Automated methods should not replace manual reviews of preventable readmissions

Automated classification is insufficient to replace manual reviews when identifying potentially preventable readmissions, according to a study appearing in BMC Medical Informatics and Decision Making.

Researchers manually reviewed 459 30-day all-cause readmissions at 18 Kaiser Permanente Northern California hospitals, which entailed determining preventability through a four-step process including a chart review tool, interviews with patients, families and treating providers, and nurse reviewer and physician evaluation of findings and determination of preventability on a five-point scale. These same admissions then were analyzed with software.

Automated classification provided by the software identified 78 percent, or 358, of readmissions as potentially preventable, compared to 47 percent, or 227, of those identified manually. Overall, the methods agreed about the preventability of 56 percent (258) of readmissions.

“Thorough manual review and automated classification methods differed substantially in the proportion of readmissions classified as potentially preventable. [The software] identified many more readmissions as potentially preventable. Not enough concordance currently exists between methods to use automated classification to replace manual review for quality improvement initiatives,” concluded the authors.

Read the study here.