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

Wiens J, Campbell WN, Franklin ES, Guttag JV, Horvitz E - Open Forum Infect Dis (2014)

Bottom Line: 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).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.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering and Computer Science , Massachusetts Institute of Technology , Cambridge.

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.

No MeSH data available.


Related in: MedlinePlus

Study population flow diagram.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4281796&req=5

OFU045F1: Study population flow diagram.

Mentions: After applying exclusion criteria (described in Figure 1), the final population consisted of 69 568 admissions. Table 1 summarizes the demographic and admission-related characteristics of the study population. Given the EMRs of all patients in our dataset, we extracted the features referenced in Table 2 for each patient admission and a binary label indicating whether a patient tested positive for C difficile (and when). This process resulted in 14 curated features and 10 845 additional features derived from the EMR.Table 1.


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

Wiens J, Campbell WN, Franklin ES, Guttag JV, Horvitz E - Open Forum Infect Dis (2014)

Study population flow diagram.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4281796&req=5

OFU045F1: Study population flow diagram.
Mentions: After applying exclusion criteria (described in Figure 1), the final population consisted of 69 568 admissions. Table 1 summarizes the demographic and admission-related characteristics of the study population. Given the EMRs of all patients in our dataset, we extracted the features referenced in Table 2 for each patient admission and a binary label indicating whether a patient tested positive for C difficile (and when). This process resulted in 14 curated features and 10 845 additional features derived from the EMR.Table 1.

Bottom Line: 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).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.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering and Computer Science , Massachusetts Institute of Technology , Cambridge.

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.

No MeSH data available.


Related in: MedlinePlus