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

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

  • By

  • 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

  • Michael Starck

  • Clemens-Martin Wendtner

  • Peter Bojko

  • Marcus Hentrich

  • Katharina Elisabeth Nickel

  • Katharina Goetze

  • Florian Bassermann

  • Sabine Janina Ehrlich

  • Marion Subklewe

  • Andreas Pircher

  • Dominik Wolf

  • Michael von Bergwelt-Baildon

  • Karsten Spiekermann

  • June 30, 2026

  • 0 min

Share

Objective:

To develop a machine learning tool, the HLH-Risk-Calculator, for predicting initial disease severity and time-point specific mortality in adult patients with secondary hemophagocytic lymphohistiocytosis (sHLH).

Approach:
  • Model Development: The HLH-Risk-Calculator utilizes six Random Forest models to predict initial disease severity and mortality at various time points based on laboratory and demographic features.
  • Patient Inclusion: 167 adult patients diagnosed with sHLH were included from six study centers across Germany, Switzerland, and Austria.
  • Statistical Analysis: Statistical analyses were performed using Python, including survival analyses and comparisons of laboratory parameters.
Key Findings:
  • The strongest predictors for adverse outcomes were low platelet counts and high levels of soluble interleukin-2 receptor.
  • Mortality rates for sHLH patients range from 26% to 75%.
Interpretation:

The HLH-Risk-Calculator requires external validation before clinical use.

Limitations:
  • The study is retrospective and based on a limited number of patients.
  • External validation of the HLH-Risk-Calculator is necessary.
Conclusion:

The HLH-Risk-Calculator requires further validation to assess its effectiveness in clinical settings.

Original Source(s)

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

  • by 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, Michael Starck, Clemens-Martin Wendtner, Peter Bojko, Marcus Hentrich, Katharina Elisabeth Nickel, Katharina Goetze, Florian Bassermann, Sabine Janina Ehrlich, Marion Subklewe, Andreas Pircher, Dominik Wolf, Michael von Bergwelt-Baildon, Karsten Spiekermann

  • June 30, 2026

Related Content

Factors associated with pulmonary embolism in children with refractory Mycoplasma pneumoniae pneumonia and elevated D-dimer

Steroid-resistant bilateral facial nerve palsies, ophthalmoparesis, and multilevel thoracic radiculopathy as immune effector cell-associated late-onset neurotoxicity after cilta-cel CAR-T therapy: a case report and review of similar cases

Systemic lupus erythematosus associated with paroxysmal nocturnal hemoglobinuria: a case report and literature review highlighting the clinical significance of small PNH clones