This study aims to discriminate between leucine-rich glioma-inactivated 1(LGI1)antibody encephalitis and gammaaminobutyric acid B(GABAB)receptor antibody encephalitis using a convolutional neural network(CNN)model.A t...This study aims to discriminate between leucine-rich glioma-inactivated 1(LGI1)antibody encephalitis and gammaaminobutyric acid B(GABAB)receptor antibody encephalitis using a convolutional neural network(CNN)model.A total of 81 patients were recruited for this study.ResNet18,VGG16,and ResNet50 were trained and tested separately using 3828 positron emission tomography image slices that contained the medial temporal lobe(MTL)or basal ganglia(BG).Leave-one-out cross-validation at the patient level was used to evaluate the CNN models.The receiver operating characteristic(ROC)curve and the area under the ROC curve(AUC)were generated to evaluate the CNN models.Based on the prediction results at slice level,a decision strategy was employed to evaluate the CNN models’performance at patient level.The ResNet18 model achieved the best performance at the slice(AUC=0.86,accuracy=80.28%)and patient levels(AUC=0.98,accuracy=96.30%).Specifically,at the slice level,73.28%(1445/1972)of image slices with GABAB receptor antibody encephalitis and 87.72%(1628/1856)of image slices with LGI1 antibody encephalitis were accurately detected.At the patient level,94.12%(16/17)of patients with GABAB receptor antibody encephalitis and 96.88%(62/64)of patients with LGI1 antibody encephalitis were accurately detected.Heatmaps of the image slices extracted using gradient-weighted class activation mapping indicated that the model focused on the MTL and BG for classification.In general,the ResNet18 model is a potential approach for discriminating between LGI1 and GABAB receptor antibody encephalitis.Metabolism in the MTL and BG is important for discriminating between these two encephalitis subtypes.展开更多
Background:Some COVID-19 patients deteriorate to severe cases with relatively higher case-fatality rates,which increases the medical burden.This necessitates identification of patients at risk of severe disease.Early ...Background:Some COVID-19 patients deteriorate to severe cases with relatively higher case-fatality rates,which increases the medical burden.This necessitates identification of patients at risk of severe disease.Early assessment plays a crucial role in identifying patients at risk of severe disease.This study is to assess the effectiveness of SUPER score as a predictor of severe COVID-19 cases.Methods:We consecutively enrolled COVID-19 patients admitted to a comprehensive medical center in Wuhan,China,and recorded clinical characteristics and laboratory indexes.The SUPER score was calculated using pa-rameters including oxygen saturation,urine volume,pulse,emotional state,and respiratory rate.In addition,the area under the receiver operating characteristic curve(AUC),specificity,and sensitivity of the SUPER score for the diagnosis of severe COVID-19 were calculated and compared with the National Early Warning Score 2(NEWS2).Results:The SUPER score at admission,with a threshold of 4,exhibited good predictive performance for early identification of severe COVID-19 cases,yielding an AUC of 0.985(95%confidence interval[CI]0.897-1.000),sensitivity of 1.00(95%CI 0.715-1.000),and specificity of 0.92(95%CI 0.775-0.982),similar to NEWS2(AUC 0.984;95%CI 0.895-1.000,sensitivity 0.91;95%CI 0.587-0.998,specificity 0.97;95%CI 0.858-0.999).Com-pared with patients with a SUPER score<4,patients in the high-risk group exhibited lower lymphocyte counts,interleukin-2,interleukin-4 and higher fibrinogen,C-reactive protein,aspartate aminotransferase,and lactate dehydrogenase levels.Conclusions:In conclusion,the SUPER score demonstrated equivalent accuracy to the NEWS2 score in predicting severe COVID-19.Its application in prognostic assessment therefore offers an effective early warning system for critical management and facilitating efficient allocation of health resources.展开更多
Hybrid composite materials with hierarchical structures have attracted continuing attention for their enhanced features and various applications.The new hybrid composites XW_(9)@PDA(XW_(9) means Na_(8)H[α-PW_(9)O_(34...Hybrid composite materials with hierarchical structures have attracted continuing attention for their enhanced features and various applications.The new hybrid composites XW_(9)@PDA(XW_(9) means Na_(8)H[α-PW_(9)O_(34)],Na_(10)[α-SiW_(9)O_(34)]and Na_(10)[α-GeW_(9)O_(34)];PDA means polydopamine)have been synthesized for potential sensing applications.The effect of polyoxometalates on the formation of the hybrid composites was investigated.Scanning electron microscopy(SEM)supported the obtained XW_(9)@PDA were hierarchical microsphere.By monitoring the reaction of classical peroxidase substrate o-phenylenediamine(OPD)to form yellow 2,3-diaminophenazine(DAB)in the presence of H_(2)O_(2),the peroxidase-like activity of XW_(9)@PDA was calculated.The results showed that XW_(9)@PDA still keep the peroxidase-like activity and have 505.98%,208.58%and 582.78%enhancement in intrinsic catalytic activity for PW_(9)@PDA,SiW_(9)@PDA and GeW_(9)@PDA.Among the three composites,PW_(9)@PDA showed the highest peroxidase-like activity.Therefore,PW_(9)@PDA was applicable to the colorimetric and electrochemical sensing for H_(2)O_(2).展开更多
基金grants from the Beijing Natural Science Foundation-Haidian Original Innovation Joint Foundation,No.L222033the National Key Research and Development Program of China“Common Disease Prevention and Control Research”Key Project,No.2022YFC2503800+2 种基金the National Natural Science Foundation of China,No.81771143the Beijing Natural Science Foundation,No.7192054and the National Key Research and Development Program of China,No.2018YFC1315201.
文摘This study aims to discriminate between leucine-rich glioma-inactivated 1(LGI1)antibody encephalitis and gammaaminobutyric acid B(GABAB)receptor antibody encephalitis using a convolutional neural network(CNN)model.A total of 81 patients were recruited for this study.ResNet18,VGG16,and ResNet50 were trained and tested separately using 3828 positron emission tomography image slices that contained the medial temporal lobe(MTL)or basal ganglia(BG).Leave-one-out cross-validation at the patient level was used to evaluate the CNN models.The receiver operating characteristic(ROC)curve and the area under the ROC curve(AUC)were generated to evaluate the CNN models.Based on the prediction results at slice level,a decision strategy was employed to evaluate the CNN models’performance at patient level.The ResNet18 model achieved the best performance at the slice(AUC=0.86,accuracy=80.28%)and patient levels(AUC=0.98,accuracy=96.30%).Specifically,at the slice level,73.28%(1445/1972)of image slices with GABAB receptor antibody encephalitis and 87.72%(1628/1856)of image slices with LGI1 antibody encephalitis were accurately detected.At the patient level,94.12%(16/17)of patients with GABAB receptor antibody encephalitis and 96.88%(62/64)of patients with LGI1 antibody encephalitis were accurately detected.Heatmaps of the image slices extracted using gradient-weighted class activation mapping indicated that the model focused on the MTL and BG for classification.In general,the ResNet18 model is a potential approach for discriminating between LGI1 and GABAB receptor antibody encephalitis.Metabolism in the MTL and BG is important for discriminating between these two encephalitis subtypes.
文摘Background:Some COVID-19 patients deteriorate to severe cases with relatively higher case-fatality rates,which increases the medical burden.This necessitates identification of patients at risk of severe disease.Early assessment plays a crucial role in identifying patients at risk of severe disease.This study is to assess the effectiveness of SUPER score as a predictor of severe COVID-19 cases.Methods:We consecutively enrolled COVID-19 patients admitted to a comprehensive medical center in Wuhan,China,and recorded clinical characteristics and laboratory indexes.The SUPER score was calculated using pa-rameters including oxygen saturation,urine volume,pulse,emotional state,and respiratory rate.In addition,the area under the receiver operating characteristic curve(AUC),specificity,and sensitivity of the SUPER score for the diagnosis of severe COVID-19 were calculated and compared with the National Early Warning Score 2(NEWS2).Results:The SUPER score at admission,with a threshold of 4,exhibited good predictive performance for early identification of severe COVID-19 cases,yielding an AUC of 0.985(95%confidence interval[CI]0.897-1.000),sensitivity of 1.00(95%CI 0.715-1.000),and specificity of 0.92(95%CI 0.775-0.982),similar to NEWS2(AUC 0.984;95%CI 0.895-1.000,sensitivity 0.91;95%CI 0.587-0.998,specificity 0.97;95%CI 0.858-0.999).Com-pared with patients with a SUPER score<4,patients in the high-risk group exhibited lower lymphocyte counts,interleukin-2,interleukin-4 and higher fibrinogen,C-reactive protein,aspartate aminotransferase,and lactate dehydrogenase levels.Conclusions:In conclusion,the SUPER score demonstrated equivalent accuracy to the NEWS2 score in predicting severe COVID-19.Its application in prognostic assessment therefore offers an effective early warning system for critical management and facilitating efficient allocation of health resources.
基金financially supported by National Natural Science Foundation of China(grant No.82073602)Natural Science Foundation of Jilin Province(grant No.20200201081JC)+1 种基金the open project of the CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety(grant No.NSKF202006)the Graduate Innovation Fund of Jilin University(grant Nos.101832020CX273,101832020CX276).
文摘Hybrid composite materials with hierarchical structures have attracted continuing attention for their enhanced features and various applications.The new hybrid composites XW_(9)@PDA(XW_(9) means Na_(8)H[α-PW_(9)O_(34)],Na_(10)[α-SiW_(9)O_(34)]and Na_(10)[α-GeW_(9)O_(34)];PDA means polydopamine)have been synthesized for potential sensing applications.The effect of polyoxometalates on the formation of the hybrid composites was investigated.Scanning electron microscopy(SEM)supported the obtained XW_(9)@PDA were hierarchical microsphere.By monitoring the reaction of classical peroxidase substrate o-phenylenediamine(OPD)to form yellow 2,3-diaminophenazine(DAB)in the presence of H_(2)O_(2),the peroxidase-like activity of XW_(9)@PDA was calculated.The results showed that XW_(9)@PDA still keep the peroxidase-like activity and have 505.98%,208.58%and 582.78%enhancement in intrinsic catalytic activity for PW_(9)@PDA,SiW_(9)@PDA and GeW_(9)@PDA.Among the three composites,PW_(9)@PDA showed the highest peroxidase-like activity.Therefore,PW_(9)@PDA was applicable to the colorimetric and electrochemical sensing for H_(2)O_(2).
