ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on Twitter

Kidney Week

Abstract: PO0189

Healthcare Analytics with Time-Invariant and Time-Variant Feature Importance to Predict Hospital-Acquired AKI

Session Information

Category: Acute Kidney Injury

  • 101 AKI: Epidemiology, Risk Factors, and Prevention

Authors

  • Chua, Horng-Ruey, National University Hospital, Department of Medicine, Division of Nephrology, Singapore, Singapore
  • Zheng, Kaiping, National University of Singapore, School of Computing, Department of Computer Science, Singapore, Singapore
  • Lu, Liangjian, Khoo Teck Puat - National University Children's Medical Institute, Singapore, Singapore
  • Maclaren, Graeme, National University Hospital, Department of Cardiothoracic and Vascular Surgery, Singapore, Singapore
  • Yap, Hui Kim, Khoo Teck Puat - National University Children's Medical Institute, Singapore, Singapore

Group or Team Name

  • National University Health System Academic Informatics and Innovation Office
Background

Acute kidney injury (AKI) develops in 4% of inpatients 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 patients for preemptive care. We applied machine learning 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 clinical features temporal to AKI in cases. 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 cases without AKI.

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.

Conclusion

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 better-timed AKI biomarker assessment in the high-risk cohort identified.

Funding

  • Government Support – Non-U.S.