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 observe the clinical efficacy of thumb-tack needling for subcutaeous embedding combined with joint mobilization in the treatment of post-stroke shoulder-hand syndrome.Methods A total of 80 patients with post-stroke shoulder-hand syndrome were randomly divided into a treatment group and a control group,with 40 patients in each group.Both groups were given arthrocentesis,the control group was given ordinary acupuncture on the basis of arthrocentesis,and the treatment group was combined with thumb-tack needling for subcutaeous embedding.One course of treatment was 4 weeks and a total of 4 weeks of treatment was given.After 1 month of treatment,the clinical efficacy of the two groups was evaluated.The changes of Visual Analogue Scale(VAS)of pain scores and simplified Fugl-Meyer Assessment(FMA)scores,as well as the pain-free passive forward flexion and abduction of the shoulder joint of the affected limb were observed before and after treatment.The Simple Quality of Life Scale(SF-36)scores of the patients in the two groups were compared after treatment.The safety and the occurrence of adverse reactions in the two groups were also evaluated.Results(1)The total effective rate was 95.00%(38/40)in the treatment group and 80.00%(32/40)in the control group.The efficacy of the treatment group was superior to that of the control group,and the difference was statistically significant(P＜0.05).(2)After treatment,the VAS scores and upper extremity FMA scores of the patients in the two groups were significantly improved(P＜0.05),and the treatment group was significantly superior to the control group in improving the VAS scores and upper extremity FMA scores,and the differences were statistically significant(P＜0.05).(3)After treatment,the joint mobility of patients in the two groups were significantly improved(P＜0.05),and the improvement of shoulder joint movement in the treatment group was superior to that in the control group,and the difference was statistically significant(P＜0.05).(4)After treatment,the SF-36 Quality of Life Scale scores of the treatment group were significantly superior to those of the control group in terms of physical function,psychological function,emotional health,and social function levels,and the difference was statistically significant(P＜0.05).(5)There was no significant difference in the incidence of adverse reactions between the treatment group and the control group(P＞0.05).Conclusion Thumb-tack needling for subcutaeous embedding combined with joint mobilization exert certain effect in the treatment of post-stroke shoulder-hand syndrome.It can significantly improve the pain symptoms of patients,thus improving their quality of life,and the clinical effect is remarkable.

The medical-industrial fusion training model combines the knowledge and technology of medical and engineering disciplines in the training of oncology graduate students, which can help accurate diagnosis and treatment of tumors, promote cooperation and innovation in oncology research, as well as promote the cultivation and exchanges of composite and innovative medical talents in oncology, promote the innovation and development of oncology diagnostic and treatment technology, and improve the survival rate and quality of life of oncology patients. This paper discusses the application of medical-industrial fusion training model in the training of o ncology professionals, and explores the new teaching mode of medical-industrial fusion thinking in the cultivation of complex and innovative medical talents in oncology under the background of "new medical science".

Objective This paper aims to investigate the application of intraoral scanning and cone beam computed tomography(CBCT)registration implant robot in dental implant surgery.Methods The data of 40 cases with dental de-fect of robot-assisted implantation from November 2023 to May 2024 were retrospectively analyzed.Before the opera-tion,the intraoral scan data and CBCT data of the posi-tioning markers were automatically fused with the initial CBCT images,and the registration error was calculated.The average registration error of positioning markers was determined during the operation,and the implantation ac-curacy was analyzed after the operation.Results The intraoral scan data and CBCT data of 40 patients with dental defect wearing positioning markers were successfully registered with the initial CBCT image,and the registration errors were(0.157±0.026)mm and(0.154±0.033)mm,respectively.Statistical analysis showed no statistical significance between them.The registration errors of the marker was(0.037 3±0.003 6)mm.A total of 55 implants were performed,and the total deviations of the implant point and the apical point were(0.78±0.41)and(0.89±0.28)mm,respectively.The transverse deviations of the implant point and the apical point were(0.44±0.36)and(0.58±0.25)mm,respectively.The depth deviations of the implant point and the apical point were(0.51±0.32)and(0.54±0.36)mm,respectively.The devia-tion of the implant angle was 1.24°±0.67°.Conclusion The fusion technology based on intraoral scanning and CBCT registration can meet the accuracy requirements of preoperative registration of oral implant robots.The technology in-creases the choice of registration methods before robot-assisted dental implant surgery and reduces the multiple radiation exposuresof the patient.

Objective To investigate the effect of reducing the image-guided X-ray field area on the accuracy of Cyberknife radiotherapy,in order to provide a feasible method for achieving patient protection optimization.Methods Firstly,the spine-tracking,fiducial tracking and lung-tracking radiotherapy plans were formulated for the simulation phantom,and then image-guided full-field localization and position pre-setting were carried out for the simulation phantom,and the spine-tracking,fiducial tracking and lung-tracking radiotherapy plans were executed for the simulation phantom using a reduced lead block field area,respectively.Secondly,the radiotherapy accuracy of different radiotherapy plans was verified by end-to-end(E2E)software using new EBT films of the same batch as the base film.Finally,the changes of the simulation phantom were compared in terms of position pre-presetting error,radiotherapy accuracy and lead block field area.Results The spine-tracking and fiducial tracking radiotherapy plans had the translation errors not higher than 0.1 mm and the rotation errors not higher than 0.1°,which were comparable to the fluctuated conventional Cyberknife image-guided locating;the spine-tracking,fiducial tracking and lung-tracking radiotherapy plans had the lead block field radiotherapy accu-racies being 0.71,0.18 and 1.06 mm,respectively,which met the clinical requirements for Cyberknife radiotherapy;the lead block field areas of the spine-tracking,fiducial tracking and lung-tracking radiotherapy plans were reduced to 19.75％,29.28％and 12.71％of the full field area,respectively,and the efficacy for field area optimization was significant.Conclusion It's feasible to involve a reduced image-guided X-ray field area in Cyberknife radiotherapy,which contributes to optimizing radiation protection for the patients.[Chinese Medical Equipment Journal,2024,45(11):49-53]

Since the implementation of the Measures for the Management of Radiation Workers’ Occupational Health in November 2007, it has played an extremely important role in protecting the occupational health of radiation workers. There are more than 700 000 radiation workers in about 100 000 workplaces with potential radiation exposure, as well as a large number of miners exposed to high levels of radon. As the radiation health monitoring project suggests, measures of occupational health management such as personal dose monitoring and occupational health examination of radiation workers have been widely implemented and achieved good results in the protection of radiation workers. However, the risks of chromosomal aberration and specific turbidity of the eye lens of radiation workers have increased in high-risk positions such as interventional radiology, nuclear medicine, and industrial flaw detection. The control of high radon exposure in miners needs to be strengthened. It is necessary to adapt to the new situation in view of new challenges and actively promote the revision of the Measures for the Management of Radiation Workers’ Occupational Health, so as to further improve the occupational health management of radiation workers in China.