BACKGROUND Risk stratification tools exist for patients presenting with chest pain to the emergency room and have achieved the recommended negative predictive value(NPV)of 99%.However,due to low positive predictive va...BACKGROUND Risk stratification tools exist for patients presenting with chest pain to the emergency room and have achieved the recommended negative predictive value(NPV)of 99%.However,due to low positive predictive value(PPV),current stratification tools result in unwarranted investigations such as serial laboratory tests and cardiac stress tests(CSTs).AIM To create a machine learning model(MLM)for risk stratification of chest pain with a better PPV.METHODS This retrospective cohort study used de-identified hospital data from January 2016 until November 2021.Inclusion criteria were patients aged>21 years who presented to the ER,had at least two serum troponins measured,were subsequently admitted to the hospital,and had a CST within 4 d of presentation.Exclusion criteria were elevated troponin value(>0.05 ng/mL)and missing values for body mass index.The primary outcome was abnormal CST.Demographics,coronary artery disease(CAD)history,hypertension,hyperlipidemia,diabetes mellitus,chronic kidney disease,obesity,and smoking were evaluated as potential risk factors for abnormal CST.Patients were also categorized into a high-risk group(CAD history or more than two risk factors)and a low-risk group(all other patients)for comparison.Bivariate analysis was performed using a χ^(2) test or Fisher’s exact test.Age was compared by t test.Binomial regression(BR),random forest,and XGBoost MLMs were used for prediction.Bootstrapping was used for the internal validation of prediction models.BR was also used for inference.Alpha criterion was set at 0.05 for all statistical tests.R software was used for statistical analysis.RESULTS The final cohort of the study included 2328 patients,of which 245(10.52%)patients had abnormal CST.When adjusted for covariates in the BR model,male sex[risk ratio(RR)=1.52,95%confidence interval(CI):1.2-1.94,P<0.001],CAD history(RR=4.46,95%CI:3.08-6.72,P<0.001),and hyperlipidemia(RR=3.87,95%CI:2.12-8.12,P<0.001)remained statistically significant.Incidence of abnormal CST was 12.2%in the high-risk group and 2.3%in the low-risk group(RR=5.31,95%CI:2.75-10.24,P<0.001).The XGBoost model had the best PPV of 24.33%,with an NPV of 91.34%for abnormal CST.CONCLUSION The XGBoost MLM achieved a PPV of 24.33%for an abnormal CST,which is better than current stratification tools(13.00%-17.50%).This highlights the beneficial potential of MLMs in clinical decision-making.展开更多
BACKGROUND Many studies have investigated the progression of nonalcoholic fatty liver disease(NAFLD)and its predisposing risk factors,but the conclusions from these studies have been conflicting.More challenging is th...BACKGROUND Many studies have investigated the progression of nonalcoholic fatty liver disease(NAFLD)and its predisposing risk factors,but the conclusions from these studies have been conflicting.More challenging is the fact that no effective treatment is currently available for NAFLD.AIM To determine the effects of proprotein convertase subtilisin/kexin type-9(PCSK9)inhibitors on fatty infiltration of the liver.METHODS This retrospective,chart review-based study was conducted on patients,18-yearold and above,who were currently on PCSK9 inhibitor drug therapy.Patients were excluded from the study according to missing pre-or post-treatment imaging or laboratory values,presence of cirrhosis or rhabdomyolysis,or development of acute liver injury during the PCSK9 inhibitor treatment period;the latter being due to false elevation of liver function markers,alanine aminotransferase(ALT)and aspartate aminotransferase(AST).Radiographic improvement was assessed by a single radiologist,who read both the pre-and post-treatment images to minimize reading bias.Fatty infiltration of the liver was also assessed by changes in ALT and AST,with pre-and post-treatment levels compared by paired t-test(alpha criterion:0.05).RESULTS Of the 29 patients included in the study,8 were male(27.6%)and 21 were female(72.4%).Essential hypertension was present in 25(86.2%)of the patients,diabetes mellitus in 18(62.1%)and obesity in 15(51.7%).In all,patients were on PCSK9 inhibitors for a mean duration of 23.69±11.18 mo until the most recent ALT and AST measures were obtained.Of the 11 patients who received the radiologic diagnosis of hepatic steatosis,8(72.73%)achieved complete radiologic resolution upon use of PCSK9 inhibitors(mean duration of 17.6 mo).On average,the ALT level(IU/L)decreased from 21.83±11.89 at pretreatment to 17.69±8.00 at posttreatment(2-tailed P=0.042)and AST level(IU/L)decreased from 22.48±9.00 pretreatment to 20.59±5.47 post-treatment(2-tailed P=0.201).CONCLUSION PCSK9 inhibitors can slow down or even completely resolve NAFLD.展开更多
BACKGROUND Liver transplant patients are at higher risk of infection due to immunosuppression.Whether liver transplant recipients are also more susceptible to severe acute respiratory syndrome coronavirus 2(SARS-CoV-2...BACKGROUND Liver transplant patients are at higher risk of infection due to immunosuppression.Whether liver transplant recipients are also more susceptible to severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)and will have worse outcomes than the general population if they develop coronavirus disease 2019(COVID-19)due to SARS-CoV-2 is a topic of ongoing studies,including ours.AIM To assess the clinical outcomes of COVID-19 in liver transplant recipients.METHODS This was a case-control study,with a database search performed(at the study site)from March 1,2020 through February 28,2021.Patients 18 years or older who tested positive for SARS-CoV-2 via polymerase chain reaction(PCR)were included in the study.Patients with infection other than pneumonia at the time of admission were excluded.After selection,patients who had been the recipient of liver transplant were considered cases and those without as controls.After being matched by age,sex,and obesity,two controls were randomly selected for each case.Death and hospitalization due to COVID-19 infection were the primary outcomes.Secondary outcomes were pertinent only to patients who were hospitalized,and they included duration of hospital stay,need for supplemental oxygen,presence of at least one type of end-organ damage,effects on liver enzymes,incidence of acute liver failure,effect on d-dimer levels,and incidence of venous thromboembolism(VTE).Chi-square or Fisher’s exact test was used to compare all primary and secondary outcomes with the exception of duration of hospital stay and d-dimer levels,which were compared using the Wilcoxon signed-rank test.Alpha criterion was set at 0.05.Logistic regression was performed for each primary outcome(as the dependent variable).Statistical analyses were performed using R software.RESULTS Of the 470 Liver transplant recipients who were tested for COVID-19 via the PCR test,39 patients tested positive(8.3%).There was no significant difference between cases and controls regarding death[odds ratio(OR):2.04,95%confidence interval(CI):0.14–29.17;P=0.60]and hospitalization rates(OR:1.38,95%CI:0.59–3.24;P=0.46).There also was no significant difference between cases and controls with respect to all secondary outcomes.Among all patients who had elevated liver enzymes,their levels were either normalized,improving,or remained stable at the time of discharge.No patient developed acute liver failure.Of the 31 hospitalized patients,27 received a prophylactic anticoagulation dose and no patient developed VTE in either group.Among cases who were hospitalized,immunosuppression was decreased in 5 patients and there was no change in immunosuppression among the remaining 7 patients.One patient died in each of these two subgroups.Logistic regression analysis was done,but all of the models had poor model predictions as well as insignificant predictors(independent variables).Therefore,they could not be used for either prediction or inference.CONCLUSION Clinical outcomes of COVID-19 in liver transplant recipients are not different than those without transplantation.COVID-19 should not impact timely health care access and immunosuppression continuation among these patients.展开更多
基金supported by the Clinical and Translational Science Award from the National Center for Advancing Translational Sciences,which has been awarded to the University of Kansas Clinical and Translational Science Institute.
文摘BACKGROUND Risk stratification tools exist for patients presenting with chest pain to the emergency room and have achieved the recommended negative predictive value(NPV)of 99%.However,due to low positive predictive value(PPV),current stratification tools result in unwarranted investigations such as serial laboratory tests and cardiac stress tests(CSTs).AIM To create a machine learning model(MLM)for risk stratification of chest pain with a better PPV.METHODS This retrospective cohort study used de-identified hospital data from January 2016 until November 2021.Inclusion criteria were patients aged>21 years who presented to the ER,had at least two serum troponins measured,were subsequently admitted to the hospital,and had a CST within 4 d of presentation.Exclusion criteria were elevated troponin value(>0.05 ng/mL)and missing values for body mass index.The primary outcome was abnormal CST.Demographics,coronary artery disease(CAD)history,hypertension,hyperlipidemia,diabetes mellitus,chronic kidney disease,obesity,and smoking were evaluated as potential risk factors for abnormal CST.Patients were also categorized into a high-risk group(CAD history or more than two risk factors)and a low-risk group(all other patients)for comparison.Bivariate analysis was performed using a χ^(2) test or Fisher’s exact test.Age was compared by t test.Binomial regression(BR),random forest,and XGBoost MLMs were used for prediction.Bootstrapping was used for the internal validation of prediction models.BR was also used for inference.Alpha criterion was set at 0.05 for all statistical tests.R software was used for statistical analysis.RESULTS The final cohort of the study included 2328 patients,of which 245(10.52%)patients had abnormal CST.When adjusted for covariates in the BR model,male sex[risk ratio(RR)=1.52,95%confidence interval(CI):1.2-1.94,P<0.001],CAD history(RR=4.46,95%CI:3.08-6.72,P<0.001),and hyperlipidemia(RR=3.87,95%CI:2.12-8.12,P<0.001)remained statistically significant.Incidence of abnormal CST was 12.2%in the high-risk group and 2.3%in the low-risk group(RR=5.31,95%CI:2.75-10.24,P<0.001).The XGBoost model had the best PPV of 24.33%,with an NPV of 91.34%for abnormal CST.CONCLUSION The XGBoost MLM achieved a PPV of 24.33%for an abnormal CST,which is better than current stratification tools(13.00%-17.50%).This highlights the beneficial potential of MLMs in clinical decision-making.
基金Data for this research project was obtained from Health System of the University of Kansas Medical Center,Kansas City,KS 66160,United States.The authors are grateful to the Department of Clinical Informatics at the University of Kansas Medical Center for their help in accessing the patient medical record database.Data extraction was conducted by the HERON automated data extraction tool.
文摘BACKGROUND Many studies have investigated the progression of nonalcoholic fatty liver disease(NAFLD)and its predisposing risk factors,but the conclusions from these studies have been conflicting.More challenging is the fact that no effective treatment is currently available for NAFLD.AIM To determine the effects of proprotein convertase subtilisin/kexin type-9(PCSK9)inhibitors on fatty infiltration of the liver.METHODS This retrospective,chart review-based study was conducted on patients,18-yearold and above,who were currently on PCSK9 inhibitor drug therapy.Patients were excluded from the study according to missing pre-or post-treatment imaging or laboratory values,presence of cirrhosis or rhabdomyolysis,or development of acute liver injury during the PCSK9 inhibitor treatment period;the latter being due to false elevation of liver function markers,alanine aminotransferase(ALT)and aspartate aminotransferase(AST).Radiographic improvement was assessed by a single radiologist,who read both the pre-and post-treatment images to minimize reading bias.Fatty infiltration of the liver was also assessed by changes in ALT and AST,with pre-and post-treatment levels compared by paired t-test(alpha criterion:0.05).RESULTS Of the 29 patients included in the study,8 were male(27.6%)and 21 were female(72.4%).Essential hypertension was present in 25(86.2%)of the patients,diabetes mellitus in 18(62.1%)and obesity in 15(51.7%).In all,patients were on PCSK9 inhibitors for a mean duration of 23.69±11.18 mo until the most recent ALT and AST measures were obtained.Of the 11 patients who received the radiologic diagnosis of hepatic steatosis,8(72.73%)achieved complete radiologic resolution upon use of PCSK9 inhibitors(mean duration of 17.6 mo).On average,the ALT level(IU/L)decreased from 21.83±11.89 at pretreatment to 17.69±8.00 at posttreatment(2-tailed P=0.042)and AST level(IU/L)decreased from 22.48±9.00 pretreatment to 20.59±5.47 post-treatment(2-tailed P=0.201).CONCLUSION PCSK9 inhibitors can slow down or even completely resolve NAFLD.
文摘BACKGROUND Liver transplant patients are at higher risk of infection due to immunosuppression.Whether liver transplant recipients are also more susceptible to severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)and will have worse outcomes than the general population if they develop coronavirus disease 2019(COVID-19)due to SARS-CoV-2 is a topic of ongoing studies,including ours.AIM To assess the clinical outcomes of COVID-19 in liver transplant recipients.METHODS This was a case-control study,with a database search performed(at the study site)from March 1,2020 through February 28,2021.Patients 18 years or older who tested positive for SARS-CoV-2 via polymerase chain reaction(PCR)were included in the study.Patients with infection other than pneumonia at the time of admission were excluded.After selection,patients who had been the recipient of liver transplant were considered cases and those without as controls.After being matched by age,sex,and obesity,two controls were randomly selected for each case.Death and hospitalization due to COVID-19 infection were the primary outcomes.Secondary outcomes were pertinent only to patients who were hospitalized,and they included duration of hospital stay,need for supplemental oxygen,presence of at least one type of end-organ damage,effects on liver enzymes,incidence of acute liver failure,effect on d-dimer levels,and incidence of venous thromboembolism(VTE).Chi-square or Fisher’s exact test was used to compare all primary and secondary outcomes with the exception of duration of hospital stay and d-dimer levels,which were compared using the Wilcoxon signed-rank test.Alpha criterion was set at 0.05.Logistic regression was performed for each primary outcome(as the dependent variable).Statistical analyses were performed using R software.RESULTS Of the 470 Liver transplant recipients who were tested for COVID-19 via the PCR test,39 patients tested positive(8.3%).There was no significant difference between cases and controls regarding death[odds ratio(OR):2.04,95%confidence interval(CI):0.14–29.17;P=0.60]and hospitalization rates(OR:1.38,95%CI:0.59–3.24;P=0.46).There also was no significant difference between cases and controls with respect to all secondary outcomes.Among all patients who had elevated liver enzymes,their levels were either normalized,improving,or remained stable at the time of discharge.No patient developed acute liver failure.Of the 31 hospitalized patients,27 received a prophylactic anticoagulation dose and no patient developed VTE in either group.Among cases who were hospitalized,immunosuppression was decreased in 5 patients and there was no change in immunosuppression among the remaining 7 patients.One patient died in each of these two subgroups.Logistic regression analysis was done,but all of the models had poor model predictions as well as insignificant predictors(independent variables).Therefore,they could not be used for either prediction or inference.CONCLUSION Clinical outcomes of COVID-19 in liver transplant recipients are not different than those without transplantation.COVID-19 should not impact timely health care access and immunosuppression continuation among these patients.