Abstract: PO0174
Risk for AKI in the Outpatient Setting
Session Information
- AKI: Epidemiology, Risk Factors, and Prevention
November 04, 2021 | Location: On-Demand, Virtual Only
Abstract Time: 10:00 AM - 12:00 PM
Category: Acute Kidney Injury
- 101 AKI: Epidemiology, Risk Factors, and Prevention
Authors
- Murphy, Daniel P., University of Minnesota Medical School Twin Cities, Minneapolis, Minnesota, United States
- Reule, Scott, Minneapolis VA Health Care System, Minneapolis, Minnesota, United States
- Vock, David Michael, University of Minnesota Medical School Twin Cities, Minneapolis, Minnesota, United States
- Drawz, Paul E., University of Minnesota Medical School Twin Cities, Minneapolis, Minnesota, United States
Background
Risk-factors for acute kidney injury (AKI) in the hospital have been well studied. Yet, tools for identifying outpatients at high risk for AKI are not available.
Methods
A development cohort for modelling risk of AKI without concurrent or subsequent hospitalization was defined by repeated primary care encounters in an urban healthcare system. An external validation cohort was similarly defined in the Veterans Health Administration. Logistic regression with bootstrap sampling for backward stepwise covariate elimination was used to develop a model for outpatient AKI in an 18-month outcome period. The model was then transformed into two binary tests to identify high-risk patients: one for research and another for clinical care.
Results
Outpatient AKI occurred in 4611 of 152,371 (3.0%) and 115,744 of 4,864,576 (2.4%) patients in the development and validation cohorts, respectively. The model C-statistics were 0.72 (95% CI: 0.71-0.73) and 0.72 (95% CI: 0.72-0.72) in the development and validation cohorts. The research test had sensitivity of 0.21 (95% CI: 0.21-0.21) and specificity of 0.95 (95% CI: 0.95-0.95). The clinical test, with a lower test-positivity threshold, had sensitivity of 0.49 (95% CI: 0.49-0.50) and specificity of 0.81 (95% CI: 0.81-0.81).
Conclusion
The outpatient AKI-risk prediction model performed well in both continuous and binary forms.
Performance in the validation cohort of two binary tests for outpatient AKI in 18 months
| Statistic | Research Test | Clinical Test |
| Threshold for test-positivity (a) | ≥9.5% (b) | ≥4.5% (b) |
| Sensitivity | 0.210 (95% CI: 0.208-0.213) | 0.494 (95% CI: 0.491-0.497) |
| Specificity | 0.952 (95% CI: 0.951-0.952) | 0.806 (95% CI: 0.806-0.807) |
| Positive predictive value | 0.096 (95% CI: 0.094-0.097) | 0.058 (95% CI: 0.058-0.059) |
| Negative predictive value | 0.980 (95% CI: 0.980-0.980) | 0.985 (95% CI: 0.985-0.985) |
| Percent of cohort "positive" by the test | 5.2% | 20.0% |
(a) Derived in the development cohort (b) P <0.001 for predicting outpatient AKI in the validation cohort
Observed risk vs. mean predicted risk of outpatient AKI in 18 months by decile of predicted risk in the validation cohort.