Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: May 30, 2021
Date Accepted: Oct 29, 2021
Healthcare Analytics with Time-invariant and Time-variant Feature Importance to Predict Hospital-Acquired Acute Kidney Injury: Observational Longitudinal Study
ABSTRACT
Background:
Acute kidney injury (AKI) develops in 4% of hospitalized patients and is a marker of clinical deterioration and nephrotoxicity. AKI onset is highly variable in hospital which makes it difficult to time biomarker assessment in all patients for preemptive care.
Objective:
The study sought to apply machine learning techniques to electronic health records and predict hospital-acquired AKI by a 48-hour lead time, with aim to create an AKI surveillance algorithm that is deployable in real-time.
Methods:
The data was sourced from 20,732 case-admissions in 16,288 patients over one year in our institution. We enhanced our bidirectional recurrent neural network with a novel time-invariant and time-variant module to capture important clinical features temporal to AKI in every patient. Time-series features included laboratory parameters that preceded a 48-hour prediction window before AKI onset; the latter’s corresponding reference was the final in-hospital serum creatinine performed in case-admissions without AKI episodes.
Results:
The cohort was of mean age 53(±25) years, of whom 29%, 12%, 12%, and 53% had diabetes mellitus, ischemic heart disease, cancers, and baseline eGFR <90 mL/min/1.73m2, respectively. There were 911 AKI episodes in 869 patients. We derived and validated an algorithm in the testing dataset with an AUROC of 0.81 (0.78–0.85) for predicting AKI. At a 15% prediction threshold, our model generated 699 AKI alerts with 2 false positives for every true AKI and predicted 26% of AKIs. A lowered 5% prediction threshold improved the recall to 60% but generated 3,746 AKI alerts with 6 false positives for every true AKI.
Conclusions:
We generated an accurate algorithm from electronic health records through machine learning that predicted AKI by 48 hours prior. The prediction threshold could be adjusted during deployment to balance an optimal recall with alert-fatigue, while its precision could be augmented by targeted AKI biomarker assessment in the high-risk cohort identified. Clinical Trial: Null
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.