Objective:To investigate microstructural alterations in the optic chiasm and optic radiations of multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD) based on diffusion kurtosis imaging (DKI).Methods:This study was a cross-sectional study. Retrospective analyses were conducted on the clinical and imaging data of 63 patients with relapsing-remitting MS (RRMS) and 62 patients with NMOSD diagnosed at First Affiliated Hospital of Chongqing Medical University from January 2019 to December 2023. According to the occurrence of optic neuritis (ON), they were categorized into ON-positive MS (ON+MS) group (40 cases), ON-negative MS (ON-MS) group (23 cases), ON-positive NMOSD (ON+NMOSD) group (40 cases) and ON-negative NMOSD (ON-NMOSD) group (22 cases). In addition, 40 healthy controls were enrolled during the same period. DKI data of all subjects were collected, and DKI post-processing was performed to obtain fractional anisotropy (FA), mean kurtosis (MK), axial kurtosis (AK), and radial kurtosis (RK) values of the optic chiasm and bilateral optic radiations. The scores of the mini-mental state examination (MMSE), montreal cognitive assessment (MoCA), and expanded disability status scale (EDSS) were obtained. The Kruskal-Wallis test was used to analyze the differences in DKI parameters of the optic chiasm and bilateral optic radiation among the 5 groups, and the Holm-Bonferroni method was employed for multiple comparison correction in pairwise comparisons.Results:There were statistically significant overall differences in the DKI parameters of the optic chiasm and bilateral optic radiations among healthy control group, ON+MS group, ON-MS group, ON+NMOSD group, and ON-NMOSD group (all P0.05). The FA value of the optic chiasm in ON+NMOSD group was significantly lower than that of healthy control group and ON-MS group, as well as ON-NMOSD group ( P0.05). The FA value of the left optic radiation in ON+NMOSD group was lower than that in healthy control group and the ON-MS group. The RK value of the optic chiasm in ON+MS group was lower than that in the healthy control group and ON-NMOSD group ( P0.05). The MK and RK values of the left optic radiation in ON-MS group were significantly lower than those in the ON+NMOSD group and ON-NMOSD group ( P0.05). Conclusions:NMOSD and RRMS patients demonstrate varying degrees of microstructural damage in the optic chiasm and optic radiations. Differences of DKI parameters suggest different pathological mechanisms of visual pathway damage between NMOSD and MS, which may be helpful for early detection of occult visual pathway lesions.

ObjectiveTo investigate the application value of a multimodal model integrating radiomics features， deep learning features， and clinical structured data in predicting severe acute pancreatitis （SAP）， and to provide more accurate tools for the early identification of SAP in clinical practice. MethodsThe patients with acute pancreatitis （AP） who attended The First Affiliated Hospital of Soochow University， Jintan Hospital Affiliated to Jiangsu University， and Suzhou Yongding Hospital from January 1， 2017 to December 31， 2023 were included. Related data were collected， including demographic information， previous medical history， etiology， laboratory test data， and systemic inflammatory response syndrome （SIRS） within 24 hours after admission， as well as imaging data within 72 hours after admission， while related scores were calculated， including Ranson score， modified CT severity index （MCTSI）， bedside index for severity in acute pancreatitis （BISAP）， and systemic inflammatory response syndrome， albumin， blood urea nitrogen and pleural effusion （SABP） score. The model was constructed in the following process： （1） three-dimensional CT images were used to extract and identify radiomics features， and a radiomics classification model was established based on the extreme gradient Boost （XGBoost） algorithm； （2） U-Net is used to perform semantic segmentation of three-dimensional CT images， and then the results of segmentation were imported into 3D ResNet50 to construct a deep learning classification model； （3） the predicted values of the above two models were integrated with clinical structured data to establish a multimodal model based on the XGBoost algorithm. The variable importance plot and local interpretability plot were used to perform visual interpretation of the model. The independent samples t-test was used for comparison of normally distributed continuous data between groups， and the Mann-Whitney U test was used for comparison of non-normally distributed continuous data between groups； the chi-square test or Fisher’s exact test was used for comparison of categorical data between groups. The receiver operating characteristic （ROC） curve was plotted for each model and existing scoring systems， and the area under the ROC curve （AUC） was calculated to assess their performance； the Delong test was used for comparison of AUC. ResultsA total of 609 patients who met the criteria were included， among whom 114 （18.7%） developed SAP. In this study， the data of 426 patients from The First Affiliated Hospital of Soochow University was used as the training set， and the data of 183 patients from Jintan Hospital Affiliated to Jiangsu University and Suzhou Yongding Hospital were used as the independent test set. The multimodal model had an AUC of 0.914 in the test set， which was significantly higher than the AUC of traditional scoring systems such as MCTSI （AUC=0.827）， Ranson score （AUC=0.675）， BISAP （AUC=0.791）， and SABP score （AUC=0.648）； in addition， the multimodal model showed a significant improvement in performance compared with the radiomics classification model （AUC=0.739） and the deep learning classification model （AUC=0.685） （the Delong test： Z=-3.23， -4.83， -3.48， -4.92， -4.31， and -4.59， all P <0.01）. The top 10 variables in terms of importance in the multimodal model were pleural effusion， predicted value of the deep learning model， predicted value of the radiomics model， triglycerides， calcium ions， SIRS， white blood cell count， age， platelets， and C-reactive protein， suggesting that the above variables had significant contributions to the performance of the model in predicting SAP. ConclusionBased on structured data， radiomic features， and deep learning features， this study constructs a multicenter prediction model for SAP based on the XGBoost algorithm， which has a better predictive performance than existing traditional scoring systems and unimodal models.

Traditional Chinese Medicine (TCM), as a treasure of the Chinese nation, plays a significant role in maintaining public health. In 2019, the Central Committee of the Communist Party of China and the State Council proposed for the first time the establishment of a TCM registration and evaluation evidence system that integrates TCM theory, "personal experience" and clinical trials (referred to as the "Three-in-One" System) to promote the inheritance and innovation of TCM. Subsequently, the National Medical Products Administration issued several guiding principles to advance the improvement and implementation of this system. Owing to the complexity of its implementation, there are still differing understandings within the TCM industry regarding the positioning of the "Three-in-One" Registration and Evaluation Evidence System, as well as the connotation and value orientation of the "personal experience." To address this, Academician WANG Qi, President of the TCM Association, China International Exchange and Promotion Association for Medical and Healthcare and TCM master, led a group of academicians, TCM masters, TCM pharmacology experts and clinical TCM experts to convene a "Seminar on Promoting the Implementation of the ′Three-in-One′ Registration and Evaluation Evidence System for Chinese Medicinals." Through extensive discussions, an expert consensus was formed, clarifying the different roles of the TCM theory, "personal experience" and clinical trials within the system. It was further emphasized that the "personal experience" is the core of this system, and its data should be derived from clinical practice scenarios. In the future, the improvement of this system will require collaborative efforts across multiple fields to promote the high-quality development of the Chinese medicinal industry.

Objective:To establish and validate a multimodal model based on radiomics and deep learning for predicting acute pancreatitis (AP) complicated with acute respiratory distress syndrome (ARDS).Methods:Patients diagnosed with AP from The First Affiliated Hospital of Soochow University, Donghai County People's Hospital and Jintan Affiliated Hospital of Jiangsu University between January 2017 and December 2023 were enrolled. Based on the diagnosis of ARDS within 1 week after admission, the patients were classified into the ARDS group and the non-ARDS group. Patients in the First Affiliated Hospital of Soochow University ( n=406) was used as the training set (non-ARDS group n=212 vs ARDS group n=194), while Donghai and Jintan hospitals served as the test set ( n=175; non-ARDS group n=104 vs ARDS group n=71). Clinical data, laboratory tests and the occurrence of systemic inflammatory response syndrome (SIRS) within 24 hours after admission were collected. Scoring systems such as bedside index for severity in acute pancreatitis (BISAP), Ranson score and modified CT severity index (MCTSI) were calculated. Radiomics features were extracted from three-dimensional CT images to develop a radiomics model based on XGBoost algorithm. At the same time, a deep learning model was constructed using deep convolutional networks to extract deep features. Finally, clinical features and the predictions from the aforementioned models were integrated to establish a multimodal model based on XGBoost algorithm. To enhance model visualization, variable importance ranking and local interpretable visualization were used. The receiver operating characteristic (ROC) curves of the three models and the three scores including BISAP, Ranson and MCTSI were plotted and the area under the curves (AUCs) were calculated to evaluate the prediction performance for ARDS in AP patients, as well as sensitivity and specificity. Results:In the multimodal model for predicting ARDS in AP patients, predictions of the deep learning model and the radiomics model were the most important variables, followed by SIRS, C-reactive protein, procalcitonin, albumin, glucose, creatinine, neutrophil, and Ca 2+. In the training set, the multimodal model achieved an AUC of 0.933 for predicting ARDS in AP patients, higher than the radiomics model (0.727), the deep learning model (0.877), MCTSI (0.870), Ranson (0.620) and BISAP (0.898). In the test set, the model's AUC was 0.916 for predicting ARDS in AP patients, higher than the radiomics model (0.660), the deep learning model (0.864), MCTSI (0.851), Ranson (0.609), and BISAP (0.860). Conclusions:Based on clinical structured data, radiomics and deep learning features, the multimodal model could predict the risk of ARDS in AP patients at an early stage, whose performance is better than the single-modal models and the traditional scoring systems.

Objective To construct a classification model for the Los Angeles grading of endoscopic reflux esophagitis based on the SimCLR algorithm's semi-supervised learning framework.Methods The designed learning framework was pre-trained on a large unlabeled dataset through self-supervised learning,and further finely tuned on a small labeled dataset according to the Los Angeles grading criteria.The performance test on the model was conducted on an independent dataset,and the proposed model was compared with the models of supervised learning algorithms and endoscopists in terms of accuracy,Matthews correlation coefficient,and Cohen's kappa value.Finally,Grad-CAM and t-SNE were used for the visualization of the model's interpretation.Results The SimCLR model with ResNet as the backbone network showed superior performance in accuracy(0.840),Matthews correlation coefficient(0.800),and Cohen's kappa value(0.960)than the traditional supervised learning model with ResNet as the backbone(0.680,0.601,and 0.870)as well as junior endoscopists(0.770,0.713,and 0.940),but there was still a slight gap compared with senior endoscopists(0.850,0.813,and 0.960).In addition,the results of t-SNE showed that self-supervised learning in SimCLR was more effective in clustering multi-dimensional samples than traditional supervised transfer learning.Conclusion Compared with traditional supervised learning methods,semi-supervised learning demonstrates outstanding performance even with only a small number of labeled endoscopic images.

Objective:To explore the application value of problem-based learning (PBL) combined with mini-clinical evaluation exercise (Mini-CEX) in the development of post competency for interns in the Department of Neurology.Methods:A total of 56 interns rotating at the Department of Neurology of The First Affiliated Hospital of Chongqing Medical University from June 2023 to January 2024 were enrolled as the study subjects. They were randomly divided into a control group and an experiment group using the random number table method, with 28 interns in each group. The control group received traditional methods including small lectures and teaching rounds, while the experimental group received the PBL teaching method combined with Mini-CEX. The teaching effectiveness was evaluated through theoretical assessments, practical skill evaluations, teacher and student satisfaction surveys, and Mini-CEX scale assessments conducted at the beginning, middle, and end of the rotation for the experimental group. The data were analyzed using SPSS 23.0 software. For continuous data, the independent-samples t test or Mann-Whitney U test was used for comparison between groups. The chi-square test was used for categorical data and the Kruskal-Wallis H test for repeated-measurement data. Results:The theoretical scores [(45.36±2.67) vs. (42.00±4.29), P<0.01] and practical skill scores [(45.11±2.53) vs. (42.39±4.53), P<0.01] were significantly higher in the experimental group compared to the control group. The Mini-CEX score of the experimental group at the end of the rotation was notably higher than that at the beginning of rotation ( P<0.05), and their abilities improved continuously. The satisfaction rates of teachers and students in the experimental group were 71.43% (20/28) and 67.86% (19/28), respectively, which were significantly higher than those in the control group [39.29% (11/28) and 35.71% (10/28), P<0.05]. Conclusions:The teaching model integrating PBL and Mini-CEX can effectively enhance the post competency of interns in the Department of Neurology, thus offering a new perspective for clinical undergraduate teaching.

Objective:To explore the application value of problem-based learning (PBL) combined with mini-clinical evaluation exercise (Mini-CEX) in the development of post competency for interns in the Department of Neurology.Methods:A total of 56 interns rotating at the Department of Neurology of The First Affiliated Hospital of Chongqing Medical University from June 2023 to January 2024 were enrolled as the study subjects. They were randomly divided into a control group and an experiment group using the random number table method, with 28 interns in each group. The control group received traditional methods including small lectures and teaching rounds, while the experimental group received the PBL teaching method combined with Mini-CEX. The teaching effectiveness was evaluated through theoretical assessments, practical skill evaluations, teacher and student satisfaction surveys, and Mini-CEX scale assessments conducted at the beginning, middle, and end of the rotation for the experimental group. The data were analyzed using SPSS 23.0 software. For continuous data, the independent-samples t test or Mann-Whitney U test was used for comparison between groups. The chi-square test was used for categorical data and the Kruskal-Wallis H test for repeated-measurement data. Results:The theoretical scores [(45.36±2.67) vs. (42.00±4.29), P<0.01] and practical skill scores [(45.11±2.53) vs. (42.39±4.53), P<0.01] were significantly higher in the experimental group compared to the control group. The Mini-CEX score of the experimental group at the end of the rotation was notably higher than that at the beginning of rotation ( P<0.05), and their abilities improved continuously. The satisfaction rates of teachers and students in the experimental group were 71.43% (20/28) and 67.86% (19/28), respectively, which were significantly higher than those in the control group [39.29% (11/28) and 35.71% (10/28), P<0.05]. Conclusions:The teaching model integrating PBL and Mini-CEX can effectively enhance the post competency of interns in the Department of Neurology, thus offering a new perspective for clinical undergraduate teaching.

Objective:To investigate microstructural alterations in the optic chiasm and optic radiations of multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD) based on diffusion kurtosis imaging (DKI).Methods:This study was a cross-sectional study. Retrospective analyses were conducted on the clinical and imaging data of 63 patients with relapsing-remitting MS (RRMS) and 62 patients with NMOSD diagnosed at First Affiliated Hospital of Chongqing Medical University from January 2019 to December 2023. According to the occurrence of optic neuritis (ON), they were categorized into ON-positive MS (ON+MS) group (40 cases), ON-negative MS (ON-MS) group (23 cases), ON-positive NMOSD (ON+NMOSD) group (40 cases) and ON-negative NMOSD (ON-NMOSD) group (22 cases). In addition, 40 healthy controls were enrolled during the same period. DKI data of all subjects were collected, and DKI post-processing was performed to obtain fractional anisotropy (FA), mean kurtosis (MK), axial kurtosis (AK), and radial kurtosis (RK) values of the optic chiasm and bilateral optic radiations. The scores of the mini-mental state examination (MMSE), montreal cognitive assessment (MoCA), and expanded disability status scale (EDSS) were obtained. The Kruskal-Wallis test was used to analyze the differences in DKI parameters of the optic chiasm and bilateral optic radiation among the 5 groups, and the Holm-Bonferroni method was employed for multiple comparison correction in pairwise comparisons.Results:There were statistically significant overall differences in the DKI parameters of the optic chiasm and bilateral optic radiations among healthy control group, ON+MS group, ON-MS group, ON+NMOSD group, and ON-NMOSD group (all P0.05). The FA value of the optic chiasm in ON+NMOSD group was significantly lower than that of healthy control group and ON-MS group, as well as ON-NMOSD group ( P0.05). The FA value of the left optic radiation in ON+NMOSD group was lower than that in healthy control group and the ON-MS group. The RK value of the optic chiasm in ON+MS group was lower than that in the healthy control group and ON-NMOSD group ( P0.05). The MK and RK values of the left optic radiation in ON-MS group were significantly lower than those in the ON+NMOSD group and ON-NMOSD group ( P0.05). Conclusions:NMOSD and RRMS patients demonstrate varying degrees of microstructural damage in the optic chiasm and optic radiations. Differences of DKI parameters suggest different pathological mechanisms of visual pathway damage between NMOSD and MS, which may be helpful for early detection of occult visual pathway lesions.

Objective To construct a classification model for the Los Angeles grading of endoscopic reflux esophagitis based on the SimCLR algorithm's semi-supervised learning framework.Methods The designed learning framework was pre-trained on a large unlabeled dataset through self-supervised learning,and further finely tuned on a small labeled dataset according to the Los Angeles grading criteria.The performance test on the model was conducted on an independent dataset,and the proposed model was compared with the models of supervised learning algorithms and endoscopists in terms of accuracy,Matthews correlation coefficient,and Cohen's kappa value.Finally,Grad-CAM and t-SNE were used for the visualization of the model's interpretation.Results The SimCLR model with ResNet as the backbone network showed superior performance in accuracy(0.840),Matthews correlation coefficient(0.800),and Cohen's kappa value(0.960)than the traditional supervised learning model with ResNet as the backbone(0.680,0.601,and 0.870)as well as junior endoscopists(0.770,0.713,and 0.940),but there was still a slight gap compared with senior endoscopists(0.850,0.813,and 0.960).In addition,the results of t-SNE showed that self-supervised learning in SimCLR was more effective in clustering multi-dimensional samples than traditional supervised transfer learning.Conclusion Compared with traditional supervised learning methods,semi-supervised learning demonstrates outstanding performance even with only a small number of labeled endoscopic images.

Objective:To establish and validate a multimodal model based on radiomics and deep learning for predicting acute pancreatitis (AP) complicated with acute respiratory distress syndrome (ARDS).Methods:Patients diagnosed with AP from The First Affiliated Hospital of Soochow University, Donghai County People's Hospital and Jintan Affiliated Hospital of Jiangsu University between January 2017 and December 2023 were enrolled. Based on the diagnosis of ARDS within 1 week after admission, the patients were classified into the ARDS group and the non-ARDS group. Patients in the First Affiliated Hospital of Soochow University ( n=406) was used as the training set (non-ARDS group n=212 vs ARDS group n=194), while Donghai and Jintan hospitals served as the test set ( n=175; non-ARDS group n=104 vs ARDS group n=71). Clinical data, laboratory tests and the occurrence of systemic inflammatory response syndrome (SIRS) within 24 hours after admission were collected. Scoring systems such as bedside index for severity in acute pancreatitis (BISAP), Ranson score and modified CT severity index (MCTSI) were calculated. Radiomics features were extracted from three-dimensional CT images to develop a radiomics model based on XGBoost algorithm. At the same time, a deep learning model was constructed using deep convolutional networks to extract deep features. Finally, clinical features and the predictions from the aforementioned models were integrated to establish a multimodal model based on XGBoost algorithm. To enhance model visualization, variable importance ranking and local interpretable visualization were used. The receiver operating characteristic (ROC) curves of the three models and the three scores including BISAP, Ranson and MCTSI were plotted and the area under the curves (AUCs) were calculated to evaluate the prediction performance for ARDS in AP patients, as well as sensitivity and specificity. Results:In the multimodal model for predicting ARDS in AP patients, predictions of the deep learning model and the radiomics model were the most important variables, followed by SIRS, C-reactive protein, procalcitonin, albumin, glucose, creatinine, neutrophil, and Ca 2+. In the training set, the multimodal model achieved an AUC of 0.933 for predicting ARDS in AP patients, higher than the radiomics model (0.727), the deep learning model (0.877), MCTSI (0.870), Ranson (0.620) and BISAP (0.898). In the test set, the model's AUC was 0.916 for predicting ARDS in AP patients, higher than the radiomics model (0.660), the deep learning model (0.864), MCTSI (0.851), Ranson (0.609), and BISAP (0.860). Conclusions:Based on clinical structured data, radiomics and deep learning features, the multimodal model could predict the risk of ARDS in AP patients at an early stage, whose performance is better than the single-modal models and the traditional scoring systems.