A rat model of depression was prepared using the CUMS method,and rats were treated with normal saline(NS)or different doses of UPPs by gavage.The general condition of the rats was observed,and depressive-like behavior was detected by the open field test(OFT),sucrose preference test(SPT),and forced swimming test(FST).The activity or levels of 5-hydroxytryptamine(5-HT),dopamine(DA)and norepinephrine(NE),malondialdehyde(MDA),superoxide disidase(SOD)and catalase(CAT),adrenocorticotrop-ic hormore(ACTH),corticosterone(CORT)in the hippocampus or serum of rats were detected using commercial kits.Western Blot was used to detect the expression level of hippocampal glucocorticoid receptor(GR)protein,and hema-toxylin-eosin(HE)staining was used to observe the tissue structure of hippocampus of rats.Results:The depressive-like behavior of rats in the UPPs medium and high dose groups was significantly improved(P＜0.05).In the UPPs high dose group,the contents of 5-HT,DA,and NE in the hippocampus of rats increased(P＜0.05),while the con-tents of MDA in both serum and hippocampus decreased(P＜0.05),and the activities of SOD and CAT increased(P＜0.05).The contents of ACTH and CORT in serum decreased(P＜0.05).In the UPPs medium dose group,the levels of hippocampal MDA and CAT,as well as serum SOD,ACTH,and CORT were improved(P＜0.05).The expression level of GR protein in the hippocampus increased(P＜0.05),and the pathological changes in the hipp-ocampal dentate gyrus were significantly improved.Conclusion:UPPs can alleviate depressive-like behavior in CUMS rats,and its mechanism may be related to increasing the content of monoamine neurotransmitters in the hippocampus,reducing oxidative stress damage,and HPA axis hyperfunction.

Objective To predict the risk of in-hospital death in patients with chronic heart failure(CHF)complicated by lung infections using interpretable machine learning.Methods The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database.According to the pathogen type,the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups,and their risks of in-hospital death were compared using Kaplan-Meier survival curves.Univariate analysis and LASSO regression were used to select the features for constructing LR,AdaBoost,XGBoost,and LightGBM models,and their performance was compared in terms of accuracy,precision,F1 value,and AUC.External validation of the models was performed using the data from eICU-CRD database.SHAP algorithm was applied for interpretive analysis of XGBoost model.Results Among the 4 constructed models,the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set.In the external test set,the XGBoost model had an AUC of 0.691(95%CI:0.654-0.720)in bacterial pneumonia group and an AUC of 0.725(95%CI:0.577-0.782)in non-bacterial pneumonia group,and showed better predictive ability and stability than the other models.Conclusion The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections.The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.

Objective The aim of this study was to investigate the prospective association between physical activity (PA),independently or in conjunction with other contributing factors,and osteoporosis (OP) outcomes. Methods The Physical Activity in Osteoporosis Outcomes (PAOPO) study was a community-based cohort investigation. A structured questionnaire was used to gather the participants' sociodemographic characteristics. Bone mineral density (BMD) measurements were performed to assess OP outcomes,and the relationship between BMD and OP was evaluated within this cohort. Results From 2013 to 2014,8,471 participants aged 18 years and older were recruited from Tangshan,China's Jidong community. Based on their PA level,participants were categorized as inactive,moderately active,or very active. Men showed higher physical exercise levels than women across the activity groups. BMD was significantly higher in the very active group than in the moderately active and inactive groups. Individuals aged>50 years are at a higher risk of developing OP and osteopenia. Conclusion The PAOPO study offers promising insights into the relationship between PA and OP outcomes,encouraging the implementation of PA in preventing and managing OP.

Objective To investigate the dietary patterns of rural residents in the high-incidence areas of esophageal cancer (EC), and to explore the clustering and influencing factors of risk factors associated with high-incidence characteristics. Methods A special structured questionnaire was applied to conduct a face-to-face survey on the dietary patterns of rural residents in Yanting county of Sichuan Province from July to August 2021. Univariate and multivariate logistic regression models were used to analyze the influencing factors of risk factor clustering for EC. Results There were 838 valid questionnaires in this study. A total of 90.8% of rural residents used clean water such as tap water. In the past one year, the people who ate fruits and vegetables, soybean products, onions and garlic in high frequency accounted for 69.5%, 32.8% and 74.5%, respectively; the people who ate kimchi, pickled vegetables, sauerkraut, barbecue, hot food and mildew food in low frequency accounted for 59.2%, 79.6%, 68.2%, 90.3%, 80.9% and 90.3%, respectively. The clustering of risk factors for EC was found in 73.3% of residents, and the aggregation of two risk factors was the most common mode (28.2%), among which tumor history and preserved food was the main clustering pattern (4.6%). The logistic regression model revealed that the gender, age, marital status and occupation were independent influencing factors for the risk factors clustering of EC (P<0.05). Conclusion A majority of rural residents in high-incidence areas of EC in Yanting county have good eating habits, but the clustering of some risk factors is still at a high level. Gender, age, marital status, and occupation are influencing factors of the risk factors clustering of EC.

Objective:To construct an analytic method aimed at the characteristics of the commonly method of supplementing and pouring of acupuncture based on the analysis and modeling of ultrasound images around acupoint region in the process of acupuncture.Methods:A total of 7 healthy subjects who underwent physical examination in Beijing Zhongguancun Hospital from June,2022 to June,2023 were selected,and their Kongzui acupoints were acupunctured by 10 acupuncturists with associate senior title as 4 kinds of acupuncture manipulations included reinforcing by twisting and rotating(RFTR),reducing by twisting and rotating(RDTR),reinforcing by lifting and thrusting(RFLT),and reducing by lifting and thrusting(RDLT).The B-ultrasound diagnostic device was used to collect the images of muscle and fascial tissue below the acupoint,so as to construct the model of images.The definition of virtual acupuncture point was adopted to study the regulation of perturbation of subcutaneous tissue that was caused after the skin was acupunctured by needle.The change regulation of the virtual acupuncture point of muscle bundle below skin at Zuikong acupoint of subjects was analyzed.Results:The difference value of average absolution value between peak and trough of the trajectory of virtual acupuncture point of twisting and rotating was 0.066±0.045,and the average value of amplitude of this method was less than that(0.428±0.276)of lifting and thrusting method,and the twisting and rotating method was uniform and symmetrical,and there was difference between two kinds of acupuncture methods.The characteristics of computer graphics was used to qualify the work effect of lifting and thrusting,and reinforcing and reducing,which showed the heavy insertion and light lifting of RFLT,and showed heavy lifting and light insertion of RDLT,thus distinguished the two methods[(RFLT)and(RDLT)].Conclusions:The ultrasound imaging and computer graphics can be used to analyze the regularity of the common"reinforcing and reducing"method of acupuncture and moxibustion.

Objective:To establish a method for rapid detection of OXA and par C resistance genes of Acinetobacter baumannii(Ab)by double nucleic acid colloidal gold strip and to develop kit.Methods:DNA of Ab was extracted by heating and boiling method.OXA and par C genes sequences of Ab were selected as target gene fragments based on NCBI.Primers were designed and labeled with 6-FAM,digoxin and biotin,respectively.Drug resistance gene detection reagents were developed,and nucleic acid gold test strips were used for rapid and visual detection.Molecular cloning and sequencing techniques were used to clone positive control samples and evaluate specificity,sensitivity and stability of kit.Results:DNA concentration and purity of Ab extracted by boiling method were good.Homology between cloned and sequenced plasmid DNA and gene sequence in GenBank database was 100%,respectively.Speci-ficity of kit was good,with only Ab showing positive results and other bacterial genera showing negative results;DNA concentration of Ab in double nucleic acid colloidal gold test strip decreased to 10-3 ng/μl,a red line still appeared,whose sensitivity was 10 times higher consistent with minimum detection limit of electrophoresis 10-2 ng/μl;test kits were tested at 3rd,6th and 9th months,and showed good stability.Conclusion:Double resistance detection kit established in this study can simultaneously detect OXA and par C resis-tance of Ab,who has advantages of high sensitivity,strong specificity,rapid and simple,and provides a new method for detection of carbapenem and quinolone antibiotic resistance of Ab.

Objective To predict the risk of in-hospital death in patients with chronic heart failure(CHF)complicated by lung infections using interpretable machine learning.Methods The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database.According to the pathogen type,the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups,and their risks of in-hospital death were compared using Kaplan-Meier survival curves.Univariate analysis and LASSO regression were used to select the features for constructing LR,AdaBoost,XGBoost,and LightGBM models,and their performance was compared in terms of accuracy,precision,F1 value,and AUC.External validation of the models was performed using the data from eICU-CRD database.SHAP algorithm was applied for interpretive analysis of XGBoost model.Results Among the 4 constructed models,the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set.In the external test set,the XGBoost model had an AUC of 0.691(95%CI:0.654-0.720)in bacterial pneumonia group and an AUC of 0.725(95%CI:0.577-0.782)in non-bacterial pneumonia group,and showed better predictive ability and stability than the other models.Conclusion The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections.The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.