Learning Data-Driven Patient Risk Stratification Models for Clostridium difficile

By Jenna Wiens, Wayne N. Campbell, Ella S. Franklin, John V. Guttag, Eric Horvitz. 2014

51 citations recorded by the source corpus.

We take a data-driven approach to predicting which inpatients are most likely to test positive for pathogenic Clostridium difficile (C. difficile). Using EMR data from 69,568 admissions, we develop and validate a risk-stratification model, based on over 10,000 variables.

Subfields: Critical Care and Intensive Care Medicine, Epidemiology, Infectious Diseases

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Epidemiology

1. D. Hooper
2. Cynthia Rudin

Citations in the corpus

• Learning Credible Models (2017, background): “We identified these variables working with experts in infectious disease who identified key factors based on the literature [6, 8, 34].”
• Learning Classification Models of Cognitive Conditions from Subtle Behaviors in the Digital Clock Drawing Test (2015, background): “More recently, examples of successful machine learning medical applications include the detection and classification of tumors via X-ray and CRT images [36, 3]; the classification of malignancies from proteomic and genomic (microarray) assays [59, 12, 53]; heartbeat classification from electrocardio”
• Machine Learning for Healthcare: On the Verge of a Major Shift in Healthcare Epidemiology (2018, background): “Although more complex than low-dimensional tools for calculating patient risk, models that leverage the richness of the EHR can be significantly more accurate [33].”
• A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers (2018, background): “In addition, exposure to the pathogen was estimated based on daily in-hospital locations and both hospital-level and ward-level colonization pressure.(11,17) All data considered were structured (ie, we did not consider free text notes); some variables were continuous and others categorical.”