Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Comment
  • Published:

Leveraging machine learning for hemodynamic phenotyping in pediatric continuous renal replacement therapy—toward precision monitoring

Pediatric Research (2026)Cite this article

While continuous renal replacement therapy (CRRT) has become a cornerstone of care for critically ill children with severe acute kidney injury (AKI), its initiation phase represents a hemodynamically fragile time often complicated by intradialytic hypotension (IDH).1,2 In adults, such events are closely linked to increased mortality;3 however, pediatric data remain limited, primarily derived from small, single-center studies.2 Similarly, studies evaluating factors associated with outcomes in this uniquely vulnerable patient population are limited.4,5,6 In this issue of Pediatric Research, Thadani et al. present a single-center retrospective study of 232 CRRT connections in 59 patients to evaluate associations between IDH and outcomes and to use unsupervised time series clustering to identify novel hemodynamic phenotypes among patients in the hour following CRRT connection.7

Advancing critical care nephrology requires understanding modifiable risk factors that influence patient outcomes. These may include the timing of CRRT initiation, hemodynamic instability, and electrolyte or laboratory abnormalities at the time of CRRT initiation such as anemia, hypoalbuminemia, acidosis, or hypocalcemia.8 Currently, the precise impact of these individual risk factors on pediatric CRRT outcomes remains unclear. Moreover, the thresholds and timing for correcting these disturbances prior to CRRT initiation, and their effects on intradialytic hypotension and clinical outcomes, have yet to be systematically studied.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Conceptual framework illustrating future directions for precision continuous renal replacement therapy (CRRT) and intradialytic hypotension (IDH) trajectory phenotyping.

References

  1. Raina, R. et al. Pediatric intradialytic hypotension: recommendations from the Pediatric Continuous Renal Replacement Therapy (PCRRT) Workgroup. Pediatr. Nephrol. 34, 925–941 (2019).

    Article  PubMed  Google Scholar 

  2. Thadani, S. et al. Hemodynamic instability during connection to continuous kidney replacement therapy in critically ill pediatric patients. Pediatr. Nephrol. 37, 2167–2177 (2022).

    Article  PubMed  Google Scholar 

  3. Shawwa, K. et al. Hypotension within one-hour from starting CRRT is associated with in-hospital mortality. J. Crit. Care 54, 7–13 (2019).

    Article  PubMed  Google Scholar 

  4. Goldstein, S. L. et al. Pediatric patients with multi-organ dysfunction syndrome receiving continuous renal replacement therapy. Kidney Int. 67, 653–658 (2005).

    Article  PubMed  Google Scholar 

  5. Menon, S. et al. Worldwide Exploration of Renal Replacement Outcomes Collaborative in Kidney Disease (WE-ROCK). Kidney Int. Rep. 8, 1542–1552 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  6. Symons, J. M. et al. Demographic characteristics of pediatric continuous renal replacement therapy: a report of the prospective pediatric continuous renal replacement therapy registry. Clin. J. Am. Soc. Nephrol. 2, 732–738 (2007).

    Article  PubMed  Google Scholar 

  7. Thadani, S. et al. Intradialytic hypotension and hemodynamic phenotypes in children following continuous renal replacement therapy initiation. Pediatr Res. (2025) Published online ahead of print.

  8. Xue, M. et al. Factors associated with hypotension during the first hour of continuous renal replacement therapy in critically ill patients: a prospective observational study. PLoS One 20, e0324235 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Flythe, J. E., Xue, H., Lynch, K. E., Curhan, G. C. & Brunelli, S. M. Association of mortality risk with various definitions of intradialytic hypotension. J. Am. Soc. Nephrol. 26, 724–734 (2015).

    Article  CAS  PubMed  Google Scholar 

  10. Shah, N. et al. The use of machine learning and artificial intelligence within pediatric critical care. Pediatr. Res. 93, 405–412 (2023).

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. The Kidney and Urinary Tract Center, Nationwide Children’s Hospital, Columbus, OH, USA

    Tahagod Mohamed

  2. Division of Nephrology and Hypertension, Department of Pediatrics, Nationwide Children’s Hospital, Columbus, OH, USA

    Tahagod Mohamed

  3. Center for Clinical and Translational Research, Abigail Wexner Research Institute, Nationwide Children’s Hospital, Columbus, OH, USA

    Jennifer Muszynski

  4. Division of Critical Care Medicine, Department of Pediatrics, Nationwide Children’s Hospital, Columbus, OH, USA

    Jennifer Muszynski

Authors
  1. Tahagod Mohamed
    View author publications

    Search author on:PubMed Google Scholar

  2. Jennifer Muszynski
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Tahagod Mohamed.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mohamed, T., Muszynski, J. Leveraging machine learning for hemodynamic phenotyping in pediatric continuous renal replacement therapy—toward precision monitoring. Pediatr Res (2026). https://doi.org/10.1038/s41390-025-04757-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s41390-025-04757-9

Search

Advanced search

Quick links