Validation of a Prediction Model Used at Kaiser Permanente Northwest in Collaboration With Operations
managed care (features), evaluation research, health care organizations, hospitals
Background: The LACE risk score is used by Kaiser Permanente Northwest (KPNW) to identify patients at high risk for hospital readmission or mortality. LACE triggers the delivery of Transitions of Care interventions to reduce unnecessary readmissions. However, LACE was put into practice before it was validated for Kaiser Permanente hospitals. This study validated the LACE model in the KPNW patient population using routine electronic medical record data (not research data from the virtual data warehouse) to evaluate the accuracy and applicability of the predictions. The validation was only possible through collaboration with KPNW operations.
Methods: This is a retrospective study of adult patients hospitalized from August 2014 to July 2015 at Sunnyside Medical Center (KSMC) at KPNW. Only the initial admission was included. The study outcome was readmission to the hospital or death within 30 days of discharge. The C-statistic was compared to the published value (Van Walraven et al, 2010). We assessed calibration (accuracy) graphically before and after we updated the LACE model with the KSMC-specific intercept.
Results: Of the 9,699 patients, 10.8% experienced the outcome. The C-statistic for KPNW (0.728) was slightly higher than the published value from Ontario hospitals (0.7114). The published LACE score was well calibrated with the KPNW population (observed vs predicted risks for the low/mid/high-risk groups were 0.042/0.102/0.256 vs 0.053/0.112/0.234, respectively). The updated LACE model with the KSMC-specific intercept (ie, probability in the lowest-risk patients) resulted in slightly better calibration (predicted risks for the low/mid/high-risk groups were 0.043/0.106/0.247). To target high-risk patients for Transitions of Care interventions, KPNW applies a cut-off of 11 or more LACE points, which resulted in a positive predictive value of 25.6%.
Conclusion: The LACE score validated successfully at KPNW’s KSMC, with only a slight underestimate of risk in high-risk patients. Updating LACE improved the predicted risk modestly (1.3%) for high-risk patients. Kaiser Permanente operations will continue to collaborate with colleagues in research to evaluate the LACE+ index and other predictors of readmission and mortality.
Smith N, Yang X, Petrik A, Rice Y, Crowland K, Moore D, Johnson E. Validation of a prediction model used at Kaiser Permanente Northwest in collaboration with operations. J Patient Cent Res Rev. 2017;4:169-70.