Study: EHR data limited in capture of patient outcomes, risk factors needed for risk adjustment

Editor's Note

Retooling paper-based measures to electronic format for reporting performance measures can help reduce hospitals’ reporting burden. However, in this study by Joint Commission and State University of New York researchers, a simplified risk model using electronic health record (EHR) elements could not capture most risk factors in the New York State (NYS) coronary artery bypass graft (CABG) surgery risk models for mortality and readmission.

Only six of 28 data elements could be obtained from the EHR−age, gender, creatinine level, height, weight, and heart failure status−and outlier hospitals differed substantially for readmission but not for mortality.

Patient-level measures of fit and predictive ability in the EHR-derived risk models were inferior to the NYS CABG surgery risk model, although correlation of the predicted probabilities between the NYS and EHR models was high.

Most data currently used for CABG surgery outcomes measures risk adjustment are not in a structured format, precluding the reporting of these measures through the EHR in a form that would be acceptable to the medical community, the researchers say.