Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

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

As a new type of production factor that can empower the development of new quality productivity, the data element is an important engine to promote the high quality development of the industry. Traditional Chinese medicine(TCM) dispensing is the most basic work of TCM clinical pharmacy, and its quality directly affects the clinical efficacy of TCM. The integration of data elements and TCM dispensing can stimulate the innovation and vitality of the TCM dispensing industry and promote the high-quality and sustainable development of the industry. A large-scale, detailed, and systematic study on TCM dispensing was conducted. The innovative practice path of data fusion construction in the whole process of TCM dispensing was investigated by integrating the digital resources "nine full activities" of TCM dispensing, creating the digital dictionary of "TCM clinical information data elements", and exploring innovative applications of TCM dispensing driven by data and technology, so as to promote the standardized, digital, and intelligent development of TCM dispensing in medical health services. The research content of this project was successfully selected as the second batch of "Data element×" typical cases of National Data Administration in 2024, which is the only selected case in the field of TCM.
Medicine, Chinese Traditional/methods* ; Drugs, Chinese Herbal ; Humans

OBJECTIVE: To investigate the clinical efficacy and key techniques of proximal femoral nail antirotation (PFNA) in the treatment of Basicervical fracture. METHODS: A retrospective analysis was performed on 23 patients with Basicervical fractures who underwent closed reduction and PFNA internal fixation under C-arm X-ray fluoroscopy between March 2019 and March 2023. The cohort included 9 males and 14 females. The age distributions was as follows:7 individuals aged from 60 to 69 years old, 5 individuals aged from 70 to 79 years old, 9 individuals aged from 80 to 89 years old, and 2 individuals aged from 90 to 99 years old. The operative time, intraoperative blood loss and fracture healing time were recorded. Hip function was evaluated according to the Harris score. RESULTS: All 23 patients successfully underwent the operation, with the operation time ranging from 30 to 75 minutes and an average of (60.51±9.82) minutes. The intraoperative blood loss varied from 100 to 180 ml, averaging (145.36±25.21) ml, and the hidden blood loss ranged from 150 to 220 ml, with an average of (189.00±30.12) ml. All 23 patients were followed up, and the duration ranged from 6 to 28 months, with an average of (18.56±6.35) months. All incisions healed well, the fracture healing time ranged from 12 to 15 weeks, with an average of (14.30±1.82) weeks. During the follow-up period, one patient experienced a spiral blade cut-out, and no complications such as internal fixation rupture, avascular necrosis of the femoral head, fracture nonunion, hip varus deformity, or refracture occurred. At the latest follow-up, the results were evaluated by Harris hip function score:17 cases were excellent, 4 cases were good, 1 case was fair, and 1 case was poor. CONCLUSION PFNA internal fixation in the treatment of Basicervical fracture has the advantages of simple operation, less trauma, short operation time, rigid fixation, postoperative functional recovery and so on, which is an ideal fixation for elderly Basicervical fracture.
Humans ; Female ; Male ; Aged, 80 and over ; Aged ; Retrospective Studies ; Bone Nails ; Middle Aged ; Fracture Fixation, Internal/methods* ; Fracture Healing ; Fracture Fixation, Intramedullary

The patient was a boy aged 1 year and 9 months who presented with 46,XY disorder of sex development (DSD), with severe undermasculinization of the external genitalia. Laboratory tests and ultrasound examinations showed normal functions of Leydig cells and Sertoli cells in the testes. Genetic testing revealed a novel pathogenic heterozygous variant, c.1186dupA (p.T396Nfs*17), in the PPP1R12A gene. Thirteen cases of PPP1R12A gene variants have been reported previously. These variants may cause isolated involvement of the genitourinary or neurological systems, or affect other systems/organs including the digestive tract, eyes, heart, etc. Patients with DSD typically present with a 46,XY karyotype and variable degrees of undermasculinization involving the external genitalia, gonads, and reproductive tract. This article reports a child with 46,XY DSD accompanied by growth retardation caused by a heterozygous variant in the PPP1R12A gene, which expands the clinical disease spectrum associated with PPP1R12A gene variants.
Humans ; Male ; Infant ; Disorder of Sex Development, 46,XY/etiology* ; Protein Phosphatase 1/genetics*

OBJECTIVE: To explore the efficacy and safety of Juan Bi Pill (JBP) in treatment of active rheumatoid arthritis (RA). METHODS: From February 2017 to May 2018, 115 participants from 4 centers were randomly divided into JBP group (57 cases) and placebo group (58 cases) in a 1:1 ratio using a random number table method. Participants received a dose of JBP (4 g, twice a day, orally) combined with methotrexate (MTX, 10 mg per week) or placebo (4 g, twice a day, orally) combined with MTX for 12 weeks. Participants were required with follow-up visits at 24 and 48 weeks, attending 7 assessment visits. Participants were undergo disease activity assessment 7 times (at baseline and 2, 4, 8, 12, 24, 48 weeks) and safety assessments 6 times (at baseline and 4, 8, 12, 24, 48 weeks). The primary endpoint was 28-joint Disease Activity Score (DAS28-ESR and DAS28-CRP). The secondary endpoints included American College of Rheumatology (ACR) criteria for 20% and 50% improvement (ACR20/50), Health Assessment Questionnaire Disability Index (HAQ-DI), clinical disease activity index (CDAI), visual analog scale (VAS), Short Form-36 (SF-36) score, Medial Outcomes Study (MOS) sleep scale score, serum erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), tender joint count, swollen joint count, and morning stiffness. The adverse reactions were observed during the treatment. RESULTS: After 12 weeks of treatment, DAS28-ESR and DAS28-CRP scores in both groups were lower than before treatment (both P<0.01), while the remission rate of DAS28-ESR and DAS28-CRP and low disease activity of JBP group were higher than those in the placebo group (both P<0.01). JBP demonstrated better efficacy on ACR20 and ACR50 compliance rate at 12 and 48 weeks comparing to placebo (all P<0.05). The CDAI and HAQ-DI score, pain VAS and global VAS change of RA patients and physicians, the serum ESR and CRP levels, and the number of tenderness and swelling joints were lower than before treatment at 4, 8, 12, 24, 48 weeks in both groups (P<0.05 or P<0.01), while the reduction of above indices in the JBP group was more obvious than those in the placebo group at 12 weeks (ESR and CRP, both P<0.05) or at 12 and 48 weeks (all P<0.01). There was no difference in adverse reactions between the 2 groups during treatment (P=0.75). CONCLUSION JBP combined with MTX could effectively reduce disease activity in patients with RA in active stage, reduce the symptoms of arthritis, and improve the quality of life, while ensuring safety, reliability, and fewer adverse effects. (Trial Registration: ClinicalTrials.gov, No. NCT02885597).
Humans ; Arthritis, Rheumatoid/drug therapy* ; Methotrexate/adverse effects* ; Female ; Double-Blind Method ; Male ; Middle Aged ; Treatment Outcome ; Drugs, Chinese Herbal/adverse effects* ; Drug Therapy, Combination ; Adult ; Antirheumatic Agents/adverse effects* ; Aged