Readmission-Prediction Software Not Ready to Replace Manual Review, Study Finds

Oakland, Calif.-based Kaiser Permanente has released the results of a study that found an automated method of identifying potentially preventable readmissions to hospitals is not yet accurate enough to replace manual review.

For the study, researchers manually reviewed 459 30-day all-cause readmissions at 18 Kaiser Permanente hospitals in northern California. Researchers utilized a four-step manual review process that included a chart review tool; interviews with patients and their families; interviews with treating providers; nurse review of findings; and physician evaluation of findings and determinations of preventability on a five-point scale.

The same readmissions examined in the manual review were reassessed with 3M's Potentially Preventable Readmission software.

The software identified 78 percent of cases as potentially preventable, while only 47 percent were identified as potentially preventable using the manual review process.

Based on their findings, researchers concluded the concordance between the two methods was not high enough to replace manual review with the automated classification as the primary method of identifying preventable hospital readmissions.

More Articles on Hospital Readmissions:

Mayo's App Helps Cut Cardiac ED Visits, Readmissions, Study Finds
Top 10 Health Conditions Targeted to Reduce Readmissions
4 Characteristics of Poorly Performing Hospitals