Development and validation of computable Phenotype to Identify and Characterize Kidney Health in Adult Hospitalized Patients
share
Background: Acute kidney injury (AKI) is one of the most common complications among hospitalized patients and is central to the subsequent development of chronic kidney disease (CKD). It is associated with up to five-fold increases in risk for both other serious complications and hospital death, and an increase in hospital cost of up to 28,000 per hospitalization. Methods: We created a database with electronic health records data from a retrospective study cohort of 84,352 adult patients hospitalized at UF Health. We developed algorithms to identify CKD and AKI based on the Kidney Disease: Improving Global Outcomes criteria. We identified presence and stage of AKI by running algorithms each time a new creatinine measurement was detected. To measure diagnostic performance of the algorithms, the clinical adjudication of AKI and CKD on 300 selected cases was performed.by clinician experts. Results: Among 149,136 encounters, 12 percent of patients with CKD identified increased to 16 encounters who had sufficient data for AKI phenotyping after excluding those with end-stage renal disease on admission, AKI during hospitalization was identified in 21 manual chart review performed in 300 cases yielded PPV of 0.87 (95 interval (CI) 0.81-0.92), NPV of 0.99 (95 (95 developed phenotyping algorithms that yielded very good performance in identification of patients with CKD and AKI in validation cohort. This tool may be useful in identifying patients with kidney disease in a large population, in assessing the quality and value of care provided to such patients and in clinical decision support tools to help providers care for these patients.
READ FULL TEXT