ICU sedation, delirium & recovery
Early heart-rate trajectory phenotypes predict short-term mortality in critically ill patients: a dynamic time-warping cluster analysis
Authors' conclusion
Machine learning-based phenotyping of 24-hour HR trajectories stratified short-term mortality risk and revealed time-dependent patterns potentially reflecting treatment responsiveness.
Study context
- Population
- Adults admitted to the intensive care unit (ICU) between January 2018 and December 2024 with ≥ 12 h of HR data; early discharge/death, mechanical support or sustained bradycardia excludedanalysed after exclusions
- Participants
- 4,491 adults
- Exposure
- Early HR trajectory phenotypes vs Cluster E
- Outcome
- 30-day mortality
- Follow-up
- 30 days
Methodological detailsdynamic time-warping cluster analysis, machine learning-based phenotyping, multivariable Cox models
- Dynamic time-warping cluster analysis
- Machine learning-based phenotyping
- Multivariable Cox models
Main finding
As reported in the abstract
Each group vs cluster EHazard ratio (95% CI)P value
Cluster A
3.21(2.32–4.45)
P < 0.001Cluster C
2.09(1.53–2.85)
P < 0.001- Significant differences in survival across clusters (Kaplan-Meier, log-rank)
- P < 0.001
Observational data: associations, not effects.
Original publication
Early heart-rate trajectory phenotypes predict short-term mortality in critically ill patients: a dynamic time-warping cluster analysis. J Clin Monit Comput. Published 3 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →