The innovative study by Zhang et al published in the World Journal of Cardiology focused on predicting 30-day mortality in patients with acute myocardial infarction complicated by ventricular septal rupture at high al...The innovative study by Zhang et al published in the World Journal of Cardiology focused on predicting 30-day mortality in patients with acute myocardial infarction complicated by ventricular septal rupture at high altitudes.Based on a retrospective analysis of 48 patients from Yunnan Province,China,the authors identified four independent predictors of mortality:Age;Elevated uric acid levels;Interleukin-6 and decreased hemoglobin.Integrating these factors into a nomogram demonstrated high predictive accuracy(area under the curve=0.939).This model addressed the critical challenge of risk stratification in the resource-limited settings typical of high-altitude areas.This editorial underscored the practical value of the nomogram for timely identification of candidates for intensive therapy and surgical intervention while emphasizing the need for model validation in multicenter cohorts to optimize the management of these patients.展开更多
Cardiovascular diseases(CVD)remain a leading cause of mortality worldwide,highlighting the need for precise risk assessment tools to support clinical decision-making.This study introduces a meta-learning model for pre...Cardiovascular diseases(CVD)remain a leading cause of mortality worldwide,highlighting the need for precise risk assessment tools to support clinical decision-making.This study introduces a meta-learning model for predicting mortality risk in patients with CVD,classifying them into high-risk and low-risk groups.Data were collected from 868 patients at Tabriz Heart Hospital(THH)in Iran,along with two open-access datasets—the Cleveland Heart Disease(CHD)and Faisalabad Institute of Cardiology(FIC)datasets.Data preprocessing involved class balancing via the Synthetic Minority Over-Sampling Technique(SMOTE).Each dataset was then split into training and test sets,and 5-fold cross-validation was employed to validate generalizability.Several machine-learning algorithms were stacked as base classifiers to generate meta-features,which were then input to a meta-learner combining their predictive strengths through soft voting.An ablation experiment was performed to identify the optimal configuration with two base classifiers—Random Forest(RF)and Support Vector Machine(SVM)—and two boosting classifiers—AdaBoost(ADB)and XGBoost(XGB).The model achieved 88%accuracy,91%AUC,and 79.1%sensitivity on the THH dataset;82.77%accuracy,89.37%AUC,and 93.72%sensitivity on the CHD dataset;and 81.8%accuracy,82.8%AUC and 78.8%sensitivity the FIC dataset,demonstrating the model’s generalizability across diverse datasets.To further enhance interpretability,Shapley Additive Explanations(SHAP)were applied to quantify each attribute’s contribution to predicted CVD risk,providing both global and local insights to help clinicians identify key risk factors and guide personalized care.展开更多
Objective:This paper aims to address the clinical challenge of predicting the outcomes of stroke patients and proposes a comprehensive model called RGX to help clinicians adopt more personalized treatment plans.Impact...Objective:This paper aims to address the clinical challenge of predicting the outcomes of stroke patients and proposes a comprehensive model called RGX to help clinicians adopt more personalized treatment plans.Impact Statement:The comprehensive model is first proposed and applied to clinical datasets with missing data.The introduction of the Shapley additive explanations(SHAP)model to explain the impact of patient indicators on prognosis improves the accuracy of stroke patient mortality prediction.Introduction:At present,the prediction of stroke treatment outcomes faces many challenges,including the lack of models to quantify which clinical variables are closely related to patient survival.Methods:We developed a series of machine learning models to systematically predict the mortality of stroke patients.Additionally,by introducing the SHAP model,we revealed the contribution of risk factors to the prediction results.The performance of the models was evaluated using multiple metrics,including the area under the curve,accuracy,and specificity,to comprehensively measure the effectiveness and stability of the models.Results:The RGX model achieved an accuracy of 92.18%on the complete dataset,an improvement of 11.38%compared to that of the most advanced state-of-the-art model.Most importantly,the RGX model maintained excellent predictive ability even when faced with a dataset containing a large number of missing values,achieving an accuracy of 84.62%.Conclusion:In summary,the RGX ensemble model not only provides clinicians with a highly accurate predictive tool but also promotes the understanding of stroke patient survival prediction,laying a solid foundation for the development of precision medicine.展开更多
Shen et al’s retrospective study aims to compare the utility of two separate scoring systems for predicting mortality attributable to gastrointestinal(GI)injury in critically ill patients[the GI Dysfunction Score(GID...Shen et al’s retrospective study aims to compare the utility of two separate scoring systems for predicting mortality attributable to gastrointestinal(GI)injury in critically ill patients[the GI Dysfunction Score(GIDS)and the Acute Gastroin-testinal Injury(AGI)grade].The authors note that this study is the first proposal that suggests an equivalence between the ability of both scores to predict mor-tality at 28 days from intensive care unit(ICU)admission.Shen et al retrospec-tively analysed an ICU cohort of patients utilising two physicians administering both the AGI grade and GIDS score,using electronic healthcare records and ICU flowsheets.Where these physicians disagreed about the scores,the final decision as to the scores was made by an associate chief physician,or chief physician.We note that the primary reason for the development of GIDS was to create a clear score for GI dysfunction,with minimal subjectivity or inter-operator variability.The subjectivity inherent to the older AGI grading system is what ultimately led to the development of GIDS in 2021.By ensuring consensus between physicians administering the AGI,Shen et al have controlled for one of this grading systems biggest issues.We have concerns,however,that this does not represent the real-world challenges associated with applying the AGI compared to the newer GIDS,and wonder if this arbitration process had not been instituted,would the two scoring systems remain equivalent in terms of predicted mortality?展开更多
BACKGROUND The prognosis of critically ill patients is closely linked to their gastrointestinal(GI)function.The acute GI injury(AGI)grading system,established in 2012,is extensively utilized to evaluate GI dysfunction...BACKGROUND The prognosis of critically ill patients is closely linked to their gastrointestinal(GI)function.The acute GI injury(AGI)grading system,established in 2012,is extensively utilized to evaluate GI dysfunction and forecast outcomes in clinical settings.In 2021,the GI dysfunction score(GIDS)was developed,building on the AGI grading system,to enhance the accuracy of GI dysfunction severity assessment,improve prognostic predictions,reduce subjectivity,and increase reproducibility.AIM To compare the predictive capabilities of GIDS and the AGI grading system for 28-day mortality in critically ill patients.METHODS A retrospective study was conducted at the general intensive care unit(ICU)of a regional university hospital.All data were collected during the first week of ICU admission.The primary outcome was 28-day mortality.Multivariable logistic regression analyzed whether GIDS and AGI grade were independent risk factors for 28-day mortality.The predictive abilities of GIDS and AGI grade were compared using the receiver operating characteristic curve,with DeLong’s test assessing differences between the curves’areas.RESULTS The incidence of AGI in the first week of ICU admission was 92.13%.There were 85 deaths(47.75%)within 28 days of ICU admission.There was no initial 24-hour difference in GIDS between the non-survival and survival groups.Both GIDS(OR 2.01,95%CI:1.25-3.24;P=0.004)and AGI grade(OR 1.94,95%CI:1.12-3.38;P=0.019)were independent predictors of 28-day mortality.No significant difference was found between the predictive accuracy of GIDS and AGI grade for 28-day mortality during the first week of ICU admission(Z=-0.26,P=0.794).CONCLUSION GIDS within the first 24 hours was an unreliable predictor of 28-day mortality.The predictive accuracy for 28-day mortality from both systems during the first week was comparable.展开更多
Shandong Province, with a population of 84 million and located in the east coastline of China, is rich in natural resources and ranks middle in economic develpment of the whole nation. Around 90000 people are dead of ...Shandong Province, with a population of 84 million and located in the east coastline of China, is rich in natural resources and ranks middle in economic develpment of the whole nation. Around 90000 people are dead of cancer each year. In the recent twenty years, trends in malignant neoplasm展开更多
Objective To compare the validation of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) with the European system for cardiac operative risk evaluation (EuroSCORE) in patients undergoing off-pump coro...Objective To compare the validation of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) with the European system for cardiac operative risk evaluation (EuroSCORE) in patients undergoing off-pump coronary artery bypass (OPCAB) surgery in China. Methods Data of patients who underwent OPCAB between 2004 and 2005 in展开更多
Particularly commendable is the important work of Calvo,et al.[1]in comparing geriatric assessment tools to predict mortality and readmissions in elderly patients undergoing transcatheter aortic valve implantation(TAV...Particularly commendable is the important work of Calvo,et al.[1]in comparing geriatric assessment tools to predict mortality and readmissions in elderly patients undergoing transcatheter aortic valve implantation(TAVI).Their efforts underscore the growing importance of frailty assessment in cardiovascular risk stratification.We would like to respectfully highlight several areas that,if addressed in future studies(Figure 1),could further enhance the utility and inclusivity of these assessments.展开更多
Background Based on the China-VHD database,this study sought to develop and validate a Valvular Heart Disease-specific Age-adjusted Comorbidity Index(VHD-ACI)for predicting mortality risk in patients with VHD.Methods&...Background Based on the China-VHD database,this study sought to develop and validate a Valvular Heart Disease-specific Age-adjusted Comorbidity Index(VHD-ACI)for predicting mortality risk in patients with VHD.Methods&Results The China-VHD study was a nationwide,multi-centre multi-centre cohort study enrolling 13,917 patients with moderate or severe VHD across 46 medical centres in China between April-June 2018.After excluding cases with missing key variables,11,459 patients were retained for final analysis.The primary endpoint was 2-year all-cause mortality,with 941 deaths(10.0%)observed during follow-up.The VHD-ACI was derived after identifying 13 independent mortality predictors:cardiomyopathy,myocardial infarction,chronic obstructive pulmonary disease,pulmonary artery hypertension,low body weight,anaemia,hypoalbuminaemia,renal insufficiency,moderate/severe hepatic dysfunction,heart failure,cancer,NYHA functional class and age.The index exhibited good discrimination(AUC,0.79)and calibration(Brier score,0.062)in the total cohort,outperforming both EuroSCORE II and ACCI(P<0.001 for comparison).Internal validation through 100 bootstrap iterations yielded a C statistic of 0.694(95%CI:0.665−0.723)for 2-year mortality prediction.VHD-ACI scores,as a continuous variable(VHD-ACI score:adjusted HR(95%CI):1.263(1.245-1.282),P<0.001)or categorized using thresholds determined by the Yoden index(VHDACI≥9 vs.<9,adjusted HR(95%CI):6.216(5.378-7.184),P<0.001),were independently associated with mortality.The prognostic performance remained consistent across all VHD subtypes(aortic stenosis,aortic regurgitation,mitral stenosis,mitral regurgitation,tricuspid valve disease,mixed aortic/mitral valve disease and multiple VHD),and clinical subgroups stratified by therapeutic strategy,LVEF status(preserved vs.reduced),disease severity and etiology.Conclusion The VHD-ACI is a simple 13-comorbidity algorithm for the prediction of mortality in VHD patients and providing a simple and rapid tool for risk stratification.展开更多
Predicting mortality risk in the Intensive Care Unit(ICU)using Electronic Medical Records(EMR)is crucial for identifying patients in need of immediate attention.However,the incompleteness and the variability of EMR fe...Predicting mortality risk in the Intensive Care Unit(ICU)using Electronic Medical Records(EMR)is crucial for identifying patients in need of immediate attention.However,the incompleteness and the variability of EMR features for each patient make mortality prediction challenging.This study proposes a multimodal representation learning framework based on a novel personalized graph-based fusion approach to address these challenges.The proposed approach involves constructing patient-specific modality aggregation graphs to provide information about the features associated with each patient from incomplete multimodal data,enabling the effective and explainable fusion of the incomplete features.Modality-specific encoders are employed to encode each modality feature separately.To tackle the variability and incompleteness of input features among patients,a novel personalized graph-based fusion method is proposed to fuse patient-specific multimodal feature representations based on the constructed modality aggregation graphs.Furthermore,a MultiModal Gated Contrastive Representation Learning(MMGCRL)method is proposed to facilitate capturing adequate complementary information from multimodal representations and improve model performance.We evaluate the proposed framework using the large-scale ICU dataset,MIMIC-III.Experimental results demonstrate its effectiveness in mortality prediction,outperforming several state-of-the-art methods.展开更多
ICU patients are vulnerable to medications,especially infusion medications,and the rate and dosage of infusion drugs may worsen the condition.The mortality prediction model can monitor the real-time response of patien...ICU patients are vulnerable to medications,especially infusion medications,and the rate and dosage of infusion drugs may worsen the condition.The mortality prediction model can monitor the real-time response of patients to drug treatment,evaluate doctors’treatment plans to avoid severe situations such as inverse Drug-Drug Interactions(DDI),and facilitate the timely intervention and adjustment of doctor’s treatment plan.The treatment process of patients usually has a time-sequence relation(which usually has the missing data problem)in patients’treatment history.The state-of-the-art method to model such time-sequence is to use Recurrent Neural Network(RNN).However,sometimes,patients’treatment can last for a long period of time,which RNN may not fit for modelling long time sequence data.Therefore,we propose to use the heterogeneous medication events driven LSTM to predict the outcome of the patient,and the Natural Language Processing and Gaussian Process(GP),which can handle noisy,incomplete,sparse,heterogeneous and unevenly sampled patients’medication records.In our work,we emphasize the semantic meaning of each medication event and the sequence of the medication events on patients,while also handling the missing value problem using kernel-based Gaussian process.We compare the performance of LSTM and Phased-LSTM on modelling the outcome of patients’treatment and data imputation using kernel-based Gaussian process and conduct an empirical study on different data imputation approaches.展开更多
Traumatic brain injury（TBI）represents a global pandemic and is currently a leading cause of injury related death worldwide.Unfortunately,those who survive initial injury often suffer devastating functional,social,an...Traumatic brain injury（TBI）represents a global pandemic and is currently a leading cause of injury related death worldwide.Unfortunately,those who survive initial injury often suffer devastating functional,social,and economic consequences.展开更多
BACKGROUND Acute liver failure(ALF)in dengue is rare but fatal.Early identification of patients who are at risk of ALF is the key strategy to improve survival.AIM To validate prognostic scores for predicting ALF and i...BACKGROUND Acute liver failure(ALF)in dengue is rare but fatal.Early identification of patients who are at risk of ALF is the key strategy to improve survival.AIM To validate prognostic scores for predicting ALF and in-hospital mortality in dengue-induced severe hepatitis(DISH).METHODS We retrospectively reviewed 2532 dengue patients over a period of 16 years(2007-2022).Patients with DISH,defined as transaminases>10 times the normal reference level and DISH with subsequent ALF,were included.Univariate regre-ssion analysis was used to identify factors associated with outcomes.Youden’s index in conjunction with receiver operating characteristic(ROC)analysis was used to determine optimal cut-off values for prognostic scores in predicting ALF and in-hospital death.Area under the ROC(AUROC)curve values were compared using paired data nonparametric ROC curve estimation.RESULTS Of 193 DISH patients,20 developed ALF(0.79%),with a mortality rate of 60.0%.International normalized ratio,bilirubin,albumin,and creatinine were indepen-dent predictors associated with ALF and death.Prognostic scores showed excel-lent performance:Model for end-stage liver disease(MELD)score≥15 predicted ALF(AUROC 0.917,sensitivity 90.0%,specificity 88.4%)and≥18 predicted death(AUROC 0.823,sensitivity 86.9%,specificity 89.1%);easy albumin-bilirubin(ALBI)score≥-30 predicted ALF and death(ALF:AUROC 0.835,sensitivity80.0%,specificity 72.2%;death:AUROC 0.808,sensitivity 76.9%,specificity 69.3%);ALBI score≥-2 predicted ALF and death(ALF:AUROC 0.806,sensitivity 80.0%,specificity 77.4%;death:AUROC 0.799,sensitivity 76.9%,specificity 74.3%).Platelet-ALBI score also showed good performance in predicting ALF and death(AUROC=0.786 and 0.699,respectively).MELD and EZ-ALBI scores had similar performance in predicting ALF(Z=1.688,P=0.091)and death(Z=0.322,P=0.747).CONCLUSION MELD score is the best predictor of ALF and death in DISH patients.EZ-ALBI score,a simpler yet effective score,shows promise as an alternative prognostic tool in dengue patients.展开更多
Objective To evaluate the performance of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) on in hospital mortality and postoperative complications in patients undergoing coronary artery bypass grafti...Objective To evaluate the performance of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) on in hospital mortality and postoperative complications in patients undergoing coronary artery bypass grafting (CABG) in a single heart center. Methods From January 2007 to December 2008,clinical information of 201 consecutive patients undergoing isolated CABG in our hospital was collected. The SinoSCORE was used to展开更多
Life insurance companies,as equity stakeholders in policyholders’lives,have incentives to mitigate their health risks.I introduce a framework that enables life insurers to evaluate the financial viability of developi...Life insurance companies,as equity stakeholders in policyholders’lives,have incentives to mitigate their health risks.I introduce a framework that enables life insurers to evaluate the financial viability of developing and implementing health engagement programs.By leveraging a proprietary big database of health and mortality information from a large U.S.life insurer,I use machine learning techniques to quantify the benefits and use a rational addiction model to calculate the costs associated with these programs.The estimated net benefit available to the life insurer from the smoking cessation program is USD 87 million and the aggregate benefit from including other chronic conditions is USD 872 million.I explore the broader application of this framework in a general health policy context.展开更多
Objective To investigate the value of Sequential Organ Failure(SOFA)score and its dynamics(△SOFA)in predicting mortality in hematology care unit(HCU).Methods A retrospective clinical study was conducted on 79 critica...Objective To investigate the value of Sequential Organ Failure(SOFA)score and its dynamics(△SOFA)in predicting mortality in hematology care unit(HCU).Methods A retrospective clinical study was conducted on 79 critically ill hematologic patients admitted to the Center for Critical Care Medicine,Institute of Hematology&Blood Diseases Hospital,Chinese Academy of Medical Sciences,between May and June 2024.SOFA scores and△SOFA were calculated within 2 days before and after HCU admission.The predictive value of SOFA and ASOFA in mortality was assessed using receiver operating characteristic(ROC)curve analysis.Results Among the 79 patients,the HCU mortality rate was 54.4%.The SOFA scores on days 1-3(Dl,D2,and D3)and ASOFAon day 1(△D_1)of all patients,leukemia patients and hematopoietic stem cell transplantation(HSCT)patients were significantly higher in the death group compared with the non-death group(all P<0.05).ROC curve analysis revealed that the D_1,D_2,D_3 scores,and△D_1 significantly predicted mortality(P<0.001),with areas under the curve(AUCs)of 0.786,0.866,0.901,and 0.843,respectively.The sensitivity values were 74.36%,57.89%,62.85%,and 86.84%,while specificity values were 70%,100%,100%,and 67.65%,respectively.In the HSCT group,the D_-1,D_1,D_2,D_3,scores and△D_1 were predictive of HCU mortality,with AUCs of 0.833,0.794,0.871,0.846,and 0.795,respectively.Sensitivity values for these scores were 100%,85.71%,71.43%,57.14%,and 57.14%,while specificity values were 73.33%,70.59%,91.33%,100%,and 100%,respectively.In the leukemia group,the D_1,D_2,D_3 scores,and△D_1 were predictive of HCU mortality,with AUCs of 0.760,0.829,0.846,and 0.756,respectively.Sensitivityvalueswere71.43%,78.57%,53.85%,and 71.43%,while specificity values were 76.19%,78.95%,100%,and 63.16%,respectively.For all patients,the D_3 score exhibited the highest specificity,while the D_1 demonstrated the highest sensitivity.For patients in both the HSCT and leukemia groups,the sensitivity and specificity values of the D_1 and D_3 scores exceeded those of the D_1.Conclusion For patients with hematologic critical illness,including leukemia and those undergoing HSCT hospitalized in the HCU,D_1,D_2,D_3 scores and△D_1 are significantly associated with HCU mortality.展开更多
Background Precise estimation of current and future comorbidities of patients with cardiovascular disease is an important factor in prioritizing continuous physiological monitoring and new therapies.Machine learning(M...Background Precise estimation of current and future comorbidities of patients with cardiovascular disease is an important factor in prioritizing continuous physiological monitoring and new therapies.Machine learning(ML)models have shown satisfactory performance in short-term mortality prediction in patients with heart disease,whereas their utility in long-term predictions is limited.This study aimed to investigate the performance of tree-based ML models on long-term mortality prediction and effect of two recently introduced biomarkers on long-term mortality.Methods This study used publicly available data from the Collaboration Center of Health Information Appli-cation at the Ministry of Health and Welfare,Taiwan,China.The collected data were from patients admitted to the cardiac care unit for acute myocardial infarction(AMI)between November 2003 and September 2004.We collected and analyzed mortality data up to December 2018.Medical records were used to gather demo-graphic and clinical data,including age,gender,body mass index,percutaneous coronary intervention status,and comorbidities such as hypertension,dyslipidemia,ST-segment elevation myocardial infarction,and non-ST-segment elevation myocardial infarction.Using the data,collected from 139 patients with AMI,from medical and demographic records as well as two recently introduced biomarkers,brachial pre-ejection period(bPEP)and brachial ejection time(bET),we investigated the performance of advanced ensemble tree-based ML algorithms(random forest,AdaBoost,and XGBoost)to predict all-cause mortality within 14 years.A nested cross-validation was performed to evaluate and compare the performance of our developed models precisely with that of the conventional logistic regression(LR)as the baseline method.Results The developed ML models achieved significantly better performance compared to the baseline LR(C-Statistic,0.80 for random forest,0.79 for AdaBoost,and 0.78 for XGBoost,vs.0.77 for LR)(PRF<0.001,PAdaBoost<0.001,and PXGBoost<0.05).Adding bPEP and bET to our feature set significantly improved the performance of the algorithm,leading to an absolute increase in C-statistic of up to 0.03(C-statistic,0.83 for random forest,0.82 for AdaBoost,and 0.80 for XGBoost,vs.0.74 for LR)(PRF<0.001,PAdaBoost<0.001,PXGBoost<0.05).Conclusion The study indicates that incorporating new biomarkers into advanced ML models may significantly improve long-term mortality prediction in patients with cardiovascular diseases.This advancement may enable better treatment prioritization for high-risk individuals.展开更多
Background Acute myocarditis(AMC)can cause poor outcomes or even death in children.We aimed to identify AMC risk factors and create a mortality prediction model for AMC in children at hospital admission.Methods This w...Background Acute myocarditis(AMC)can cause poor outcomes or even death in children.We aimed to identify AMC risk factors and create a mortality prediction model for AMC in children at hospital admission.Methods This was a single-center retrospective cohort study of AMC children hospitalized between January 2016 and January 2020.The demographics,clinical examinations,types of AMC,and laboratory results were collected at hospital admission.In-hospital survival or death was documented.Clinical characteristics associated with death were evaluated.Results Among 67 children,51 survived,and 16 died.The most common symptom was digestive disorder(67.2%).Based on the Bayesian model averaging and Hosmer–Lemeshow test,we created a final best mortality prediction model(acute myocarditis death risk score,AMCDRS)that included ten variables(male sex,fever,congestive heart failure,left-ventricular ejection fraction<50%,pulmonary edema,ventricular tachycardia,lactic acid value>4,fulminant myocarditis,abnormal creatine kinase-MB,and hypotension).Despite differences in the characteristics of the validation cohort,the model discrimination was only marginally lower,with an AUC of 0.781(95%confidence interval=0.675–0.852)compared with the derivation cohort.Model calibration likewise indicated acceptable fit(Hosmer‒Lemeshow goodness-of-fit,P¼=0.10).Conclusions Multiple factors were associated with increased mortality in children with AMC.The prediction model AMCDRS might be used at hospital admission to accurately identify AMC in children who are at an increased risk of death.展开更多
BACKGROUND： Post-transplant model for predicting mortality（PMPM, calculated as-5.359＋1.988×ln（serum creatinine [mg/d L]）＋1.089×ln（total bilirubin [mg/d L]）） score has been proved to be a simple and ...BACKGROUND： Post-transplant model for predicting mortality（PMPM, calculated as-5.359＋1.988×ln（serum creatinine [mg/d L]）＋1.089×ln（total bilirubin [mg/d L]）） score has been proved to be a simple and accurate model for predicting the prognosis after liver transplantation（LT） in a single center study. Here we aim to verify this model in a large cohort of patients.METHODS： A total of 2727 patients undergoing LT with endstage liver cirrhosis from January 2003 to December 2010 were included in this retrospective study. Data were collected from the China Liver Transplant Registry（CLTR）. PMPM score was calculated at 24-h and 7-d following LT. According to the PMPM score at 24-h, all patients were divided into the low-risk group（PMPM score ≤-1.4, n=2509） and the high-risk group（PMPM score 〉-1.4, n=218）. The area under receiver operator characteristic curve（AUROC） was calculated for evaluating the prognostic accuracy.RESULTS： The 1-, 3-, and 5-year patient survival rates in the low-risk group were significantly higher than those in the high-risk group（90.23%, 88.01%, and 86.03% vs 63.16%, 59.62%, and 56.43%, respectively, P〈0.001）. In the high-risk group, 131 patients had a decreased PMPM score（≤-1.4） at 7-d, and their cumulative survival rate was significantly higher than the other 87 patients with sustained high PMPM score（〉-1.4）（P〈0.001）. For predicting 3-month mortality, PMPM score showed a much higher AUROC than post-transplant MELD score（P〈0.05）.CONCLUSION： PMPM score is a simple and effective tool to predict short-term mortality after liver transplantation in patients with benign liver diseases, and an indicator for prompt salvaging treatment as well.展开更多
Coronavirus disease 2019(COVID-19)has become a worldwide pandemic.Hospitalized patients of COVID-19 suffer from a high mortality rate,motivating the development of convenient and practical methods that allow clinician...Coronavirus disease 2019(COVID-19)has become a worldwide pandemic.Hospitalized patients of COVID-19 suffer from a high mortality rate,motivating the development of convenient and practical methods that allow clinicians to promptly identify high-risk patients.Here,we have developed a risk score using clinical data from 1479 inpatients admitted to Tongji Hospital,Wuhan,China(development cohort)and externally validated with data from two other centers:141 inpatients from Jinyintan Hospital,Wuhan,China(validation cohort 1)and 432 inpatients from The Third People’s Hospital of Shenzhen,Shenzhen,China(validation cohort 2).The risk score is based on three biomarkers that are readily available in routine blood samples and can easily be translated into a probability of death.The risk score can predict the mortality of individual patients more than 12 d in advance with more than 90%accuracy across all cohorts.Moreover,the Kaplan-Meier score shows that patients can be clearly differentiated upon admission as low,intermediate,or high risk,with an area under the curve(AUC)score of 0.9551.In summary,a simple risk score has been validated to predict death in patients infected with severe acute respiratory syndrome coronavirus 2(SARS-CoV-2);it has also been validated in independent cohorts.展开更多
文摘The innovative study by Zhang et al published in the World Journal of Cardiology focused on predicting 30-day mortality in patients with acute myocardial infarction complicated by ventricular septal rupture at high altitudes.Based on a retrospective analysis of 48 patients from Yunnan Province,China,the authors identified four independent predictors of mortality:Age;Elevated uric acid levels;Interleukin-6 and decreased hemoglobin.Integrating these factors into a nomogram demonstrated high predictive accuracy(area under the curve=0.939).This model addressed the critical challenge of risk stratification in the resource-limited settings typical of high-altitude areas.This editorial underscored the practical value of the nomogram for timely identification of candidates for intensive therapy and surgical intervention while emphasizing the need for model validation in multicenter cohorts to optimize the management of these patients.
文摘Cardiovascular diseases(CVD)remain a leading cause of mortality worldwide,highlighting the need for precise risk assessment tools to support clinical decision-making.This study introduces a meta-learning model for predicting mortality risk in patients with CVD,classifying them into high-risk and low-risk groups.Data were collected from 868 patients at Tabriz Heart Hospital(THH)in Iran,along with two open-access datasets—the Cleveland Heart Disease(CHD)and Faisalabad Institute of Cardiology(FIC)datasets.Data preprocessing involved class balancing via the Synthetic Minority Over-Sampling Technique(SMOTE).Each dataset was then split into training and test sets,and 5-fold cross-validation was employed to validate generalizability.Several machine-learning algorithms were stacked as base classifiers to generate meta-features,which were then input to a meta-learner combining their predictive strengths through soft voting.An ablation experiment was performed to identify the optimal configuration with two base classifiers—Random Forest(RF)and Support Vector Machine(SVM)—and two boosting classifiers—AdaBoost(ADB)and XGBoost(XGB).The model achieved 88%accuracy,91%AUC,and 79.1%sensitivity on the THH dataset;82.77%accuracy,89.37%AUC,and 93.72%sensitivity on the CHD dataset;and 81.8%accuracy,82.8%AUC and 78.8%sensitivity the FIC dataset,demonstrating the model’s generalizability across diverse datasets.To further enhance interpretability,Shapley Additive Explanations(SHAP)were applied to quantify each attribute’s contribution to predicted CVD risk,providing both global and local insights to help clinicians identify key risk factors and guide personalized care.
基金supported by the Beijing Municipal Natural Science Foundation(7244510).
文摘Objective:This paper aims to address the clinical challenge of predicting the outcomes of stroke patients and proposes a comprehensive model called RGX to help clinicians adopt more personalized treatment plans.Impact Statement:The comprehensive model is first proposed and applied to clinical datasets with missing data.The introduction of the Shapley additive explanations(SHAP)model to explain the impact of patient indicators on prognosis improves the accuracy of stroke patient mortality prediction.Introduction:At present,the prediction of stroke treatment outcomes faces many challenges,including the lack of models to quantify which clinical variables are closely related to patient survival.Methods:We developed a series of machine learning models to systematically predict the mortality of stroke patients.Additionally,by introducing the SHAP model,we revealed the contribution of risk factors to the prediction results.The performance of the models was evaluated using multiple metrics,including the area under the curve,accuracy,and specificity,to comprehensively measure the effectiveness and stability of the models.Results:The RGX model achieved an accuracy of 92.18%on the complete dataset,an improvement of 11.38%compared to that of the most advanced state-of-the-art model.Most importantly,the RGX model maintained excellent predictive ability even when faced with a dataset containing a large number of missing values,achieving an accuracy of 84.62%.Conclusion:In summary,the RGX ensemble model not only provides clinicians with a highly accurate predictive tool but also promotes the understanding of stroke patient survival prediction,laying a solid foundation for the development of precision medicine.
文摘Shen et al’s retrospective study aims to compare the utility of two separate scoring systems for predicting mortality attributable to gastrointestinal(GI)injury in critically ill patients[the GI Dysfunction Score(GIDS)and the Acute Gastroin-testinal Injury(AGI)grade].The authors note that this study is the first proposal that suggests an equivalence between the ability of both scores to predict mor-tality at 28 days from intensive care unit(ICU)admission.Shen et al retrospec-tively analysed an ICU cohort of patients utilising two physicians administering both the AGI grade and GIDS score,using electronic healthcare records and ICU flowsheets.Where these physicians disagreed about the scores,the final decision as to the scores was made by an associate chief physician,or chief physician.We note that the primary reason for the development of GIDS was to create a clear score for GI dysfunction,with minimal subjectivity or inter-operator variability.The subjectivity inherent to the older AGI grading system is what ultimately led to the development of GIDS in 2021.By ensuring consensus between physicians administering the AGI,Shen et al have controlled for one of this grading systems biggest issues.We have concerns,however,that this does not represent the real-world challenges associated with applying the AGI compared to the newer GIDS,and wonder if this arbitration process had not been instituted,would the two scoring systems remain equivalent in terms of predicted mortality?
基金approved by the Ethics Committee of the First Affiliated Hospital of Zhejiang Chinese Medical University(No.2024-KLS-369-02).
文摘BACKGROUND The prognosis of critically ill patients is closely linked to their gastrointestinal(GI)function.The acute GI injury(AGI)grading system,established in 2012,is extensively utilized to evaluate GI dysfunction and forecast outcomes in clinical settings.In 2021,the GI dysfunction score(GIDS)was developed,building on the AGI grading system,to enhance the accuracy of GI dysfunction severity assessment,improve prognostic predictions,reduce subjectivity,and increase reproducibility.AIM To compare the predictive capabilities of GIDS and the AGI grading system for 28-day mortality in critically ill patients.METHODS A retrospective study was conducted at the general intensive care unit(ICU)of a regional university hospital.All data were collected during the first week of ICU admission.The primary outcome was 28-day mortality.Multivariable logistic regression analyzed whether GIDS and AGI grade were independent risk factors for 28-day mortality.The predictive abilities of GIDS and AGI grade were compared using the receiver operating characteristic curve,with DeLong’s test assessing differences between the curves’areas.RESULTS The incidence of AGI in the first week of ICU admission was 92.13%.There were 85 deaths(47.75%)within 28 days of ICU admission.There was no initial 24-hour difference in GIDS between the non-survival and survival groups.Both GIDS(OR 2.01,95%CI:1.25-3.24;P=0.004)and AGI grade(OR 1.94,95%CI:1.12-3.38;P=0.019)were independent predictors of 28-day mortality.No significant difference was found between the predictive accuracy of GIDS and AGI grade for 28-day mortality during the first week of ICU admission(Z=-0.26,P=0.794).CONCLUSION GIDS within the first 24 hours was an unreliable predictor of 28-day mortality.The predictive accuracy for 28-day mortality from both systems during the first week was comparable.
文摘Shandong Province, with a population of 84 million and located in the east coastline of China, is rich in natural resources and ranks middle in economic develpment of the whole nation. Around 90000 people are dead of cancer each year. In the recent twenty years, trends in malignant neoplasm
文摘Objective To compare the validation of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) with the European system for cardiac operative risk evaluation (EuroSCORE) in patients undergoing off-pump coronary artery bypass (OPCAB) surgery in China. Methods Data of patients who underwent OPCAB between 2004 and 2005 in
文摘Particularly commendable is the important work of Calvo,et al.[1]in comparing geriatric assessment tools to predict mortality and readmissions in elderly patients undergoing transcatheter aortic valve implantation(TAVI).Their efforts underscore the growing importance of frailty assessment in cardiovascular risk stratification.We would like to respectfully highlight several areas that,if addressed in future studies(Figure 1),could further enhance the utility and inclusivity of these assessments.
基金supported by the Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences(No.2017-12M-3-002)the National Key R&D Program of China(No.2020YFC2008100).
文摘Background Based on the China-VHD database,this study sought to develop and validate a Valvular Heart Disease-specific Age-adjusted Comorbidity Index(VHD-ACI)for predicting mortality risk in patients with VHD.Methods&Results The China-VHD study was a nationwide,multi-centre multi-centre cohort study enrolling 13,917 patients with moderate or severe VHD across 46 medical centres in China between April-June 2018.After excluding cases with missing key variables,11,459 patients were retained for final analysis.The primary endpoint was 2-year all-cause mortality,with 941 deaths(10.0%)observed during follow-up.The VHD-ACI was derived after identifying 13 independent mortality predictors:cardiomyopathy,myocardial infarction,chronic obstructive pulmonary disease,pulmonary artery hypertension,low body weight,anaemia,hypoalbuminaemia,renal insufficiency,moderate/severe hepatic dysfunction,heart failure,cancer,NYHA functional class and age.The index exhibited good discrimination(AUC,0.79)and calibration(Brier score,0.062)in the total cohort,outperforming both EuroSCORE II and ACCI(P<0.001 for comparison).Internal validation through 100 bootstrap iterations yielded a C statistic of 0.694(95%CI:0.665−0.723)for 2-year mortality prediction.VHD-ACI scores,as a continuous variable(VHD-ACI score:adjusted HR(95%CI):1.263(1.245-1.282),P<0.001)or categorized using thresholds determined by the Yoden index(VHDACI≥9 vs.<9,adjusted HR(95%CI):6.216(5.378-7.184),P<0.001),were independently associated with mortality.The prognostic performance remained consistent across all VHD subtypes(aortic stenosis,aortic regurgitation,mitral stenosis,mitral regurgitation,tricuspid valve disease,mixed aortic/mitral valve disease and multiple VHD),and clinical subgroups stratified by therapeutic strategy,LVEF status(preserved vs.reduced),disease severity and etiology.Conclusion The VHD-ACI is a simple 13-comorbidity algorithm for the prediction of mortality in VHD patients and providing a simple and rapid tool for risk stratification.
基金supported by the National Natural Science Foundation of China(No.U24A20256)and the Science and Technology Major Project of Changsha(No.kh2402004).
文摘Predicting mortality risk in the Intensive Care Unit(ICU)using Electronic Medical Records(EMR)is crucial for identifying patients in need of immediate attention.However,the incompleteness and the variability of EMR features for each patient make mortality prediction challenging.This study proposes a multimodal representation learning framework based on a novel personalized graph-based fusion approach to address these challenges.The proposed approach involves constructing patient-specific modality aggregation graphs to provide information about the features associated with each patient from incomplete multimodal data,enabling the effective and explainable fusion of the incomplete features.Modality-specific encoders are employed to encode each modality feature separately.To tackle the variability and incompleteness of input features among patients,a novel personalized graph-based fusion method is proposed to fuse patient-specific multimodal feature representations based on the constructed modality aggregation graphs.Furthermore,a MultiModal Gated Contrastive Representation Learning(MMGCRL)method is proposed to facilitate capturing adequate complementary information from multimodal representations and improve model performance.We evaluate the proposed framework using the large-scale ICU dataset,MIMIC-III.Experimental results demonstrate its effectiveness in mortality prediction,outperforming several state-of-the-art methods.
基金This research is supported by Natural Science Foundation of Hunan Province(No.2019JJ40145)Scientific Research Key Project of Hunan Education Department(No.19A273)Open Fund of Key Laboratory of Hunan Province(2017TP1026).
文摘ICU patients are vulnerable to medications,especially infusion medications,and the rate and dosage of infusion drugs may worsen the condition.The mortality prediction model can monitor the real-time response of patients to drug treatment,evaluate doctors’treatment plans to avoid severe situations such as inverse Drug-Drug Interactions(DDI),and facilitate the timely intervention and adjustment of doctor’s treatment plan.The treatment process of patients usually has a time-sequence relation(which usually has the missing data problem)in patients’treatment history.The state-of-the-art method to model such time-sequence is to use Recurrent Neural Network(RNN).However,sometimes,patients’treatment can last for a long period of time,which RNN may not fit for modelling long time sequence data.Therefore,we propose to use the heterogeneous medication events driven LSTM to predict the outcome of the patient,and the Natural Language Processing and Gaussian Process(GP),which can handle noisy,incomplete,sparse,heterogeneous and unevenly sampled patients’medication records.In our work,we emphasize the semantic meaning of each medication event and the sequence of the medication events on patients,while also handling the missing value problem using kernel-based Gaussian process.We compare the performance of LSTM and Phased-LSTM on modelling the outcome of patients’treatment and data imputation using kernel-based Gaussian process and conduct an empirical study on different data imputation approaches.
文摘Traumatic brain injury（TBI）represents a global pandemic and is currently a leading cause of injury related death worldwide.Unfortunately,those who survive initial injury often suffer devastating functional,social,and economic consequences.
基金Supported by the Fatty Liver Unit,Foundation of the Faculty of Medicine,Chulalongkorn University.
文摘BACKGROUND Acute liver failure(ALF)in dengue is rare but fatal.Early identification of patients who are at risk of ALF is the key strategy to improve survival.AIM To validate prognostic scores for predicting ALF and in-hospital mortality in dengue-induced severe hepatitis(DISH).METHODS We retrospectively reviewed 2532 dengue patients over a period of 16 years(2007-2022).Patients with DISH,defined as transaminases>10 times the normal reference level and DISH with subsequent ALF,were included.Univariate regre-ssion analysis was used to identify factors associated with outcomes.Youden’s index in conjunction with receiver operating characteristic(ROC)analysis was used to determine optimal cut-off values for prognostic scores in predicting ALF and in-hospital death.Area under the ROC(AUROC)curve values were compared using paired data nonparametric ROC curve estimation.RESULTS Of 193 DISH patients,20 developed ALF(0.79%),with a mortality rate of 60.0%.International normalized ratio,bilirubin,albumin,and creatinine were indepen-dent predictors associated with ALF and death.Prognostic scores showed excel-lent performance:Model for end-stage liver disease(MELD)score≥15 predicted ALF(AUROC 0.917,sensitivity 90.0%,specificity 88.4%)and≥18 predicted death(AUROC 0.823,sensitivity 86.9%,specificity 89.1%);easy albumin-bilirubin(ALBI)score≥-30 predicted ALF and death(ALF:AUROC 0.835,sensitivity80.0%,specificity 72.2%;death:AUROC 0.808,sensitivity 76.9%,specificity 69.3%);ALBI score≥-2 predicted ALF and death(ALF:AUROC 0.806,sensitivity 80.0%,specificity 77.4%;death:AUROC 0.799,sensitivity 76.9%,specificity 74.3%).Platelet-ALBI score also showed good performance in predicting ALF and death(AUROC=0.786 and 0.699,respectively).MELD and EZ-ALBI scores had similar performance in predicting ALF(Z=1.688,P=0.091)and death(Z=0.322,P=0.747).CONCLUSION MELD score is the best predictor of ALF and death in DISH patients.EZ-ALBI score,a simpler yet effective score,shows promise as an alternative prognostic tool in dengue patients.
文摘Objective To evaluate the performance of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) on in hospital mortality and postoperative complications in patients undergoing coronary artery bypass grafting (CABG) in a single heart center. Methods From January 2007 to December 2008,clinical information of 201 consecutive patients undergoing isolated CABG in our hospital was collected. The SinoSCORE was used to
文摘Life insurance companies,as equity stakeholders in policyholders’lives,have incentives to mitigate their health risks.I introduce a framework that enables life insurers to evaluate the financial viability of developing and implementing health engagement programs.By leveraging a proprietary big database of health and mortality information from a large U.S.life insurer,I use machine learning techniques to quantify the benefits and use a rational addiction model to calculate the costs associated with these programs.The estimated net benefit available to the life insurer from the smoking cessation program is USD 87 million and the aggregate benefit from including other chronic conditions is USD 872 million.I explore the broader application of this framework in a general health policy context.
文摘Objective To investigate the value of Sequential Organ Failure(SOFA)score and its dynamics(△SOFA)in predicting mortality in hematology care unit(HCU).Methods A retrospective clinical study was conducted on 79 critically ill hematologic patients admitted to the Center for Critical Care Medicine,Institute of Hematology&Blood Diseases Hospital,Chinese Academy of Medical Sciences,between May and June 2024.SOFA scores and△SOFA were calculated within 2 days before and after HCU admission.The predictive value of SOFA and ASOFA in mortality was assessed using receiver operating characteristic(ROC)curve analysis.Results Among the 79 patients,the HCU mortality rate was 54.4%.The SOFA scores on days 1-3(Dl,D2,and D3)and ASOFAon day 1(△D_1)of all patients,leukemia patients and hematopoietic stem cell transplantation(HSCT)patients were significantly higher in the death group compared with the non-death group(all P<0.05).ROC curve analysis revealed that the D_1,D_2,D_3 scores,and△D_1 significantly predicted mortality(P<0.001),with areas under the curve(AUCs)of 0.786,0.866,0.901,and 0.843,respectively.The sensitivity values were 74.36%,57.89%,62.85%,and 86.84%,while specificity values were 70%,100%,100%,and 67.65%,respectively.In the HSCT group,the D_-1,D_1,D_2,D_3,scores and△D_1 were predictive of HCU mortality,with AUCs of 0.833,0.794,0.871,0.846,and 0.795,respectively.Sensitivity values for these scores were 100%,85.71%,71.43%,57.14%,and 57.14%,while specificity values were 73.33%,70.59%,91.33%,100%,and 100%,respectively.In the leukemia group,the D_1,D_2,D_3 scores,and△D_1 were predictive of HCU mortality,with AUCs of 0.760,0.829,0.846,and 0.756,respectively.Sensitivityvalueswere71.43%,78.57%,53.85%,and 71.43%,while specificity values were 76.19%,78.95%,100%,and 63.16%,respectively.For all patients,the D_3 score exhibited the highest specificity,while the D_1 demonstrated the highest sensitivity.For patients in both the HSCT and leukemia groups,the sensitivity and specificity values of the D_1 and D_3 scores exceeded those of the D_1.Conclusion For patients with hematologic critical illness,including leukemia and those undergoing HSCT hospitalized in the HCU,D_1,D_2,D_3 scores and△D_1 are significantly associated with HCU mortality.
文摘Background Precise estimation of current and future comorbidities of patients with cardiovascular disease is an important factor in prioritizing continuous physiological monitoring and new therapies.Machine learning(ML)models have shown satisfactory performance in short-term mortality prediction in patients with heart disease,whereas their utility in long-term predictions is limited.This study aimed to investigate the performance of tree-based ML models on long-term mortality prediction and effect of two recently introduced biomarkers on long-term mortality.Methods This study used publicly available data from the Collaboration Center of Health Information Appli-cation at the Ministry of Health and Welfare,Taiwan,China.The collected data were from patients admitted to the cardiac care unit for acute myocardial infarction(AMI)between November 2003 and September 2004.We collected and analyzed mortality data up to December 2018.Medical records were used to gather demo-graphic and clinical data,including age,gender,body mass index,percutaneous coronary intervention status,and comorbidities such as hypertension,dyslipidemia,ST-segment elevation myocardial infarction,and non-ST-segment elevation myocardial infarction.Using the data,collected from 139 patients with AMI,from medical and demographic records as well as two recently introduced biomarkers,brachial pre-ejection period(bPEP)and brachial ejection time(bET),we investigated the performance of advanced ensemble tree-based ML algorithms(random forest,AdaBoost,and XGBoost)to predict all-cause mortality within 14 years.A nested cross-validation was performed to evaluate and compare the performance of our developed models precisely with that of the conventional logistic regression(LR)as the baseline method.Results The developed ML models achieved significantly better performance compared to the baseline LR(C-Statistic,0.80 for random forest,0.79 for AdaBoost,and 0.78 for XGBoost,vs.0.77 for LR)(PRF<0.001,PAdaBoost<0.001,and PXGBoost<0.05).Adding bPEP and bET to our feature set significantly improved the performance of the algorithm,leading to an absolute increase in C-statistic of up to 0.03(C-statistic,0.83 for random forest,0.82 for AdaBoost,and 0.80 for XGBoost,vs.0.74 for LR)(PRF<0.001,PAdaBoost<0.001,PXGBoost<0.05).Conclusion The study indicates that incorporating new biomarkers into advanced ML models may significantly improve long-term mortality prediction in patients with cardiovascular diseases.This advancement may enable better treatment prioritization for high-risk individuals.
基金Shanghai Top Priority Clinical Medical Center Project(No.2017ZZ01008-001).
文摘Background Acute myocarditis(AMC)can cause poor outcomes or even death in children.We aimed to identify AMC risk factors and create a mortality prediction model for AMC in children at hospital admission.Methods This was a single-center retrospective cohort study of AMC children hospitalized between January 2016 and January 2020.The demographics,clinical examinations,types of AMC,and laboratory results were collected at hospital admission.In-hospital survival or death was documented.Clinical characteristics associated with death were evaluated.Results Among 67 children,51 survived,and 16 died.The most common symptom was digestive disorder(67.2%).Based on the Bayesian model averaging and Hosmer–Lemeshow test,we created a final best mortality prediction model(acute myocarditis death risk score,AMCDRS)that included ten variables(male sex,fever,congestive heart failure,left-ventricular ejection fraction<50%,pulmonary edema,ventricular tachycardia,lactic acid value>4,fulminant myocarditis,abnormal creatine kinase-MB,and hypotension).Despite differences in the characteristics of the validation cohort,the model discrimination was only marginally lower,with an AUC of 0.781(95%confidence interval=0.675–0.852)compared with the derivation cohort.Model calibration likewise indicated acceptable fit(Hosmer‒Lemeshow goodness-of-fit,P¼=0.10).Conclusions Multiple factors were associated with increased mortality in children with AMC.The prediction model AMCDRS might be used at hospital admission to accurately identify AMC in children who are at an increased risk of death.
基金supported by grants from the Cheung Kong Scholars Programthe Youth Science and Technology Innovation Leader Program of Science Technology Ministrythe Projects of Medical and Health Technology Program in Zhejiang Province(2017RC002)
文摘BACKGROUND： Post-transplant model for predicting mortality（PMPM, calculated as-5.359＋1.988×ln（serum creatinine [mg/d L]）＋1.089×ln（total bilirubin [mg/d L]）） score has been proved to be a simple and accurate model for predicting the prognosis after liver transplantation（LT） in a single center study. Here we aim to verify this model in a large cohort of patients.METHODS： A total of 2727 patients undergoing LT with endstage liver cirrhosis from January 2003 to December 2010 were included in this retrospective study. Data were collected from the China Liver Transplant Registry（CLTR）. PMPM score was calculated at 24-h and 7-d following LT. According to the PMPM score at 24-h, all patients were divided into the low-risk group（PMPM score ≤-1.4, n=2509） and the high-risk group（PMPM score 〉-1.4, n=218）. The area under receiver operator characteristic curve（AUROC） was calculated for evaluating the prognostic accuracy.RESULTS： The 1-, 3-, and 5-year patient survival rates in the low-risk group were significantly higher than those in the high-risk group（90.23%, 88.01%, and 86.03% vs 63.16%, 59.62%, and 56.43%, respectively, P〈0.001）. In the high-risk group, 131 patients had a decreased PMPM score（≤-1.4） at 7-d, and their cumulative survival rate was significantly higher than the other 87 patients with sustained high PMPM score（〉-1.4）（P〈0.001）. For predicting 3-month mortality, PMPM score showed a much higher AUROC than post-transplant MELD score（P〈0.05）.CONCLUSION： PMPM score is a simple and effective tool to predict short-term mortality after liver transplantation in patients with benign liver diseases, and an indicator for prompt salvaging treatment as well.
基金supported by the Special Fund for Novel Coronavirus Pneumonia from the Department of Science and Technology of Hubei Province(2020FCA035)the Fundamental Research Funds for the Central Universities,Huazhong University of Science and Technology(2020kfyXGYJ023).
文摘Coronavirus disease 2019(COVID-19)has become a worldwide pandemic.Hospitalized patients of COVID-19 suffer from a high mortality rate,motivating the development of convenient and practical methods that allow clinicians to promptly identify high-risk patients.Here,we have developed a risk score using clinical data from 1479 inpatients admitted to Tongji Hospital,Wuhan,China(development cohort)and externally validated with data from two other centers:141 inpatients from Jinyintan Hospital,Wuhan,China(validation cohort 1)and 432 inpatients from The Third People’s Hospital of Shenzhen,Shenzhen,China(validation cohort 2).The risk score is based on three biomarkers that are readily available in routine blood samples and can easily be translated into a probability of death.The risk score can predict the mortality of individual patients more than 12 d in advance with more than 90%accuracy across all cohorts.Moreover,the Kaplan-Meier score shows that patients can be clearly differentiated upon admission as low,intermediate,or high risk,with an area under the curve(AUC)score of 0.9551.In summary,a simple risk score has been validated to predict death in patients infected with severe acute respiratory syndrome coronavirus 2(SARS-CoV-2);it has also been validated in independent cohorts.
