The HLH-Risk-Calculator is a machine learning-based tool to predict course & mortality of secondary hemophagocytic lymphohistiocytosis
Authors' conclusion
The HLH-Risk-Calculator is an exploratory tool predicting the clinical course of sHLH.
Study context
- Population
- Adults with secondary hemophagocytic lymphohistiocytosis (sHLH) from six centres in three European countries
- Participants
- 167 adults · 6 centres
- Outcome
- Prediction of Initial Disease Severity (IDS; Intensive care units (ICU) admission or death < 90 days without ICU admission) and mortality at distinct time points
- Follow-up
- 30, 60, 90, 180 or 365 days (mortality)
Methodological detailsmachine learning, random forest models, calibration, hold-out test sets, Random forest models trained with two sets of eight clinical and laboratory features
- Machine learning
- Random forest models
- Calibration
- Hold-out test sets
- Random forest models trained with two sets of eight clinical and laboratory features
Main finding
As reported in the abstract
Model performance on hold-out test sets
- Strong discriminatory ability, overall performance, and accurate prediction of risk
- Strongest contributors: sIL-2R and albumin (Initial Disease Severity (IDS)); sIL-2R and platelet counts (mortality)
- Hold-out test sets n = 32 (IDS), n = 43 (mortality)
Observational data: associations, not effects.
Original publication
The HLH-Risk-Calculator is a machine learning-based tool to predict course & mortality of secondary hemophagocytic lymphohistiocytosis. Intensive Care Med. Published 30 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →