Objective To explore the predictive efficacy of several multimodal MRI-based machine learning models for the promoter methylation states of O6-methylguanine-DNA methyltransferase(MGMT)of glioblastoma muliforme(GBM)patients in terms of the GBM heterogeneity and the complexity of the tumor microenvironment.Methods Firstly,the multimodal MRI images of 317 GBM patients from The University of Pennsylvania Glioblastoma(UPENN-GBM)dataset were pre-processed,with four sequences involved in including T1-weighted imaging(T1WI)sequence,T1-weighted contrast-enhanced imaging(T1CE)sequence,T2-weighted imaging(T2WI)sequence and fluid-attenuated inversion recovery(FLAIR)sequence,and the radiomics features were extracted for two regions of interest(ROIs)such as the tumor core region and the tumor edema region.Secondly,the data of the 317 GBM patients were randomly divided into a training set(254 cases)and a test set(63 cases),which underwent normalization with Z-scores and feature selection and dimensionality reduction with Lasso regression.Finally,three models were established respectively with particle swarm optimization-support vector machine(PSO-SVM),C-support vector classification(C-SVC)and adaptive boosting(adaptive boosting(Adaboost)algorithms,and the predictive efficacy of the three models for glioblastoma multiforme MGMT promoter methylation states were evaluated in terms of accuracy and AUC.Results The Adaboost model based on T2WI sequence and radiomics features of the tumor core region had the highest predictive efficacy with accuracy and AUC values of 67％and 0.74,respectively,higher than those of other combinations of sequences,models and regions of interest.Conclusion The multimodal MRI-based machine learning models can be used for the prediction of glioblastoma multiforme MGMT promoter methylation states,which provides powerful support for personalized treatment and prognostic assessment of GBM.[Chinese Medical Equipment Journal,2025,46(6):7-13]

Objective To explore the predictive efficacy of several multimodal MRI-based machine learning models for the promoter methylation states of O6-methylguanine-DNA methyltransferase(MGMT)of glioblastoma muliforme(GBM)patients in terms of the GBM heterogeneity and the complexity of the tumor microenvironment.Methods Firstly,the multimodal MRI images of 317 GBM patients from The University of Pennsylvania Glioblastoma(UPENN-GBM)dataset were pre-processed,with four sequences involved in including T1-weighted imaging(T1WI)sequence,T1-weighted contrast-enhanced imaging(T1CE)sequence,T2-weighted imaging(T2WI)sequence and fluid-attenuated inversion recovery(FLAIR)sequence,and the radiomics features were extracted for two regions of interest(ROIs)such as the tumor core region and the tumor edema region.Secondly,the data of the 317 GBM patients were randomly divided into a training set(254 cases)and a test set(63 cases),which underwent normalization with Z-scores and feature selection and dimensionality reduction with Lasso regression.Finally,three models were established respectively with particle swarm optimization-support vector machine(PSO-SVM),C-support vector classification(C-SVC)and adaptive boosting(adaptive boosting(Adaboost)algorithms,and the predictive efficacy of the three models for glioblastoma multiforme MGMT promoter methylation states were evaluated in terms of accuracy and AUC.Results The Adaboost model based on T2WI sequence and radiomics features of the tumor core region had the highest predictive efficacy with accuracy and AUC values of 67％and 0.74,respectively,higher than those of other combinations of sequences,models and regions of interest.Conclusion The multimodal MRI-based machine learning models can be used for the prediction of glioblastoma multiforme MGMT promoter methylation states,which provides powerful support for personalized treatment and prognostic assessment of GBM.[Chinese Medical Equipment Journal,2025,46(6):7-13]

The advantages of wearable devices were introduced when applied in the field of maternal prenatal care.The current application situation of wearable devices was reviewed for monitoring maternal cardiovascular parameters,physiological and psychosocially perceived stress,physical activity,contraction and placental oxygenation and fetal movement and heart rate monitoring.The deficiencies of wearable devices involved in the field of maternal prenatal care were analyzed,and the future development directions were envisioned.[Chinese Medical Equipment Journal,2025,46(10):106-113]

In order to investigate the teaching effectiveness of artificial intelligence(AI)in molecular bi-ology,this study selected students from the Animal Medicine major of the College of Animal Science and Technology at Hebei North University in 2022 and 2023 as research subjects.There was no significant difference in professional foundation,admission scores,and other aspects between the two grades,and they were taught by the same lecturer to ensure the reliability of research results.The 2022 students will adopt the traditional teaching mode,while the 2023 students will implement the AI-enabled teaching mode,which includes four stages:pre class exploration,in class assistance,post class learning support,and teaching reflection and improvement.Before class,the teaching team pushes teaching videos of vari-ous knowledge points in the course and relevant preview materials organized by the AI system to students to complete self-learning,and use AI systems to track students' learning difficulties.In class,the teacher uses various teaching methods such as case teaching,group discussions,AI animation demonstrations and virtual experiments,etc..Thus,they provide in-depth explanations of key contents based on the feed-back data from the intelligent learning companion AI system,promoting students' understanding of the knowledge.After class,the AI system generates personalized learning plans for students and provides dif-ferent levels of learning resources to broaden their horizons.At the same time,the AI system provides teachers with students'learning data analysis reports,and teachers can adjust and optimize their teaching plans accordingly.Research has found that students in the 2023 AI-empowered teaching class have signif-icantly higher satisfaction in multiple dimensions such as learning interest,understanding and mastery of knowledge points,and cultivation of scientific research thinking than those in the 2022 traditional teach-ing class.In terms of student participation in comprehensive activities,the proportion of 2023 students participating in subject competitions and innovation and entrepreneurship activities has significantly in-creased.In terms of academic performance,the mid-term,laboratory,and final grades of 2023 students are higher than those of 2022 students,with a significant increase in the excellence rate and a significant decrease in the failure rate.The results indicate that the application of AI technology in molecular biology teaching has stimulated students' interest in learning,helped them better understand and master knowl-edge,significantly improved their academic performance.In sum,it has a positive impact on improving teaching quality.

In recent years,the incidence and mortality of heatstroke have been increasing annually alongside global warming,with a marked rise in cases exhibiting atypical symptoms.To address the increasingly complex challenges in heatstroke prevention and treatment,Heatstroke Prevention and Treatment Research Center of Chinese PLA,Expert Group of Heatstroke Prevention and Treatment of Chinese PLA,and Chinese PLA Professional Committee of Critical Care Medicine have jointly developed this guideline(2025 edition).Utilizing the Grading of Recommendations Assessment,Development and Evaluation(GRADE)system,Appraisal of Guidelines for Research and Evaluation(AGREE)criteria,and Reporting Items for Practice Guidelines in Healthcare(RIGHT)standards,and based on the 2015 draft"Expert Consensus on the Standardized Diagnosis and Treatment of Heatstroke"and the 2019"Chinese Expert Consensus on the Diagnosis and Treatment of Heatstroke",this guideline has been crafted.This guideline provides 25 evidence-based recommendations to guide the prevention,treatment and research of heatstroke,which thoroughly covers 8 critical domains:clinical classification,pathophysiological mechanisms,clinical manifestations,diagnostic criteria,differential diagnosis,treatment protocols,rehabilitation and return to work,and prevention.

The advantages of wearable devices were introduced when applied in the field of maternal prenatal care.The current application situation of wearable devices was reviewed for monitoring maternal cardiovascular parameters,physiological and psychosocially perceived stress,physical activity,contraction and placental oxygenation and fetal movement and heart rate monitoring.The deficiencies of wearable devices involved in the field of maternal prenatal care were analyzed,and the future development directions were envisioned.[Chinese Medical Equipment Journal,2025,46(10):106-113]

In order to investigate the teaching effectiveness of artificial intelligence(AI)in molecular bi-ology,this study selected students from the Animal Medicine major of the College of Animal Science and Technology at Hebei North University in 2022 and 2023 as research subjects.There was no significant difference in professional foundation,admission scores,and other aspects between the two grades,and they were taught by the same lecturer to ensure the reliability of research results.The 2022 students will adopt the traditional teaching mode,while the 2023 students will implement the AI-enabled teaching mode,which includes four stages:pre class exploration,in class assistance,post class learning support,and teaching reflection and improvement.Before class,the teaching team pushes teaching videos of vari-ous knowledge points in the course and relevant preview materials organized by the AI system to students to complete self-learning,and use AI systems to track students' learning difficulties.In class,the teacher uses various teaching methods such as case teaching,group discussions,AI animation demonstrations and virtual experiments,etc..Thus,they provide in-depth explanations of key contents based on the feed-back data from the intelligent learning companion AI system,promoting students' understanding of the knowledge.After class,the AI system generates personalized learning plans for students and provides dif-ferent levels of learning resources to broaden their horizons.At the same time,the AI system provides teachers with students'learning data analysis reports,and teachers can adjust and optimize their teaching plans accordingly.Research has found that students in the 2023 AI-empowered teaching class have signif-icantly higher satisfaction in multiple dimensions such as learning interest,understanding and mastery of knowledge points,and cultivation of scientific research thinking than those in the 2022 traditional teach-ing class.In terms of student participation in comprehensive activities,the proportion of 2023 students participating in subject competitions and innovation and entrepreneurship activities has significantly in-creased.In terms of academic performance,the mid-term,laboratory,and final grades of 2023 students are higher than those of 2022 students,with a significant increase in the excellence rate and a significant decrease in the failure rate.The results indicate that the application of AI technology in molecular biology teaching has stimulated students' interest in learning,helped them better understand and master knowl-edge,significantly improved their academic performance.In sum,it has a positive impact on improving teaching quality.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.