Background:Postoperative pulmonary complications(PPCs)are major adverse events in neurosurgical patients.This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery.Methods:PPCs...Background:Postoperative pulmonary complications(PPCs)are major adverse events in neurosurgical patients.This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery.Methods:PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days.Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets:The development(data of Huashan Hospital,Fudan University from 2018 to 2020),temporal validation(data of Huashan Hospital,Fudan University in 2021)and external validation(data of other three hospitals in 2023)datasets.Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression.Temporal validation was conducted for all models and the 11-feature models were also externally validated.Independent risk factors were identified and feature importance in top models was analyzed.Results:PPCs occurred in 712 of 7533(9.5%),258 of 2824(9.1%),and 207 of 2300(9.0%)patients in the development,temporal validation and external validation datasets,respectively.During cross-validation training,all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve(AUC)of 0.840.In temporal validation of full-feature models,deep neural network(DNN)performed the best with an AUC of 0.835(95%confidence interval[CI]:0.805-0.858)and a Brier score of 0.069,followed by Logistic regression(LR),random forest and XGBoost.The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs,with the top models of DNN and LR in temporal and external validations.An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia(ARISCAT)and Laparoscopic Surgery Video Educational Guidelines(LAS VEGAS)scores with a higher AUC(LR:0.824,ARISCAT:0.672,LAS:0.663).Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features,but lacked consistency with the important features using the Shapley additive explanation(SHAP)method of the LR model.Conclusions:The developed models,especially the DNN model and the nomogram,had good discrimination and calibration,and could be used for predicting PPCs in neurosurgical patients.The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes.展开更多
Copper oxide has aroused great concern in energy storage fields due to its properties of high theoretical capacitance,low cost and mild toxicity.However,its wide application still remains challenges owing to its poor ...Copper oxide has aroused great concern in energy storage fields due to its properties of high theoretical capacitance,low cost and mild toxicity.However,its wide application still remains challenges owing to its poor electrical conductivity and unstable cycling life.Binder-free foam electrodes possess abundant porous structures and high specific surface area,which could get good contact with electrolyte.Herein,we demonstrate Ag nanoparticles decorated CuxO nanowires grown spontaneously on copper foam(CF)electrode for asymmetric supercapacitor.The skeleton structure of CF provides large amounts of active sites for the growth of CuxO nanowires.Moreover,Ag nanoparticles further decrease the internal resistance and enhance the electrochemical performance.Ag/CuxO/CF-40 electrode presents a high area specific capacitance of 1192 mF cm^(-2)at 2 mA cm^(-2)and the influence of surface capacitance-dominated process and diffusion-controlled process are discussed in detail.Besides,the energy density of the as-prepared asymmetric supercapacitor(ASC)reaches 46.32 mWh cm^(-2)at a power density of 3.00 mW cm^(-2).A 2V LED is lighted successfully by two ASC in series.This work provides a new strategy to prepare low internal resistance and binder-free flexible Ag/CuxO/CF electrode,which demonstrates a good potential application in flexible supercapacitors or other wearable electronic devices.展开更多
Production cost,capacitance,and electrode materials safety are the key factors to be concerned about for supercapacitors.In this work,a type of carbon nanosheets was produced through the carbonization of tripotassium ...Production cost,capacitance,and electrode materials safety are the key factors to be concerned about for supercapacitors.In this work,a type of carbon nanosheets was produced through the carbonization of tripotassium citrate monohydrate and nitric acidification.Subsequently,a well-designed manganese dioxide/carbon nanosheets composite was synthesized through hydrothermal treating.The carbon nanosheets served as the substrate for growing the manganese dioxide,regulating its distribution,and preventing it from inhomogeneous dimensions and severe agglomeration.Many manganese dioxide nanosheets grew vertically on the numerous functional groups generated on the surface of the carbon nanosheets during acidification.The synergistic combination of carbon nanosheets and manganese dioxide tailors the electrochemical performance of the composite,which benefits from the excellent conductivity and stability of carbon nanosheets.The carbon nanosheets derived from tripotassium citrate monohydrate are conducive to the remarkable performance of manganese dioxide/carbon nanosheets electrode.Finally,an asymmetric supercapacitor with active carbon as the cathode and manganese dioxide/carbon nanosheets as the anode was assembled,achieving an outstanding energy density of 54.68 Wh·kg^(−1) and remarkable power density of 6399.2 W·kg^(−1) superior to conventional lead-acid batteries.After 10000 charge-discharge cycles,the device retained 75.3%of the initial capacitance,showing good cycle stability.Two assembled asymmetric supercapacitors in series charged for 3 min could power a yellow light emitting diode with an operating voltage of 2 V for 2 min.This study may provide valuable insights for applying carbon materials and manganese dioxide in the energy storage field.展开更多
基金supported by grants from the National Natural Science Foundation,China(Nos.82271292,81730031)the Foundation of Shanghai Municipal Science and Technology Medical Innovation Research Project(No.23Y21900600)the Foundation of Shanghai Municipal Key Clinical Specialty(No.shslczdzk06901).
文摘Background:Postoperative pulmonary complications(PPCs)are major adverse events in neurosurgical patients.This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery.Methods:PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days.Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets:The development(data of Huashan Hospital,Fudan University from 2018 to 2020),temporal validation(data of Huashan Hospital,Fudan University in 2021)and external validation(data of other three hospitals in 2023)datasets.Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression.Temporal validation was conducted for all models and the 11-feature models were also externally validated.Independent risk factors were identified and feature importance in top models was analyzed.Results:PPCs occurred in 712 of 7533(9.5%),258 of 2824(9.1%),and 207 of 2300(9.0%)patients in the development,temporal validation and external validation datasets,respectively.During cross-validation training,all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve(AUC)of 0.840.In temporal validation of full-feature models,deep neural network(DNN)performed the best with an AUC of 0.835(95%confidence interval[CI]:0.805-0.858)and a Brier score of 0.069,followed by Logistic regression(LR),random forest and XGBoost.The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs,with the top models of DNN and LR in temporal and external validations.An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia(ARISCAT)and Laparoscopic Surgery Video Educational Guidelines(LAS VEGAS)scores with a higher AUC(LR:0.824,ARISCAT:0.672,LAS:0.663).Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features,but lacked consistency with the important features using the Shapley additive explanation(SHAP)method of the LR model.Conclusions:The developed models,especially the DNN model and the nomogram,had good discrimination and calibration,and could be used for predicting PPCs in neurosurgical patients.The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes.
基金supported by Key R&D Program of Zhenjiang(GY2018016).
文摘Copper oxide has aroused great concern in energy storage fields due to its properties of high theoretical capacitance,low cost and mild toxicity.However,its wide application still remains challenges owing to its poor electrical conductivity and unstable cycling life.Binder-free foam electrodes possess abundant porous structures and high specific surface area,which could get good contact with electrolyte.Herein,we demonstrate Ag nanoparticles decorated CuxO nanowires grown spontaneously on copper foam(CF)electrode for asymmetric supercapacitor.The skeleton structure of CF provides large amounts of active sites for the growth of CuxO nanowires.Moreover,Ag nanoparticles further decrease the internal resistance and enhance the electrochemical performance.Ag/CuxO/CF-40 electrode presents a high area specific capacitance of 1192 mF cm^(-2)at 2 mA cm^(-2)and the influence of surface capacitance-dominated process and diffusion-controlled process are discussed in detail.Besides,the energy density of the as-prepared asymmetric supercapacitor(ASC)reaches 46.32 mWh cm^(-2)at a power density of 3.00 mW cm^(-2).A 2V LED is lighted successfully by two ASC in series.This work provides a new strategy to prepare low internal resistance and binder-free flexible Ag/CuxO/CF electrode,which demonstrates a good potential application in flexible supercapacitors or other wearable electronic devices.
基金This work is financially supported by Six Talents Peak Project in Jiangsu Province(Grant No.2011-ZBZZ045)Key R&D Program of Zhenjiang(Grant No.GY2018016)Innovative Training Program in Jiangsu University(Grant No.Y18A017).
文摘Production cost,capacitance,and electrode materials safety are the key factors to be concerned about for supercapacitors.In this work,a type of carbon nanosheets was produced through the carbonization of tripotassium citrate monohydrate and nitric acidification.Subsequently,a well-designed manganese dioxide/carbon nanosheets composite was synthesized through hydrothermal treating.The carbon nanosheets served as the substrate for growing the manganese dioxide,regulating its distribution,and preventing it from inhomogeneous dimensions and severe agglomeration.Many manganese dioxide nanosheets grew vertically on the numerous functional groups generated on the surface of the carbon nanosheets during acidification.The synergistic combination of carbon nanosheets and manganese dioxide tailors the electrochemical performance of the composite,which benefits from the excellent conductivity and stability of carbon nanosheets.The carbon nanosheets derived from tripotassium citrate monohydrate are conducive to the remarkable performance of manganese dioxide/carbon nanosheets electrode.Finally,an asymmetric supercapacitor with active carbon as the cathode and manganese dioxide/carbon nanosheets as the anode was assembled,achieving an outstanding energy density of 54.68 Wh·kg^(−1) and remarkable power density of 6399.2 W·kg^(−1) superior to conventional lead-acid batteries.After 10000 charge-discharge cycles,the device retained 75.3%of the initial capacitance,showing good cycle stability.Two assembled asymmetric supercapacitors in series charged for 3 min could power a yellow light emitting diode with an operating voltage of 2 V for 2 min.This study may provide valuable insights for applying carbon materials and manganese dioxide in the energy storage field.
