BACKGROUND The electrocardiogram(ECG)is an inexpensive and easily accessible investigation for the diagnosis of cardiovascular diseases including heart failure(HF).The application of artificial intelligence(AI)has con...BACKGROUND The electrocardiogram(ECG)is an inexpensive and easily accessible investigation for the diagnosis of cardiovascular diseases including heart failure(HF).The application of artificial intelligence(AI)has contributed to clinical practice in terms of aiding diagnosis,prognosis,risk stratification and guiding clinical management.The aim of this study is to systematically review and perform a meta-analysis of published studies on the application of AI for HF detection based on the ECG.METHODS We searched Embase,PubMed and Web of Science databases to identify literature using AI for HF detection based on ECG data.The quality of included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2(QUADAS-2)criteria.Random-effects models were used for calculating the effect estimates and hierarchical receiver operating characteristic curves were plotted.Subgroup analysis was performed.Heterogeneity and the risk of bias were also assessed.RESULTS A total of 11 studies including 104,737 subjects were included.The area under the curve for HF diagnosis was 0.986,with a corresponding pooled sensitivity of 0.95(95%CI:0.86–0.98),specificity of 0.98(95%CI:0.95–0.99)and diagnostic odds ratio of 831.51(95%CI:127.85–5407.74).In the patient selection domain of QUADAS-2,eight studies were designated as high risk.CONCLUSIONS According to the available evidence,the incorporation of AI can aid the diagnosis of HF.However,there is heterogeneity among machine learning algorithms and improvements are required in terms of quality and study design.展开更多
To the Editor:Chronic kidney disease(CKD)is a global burden of the public health.The global prevalence of CKD exceeded 10%while the awareness was around 10%.[1]In the era of big data,improving the identification of CK...To the Editor:Chronic kidney disease(CKD)is a global burden of the public health.The global prevalence of CKD exceeded 10%while the awareness was around 10%.[1]In the era of big data,improving the identification of CKD using informatic tools is important.Computable phenotype is proven as an efficient tool to facilitate the process of patient identification using electronic health record(EHR)data.展开更多
Health data and cutting-edge technologies empower medicine and improve healthcare.It has become even more true during the COVID-19 pandemic.Through coronavirus data sharing and worldwide collaboration,the speed of vac...Health data and cutting-edge technologies empower medicine and improve healthcare.It has become even more true during the COVID-19 pandemic.Through coronavirus data sharing and worldwide collaboration,the speed of vaccine development for COVID-19 is unprecedented.Digital and data technologies were quickly adopted during the pandemic,showing how those technologies can be harnessed to enhance public health and healthcare.A wide range of digital data sources are being utilized and visually presented to enhance the epidemiological surveillance of COVID-19.Digital contact tracing mobile apps have been adopted by many countries to control community transmission.Deep learning has been utilized to achieve various solutions for COVID-19 disruption,including outbreak prediction,virus spread tracking.展开更多
1.Introduction Clinician-scientists have a unique strength in translational research and medical advances that improve the quality of care and patient outcomes.As big data analytics and advanced technologies such as a...1.Introduction Clinician-scientists have a unique strength in translational research and medical advances that improve the quality of care and patient outcomes.As big data analytics and advanced technologies such as artificial intelligence are being continuously applied in the healthcare scenario,it not only transforms patient care but also creates tremendous opportunities for data-driven discoveries.In a digital health era,clinicianscientists proficient in data science knowledge——that is clinician data scientists——are central to harnessing the power of big data analytics and advanced technologies in medicine.展开更多
Epstein-Barr virus(EBV)reactivation is one of the most important infections after hematopoietic stem cell transplantation(HSCT)using haplo-identical related donors(HID).We aimed to establish a comprehensive model with...Epstein-Barr virus(EBV)reactivation is one of the most important infections after hematopoietic stem cell transplantation(HSCT)using haplo-identical related donors(HID).We aimed to establish a comprehensive model with machine learning,which could predict EBV reactivation after HID HSCT with anti-thymocyte globulin(ATG)for graft-versus-host disease(GVHD)prophylaxis.We enrolled 470 consecutive acute leukemia patients,60%of them(n=282)randomly selected as a training cohort,the remaining 40%(n=188)as a validation cohort.The equation was as follows:Probability(EBV reactivation)=1/1+exp(−Y),where Y=0.0250×(age)–0.3614×(gender)+0.0668×(underlying disease)–0.6297×(disease status before HSCT)–0.0726×(disease risk index)–0.0118×(hematopoietic cell transplantation-specific comorbidity index[HCT-CI]score)+1.2037×(human leukocyte antigen disparity)+0.5347×(EBV serostatus)+0.1605×(conditioning regimen)–0.2270×(donor/recipient gender matched)+0.2304×(donor/recipient relation)–0.0170×(mononuclear cell counts in graft)+0.0395×(CD34+cell count in graft)–2.4510.The threshold of probability was 0.4623,which separated patients into low-and high-risk groups.The 1-year cumulative incidence of EBV reactivation in the low-and high-risk groups was 11.0%versus 24.5%(P<.001),10.7%versus 19.3%(P=.046),and 11.4%versus 31.6%(P=.001),respectively,in total,training and validation cohorts.The model could also predict relapse and survival after HID HSCT.We established a comprehensive model that could predict EBV reactivation in HID HSCT recipients using ATG for GVHD prophylaxis.展开更多
Consecutively hospitalized patients with confirmed coronavirus disease 2019(COVID-19)in Wuhan,China were retrospectively enrolled from January 2020 to March 2020 to investigate the association between the use of renin...Consecutively hospitalized patients with confirmed coronavirus disease 2019(COVID-19)in Wuhan,China were retrospectively enrolled from January 2020 to March 2020 to investigate the association between the use of renin–angiotensin system inhibitor(RAS-I)and the outcome of this disease.Associations between the use of RAS-I(angiotensin-converting enzyme inhibitor(ACEI)or angiotensin receptor blocker(ARB)),ACEI,and ARB and in-hospital mortality were analyzed using multivariate Cox proportional hazards regression models in overall and subgroup of hypertension status.A total of 2771 patients with COVID-19 were included,with moderate and severe cases accounting for 45.0%and 36.5%,respectively.A total of 195(7.0%)patients died.RAS-I(hazard ratio(HR)=0.499,95%confidence interval(CI)0.325–0.767)and ARB(HR=0.410,95%CI 0.240–0.700)use was associated with a reduced risk of all-cause mortality among patients with COVID-19.For patients with hypertension,RAS-I and ARB applications were also associated with a reduced risk of mortality with HR of 0.352(95%CI 0.162–0.764)and 0.279(95%CI 0.115–0.677),respectively.RAS-I exhibited protective effects on the survival outcome of COVID-19.ARB use was associated with a reduced risk of all-cause mortality among patients with COVID-19.展开更多
Background.Diabetic retinopathy(DR)has been primarily indicated to cause vision impairment and blindness,while no studies have focused on the cost-utility of telemedicine-based and community screening programs for DR ...Background.Diabetic retinopathy(DR)has been primarily indicated to cause vision impairment and blindness,while no studies have focused on the cost-utility of telemedicine-based and community screening programs for DR in China,especially in rural and urban areas,respectively.Methods.We developed a Markov model to calculate the cost-utility of screening programs for DR in DM patients in rural and urban settings from the societal perspective.The incremental cost-utility ratio(ICUR)was calculated for the assessment.Results.In the rural setting,the community screening program obtained 1 QALY with a cost of$4179(95%CI 3859 to 5343),and the telemedicine screening program had an ICUR of$2323(95%CI 1023 to 3903)compared with no screening,both of which satisfied the criterion of a significantly cost-effective health intervention.Likewise,community screening programs in urban areas generated an ICUR of$3812(95%CI 2906 to 4167)per QALY gained,with telemedicine screening at an ICUR of$2437(95%CI 1242 to 3520)compared with no screening,and both were also cost-effective.By further comparison,compared to community screening programs,telemedicine screening yielded an ICUR of 1212(95%CI 896 to 1590)per incremental QALY gained in rural setting and 1141(95%CI 859 to 1403)in urban setting,which both meet the criterion for a significantly cost-effective health intervention.Conclusions.Both telemedicine and community screening for DR in rural and urban settings were cost-effective in China,and telemedicine screening programs were more cost-effective.展开更多
Background.Prediction of mortality risk in intensive care units(ICU)is an important task.Data-driven methods such as scoring systems,machine learning methods,and deep learning methods have been investigated for a long...Background.Prediction of mortality risk in intensive care units(ICU)is an important task.Data-driven methods such as scoring systems,machine learning methods,and deep learning methods have been investigated for a long time.However,few datadriven methods are specially developed for pediatric ICU.In this paper,we aim to amend this gap—build a simple yet effective linear machine learning model from a number of hand-crafted features for mortality prediction in pediatric ICU.Methods.We use a recently released publicly available pediatric ICU dataset named pediatric intensive care(PIC)from Children’s Hospital of Zhejiang University School of Medicine in China.Unlike previous sophisticated machine learning methods,we want our method to keep simple that can be easily understood by clinical staffs.Thus,an ensemble step-wise feature ranking and selection method is proposed to select a small subset of effective features from the entire feature set.A logistic regression classifier is built upon selected features for mortality prediction.Results.The final predictive linear model with 11 features achieves a 0.7531 ROC-AUC score on the hold-out test set,which is comparable with a logistic regression classifier using all 397 features(0.7610 ROC-AUC score)and is higher than the existing well known pediatric mortality risk scorer PRISM III(0.6895 ROC-AUC score).Conclusions.Our method improves feature ranking and selection by utilizing an ensemble method while keeping a simple linear form of the predictive model and therefore achieves better generalizability and performance on mortality prediction in pediatric ICU.展开更多
基金supported by the National Natural Science Foundation of China(No.81970270&No.82170327)the Tianjin Natural Science Foundation(20JC ZDJC00340&20JCZXJC00130)the Tianjin Key Medical Discipline(Specialty)Construction Project(TJYXZDXK-029A)。
文摘BACKGROUND The electrocardiogram(ECG)is an inexpensive and easily accessible investigation for the diagnosis of cardiovascular diseases including heart failure(HF).The application of artificial intelligence(AI)has contributed to clinical practice in terms of aiding diagnosis,prognosis,risk stratification and guiding clinical management.The aim of this study is to systematically review and perform a meta-analysis of published studies on the application of AI for HF detection based on the ECG.METHODS We searched Embase,PubMed and Web of Science databases to identify literature using AI for HF detection based on ECG data.The quality of included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2(QUADAS-2)criteria.Random-effects models were used for calculating the effect estimates and hierarchical receiver operating characteristic curves were plotted.Subgroup analysis was performed.Heterogeneity and the risk of bias were also assessed.RESULTS A total of 11 studies including 104,737 subjects were included.The area under the curve for HF diagnosis was 0.986,with a corresponding pooled sensitivity of 0.95(95%CI:0.86–0.98),specificity of 0.98(95%CI:0.95–0.99)and diagnostic odds ratio of 831.51(95%CI:127.85–5407.74).In the patient selection domain of QUADAS-2,eight studies were designated as high risk.CONCLUSIONS According to the available evidence,the incorporation of AI can aid the diagnosis of HF.However,there is heterogeneity among machine learning algorithms and improvements are required in terms of quality and study design.
基金National Natural Science Foundation of China(Nos.82100741,82003529,91846101,81771938,81900665,82090021)Beijing Municipal Science and Technology Commission(Grant No.7212201)+5 种基金the University of Michigan Health System-Peking University Health Science Center Joint Institute for Translational and Clinical Research(Nos.BMU2020JI011,BMU2019JI005,BMU2018JI012)Beijing Nova Programme Interdisciplinary Cooperation Project(No.Z191100001119008)National Key R&D Program of the Ministry of Science and Technology of China(No.2019YFC2005000)the National Key Research and Development Program of China(No.2018AAA0102100)PKU-Baidu Fund(Nos.2020BD005,2019BD017)CAMS Innovation Fund for Medical Sciences(No.2019-I2M-5-046)
文摘To the Editor:Chronic kidney disease(CKD)is a global burden of the public health.The global prevalence of CKD exceeded 10%while the awareness was around 10%.[1]In the era of big data,improving the identification of CKD using informatic tools is important.Computable phenotype is proven as an efficient tool to facilitate the process of patient identification using electronic health record(EHR)data.
文摘Health data and cutting-edge technologies empower medicine and improve healthcare.It has become even more true during the COVID-19 pandemic.Through coronavirus data sharing and worldwide collaboration,the speed of vaccine development for COVID-19 is unprecedented.Digital and data technologies were quickly adopted during the pandemic,showing how those technologies can be harnessed to enhance public health and healthcare.A wide range of digital data sources are being utilized and visually presented to enhance the epidemiological surveillance of COVID-19.Digital contact tracing mobile apps have been adopted by many countries to control community transmission.Deep learning has been utilized to achieve various solutions for COVID-19 disruption,including outbreak prediction,virus spread tracking.
文摘1.Introduction Clinician-scientists have a unique strength in translational research and medical advances that improve the quality of care and patient outcomes.As big data analytics and advanced technologies such as artificial intelligence are being continuously applied in the healthcare scenario,it not only transforms patient care but also creates tremendous opportunities for data-driven discoveries.In a digital health era,clinicianscientists proficient in data science knowledge——that is clinician data scientists——are central to harnessing the power of big data analytics and advanced technologies in medicine.
基金the Program of the National Natural Science Foundation of China(grant number 82170208)the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(grant number 81621001)+2 种基金the CAMS Innovation Fund for Medical Sciences(CIFMS)(grant number 2019-I2M-5-034)the Key Program of the National Natural Science Foundation of China(grant number 81930004)the Fundamental Research Funds for the Central Universities,National Natural Science Foundation of China(No.62102008).
文摘Epstein-Barr virus(EBV)reactivation is one of the most important infections after hematopoietic stem cell transplantation(HSCT)using haplo-identical related donors(HID).We aimed to establish a comprehensive model with machine learning,which could predict EBV reactivation after HID HSCT with anti-thymocyte globulin(ATG)for graft-versus-host disease(GVHD)prophylaxis.We enrolled 470 consecutive acute leukemia patients,60%of them(n=282)randomly selected as a training cohort,the remaining 40%(n=188)as a validation cohort.The equation was as follows:Probability(EBV reactivation)=1/1+exp(−Y),where Y=0.0250×(age)–0.3614×(gender)+0.0668×(underlying disease)–0.6297×(disease status before HSCT)–0.0726×(disease risk index)–0.0118×(hematopoietic cell transplantation-specific comorbidity index[HCT-CI]score)+1.2037×(human leukocyte antigen disparity)+0.5347×(EBV serostatus)+0.1605×(conditioning regimen)–0.2270×(donor/recipient gender matched)+0.2304×(donor/recipient relation)–0.0170×(mononuclear cell counts in graft)+0.0395×(CD34+cell count in graft)–2.4510.The threshold of probability was 0.4623,which separated patients into low-and high-risk groups.The 1-year cumulative incidence of EBV reactivation in the low-and high-risk groups was 11.0%versus 24.5%(P<.001),10.7%versus 19.3%(P=.046),and 11.4%versus 31.6%(P=.001),respectively,in total,training and validation cohorts.The model could also predict relapse and survival after HID HSCT.We established a comprehensive model that could predict EBV reactivation in HID HSCT recipients using ATG for GVHD prophylaxis.
基金supported by grants from Special Research Fund of PKU for Prevention and Control of COVID-19 and the Fundamental Research Funds for the Central Universities(Nos.PKU2020P-KYZX003,BMU2020HKYZX007)the National Natural Science Foundation of China(Nos.91846101,81771938,81301296,81900665,81570667,81470948,81670633)+8 种基金Major Research Plan of the National Natural Science Foundation of China(No.91742204)The International(Regional)Cooperation and Exchange Projects(NSFC-DFG,No.81761138041)Beijing Nova Programme Interdisciplinary Cooperation Project(No.Z1911-00001119008)the National Key R&D Program of the Ministry of Science and Technology of China(Nos.2016YFC1305405,2019-YFC2005000,2018YFC1314003-1,,2015BAI12B07)National Key Research and Development Program(No.2016YFC0906103)the University of Michigan Health System-Peking University Health Science Center Joint Institute for Translational and Clinical Research(Nos.BMU20160466,BMU2018JI012,BMU2019JI005)Beijing Advanced Discipline Construction Project(No.BMU-2019GJJXK001)PKU-Baidu Fund(No.2019BD017)from Peking University(Nos.BMU2018MX020,PKU2017LCX05).
文摘Consecutively hospitalized patients with confirmed coronavirus disease 2019(COVID-19)in Wuhan,China were retrospectively enrolled from January 2020 to March 2020 to investigate the association between the use of renin–angiotensin system inhibitor(RAS-I)and the outcome of this disease.Associations between the use of RAS-I(angiotensin-converting enzyme inhibitor(ACEI)or angiotensin receptor blocker(ARB)),ACEI,and ARB and in-hospital mortality were analyzed using multivariate Cox proportional hazards regression models in overall and subgroup of hypertension status.A total of 2771 patients with COVID-19 were included,with moderate and severe cases accounting for 45.0%and 36.5%,respectively.A total of 195(7.0%)patients died.RAS-I(hazard ratio(HR)=0.499,95%confidence interval(CI)0.325–0.767)and ARB(HR=0.410,95%CI 0.240–0.700)use was associated with a reduced risk of all-cause mortality among patients with COVID-19.For patients with hypertension,RAS-I and ARB applications were also associated with a reduced risk of mortality with HR of 0.352(95%CI 0.162–0.764)and 0.279(95%CI 0.115–0.677),respectively.RAS-I exhibited protective effects on the survival outcome of COVID-19.ARB use was associated with a reduced risk of all-cause mortality among patients with COVID-19.
基金the Major Innovation Platform of Public Health&Disease Control and Prevention,Renmin University of China,and Beijing Nova Program(Z191100001119072).
文摘Background.Diabetic retinopathy(DR)has been primarily indicated to cause vision impairment and blindness,while no studies have focused on the cost-utility of telemedicine-based and community screening programs for DR in China,especially in rural and urban areas,respectively.Methods.We developed a Markov model to calculate the cost-utility of screening programs for DR in DM patients in rural and urban settings from the societal perspective.The incremental cost-utility ratio(ICUR)was calculated for the assessment.Results.In the rural setting,the community screening program obtained 1 QALY with a cost of$4179(95%CI 3859 to 5343),and the telemedicine screening program had an ICUR of$2323(95%CI 1023 to 3903)compared with no screening,both of which satisfied the criterion of a significantly cost-effective health intervention.Likewise,community screening programs in urban areas generated an ICUR of$3812(95%CI 2906 to 4167)per QALY gained,with telemedicine screening at an ICUR of$2437(95%CI 1242 to 3520)compared with no screening,and both were also cost-effective.By further comparison,compared to community screening programs,telemedicine screening yielded an ICUR of 1212(95%CI 896 to 1590)per incremental QALY gained in rural setting and 1141(95%CI 859 to 1403)in urban setting,which both meet the criterion for a significantly cost-effective health intervention.Conclusions.Both telemedicine and community screening for DR in rural and urban settings were cost-effective in China,and telemedicine screening programs were more cost-effective.
文摘Background.Prediction of mortality risk in intensive care units(ICU)is an important task.Data-driven methods such as scoring systems,machine learning methods,and deep learning methods have been investigated for a long time.However,few datadriven methods are specially developed for pediatric ICU.In this paper,we aim to amend this gap—build a simple yet effective linear machine learning model from a number of hand-crafted features for mortality prediction in pediatric ICU.Methods.We use a recently released publicly available pediatric ICU dataset named pediatric intensive care(PIC)from Children’s Hospital of Zhejiang University School of Medicine in China.Unlike previous sophisticated machine learning methods,we want our method to keep simple that can be easily understood by clinical staffs.Thus,an ensemble step-wise feature ranking and selection method is proposed to select a small subset of effective features from the entire feature set.A logistic regression classifier is built upon selected features for mortality prediction.Results.The final predictive linear model with 11 features achieves a 0.7531 ROC-AUC score on the hold-out test set,which is comparable with a logistic regression classifier using all 397 features(0.7610 ROC-AUC score)and is higher than the existing well known pediatric mortality risk scorer PRISM III(0.6895 ROC-AUC score).Conclusions.Our method improves feature ranking and selection by utilizing an ensemble method while keeping a simple linear form of the predictive model and therefore achieves better generalizability and performance on mortality prediction in pediatric ICU.