Paediatric anaesthesia & critical care
In-hospital mortality among patients with congenital heart disease undergoing noncardiac procedures: machine learning analysis of a multicentre study
Authors' conclusion
The risk factors shown in our dataset using ML methods are similar to those demonstrated in our prior work utilising logistic regression.
Study context
- Population
- Patients <21 yr with CHD undergoing noncardiac procedures at 7 paediatric centres, January 2021–December 2022
- Participants
- 5,977 patients · 9,837 surgical encounters
- Outcome
- In-hospital mortality (risk factors by machine learning (ML))
Methodological detailsmachine learning (random forest, eXtreme Gradient boosting)
- Machine learning (random forest, eXtreme Gradient boosting)
Main finding
As reported in the abstract
In-hospital mortality
In-hospital mortality, patients
1.74%
n=104
In-hospital mortality, surgical encounters
1.48%
n=146
Observational data: associations, not effects.
Further findings
Decision curve analysis
- Benefit in identifying patients at increased mortality risk when probability of mortality between 0% and 60%
Original publication
In-hospital mortality among patients with congenital heart disease undergoing noncardiac procedures: machine learning analysis of a multicentre study. BJA Open. Published 30 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →