Validation of Risk Prediction Models to Inform Clinical Decisions After Acute Kidney Injury

Simon Sawhney* (Corresponding Author), Zhi Tan, Corri Black, Angharad Marks, David J McLernon, Paul Ronksley , Matthew T James

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)
9 Downloads (Pure)

Abstract

Rationale & Objective There is limited evidence to guide follow-up after acute kidney injury (AKI). Knowledge gaps include which patients to prioritize, at what time point, and for mitigation of which outcomes. In this study, we sought to compare the net-benefit of risk model-based clinical decisions following AKI. Study Design External validation of two risk models of AKI outcomes: 1) the Grampian (UK) – Aberdeen AKI readmissions model and 2) the Alberta (Canada) Kidney Disease risk model of CKD G4-G5). Process mining to delineate existing care pathways. Setting and Participants Validation was based on data from adult hospital survivors of AKI from Grampian (UK), 2011-2013. Predictors KDIGO-based measures of AKI severity and comorbidities specified in the original models. Outcomes (1) death or readmission within 90 days for all hospital survivors; and (2) progression to new CKD G4-G5 for patients surviving at least 90-days after AKI. Analytical Approach Decision curve analysis to assess the “net-benefit” of use of risk models to guide clinical care compared to alternative approaches (e.g. prioritizing all AKI, severe AKI, or only those without kidney recovery). Results 26575 of 105461 hospital survivors in Grampian were included for validation of the death or readmission model, mean (SD) age 60.9 years (19.8); and 9382 for the CKD G4-G5 model, mean age 67.2 years (15.4). Both models discriminated well (AUC 0.77 and 0.86 respectively). Decision curve analysis showed greater net-benefit for follow up of all AKI than only severe AKI in most situations. Both original and refitted models provided superior net-benefit to any other decision strategy. In process mining of all hospital discharges, 41% of readmissions and deaths occurred among people recovering after AKI. 1464/3776 (39%) people readmitted after AKI had received no intervening monitoring. Limitations Both original models overstated risks indicating a need for regular updating. Conclusions Follow up after AKI has potential net-benefit for pre-empting readmissions, death and subsequent CKD progression. Decisions could be improved by using risk models and by focusing on AKI across a full spectrum of severity. The current lack of monitoring among many with poor outcomes indicates possible opportunities for implementation of decision support.
Original languageEnglish
Pages (from-to)28-37
Number of pages10
JournalAmerican Journal of Kidney Diseases
Volume78
Issue number1
Early online date9 Jan 2021
DOIs
Publication statusPublished - Jul 2021

Bibliographical note

Wellcome Trust Research Training Fellowship: 102729/Z/13/Z
Academy of Medical Sciences Starter Grant for Clinical Lecturers: SGL020\1076

We acknowledge the support of the Grampian Data Safe Haven (DaSH) facility within the Aberdeen Centre for Health Data Science and the associated financial support of the University of Aberdeen, and NHS Research Scotland (through NHS Grampian investment in DaSH). More information is available at the DaSH website: http://www.abdn.ac.uk/iahs/facilities/grampian-data-safe-haven.php

Keywords

  • acute kidney injury (AKI)
  • chronic kidney disease (CKD)
  • CKD progression
  • CKD surveillance
  • death
  • follow-up care
  • hospital readmission
  • model-guided decisions
  • mortality
  • net benefit
  • post-AKI care
  • post-discharge monitoring
  • risk prediction

Fingerprint

Dive into the research topics of 'Validation of Risk Prediction Models to Inform Clinical Decisions After Acute Kidney Injury'. Together they form a unique fingerprint.

Cite this