ABSTRACT
OBJECTIVE@#To construct an in-hospital mortality prediction model for patients with acute kidney injury (AKI) in intensive care unit (ICU) by using support vector machine (SVM), and compare it with the simplified acute physiology score II (SAPS-II) which is commonly used in the ICU.@*METHODS@#We used Medical Information Mart for Intensive Care III (MIMIC-III) database as data source. The AKI patients in the MIMIC-III database were selected according to the 2012 Kidney Disease: Improving Global Outcomes (KDIGO) definition of AKI. We employed the same predictor variable set as used in SAPS-II to construct an SVM model. Meanwhile, we also developed a customized SAPS-II model using MIMIC-III database, and compared performances between the SVM model and the customized SAPS-II model. The performance of each model was evaluated via area under the receiver operation characteristic curve (AUROC), root mean squared error (RMSE), sensitivity, specificity, Youden's index and accuracy based on 5-fold cross-validation. The agreement of the results between the SVM model and the customized SAPS-II model was illustrated using Bland-Altman plots.@*RESULTS@#A total number of 19 044 patients with AKI were included. The observed in-hospital mortality of the AKI patients was 13.58% in MIMIC-III. The results based on the 5-fold cross validation showed that the average AUROC of the SVM model and the customized SAPS-II model was 0.86 and 0.81, respectively (The difference between the two models was statistically significant with t=13.0, P<0.001). The average RMSE of the SVM model and the customized SAPS-II model was 0.29 and 0.31, respectively (The difference was statistically significant with t=-9.6, P<0.001). The SVM model also outperformed the customized SAPS-II model in terms of sensitivity and Youden's index with significant statistical differences (P=0.002 and <0.001, respectively).The Bland-Altman plot showed that the SVM model and the customized SAPS-II model had similar mortality prediction results when the mortality of a patient was certain, but the consistency between the mortality prediction results of the two models was poor when the mortality of a patient was with high uncertainty.@*CONCLUSION@#Compared with the SAPS-II model, the SVM model has a better performance, especially when the mortality of a patient is with high uncertainty. The SVM model is more suitable for predicting the mortality of patients with AKI in ICU and early intervention in patients with AKI in ICU. The SVM model can effectively help ICU clinicians improve the quality of medical treatment, which has high clinical value.
Subject(s)
Humans , Acute Kidney Injury/mortality , Critical Care , Hospital Mortality , Intensive Care Units , Prognosis , ROC Curve , Sensitivity and Specificity , Support Vector MachineABSTRACT
Objective To assess the relationship between body mass index (BMI) and ischaemic heart disease (IHD) mortality,especially in populations with low mean BMI levels.Methods We examined the data from a population-based,prospective cohort study of 220 000 Chinese men aged 40-79,who were enrolled in 1990-1991,and followed up ever since to 1/1/2006.Relative risks of the deaths from IHD by the baseline BMI were calculated,after controlling age,smoking,and the other potential confounding factors.Results The mean baseline BMI was 21.7 kg/m~2,and 2763 IHD deaths were recorded during the 15-year follow-up (6.8% of all deaths) program.Among men without prior vascular diseases at baseline,there was a J-shaped association between BMI and IHD mortality.When baseline BMI was above 20 kg/m~2,there was a strongly positive association of BMI with IHD risk,with each 5 kg/m~2 higher in BMI associated with 21%(95%CI:9%-35%,P=0.0004) higher IHD mortality.Below this BMI range,the association appeared to be reverse,with the risk ratios as 1.00,1.11,and 1.14,respectively,for men with BMI 20-21.9,18-19.9,and ＜ 18 kg/m~2.The excess IHD risk observed at low BMI levels persisted after restricting analysis to never smokers or excluding the first 3 years of follow-up.Conclusion Lower BMI was associated with lower IHD risk among people in the so-called 'normal range' of BMI values (20-25 kg/m~2).However,below that range,the association might well be reversed.