EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY-NC 4.0

The HLH-Risk-Calculator is a machine learning-based tool to predict course & mortality of secondary hemophagocytic lymphohistiocytosis

Michael Ruzicka, Hans Christian Stubbe, Josia Fauser, Manuel Trebo, Thomas Wimmer, Lena Horvath, Hans-Joachim Stemmler, Stefanie Susanne Stecher, Hendrik Schulze-Koops, Fabian Hauck, Michael Medinger, Claire Seydoux und 13 weitere

Intensive Care Medicine · 2026-07 · 52 (7) · 1514-1525

DOI: 10.1007/s00134-026-08515-1 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Intensive Care Medicine, online erschienen am 30.06.2026. Verfasst von Michael Ruzicka und 24 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine III, Ludwig Maximilian University (LMU) University Hospital, LMU Munich, Munich, Germany. michael.ruzicka@med.uni-muenchen.de. Hauptthemen laut MEDLINE: Lymphohistiocytosis, Hemophagocytic, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Klinikum der Universität München.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Secondary hemophagocytic lymphohistiocytosis (sHLH) is a life-threatening hyperinflammatory condition. While few diagnostic scores are established, none exist to predict both clinical course and time-point specific outcome of sHLH patients so far. We present a machine learning (ML)-based tool to predict Initial Disease Severity (IDS; defined as admission to intensive care units (ICU) OR death < 90 days without ICU admission) and mortality across different time points in sHLH patients.

Methods

167 adult sHLH patients from six study centers across three European countries were included retrospectively. Clinical and demographic features, course, survival, and laboratory data were assessed. Random forest models were trained with two sets of eight clinical and laboratory features: one to predict IDS, and five to predict mortality at distinct time points (30, 60, 90, 180 or 365 days). After calibration, the models were tested against hold-out test sets containing n = 32 (IDS) or n = 43 (mortality) sHLH patients.

Results

Overall, the models demonstrated strong discriminatory ability, overall performance, and accurate prediction of risk. Serum levels of the soluble interleukin-2 receptor (sIL-2R) and albumin (for IDS) or sIL-2R and platelet counts (for mortality prediction) showed the strongest contributions to the models’ predictions.

Conclusion

The HLH-Risk-Calculator is an exploratory tool predicting the clinical course of sHLH. External validation is critical to assess its validity, applicability, and robustness for real-world use. To this end, the calculator is available at www.hlh-risk-calculator.com for research use only, and is currently not intended for clinical decision-making. Visual abstract

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lymphohistiocytosis, HemophagocyticMachine LearningAdultFemaleHumansMaleMiddle AgedEuropeIntensive Care UnitsInterleukin-2 Receptor alpha SubunitPredictive Learning ModelsPrognosisRandom ForestRetrospective StudiesRisk AssessmentSeverity of Illness Index

Stichwörter der Autor:innen

HLH-Risk-CalculatorHemophagocytic lymphohistiocytosisPrognostic scoreSoluble CD25Soluble interleukin-2 receptor

Substanzen

Interleukin-2 Receptor alpha Subunit

Autor:innen und Institutionen

  • Department of Medicine III, Ludwig Maximilian University (LMU) University Hospital, LMU Munich, Munich, Germany. michael.ruzicka@med.uni-muenchen.de.
  • German Cancer Consortium (DKTK), Partner Site Munich, Munich, Germany. michael.ruzicka@med.uni-muenchen.de.
  • Department of Medicine II, LMU University Hospital, LMU Munich, Munich, Germany.
  • German Center for Infection Research, Partner Site Munich, Munich, Germany.
  • Department of Internal Medicine V, Medical University of Innsbruck, Innsbruck, Austria.
  • Department of Medicine III, Ludwig Maximilian University (LMU) University Hospital, LMU Munich, Munich, Germany.

Förderung

  • Klinikum der Universität München

Zitieren

APA

Ruzicka, M., Stubbe, H. C., Fauser, J., Trebo, M., Wimmer, T., Horvath, L., Stemmler, H. J., Stecher, S. S., Schulze-Koops, H., Hauck, F., Medinger, M., Seydoux, C., Starck, M., Wendtner, C. M., Bojko, P., Hentrich, M., Nickel, K. E., Goetze, K., Bassermann, F., …, & Spiekermann, K. (2026). The HLH-Risk-Calculator is a machine learning-based tool to predict course & mortality of secondary hemophagocytic lymphohistiocytosis. Intensive Care Medicine, 52(7), 1514-1525. https://doi.org/10.1007/s00134-026-08515-1

Vancouver

Ruzicka M, Stubbe HC, Fauser J, Trebo M, Wimmer T, Horvath L, et al. The HLH-Risk-Calculator is a machine learning-based tool to predict course & mortality of secondary hemophagocytic lymphohistiocytosis. Intensive Care Medicine. 2026;52(7):1514-1525. doi:10.1007/s00134-026-08515-1

BibTeX
@article{Ruzicka2026,
  author = {Ruzicka, Michael and Stubbe, Hans Christian and Fauser, Josia and Trebo, Manuel and Wimmer, Thomas and Horvath, Lena and Stemmler, Hans-Joachim and Stecher, Stefanie Susanne and Schulze-Koops, Hendrik and Hauck, Fabian and Medinger, Michael and Seydoux, Claire and Starck, Michael and Wendtner, Clemens-Martin and Bojko, Peter and Hentrich, Marcus and Nickel, Katharina Elisabeth and Goetze, Katharina and Bassermann, Florian and Ehrlich, Sabine Janina and Subklewe, Marion and Pircher, Andreas and Wolf, Dominik and von Bergwelt-Baildon, Michael and Spiekermann, Karsten},
  title = {The HLH-Risk-Calculator is a machine learning-based tool to predict course & mortality of secondary hemophagocytic lymphohistiocytosis},
  journal = {Intensive Care Medicine},
  year = {2026},
  volume = {52},
  number = {7},
  pages = {1514--1525},
  doi = {10.1007/s00134-026-08515-1}
}
Kostenlos starten →