Acute cardiac care & resuscitation
Machine Learning Based Prediction of Hospital Mortality in Post-Cardiotomy Cardiogenic Shock with Mechanical Support
Authors' conclusion
Machine learning models demonstrated moderate predictive performance for in-hospital mortality in post-cardiotomy cardiogenic shock patients on extracorporeal life support. The random forest model demonstrated moderate discriminative performance, highlighting the relevance of readily available clinical variables. External validation and calibration analysis are required before clinical implementation. The model is best interpreted as a tool for dynamic risk assessment during ECMO support.
Study context
- Population
- Adult patients who received extracorporeal life support for post-cardiotomy cardiogenic shock between January 2010 and December 2020 (Extracorporeal Life Support Organization (ELSO) registry)adult patients from the ELSO registry
- Participants
- 5,982 patients
- Predictors
- Six machine learning algorithms, boosting, decision tree, k-nearest neighbours, random forest, naïve Bayes, and neural networks
- Predicted outcome
- in-hospital mortality
Methodological detailsregistry data across 111 centres, training (60%), validation (20%), and test (20%) cohorts
- Registry data across 111 centres
- Training (60%), validation (20%), and test (20%) cohorts
Model performance
As reported in the abstract
Further findings
Transplant-related outcomes
- Prediction limited by class imbalance
Age (survivors vs. non-survivors)
- Age
- 57.76 ± 14.63 vs. 61.25 ± 13.41 years, p < 0.001
Lactate during support (survivors vs. non-survivors)
- Lactate during support
- 3.07 ± 2.88 vs. 5.79 ± 5.30 mmol/L, p < 0.001
Arterial pH (survivors vs. non-survivors)
- Arterial pH
- 7.302 ± 0.122 vs. 7.278 ± 0.139, p < 0.001
BMI (survivors vs. non-survivors)
- BMI
- 29.12 ± 6.57 vs. 30.00 ± 7.12 kg/m², p < 0.001
ECMO duration (survivors vs. non-survivors)
- ECMO duration
- 142.14 ± 150.91 vs. 150.50 ± 162.09 hours, p = 0.023
- On-support variable reflects clinical trajectory rather than a pre-initiation predictor
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →