Recently,the theoretical system and practical path for the deep integration of digitalization and traditional industrialization have gradually matured.Medical innovation and digital technology are progressing,and the deep integration of intensive care medicine and intelligence is surpassing the traditional informatization and ushering in new development opportunities.Technologies such as 5G,big data,artificial intelligence,and digital twins can help to understand more complex critical care issues,improve the diagnoses and prediction of diseases and symptoms,develop more accurate treatment strategies,and even transform the service model of critical care medicine.This paper summarizes the application and challenge of digital technology in the practical scenarios of critical care medicine,so as to further consolidate infrastructure,enrich application scenarios,accelerate implementation,improve effectiveness,and strengthen the safety and compliance with the regulations.

To achieve the national objectives of improving medical quality and safety,the Shanghai Shenkang Hospital Development Center has formulated a list of major targets,tasks,and key results based onthe Objective and Key Results (OKR) method.The primary approaches adopted include establishing an organizational structure to advance medical quality and safety supervision,setting up a series of quantitative indicators for medical quality and safety targets,formulating standardized management systems,building an information platform,and strengthening supervision.It argues that the adoption of OKR can effectively promote the implementation of national target management for improving medical quality and safety,establish a cross-institutional management network for medical quality and safety,strengthen process management,and effectively drive continuous improvement in medical quality and safety.

Objective To explore the value of phase contrast(PC)MRI intracranial hemodynamic parameters for predicting acute mountain sickness(AMS).Methods Totally 72 healthy young volunteers were prospectively recruited.Intracranial hemodynamic parameters of internal carotid artery(ICA)and internal jugular vein(IJV)were measured using PC MRI under normal breathing,as well as mild,moderate and severe Valsalva maneuvers(VM)in plain area.The subjects were divided into AMS group(n=9)and non-AMS group(n=63)according to results of Lake Louise score(LLS)10 h after a rapid ascent to plateau area with altitude of 4 411 m.Univariate and multivariate logistic regression analyses were performed to screen independent predictors of AMS under different states and then construct single and combined VM states prediction models.Receiver operating characteristic curves were plotted,and the area under the curve(AUC)was calculated to evaluate the predictive efficacy of each model.Results ICA pulsatility index(PIICA)under mild VM,IJV cross-sectional area(SIJV)under moderate VM and IJV resistance index(RIIJV)under severe VM were all independent predictors of AMS(all P＜0.05).The efficacy of combined VM states model(AUC=0.869)for predicting AMS was higher than each single VM state model(AUC=0.698-0.738).Conclusion The model constructed based on PIICA under mild VM,SIJV under moderate VM and RIIJV under severe VM could be used to effectively predict AMS.

To achieve the national objectives of improving medical quality and safety,the Shanghai Shenkang Hospital Development Center has formulated a list of major targets,tasks,and key results based onthe Objective and Key Results (OKR) method.The primary approaches adopted include establishing an organizational structure to advance medical quality and safety supervision,setting up a series of quantitative indicators for medical quality and safety targets,formulating standardized management systems,building an information platform,and strengthening supervision.It argues that the adoption of OKR can effectively promote the implementation of national target management for improving medical quality and safety,establish a cross-institutional management network for medical quality and safety,strengthen process management,and effectively drive continuous improvement in medical quality and safety.

Objective To explore the value of phase contrast(PC)MRI intracranial hemodynamic parameters for predicting acute mountain sickness(AMS).Methods Totally 72 healthy young volunteers were prospectively recruited.Intracranial hemodynamic parameters of internal carotid artery(ICA)and internal jugular vein(IJV)were measured using PC MRI under normal breathing,as well as mild,moderate and severe Valsalva maneuvers(VM)in plain area.The subjects were divided into AMS group(n=9)and non-AMS group(n=63)according to results of Lake Louise score(LLS)10 h after a rapid ascent to plateau area with altitude of 4 411 m.Univariate and multivariate logistic regression analyses were performed to screen independent predictors of AMS under different states and then construct single and combined VM states prediction models.Receiver operating characteristic curves were plotted,and the area under the curve(AUC)was calculated to evaluate the predictive efficacy of each model.Results ICA pulsatility index(PIICA)under mild VM,IJV cross-sectional area(SIJV)under moderate VM and IJV resistance index(RIIJV)under severe VM were all independent predictors of AMS(all P＜0.05).The efficacy of combined VM states model(AUC=0.869)for predicting AMS was higher than each single VM state model(AUC=0.698-0.738).Conclusion The model constructed based on PIICA under mild VM,SIJV under moderate VM and RIIJV under severe VM could be used to effectively predict AMS.

The accumulation of fatigue during military operations may lead to decreased operational efficiency and non-combat attrition,which can impact combat effectiveness.On-site monitoring and evaluation of fatigue during military operations,as an important means to keep track of military operations and bring about quick changes in training,underlie the combat effectiveness of military personnel.Focusing on the on-site monitoring and evaluation methods of fatigue during military operations,this paper reviews the determinants of such fatigue as well as on-site monitoring and comprehensive evaluation methods so as to provide reference for accurate and efficient evaluation of fatigue during military operations and for early warning of such fatigue.

Purpose To investigate the value of pre-treatment relative cerebral blood flow(rCBF)and relative cerebral blood volume histogram of dynamic susceptibility contrast-enhanced perfusion weighted imaging in predicting the chemotherapy response of primary central nervous system lymphoma(PCNSL)patients.Materials and Methods Thirty-eight PCNSL patients with fifty-seven lesions treated with high-dose methotrexate chemotherapy from September 2016 to October 2023 were retrospectively involved in the study.The patients were divided into response group of 30 patients and non-response group of 8 patients.Region of interest was drawn in cerebral blood flow and cerebral blood volume images,and histogram paraments were extracted.Univariate and multivariate Logistic regression analysis were performed to identify the independent predictors for chemotherapy response in PCNSL,and then combined prediction model was constructed.The area under the receiver operating characteristic curve was used to compare the predictive performance of different paraments and combined model.Results The number of lesions(OR=9.726,95％CI 1.070-88.397,P=0.043)and rCBF90(OR=0.224,95％CI 0.072-0.704,P=0.010)were the independent predictors for chemotherapy response with the area under the curve of 0.681 and 0.798,respectively.The combined model of rCBF90 and the numbers of lesions showed the best predictive performance with the area under the curve of 0.846.Conclusion The pre-treatment quantitative parameters rCBF and relative cerebral blood volume of dynamic susceptibility contrast-enhanced perfusion weighted imaging could be used for predicting the response to high-dose methotrexate chemotherapy in PCNSL patients,and the rCBF90 is an independent predictor of chemotherapy response.

Purpose To construct the model of differentiating primary central nervous system lymphoma(PCNSL)and atypical glioblastoma(GBM)by combining multi-parameter MRI radiomics and six machine learning algorithms,thus to compare the diagnostic efficacy of different machine learning algorithms.Materials and Methods The clinical and imaging data of 77(125 lesions)PCNSL and 90 atypical GBM(108 lesions)from PLA General Hospital and public databases were retrospectively analyzed from January 2013 to December 2023,and all patients were randomly divided into a training set(163 cases)and a validation set(70 cases)according to 7∶3.T1WI,T2WI and T1-weighted contrast-enhanced sequences were selected for tumor segmentation,and 1 132 radiomics features were extracted from each region of interest.The intraclass correlation coefficient(ICC)was used for the consistency test,and image features with ICC≥0.85 were selected.ICC and recursive feature elimination were used to select the best radiomics features.Six classifiers were used to train and verify three single sequence feature sets,three double-sequence sets and one multi-sequence set.The receiver operating characteristic curve was used to evaluate the diagnostic efficacy of the model.Results The combination model of the support vector machine of radial basis function classifier and multi-sequence feature set were the best model for differentiating PCNSL and atypical GBM.The area under the curve of the training set and the validation set were 0.969 and 0.913,respectively;and the accuracy were both 0.886.Conclusion Noninvasive extraction of multiparametric MRI features combined with machine learning algorithms can effectively differentiate PCNSL and atypical GBM,which provides support for the development of individualized treatment plans for patients.

Objective:To analyze the prognosis factors of cerebrospinal fluid (CSF) spread after surgery in glioblastoma (GBM) patients when tumors progressed and the effect factors on prognosis.Methods:A retrospective study was conducted on 124 patients who were pathologically diagnosed as glioblastoma after surgery, and found tumor progressed during regularly follow-up at Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University between January 2009 and August 2017.There were 82 males and 42 females, aged 47.9 years(range: 19 to 75 years) .Patients were divided into local recurrence group(96 cases) and CSF spread group (28 cases) .Clinical data were recorded in detail and compared by independent sample t test or χ 2 test.Kaplan-Meier survival curves was used to demonstrated the distribution of progression free survival (PFS) overall survival (OS) and post progression survival (PPS), and differences between local recurrence and CSF spread groups were assessed by Log-rank test.Cox proportion hazard regression analysis was used to identify independent prognostic factors. Results:Logistics regression analysis showed ventricle entry was the only prognosis factor of CSF spread ( OR=2.667, 95 % CI: 1.128 to 6.304, P=0.025).No significant distinction was observed in PFS between CSF spread group and local recurrence group(7.0 months vs.9.3 months, P=0.066).However, OS and PPS were substantially shortened in CSF spread group (13.0 months vs.23.0 months, P=0.011; 6.0 months vs.11.0 months, P=0.022, respectively).Mutations of isocitrate dehydrogenase gene, distant spread, gross-total resection, Ki-67 index>30% were independent prognostic factors of GBM patients. Conclusions:Ventricle entry is a prognosis factor for CSF spread, after which the median OS and PPS are markedly diminished.However, ventricle entry is not independent prognosis factor shortening survival.

Objective:To analyze the prognosis factors of cerebrospinal fluid (CSF) spread after surgery in glioblastoma (GBM) patients when tumors progressed and the effect factors on prognosis.Methods:A retrospective study was conducted on 124 patients who were pathologically diagnosed as glioblastoma after surgery, and found tumor progressed during regularly follow-up at Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University between January 2009 and August 2017.There were 82 males and 42 females, aged 47.9 years(range: 19 to 75 years) .Patients were divided into local recurrence group(96 cases) and CSF spread group (28 cases) .Clinical data were recorded in detail and compared by independent sample t test or χ 2 test.Kaplan-Meier survival curves was used to demonstrated the distribution of progression free survival (PFS) overall survival (OS) and post progression survival (PPS), and differences between local recurrence and CSF spread groups were assessed by Log-rank test.Cox proportion hazard regression analysis was used to identify independent prognostic factors. Results:Logistics regression analysis showed ventricle entry was the only prognosis factor of CSF spread ( OR=2.667, 95 % CI: 1.128 to 6.304, P=0.025).No significant distinction was observed in PFS between CSF spread group and local recurrence group(7.0 months vs.9.3 months, P=0.066).However, OS and PPS were substantially shortened in CSF spread group (13.0 months vs.23.0 months, P=0.011; 6.0 months vs.11.0 months, P=0.022, respectively).Mutations of isocitrate dehydrogenase gene, distant spread, gross-total resection, Ki-67 index>30% were independent prognostic factors of GBM patients. Conclusions:Ventricle entry is a prognosis factor for CSF spread, after which the median OS and PPS are markedly diminished.However, ventricle entry is not independent prognosis factor shortening survival.