Dataset Information

Learning Data-Driven Patient Risk Stratification Models for Clostridium difficile.

ABSTRACT: BACKGROUND: Although many risk factors are well known, Clostridium difficile infection (CDI) continues to be a significant problem throughout the world. The purpose of this study was to develop and validate a data-driven, hospital-specific risk stratification procedure for estimating the probability that an inpatient will test positive for C difficile. METHODS: We consider electronic medical record (EMR) data from patients admitted for ?24 hours to a large urban hospital in the U.S. between April 2011 and April 2013. Predictive models were constructed using L2-regularized logistic regression and data from the first year. The number of observational variables considered varied from a small set of well known risk factors readily available to a physician to over 10 000 variables automatically extracted from the EMR. Each model was evaluated on holdout admission data from the following year. A total of 34 846 admissions with 372 cases of CDI was used to train the model. RESULTS: Applied to the separate validation set of 34 722 admissions with 355 cases of CDI, the model that made use of the additional EMR data yielded an area under the receiver operating characteristic curve (AUROC) of 0.81 (95% confidence interval [CI], .79-.83), and it significantly outperformed the model that considered only the small set of known clinical risk factors, AUROC of 0.71 (95% CI, .69-.75). CONCLUSIONS: Automated risk stratification of patients based on the contents of their EMRs can be used to accurately identify a high-risk population of patients. The proposed method holds promise for enabling the selective allocation of interventions aimed at reducing the rate of CDI.

SUBMITTER: Wiens J

PROVIDER: S-EPMC4281796 | biostudies-literature | 2014 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Learning Data-Driven Patient Risk Stratification Models for Clostridium difficile.

Wiens Jenna J Campbell Wayne N WN Franklin Ella S ES Guttag John V JV Horvitz Eric E

Open forum infectious diseases 20140715 2

<h4>Background</h4>Although many risk factors are well known, Clostridium difficile infection (CDI) continues to be a significant problem throughout the world. The purpose of this study was to develop and validate a data-driven, hospital-specific risk stratification procedure for estimating the probability that an inpatient will test positive for C difficile.<h4>Methods</h4>We consider electronic medical record (EMR) data from patients admitted for ≥24 hours to a large urban hospital in the U.S. ...[more]

PMID: 25734117

Similar Datasets

Project description: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.

Project description:Background Preterm birth (PTB) is a growing health issue worldwide, currently considered the leading cause of newborn deaths. To address this challenge, the present work aims to develop an algorithm capable of accurately predicting the week of delivery supporting the identification of a PTB in Brazil. Methods This a population-based study analyzing data from 3,876,666 mothers with live births distributed across the 3,929 Brazilian municipalities. Using indicators comprising delivery characteristics, primary care work processes, and physical infrastructure, and sociodemographic data we applied a machine learning-based approach to estimate the week of delivery at the point of care level. We tested six algorithms: eXtreme Gradient Boosting, Elastic Net, Quantile Ordinal Regression - LASSO, Linear Regression, Ridge Regression and Decision Tree. We used the root-mean-square error (RMSE) as a precision. Findings All models obtained RMSE indexes close to each other. The lower levels of RMSE were obtained using the eXtreme Gradient Boosting approach which was able to estimate the week of delivery within a 2.09 window 95%IC (2.090–2.097). The five most important variables to predict the week of delivery were: number of previous deliveries through Cesarean-Section, number of prenatal consultations, age of the mother, existence of ultrasound exam available in the care network, and proportion of primary care teams in the municipality registering the oral care consultation. Interpretation Using simple data describing the prenatal care offered, as well as minimal characteristics of the pregnant, our approach was capable of achieving a relevant predictive performance regarding the week of delivery. Funding Bill and Melinda Gates Foundation, and National Council for Scientific and Technological Development – Brazil, (Conselho Nacional de Desenvolvimento Científico e Tecnológico - CNPQ acronym in portuguese) Support of the research project named: Data-Driven Risk Stratification for Preterm Birth in Brazil: Development of a Machine Learning-Based Innovation for Health Care- Grant: OPP1202186

Project description:BackgroundThe epidemiology of Clostridium difficile-associated infection (CDI) has changed, and it is evident that susceptibility is related not only to exposures and bacterial potency, but host factors as well. Several small studies have suggested that CDI after trauma is associated with a different patient phenotype. The purpose of this study was to examine and describe the epidemiologic factors associated with C. difficile in blunt trauma patients without traumatic brain injury using the Trauma-Related Database as a part of the "Inflammation and Host Response to Injury" (Glue Grant) and the University of Florida Integrated Data Repository.MethodsPreviously recorded baseline characteristics, clinical data, and outcomes were compared between groups (67 C. difficile and 384 uncomplicated, 813 intermediate, and 761 complicated non-C. difficile patients) as defined by the Glue Grant on admission and at days seven and 14.ResultsThe majority of CDI patients experienced complicated or intermediate clinical courses. The mean ages of all cohorts were less than 65 y and CDI patients were significantly older than uncomplicated patients without CDI. The CDI patients had increased days in the hospital and on the ventilator, as well as significantly higher new injury severity scores (NISS), and a greater percentage of patients with NISS >34 points compared with non-CDI patients. They also had greater Marshall and Denver multiple organ dysfunction scores than non-CDI uncomplicated patients, and greater creatinine, alkaline phosphatase, neutrophil count, lactic acid, and PiO2:FiO2 compared with all non-CDI cohorts on admission. In addition, the CDI patients had higher glucose concentrations and base deficit from uncomplicated patients and greater leukocytosis than complicated patients on admission. Several of these changes persisted to days seven and 14.ConclusionAnalysis of severe blunt trauma patients with C. difficile, as compared with non-CDI patients, reveals evidence of increased inflammation, immunosuppression, worse acute kidney injury, higher NISS, greater days in the hospital and on the ventilator, higher organ injury scores, and prolonged clinical courses. This supports reports of an increased prevalence of CDI in a younger population not believed previously to be at risk. This unique population may have specific genomic or inflammation-related risk factors that may play more important roles in disease susceptibility. Prospective analysis may allow early identification of at-risk patients, creation of novel therapeutics, and improved understanding of how and why C. difficile colonization transforms into infection after severe blunt trauma.

Dataset Information

Learning Data-Driven Patient Risk Stratification Models for Clostridium difficile.

Publications

Learning Data-Driven Patient Risk Stratification Models for Clostridium difficile.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets