Cardiothoracic & vascular anesthesia
Impact of Inflammation After Cardiac Surgery on 30-Day Mortality and Machine Learning Risk Prediction
Main finding · 30-day mortalityResult — go to the resultOdds ratio 2.77 95% CI 1.40–5.47Authors' conclusion
SIRS is significantly associated with increased 30-day mortality following cardiac surgery. Machine learning models effectively predict SIRS
Study context
- Population
- Patients undergoing elective or urgent cardiac surgery with cardiopulmonary bypass (CPB), 2016 to 2020
- Participants
- 1,908 patients · 483 matched pairs
- Exposure
- Systemic inflammatory response syndrome (SIRS)-positive vs SIRS-negative on first postoperative day
- Outcome
- 30-day mortality
- Follow-up
- 30 days
Methodological detailssingle tertiary care hospital, propensity score matched, machine learning risk prediction
- Single tertiary care hospital
- Propensity score matched
- Machine learning risk prediction
Main finding
As reported in the abstract
Odds ratio
2.77
95% CI 1.40–5.47
P = 0.003
By group
SIRS
12.2%
SIRS
OR 2.77 (95% CI 1.40–5.47); P = 0.003
Observational data: associations, not effects.
Further findings
| Outcome | Baseline risk model | Procedure-adjusted risk model |
|---|---|---|
| Machine learning prediction of SIRS (AUC) | ||
| AUC cross-validation | 0.77 ± 0.04 | 0.81 ± 0.02 |
| AUC test set | 0.73 (95% CI 0.70-0.85) | 0.82 (95% CI 0.76-0.85) |
SIRS incidence · first postoperative day
- SIRS incidence
- 28.7%
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Impact of Inflammation After Cardiac Surgery on 30-Day Mortality and Machine Learning Risk Prediction. J Cardiothorac Vasc Anesth. Published 9 December 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →