Scoring System for the One-Year Mortality Prediction of Sepsis Patients in Intensive Care Units

摘要

Sepsis is a life-threatening organ dysfunction induced by a dysregulated host response to infection and carries a high mortality and morbidity,therefore,after patients are admitted in an ICU it is necessary to synthesize the large volume of information that is collected in a value that represents their condition.Traditional severity of illness scores seek to be applicable to all patient populations,and usually assess in-hospital mortality.However,people who survive sepsis may have permanent organ damage and eventually suffer from a sepsis-related death.This study presents the development of a score for the one-year mortality prediction of the patients that are admitted in an ICU with a sepsis diagnosis.5650 ICU admissions extracted from MIMICIII database were evaluated and divided into two groups(70% development,30% validation).LASSO and SGB variable importance methodologies were used over the training subset to select the set of predictors that make up the score.Cut-off points that divided the cohort into two groups with different risks were found for each of these variables,and the numeric data were converted into binary.These predictors were used in a LR model,and its coefficients were rounded to the nearest integer,resulting in the point values that make up the score when multiplied with each binary variable and summed.Then,the one-year mortality probability was estimated using the score as the only variable in a LR model.The score,was evaluated using the validation subset,obtaining an AUROC of 0.73,which outperforms the results obtained with three commonly used severity of illness scores on the same subset.