event-icon
Description

Abstract: Diabetes constitutes a significant health problem that leads to many long term health issues including renal, cardiovascular, and neuropathic complications. Many of these problems can result in increased health care costs, as well risk of ICU stay and mortality. To date, no published study has used predictive modeling to examine the relative influence of diabetes, diabetic health maintenance, and comorbidities on outcomes in ICU patients. Using the MIMIC III database, machine learning and binomial logistic regression modeling were applied to predict risk of mortality. The final models achieved good fit with AUC values of 0.787 and 0.785 respectively. Additionally, this study demonstrated that robust classification can be done as a combination of five variables (HbA1c, mean glucose during stay, diagnoses upon admission, age, and type of admission) to predict risk as compared with other machine learning models that require nearly 35 variables for similar risk assessment and prediction.

Learning Objective 1: Understand differences in classfication strategies between Random Forest and Logistic Regression Modelling in predicting mortality

Learning Objective 2 (Optional): Learn more about potential factors that may be correlated with diabetic mortality in the ICU

Authors:

Rajsavi Anand (Presenter)
Warren Alpert Medical School at Brown University

Paul Stey, Brown Center for Biomedical Informatics
Sukrit Jain, Warren Alpert Medical School at Brown University
Dustin Biron, Warren Alpert Medical School at Brown University
Harikrashna Bhatt, Warren Alpert Medical School at Brown University
Kristina Monteiro, Warren Alpert Medical School at Brown University
Edward Feller, Warren Alpert Medical School at Brown University
Megan Ranney, Warren Alpert Medical School
Indra Sarkar, Brown Center for Biomedical Informatics
Elizabeth Chen, Brown Center for Biomedical Informatics

Presentation Materials:

Keywords