Skip to main content

Advertisement

SpringerLink
Log in

ARTIFICIAL INTELLIGENCE IN NEPHROLOGY IN 2019

Artificial intelligence approaches to improve kidney care

  • Year in Review
  • Published:

From Nature Reviews Nephrology

View current issue Sign up to alerts

This article has been updated

Artificial intelligence is increasingly being used to improve diagnosis and prognostication for acute and chronic kidney diseases. Studies with this objective published in 2019 relied on a variety of available data sources, including electronic health records, intraoperative physiological signals, kidney ultrasound imaging, and digitized biopsy specimens.

Key advances

  • A deep recurrent neural network model using data from electronic health records enables the prediction of inpatient episodes of acute kidney injury (AKI) with lead times of up to 48 hours5.

  • Integrating intraoperative physiological signals into an AKI risk model that dynamically integrates preoperative and intraoperative data improves the prediction of postoperative AKI6.

  • A convolutional deep learning model enables the noninvasive classification of chronic kidney disease stage and estimated glomerular filtration rate using kidney ultrasound images8.

  • A convolutional neural network trained for multiclass segmentation enables automated analysis of transplant biopsy and nephrectomy samples9.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1: A conceptual framework for the future use of artificial intelligence in nephrology.

Change history

  • 13 January 2020

    In the original html and PDF versions of this article published online, the 2 in 1.73 m2 was incorrectly formatted as a reference citation. This error has been corrected in print and online.

References

  1. United States Department of Health and Human Services. Advancing American kidney health. HHS https://aspe.hhs.gov/system/files/pdf/262046/AdvancingAmericanKidneyHealth.pdf (2019).

  2. Vinyals, O. et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350–354 (2019).

    Article  CAS  Google Scholar 

  3. American Medical Association. Augmented intelligence in health care. AMA https://www.ama-assn.org/system/files/2019-08/ai-2018-board-policy-summary.pdf (2019).

  4. Al-Jaghbeer, M. et al. Clinical decision support for in-hospital AKI. J. Am. Soc. Nephrol. 29, 654–660 (2018).

    Article  Google Scholar 

  5. Tomašev, N. et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 572, 116–119 (2019).

    Article  Google Scholar 

  6. Adhikari, L. et al. Improved predictive models for acute kidney injury with IDEA: intraoperative data embedded analytics. PLOS ONE 14, e0214904 (2019).

    Article  CAS  Google Scholar 

  7. Bihorac, A. et al. MySurgeryRisk: development and validation of a machine-learning risk algorithm for major complications and death after surgery. Ann. Surg. 269, 652–662 (2019).

    Article  Google Scholar 

  8. Kuo, C.-C. et al. Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning. NPJ Digit. Med. 2, 29 (2019).

    Article  Google Scholar 

  9. Hermsen, M. et al. Deep learning-based histopathologic assessment of kidney tissue. J. Am. Soc. Nephrol. 30, 1968–1979 (2019).

    Article  Google Scholar 

  10. Davoudi, A. et al. Intelligent ICU for autonomous patient monitoring using pervasive sensing and deep learning. Sci. Rep. 9, 8020 (2019).

    Article  Google Scholar 

Download references

Acknowledgements

The authors received research funding from the NIH (R21 EB027344 and R01GM110240 awarded to A.B.; R21 EB027344 and R01GM110240 awarded to P.R.) and the National Science Foundation (Career IIS 1750192 awarded to P.R.).

Author information

Authors and Affiliations

  1. iHeal Lab, Department of Medicine, Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA

    Parisa Rashidi

  2. Precision and Intelligent Systems in Medicine, Department of Medicine, University of Florida, Gainesville, FL, USA

    Azra Bihorac

Authors
  1. Parisa Rashidi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Azra Bihorac
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Azra Bihorac.

Ethics declarations

Competing interests

The University of Florida has two pending patent applications related to some of algorithms published in the highlighted articles: Bihorac, A., Li, X., Rashidi, P., Pardalos, P., Ozrazgat-Baslanti, T., Hogan, W., Wang, D. Z., Momcilovic, P. & Lipori, G. Method and apparatus for prediction of complications after surgery. Appl. No. PCT/IB2018/053956, 1 June 2018, A&B ref. 049648/514983, UF ref.16671; Rashidi, P., Bihorac, A. & Tighe, P. J. Method and apparatus for pervasive patient monitoring. Nonprovisional Appl. No. 16/388,351, 18 April 2019, A&B ref. 049648/529839, UF ref.17317.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rashidi, P., Bihorac, A. Artificial intelligence approaches to improve kidney care. Nat Rev Nephrol 16, 71–72 (2020). https://doi.org/10.1038/s41581-019-0243-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41581-019-0243-3

  • Springer Nature Limited

This article is cited by

Search

Navigation