An electronic Simplified Acute Physiology Score-based risk adjustment score for critical illness in an integrated healthcare system

Abstract

Objective: Risk adjustment is essential in evaluating the performance of an ICU; however, assigning scores is time-consuming. We sought to create an automated ICU risk adjustment score, based on the Simplified Acute Physiology Score 3, using only data available within the electronic medical record (Kaiser Permanente HealthConnect).

Design, setting, and patients: The eSimplified Acute Physiology Score 3 was developed by adapting Kaiser Permanente HealthConnect structured data to Simplified Acute Physiology Score 3 criteria. The model was tested among 67,889 first-time ICU admissions at 21 hospitals between 2007 and 2011 to predict hospital mortality. Model performance was evaluated using published Simplified Acute Physiology Score 3 global and North American coefficients; a first-level customized version of the eSimplified Acute Physiology Score 3 was also developed in a 40% derivation cohort and tested in a 60% validation cohort.

Measurements: Electronic variables were considered "directly" available if they could be mapped exactly within Kaiser Permanente HealthConnect; they were considered "adapted" if no exact electronic corollary was identified. Model discrimination was evaluated with area under receiver operating characteristic curves; calibration was assessed using Hosmer-Lemeshow goodness-of-fit tests.

Main results: Mean age at ICU admission was 65 ± 17 yrs. Mortality in the ICU was 6.2%; total in-hospital mortality was 11.2%. The majority of Simplified Acute Physiology Score 3 variables were considered "directly" available; others required adaptation based on diagnosis coding, medication records, or procedure tables. Mean eSimplified Acute Physiology Score 3 scores were 45 ± 13. Using published Simplified Acute Physiology Score 3 global and North American coefficients, the eSimplified Acute Physiology Score 3 demonstrated good discrimination (area under the receiver operating characteristic curve, 0.80-0.81); however, it overpredicted mortality. The customized eSimplified Acute Physiology Score 3 score demonstrated good discrimination (area under the receiver operating characteristic curve, 0.82) and calibration (Hosmer-Lemeshow goodness-of-fit chi-square p = 0.57) in the validation cohort. The eSimplified Acute Physiology Score 3 demonstrated stable performance when cohorts were limited to specific hospitals and years.

Conclusions: The customized eSimplified Acute Physiology Score 3 shows good potential for providing automated risk adjustment in the intensive care unit.