Reproducibility in critical care: a mortality prediction case study
نویسندگان
چکیده
Mortality prediction of intensive care unit (ICU) patients facilitates hospital benchmarking and has the opportunity to provide caregivers with useful summaries of patient health at the bedside. The development of novel models for mortality prediction is a popular task in machine learning, with researchers typically seeking to maximize measures such as the area under the receiver operator characteristic curve (AUROC). The number of ’researcher degrees of freedom’ that contribute to the performance of a model, however, presents a challenge when seeking to compare reported performance of such models. In this study, we review publications that have reported performance of mortality prediction models based on the Medical Information Mart for Intensive Care (MIMIC) database and attempt to reproduce the cohorts used in their studies. We then compare the performance reported in the studies against gradient boosting and logistic regression models using a simple set of features extracted from MIMIC. We demonstrate the large heterogeneity in studies that purport to conduct the single task of ’mortality prediction’, highlighting the need for improvements in the way that prediction tasks are reported to enable fairer comparison between models. We reproduced datasets for 38 experiments corresponding to 28 published studies using MIMIC. In half of the experiments, the sample size we acquired was 25% greater or smaller than the sample size reported. The highest discrepancy was 11,767 patients. While accurate reproduction of each study cannot be guaranteed, we believe that these results highlight the need for more consistent reporting of model design and methodology to allow performance improvements to be compared. We discuss the challenges in reproducing the cohorts used in the studies, highlighting the importance of clearly reported methods (e.g. data cleansing, variable selection, cohort selection) and the need for open code and publicly available benchmarks.
منابع مشابه
Prediction of mortality in patients admitted to intensive care units, A comparison of three data mining techniques: a brief report.
Background: Early outcome prediction of hospitalized patients is critical because the intensivists are constantly striving to improve patients' survival by taking effective medical decisions about ill patients in Intensive Care Units (ICUs). Despite rapid progress in medical treatments and intensive care technology, the analysis of outcomes, including mortality prediction, has been a challenge ...
متن کاملStudy of Demographic Factors Affecting Neonatal Mortality Due to Respiratory Distress Syndrome in Rural Area of Ahvaz in 2010
Introduction: Neonatal mortality rate is an important index of development in different communities and respiratory distress syndrome is one of the important causes. This study aimed to determine the status and effective demographic factors of neonatal mortality due to respiratory distress syndrome in Rural Area of Ahvaz city Iran. Method: It was a case control study of all neonatal death ...
متن کاملWhich of Simplified Acute Physiology Score-III or Mortality Probability Model-III scoring systems in prediction of mortality of non-traumatic patients is superior?
Background & Aims: Different scoring systems are used in order to assess the functional quality of intensive care units (ICU) and to predict the required costs and facilities of intensive cares. Variety of scoring systems has been explained that each has advantages and disadvantages. In this study Simplified Acute Physiology Score-III (SAPS-III) and Mortality Probability Model-III (MPM-III) wer...
متن کاملImpact of a High-protein Nutritional Intake on the Clinical Outcome of the Neurocritical Patients
Disease-related malnutrition of neurocritical illness harms its treatment, which increases the mortality rate. The aim of this study was evaluating the effect of a high protein diet on the dietary factors, clinical outcome, and mortality rate of neurocritical patients. In a randomized controlled trial, 15 neurocritical patients were recruited in each group. Patients in the intervention and cont...
متن کاملImpact of a High-protein Nutritional Intake on the Clinical Outcome of the Neurocritical Patients
Disease-related malnutrition of neurocritical illness harms its treatment, which increases the mortality rate. The aim of this study was evaluating the effect of a high protein diet on the dietary factors, clinical outcome, and mortality rate of neurocritical patients. In a randomized controlled trial, 15 neurocritical patients were recruited in each group. Patients in the intervention and cont...
متن کامل