OBJECTIVE:Based on different algorithms of machine learning,the prediction model of lumbar disc herniation has become a trend and hot spot in the development of precision medicine.However,there is limited evidence on the reporting quality and methodological quality of prediction models of lumbar disc herniation outcomes using machine learning.This article is aimed to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation by comprehensively analyzing the report quality and risk of bias of previous studies that developed and validated prognosis prediction models based on machine learning through a comprehensive literature search,in order to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation.METHODS:The databases of CNKI,WanFang,VIP,SinOMED,PubMed,Web of Science,Embase,and The Cochrane Library were searched by computer.Studies on the use of machine learning to develop(and/or validate)prognostic prediction models for lumbar disc herniation were collected from the inception of the database to December 31,2023.Two researchers independently screened the literature,extracted data,and assessed the risk of bias of the included studies.The reporting quality and risk of bias of the included studies were assessed by the Multivariable Transparent Reporting of Predictive Models(TRIPOD)statement and the Predictive Model Risk of Bias Assessment Tool(PROBAST).The results of the evaluation were analyzed using descriptive statistics and visual charts.RESULTS:(1)A total of 23 articles were included,and the TRIPOD compliance of each study ranged from 11％to 87％,with a median compliance of 54％.The quality of reporting of titles,detailed descriptions of treatment measures,blinding of predictors,handling of missing data,details of risk stratification,specific procedures for enrollment,model interpretation,and model performance was mostly poor,with TRIPOD adherence rates ranging from 4％to 35％.(2)Of all included studies,61％had a high risk of bias and 39％had an unclear overall risk of bias.The area under the curve,accuracy,sensitivity and specificity were used to evaluate the performance of the model.The areas under the curve of 20 models were reported,ranging from 0.561 to 0.999.Three models reported the accuracy of the model,ranging from 82.07％to 89.65％.(3)Among all included studies,the statistical analysis domain was most often assessed as having a high risk of bias,mainly due to the small number of valid samples,the selection of predictors based on univariate analysis and the lack of calibration and discrimination assessment of the model in the study.CONCLUSION:These results indicate that machine learning can achieve good predictive ability in the development and validation of prognostic models for lumbar disc herniation.The commonly used algorithms include regression algorithm,support vector machine,decision tree,random forest,artificial neural network,naive Bayes and other algorithms.Reasonable algorithms combined with clinical practice can improve the accuracy of prognosis prediction of lumbar disc herniation.However,the reporting and methodological quality of prognosis prediction models based on machine learning are poor,the prediction performance of different models varies greatly,and the generalization and extrapolation of research models are unclear.There is an urgent need to improve the design,implementation and reporting of such studies.To promote the application of machine learning in the clinical practice of lumbar disc herniation prediction models,it is necessary to comprehensively consider various predictors related to the prognosis of the disease before modeling,and strictly follow the relevant standards of PROBAST tool during modeling.

OBJECTIVE:Based on different algorithms of machine learning,the prediction model of lumbar disc herniation has become a trend and hot spot in the development of precision medicine.However,there is limited evidence on the reporting quality and methodological quality of prediction models of lumbar disc herniation outcomes using machine learning.This article is aimed to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation by comprehensively analyzing the report quality and risk of bias of previous studies that developed and validated prognosis prediction models based on machine learning through a comprehensive literature search,in order to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation.METHODS:The databases of CNKI,WanFang,VIP,SinOMED,PubMed,Web of Science,Embase,and The Cochrane Library were searched by computer.Studies on the use of machine learning to develop(and/or validate)prognostic prediction models for lumbar disc herniation were collected from the inception of the database to December 31,2023.Two researchers independently screened the literature,extracted data,and assessed the risk of bias of the included studies.The reporting quality and risk of bias of the included studies were assessed by the Multivariable Transparent Reporting of Predictive Models(TRIPOD)statement and the Predictive Model Risk of Bias Assessment Tool(PROBAST).The results of the evaluation were analyzed using descriptive statistics and visual charts.RESULTS:(1)A total of 23 articles were included,and the TRIPOD compliance of each study ranged from 11％to 87％,with a median compliance of 54％.The quality of reporting of titles,detailed descriptions of treatment measures,blinding of predictors,handling of missing data,details of risk stratification,specific procedures for enrollment,model interpretation,and model performance was mostly poor,with TRIPOD adherence rates ranging from 4％to 35％.(2)Of all included studies,61％had a high risk of bias and 39％had an unclear overall risk of bias.The area under the curve,accuracy,sensitivity and specificity were used to evaluate the performance of the model.The areas under the curve of 20 models were reported,ranging from 0.561 to 0.999.Three models reported the accuracy of the model,ranging from 82.07％to 89.65％.(3)Among all included studies,the statistical analysis domain was most often assessed as having a high risk of bias,mainly due to the small number of valid samples,the selection of predictors based on univariate analysis and the lack of calibration and discrimination assessment of the model in the study.CONCLUSION:These results indicate that machine learning can achieve good predictive ability in the development and validation of prognostic models for lumbar disc herniation.The commonly used algorithms include regression algorithm,support vector machine,decision tree,random forest,artificial neural network,naive Bayes and other algorithms.Reasonable algorithms combined with clinical practice can improve the accuracy of prognosis prediction of lumbar disc herniation.However,the reporting and methodological quality of prognosis prediction models based on machine learning are poor,the prediction performance of different models varies greatly,and the generalization and extrapolation of research models are unclear.There is an urgent need to improve the design,implementation and reporting of such studies.To promote the application of machine learning in the clinical practice of lumbar disc herniation prediction models,it is necessary to comprehensively consider various predictors related to the prognosis of the disease before modeling,and strictly follow the relevant standards of PROBAST tool during modeling.

Emotion is defined as a physiological and psychological state that encompasses human thoughts, behaviors, and feelings. This phenomenon is also regarded as a spontaneous physiological and psychological response generated by the human body to external stimuli. Given the established correlation between electroencephalogram signal and cerebral activity, it is possible to extrapolate the emotional state of subjects by means of electroencephalogram signal analysis. In this review, emotion models, datasets, and popular machine learning and deep learning methods in recent years used in emotion recognition research were summarized. In addition, the research progress of emotion recognition based on electroencephalogram signal was reviewed, with the aim of assisting subsequent researchers in understanding developments in electroencephalogram signal domain and offering insights for addressing clinical challenges in emotion recognition.

Objective:To explore the value of deep learning (DL) models based on conventional MRI in differentiating orbital solitary fibrous tumors (SFT) from schwannomas.Methods:This was a case-control study. A retrospective analysis was conducted on patients with pathologically confirmed orbital SFT and schwannoma admitted to Eye & ENT Hospital, Fudan University (institution 1) from December 2014 to January 2022 and Ninth People′s Hospital, Shanghai Jiao Tong University School of Medicine (institution 2) from July 2015 to May 2022. A total of 140 patients were included, with 104 patients from institution 1 comprising the training cohort for building DL models and 36 patients from institution 2 comprising the external validation cohort for assessing model performance. Based on the preoperative cross-sectional fat-suppressed T 2WI and contrast-enhanced T 1WI (ceT 1WI), tumor contours were outlined on all tumor-containing slices. Six diagnostic models were constructed using residual networks (ResNet) and split-attention residual networks (ResNeSt) with 18 layers (ResNet-18 and ResNeSt-18), based solely on individual T 2WI and ceT 1WI, as well as a combination of both. A radiology resident and an attending radiologist independently reviewed conventional MRI images to determine the tumor type. The performance of the DL models and radiologists in differentiating orbital SFT from schwannoma in the external validation cohort was evaluated using receiver operating characteristic curves, and the areas under the curves (AUC) were compared using the DeLong test. Results:In the external validation cohort, the AUC (95% CI) of the ResNet-18 models based on T 2WI, ceT 1WI, and their combination were 0.861 (0.719-1), 0.896 (0.774-1), and 0.885 (0.755-1), respectively, while the AUC (95% CI) of the ResNeSt-18 models were 0.889 (0.748-1), 0.872 (0.726-1), and 0.910 (0.801-1), respectively. Among these, the ResNeSt-18 model based on the combined sequences achieved the best performance in differentiating the two tumors. The AUC (95% CI) for the individual interpretation of the radiology resident and attending radiologist were 0.729 (0.571-0.887) and 0.771 (0.618-0.923), respectively. The AUC of the ResNeSt-18 model based on the combined sequences was statistically significantly higher than those of the resident and attending radiologist ( Z=1.96, P=0.049; Z=2.00, P=0.045). Conclusion:The ResNeSt-18 model based on conventional MRI can effectively differentiate orbital SFT from schwannoma, demonstrating better performance than those of the radiology resident and the attending radiologist.

Objective To evaluate the efficacy of a combined immunosuppression regimen in modulating rejection in genetically modified pig-to-macaque xenogeneic heart transplantation.Methods Two xenogeneic heart transplantation models were constructed using genetically modified pigs and macaques.Dynamic monitoring of recipient peripheral blood immune parameters and observation of graft pathological changes were performed.Results Regimen 1,featuring B-cell depletion,T-cell inhibition,and C3 complement suppression,reduced lymphocyte levels but failed to control acute humoral rejection and macrophage infiltration.Regimen 2,adding C5 complement inhibition and interleukin-6 inhibition to Regimen 1,more effectively lowered lymphocyte levels,inhibited acute humoral rejection and complement activation,and decreased antibody deposition.However,a late-phase cytokine storm and residual T cells emerged.Conclusions Regimen 2 reduces the hyperacute and acute rejection risks through multi-target intervention.Yet,it requires balancing medication complexity and safety.This indicates the need to optimize cellular immune regulation and adjust the plan through dynamic multidimensional monitoring.

Objective To evaluate the clinical efficacy of hip-knee-ankle active and passive exercise therapy in patients with early-to mid-stage knee osteoarthritis(KOA).Methods A total of 180 patients with early to mid-stage knee osteoarthritis(KOA)were recruited from the First Affiliated Hospital of Hebei University of Tradi-tional Chinese Medicine between March 2023 and March 2024.Patients were randomly assigned to one of four groups:active movement group,passive movement group,combined movement group,and control group,with 45 patients in each group.The active movement group received hip-knee-ankle active movement therapy daily until the end of follow-up.The passive movement group underwent hip-knee-ankle passive movement therapy three times per week for two weeks.The combined movement group received both active and passive therapies.The control group was administered oral celecoxib capsules(200 mg once daily for two weeks).Joint function was assessed in all four groups before treatment,at two weeks post-treatment,and at 14 weeks post-treatment.The primary outcome measure was the WOMAC joint function score,while secondary outcomes included the WOMAC pain score,stiffness score,and quality of life score(SF-12).Results A total of 160 patients completed the trial,with 39 in the active group,42 in the passive group,40 in the combined group,and 39 in the control group.There were no significant differences in baseline characteristics among the groups(P>0.05).Compared to baseline,the WOMAC scores for function,pain,and stiffness in the passive,combined,and control groups decreased significantly at both 2 and 14 weeks post-treatment(P<0.05),while the SF-12 scores increased significantly(P<0.05).Between 2 and 14 weeks post-treat-ment,the active and combined groups showed further significant decreases in WOMAC function,pain,and stiffness scores(P<0.05)and increases in SF-12 scores(P<0.05).At 2 weeks post-treatment,compared to the control group,the passive and combined groups exhibited significantly lower WOMAC function scores(P<0.05),with no significant difference between the passive and combined groups(P>0.05).By 14 weeks post-treatment,the active and combined groups demonstrated significantly lower WOMAC function scores(P<0.05),with the combined group showing a significantly lower score than the active group(P<0.05).Conclusion The four therapeutic approaches demonstrate a certain degree of efficacy in improving joint function for patients with early and mid-stage KOA.The passive therapy group exhibits superior short-term outcomes,while the active therapy group shows better long-term benefits.The combined therapy group presents notable advantages in both short-term and long-term effi-cacy,although its short-term effectiveness does not surpass that of the passive therapy group.It is recommended for patients with early and mid-stage KOA who have underlying gastrointestinal and cardiovascular conditions.

Objective To evaluate the clinical efficacy of hip-knee-ankle active and passive exercise therapy in patients with early-to mid-stage knee osteoarthritis(KOA).Methods A total of 180 patients with early to mid-stage knee osteoarthritis(KOA)were recruited from the First Affiliated Hospital of Hebei University of Tradi-tional Chinese Medicine between March 2023 and March 2024.Patients were randomly assigned to one of four groups:active movement group,passive movement group,combined movement group,and control group,with 45 patients in each group.The active movement group received hip-knee-ankle active movement therapy daily until the end of follow-up.The passive movement group underwent hip-knee-ankle passive movement therapy three times per week for two weeks.The combined movement group received both active and passive therapies.The control group was administered oral celecoxib capsules(200 mg once daily for two weeks).Joint function was assessed in all four groups before treatment,at two weeks post-treatment,and at 14 weeks post-treatment.The primary outcome measure was the WOMAC joint function score,while secondary outcomes included the WOMAC pain score,stiffness score,and quality of life score(SF-12).Results A total of 160 patients completed the trial,with 39 in the active group,42 in the passive group,40 in the combined group,and 39 in the control group.There were no significant differences in baseline characteristics among the groups(P>0.05).Compared to baseline,the WOMAC scores for function,pain,and stiffness in the passive,combined,and control groups decreased significantly at both 2 and 14 weeks post-treatment(P<0.05),while the SF-12 scores increased significantly(P<0.05).Between 2 and 14 weeks post-treat-ment,the active and combined groups showed further significant decreases in WOMAC function,pain,and stiffness scores(P<0.05)and increases in SF-12 scores(P<0.05).At 2 weeks post-treatment,compared to the control group,the passive and combined groups exhibited significantly lower WOMAC function scores(P<0.05),with no significant difference between the passive and combined groups(P>0.05).By 14 weeks post-treatment,the active and combined groups demonstrated significantly lower WOMAC function scores(P<0.05),with the combined group showing a significantly lower score than the active group(P<0.05).Conclusion The four therapeutic approaches demonstrate a certain degree of efficacy in improving joint function for patients with early and mid-stage KOA.The passive therapy group exhibits superior short-term outcomes,while the active therapy group shows better long-term benefits.The combined therapy group presents notable advantages in both short-term and long-term effi-cacy,although its short-term effectiveness does not surpass that of the passive therapy group.It is recommended for patients with early and mid-stage KOA who have underlying gastrointestinal and cardiovascular conditions.

Objective To evaluate the efficacy of a combined immunosuppression regimen in modulating rejection in genetically modified pig-to-macaque xenogeneic heart transplantation.Methods Two xenogeneic heart transplantation models were constructed using genetically modified pigs and macaques.Dynamic monitoring of recipient peripheral blood immune parameters and observation of graft pathological changes were performed.Results Regimen 1,featuring B-cell depletion,T-cell inhibition,and C3 complement suppression,reduced lymphocyte levels but failed to control acute humoral rejection and macrophage infiltration.Regimen 2,adding C5 complement inhibition and interleukin-6 inhibition to Regimen 1,more effectively lowered lymphocyte levels,inhibited acute humoral rejection and complement activation,and decreased antibody deposition.However,a late-phase cytokine storm and residual T cells emerged.Conclusions Regimen 2 reduces the hyperacute and acute rejection risks through multi-target intervention.Yet,it requires balancing medication complexity and safety.This indicates the need to optimize cellular immune regulation and adjust the plan through dynamic multidimensional monitoring.

Objective:To explore the value of deep learning (DL) models based on conventional MRI in differentiating orbital solitary fibrous tumors (SFT) from schwannomas.Methods:This was a case-control study. A retrospective analysis was conducted on patients with pathologically confirmed orbital SFT and schwannoma admitted to Eye & ENT Hospital, Fudan University (institution 1) from December 2014 to January 2022 and Ninth People′s Hospital, Shanghai Jiao Tong University School of Medicine (institution 2) from July 2015 to May 2022. A total of 140 patients were included, with 104 patients from institution 1 comprising the training cohort for building DL models and 36 patients from institution 2 comprising the external validation cohort for assessing model performance. Based on the preoperative cross-sectional fat-suppressed T 2WI and contrast-enhanced T 1WI (ceT 1WI), tumor contours were outlined on all tumor-containing slices. Six diagnostic models were constructed using residual networks (ResNet) and split-attention residual networks (ResNeSt) with 18 layers (ResNet-18 and ResNeSt-18), based solely on individual T 2WI and ceT 1WI, as well as a combination of both. A radiology resident and an attending radiologist independently reviewed conventional MRI images to determine the tumor type. The performance of the DL models and radiologists in differentiating orbital SFT from schwannoma in the external validation cohort was evaluated using receiver operating characteristic curves, and the areas under the curves (AUC) were compared using the DeLong test. Results:In the external validation cohort, the AUC (95% CI) of the ResNet-18 models based on T 2WI, ceT 1WI, and their combination were 0.861 (0.719-1), 0.896 (0.774-1), and 0.885 (0.755-1), respectively, while the AUC (95% CI) of the ResNeSt-18 models were 0.889 (0.748-1), 0.872 (0.726-1), and 0.910 (0.801-1), respectively. Among these, the ResNeSt-18 model based on the combined sequences achieved the best performance in differentiating the two tumors. The AUC (95% CI) for the individual interpretation of the radiology resident and attending radiologist were 0.729 (0.571-0.887) and 0.771 (0.618-0.923), respectively. The AUC of the ResNeSt-18 model based on the combined sequences was statistically significantly higher than those of the resident and attending radiologist ( Z=1.96, P=0.049; Z=2.00, P=0.045). Conclusion:The ResNeSt-18 model based on conventional MRI can effectively differentiate orbital SFT from schwannoma, demonstrating better performance than those of the radiology resident and the attending radiologist.

The sternum is the pivotal component of the thoracic cavity. It is connected with the clavicle and ribs on the upper part and both sides respectively, and plays an important role in protecting the stability of the chest wall. Sternal resection usually results in a large segmental chest wall defect that causes the chest wall to float and requires sternal reconstruction. This paper reports a 62 years male patient with thymic squamous cell carcinoma with sternal metastasis, who underwent thymotomy, sternal tumor resection and autologous lilum graft combined with sternal reconstruction by titanium plate after relevant examination was completed and surgical contraindications were eliminated. The patient was followed up for 6 months, the respiratory and motor functions were normal and the thoracic appearance was good.