OBJECTIVE: To construct and validate a predictive model for the therapeutic effect of acupuncture at Tongdu Yangxin prescription (acupoint prescription for promoting the circulation of the governor vessel and nourishing the heart) on insomnia, so as to develop an open-access interactive artificial intelligence (AI)-assisted decision-making platform. METHODS: Clinical data of 139 insomnia patients treated with Tongdu Yangxin acupuncture therapy were included. All the patients had received acupuncture at Baihui (GV20), Yintang (GV24⁺), bilateral Shenmen (HT7), and bilateral Sanyinjiao (SP6); and electric stimulation was attached to Baihui (GV20) and Yintang (GV24⁺), using a continuous wave and a frequency of 2 Hz. The treatment was delivered once every other day, 3 treatments a week, and for 2 consecutive weeks. Patients with Pittsburgh sleep quality index (PSQI) score reduction rate <50% were classified as the "no response group", and those with ≥50% were as the "response group". Outliers were addressed using the 1.5×IQR rule, and missing values were imputed via predictive mean matching. Key features were selected by intersecting the feature importance results from eXtreme Gradient Boosting (XGBoost) and random forest algorithms. After balancing class distribution using the Synthetic Minority Over-sampling Technique (SMOTE), 20% of the data was reserved as a validation set. The remained data underwent the stratified sampling iterations to generate 200 pairs of 3∶1 training-test sets, which was employed for training and internal validation of 8 machine learning algorithms. The optimal algorithm and data partitioning strategy were selected to construct the final model, followed by external validation. The best-performing model was deployed online via Streamlit to create an interactive AI platform. RESULTS: Key predictive features for model construction included insomnia duration, the total PSQI score, PSQI sleep efficiency subscore, the proportion of N1 and N2 sleep stages in total sleep duration, and the maximum pulse rate during sleep. The CatBoost-based model achieved an AUC of 0.92, the average precision of 0.77, and accuracy, average recall, and average F1-score of 0.75 on the test set. On the validation set, it attained an AUC of 0.84, with accuracy, average precision, average recall, and average F1-score all at 0.72, demonstrating robust predictive performance. An interactive AI platform was subsequently developed (https://tdyx-catboost.streamlit.app/). CONCLUSION This study successfully establishes and validates a CatBoost-based efficacy prediction model for Tongdu Yangxin acupuncture therapy in treatment of insomnia. The developed AI platform provides data-driven decision support for acupuncture-based insomnia management.
Humans ; Sleep Initiation and Maintenance Disorders/physiopathology* ; Acupuncture Therapy ; Male ; Acupuncture Points ; Female ; Middle Aged ; Adult ; Artificial Intelligence ; Aged ; Young Adult

Objective:To investigate the clusters of COVID-19 associated with a market (market Y) in Haidian District, Beijing, and analyze the chain of transmission and provide reference for effective prevention and control of COVID-19.Methods:The investigation of field epidemiology and cluster epidemic was used to describe the distributions of all COVID-19 cases. The time sequence diagram of the cases, disease onset was drawn and transmission chains were analyzed. Real-time RT-PCR assay was conducted for SARS-CoV-2 nucleic acid test by using the respiratory samples of the cases.Results:The COVID-19 epidemic, originated from a wholesale farm produce market (market X) in Fengtai District, Beijing, was introduced by a marketer in the market Y who had exposed to market X, causing 8 clusters of 20 confirmed cases of COVID-19 and one asymptomatic case, including 8 men and 13 women, in market Y, surrounding communities, food plaza, companies,families and other places. The incidence peaked during June 10-14, 2020; the median age of the cases was 45 years, ranging from 5 years to 87 years. The initial symptoms of the cases included fever (10/20) and pharynx discomfort (7/20). The median of incubation period was 5 days ( IQR:3-8). The median of serial interval between primary case and secondary cases was 5 days with a secondary attack rate of 3.7%(20/538), and the secondary attack rate in household close-contacts was 14.0% (7/50). Conclusions:The clusters of COVID-19 associated with market Y were caused by several modes of transmission, including human-to-human, contaminated material-to-human, etc. The combined public-health response measures were effective to control the COVID-19 epidemic in Haidian district of Beijing.