A Generalizable, Data-Driven Approach to Predict Daily Risk ofClostridium difficileInfection at Two Large Academic Health Centers

Abstract

OBJECTIVE An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that work well across institutions. However, this one-size-fits-all approach ignores important hospital-specific factors. We focus on a generalizable method for building facility-specific models. We demonstrate the applicability of the approach using electronic health records (EHR) from the University of Michigan Hospitals (UM) and the Massachusetts General Hospital (MGH). METHODS We utilized EHR data from 191,014 adult admissions to UM and 65,718 adult admissions to MGH. We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 4,836 features from patients at UM and 1,837 from patients at MGH. We used L2 regularized logistic regression to learn the models, and we measured the discriminative performance of the models on held-out data from each hospital. RESULTS Using the UM and MGH test data, the models achieved area under the receiver operating characteristic curve (AUROC) values of 0.82 (95% confidence interval [CI], 0.80-0.84) and 0.75 ( 95% CI, 0.73-0.78), respectively. Some predictive factors were shared between the 2 models, but many of the top predictive factors differed between facilities. CONCLUSION A data-driven approach to building models for estimating daily patient risk for CDI was used to build institution-specific models at 2 large hospitals with different patient populations and EHR systems. In contrast to traditional approaches that focus on developing models that apply across hospitals, our generalizable approach yields risk-stratification models tailored to an institution. These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies. Infect Control Hosp Epidemiol 2018;39:425-433.

Novel therapies and preventative strategies for primary and recurrent Clostridium difficile infections

“…An important limiting factor for clinical deployment of preventative and recurrence reduction therapies is the identification of patients who are at high risk of developing primary or recurrent CDI and who would benefit from these therapies. To achieve this risk stratification, large studies are starting to be performed using medical data for the development of predictive models for primary and recurrent CDI risk during a patient's treatment . If the risk of primary CDI or recurrence can be accurately predicted by microbial, systemic, or intestinal/colonic markers such as specific bacterial community compositions or immune cytokine levels, then the more expensive but effective therapies, such as bezlotoxumab, can be utilized to protect against future CDI.…”

“…To achieve this risk stratification, large studies are starting to be performed using medical data for the development of predictive models for primary and recurrent CDI risk during a patient's treatment. 136 If the risk of primary CDI or recurrence can be accurately predicted by microbial, systemic, or intestinal/colonic markers such as specific bacterial community compositions or immune cytokine levels, then the more expensive but effective therapies, such as bezlotoxumab, can be utilized to protect against future CDI. This will not only increase the effective treatment of recurrent CDI, but also lower the cost to the healthcare system by targeting only those patients predicted to experience primary or recurrent CDI.…”

Learning Credible Models

“…We use the same feature extraction pipeline as described in [22]. In particular, we extract high-dimensional feature vectors for each day of a patient's admission from the structured contents of the EHR (e.g., medication, procedures, in-hospital locations etc.).…”

“…Request permissions from permissions@acm.org. KDD '18, August [19][20][21][22][23]2018, London, United Kingdom © 2018 Association for Computing Machinery. ACM ISBN 978-1-4503-5552-0/18/08.…”

Inpatient mobility to predict hospital-onset Clostridium difficile: a network approach

“…Grouping patients by their location in a hospital gives us the opportunity to examine susceptibility and risk of CDI from a population perspective, and calculation of network centrality [6] provides us with context of how inpatient units are connected in our hospital via patient transfers. Individual patient risk of CDI has been explored [12,13,14,15], but population risk of CDI, to our knowledge, has not.…”