Cardiothoracic & vascular anesthesia
Machine Learning in Risk Prediction of Continuous Renal Replacement Therapy After Surgical Repair of Acute Type A Aortic Dissection
Authors' conclusion
The XGBoost model effectively predicts the requirement for CRRT after ATAAD surgery, enabling early risk identification and intervention.
Study context
- Population
- Acute type A aortic dissection (ATAAD) patients undergoing total arch replacement with frozen elephant trunk, single-centre cardiovascular hospital, October 2020–October 2024
- Participants
- 588 patients
- Exposure
- Training vs Validation
- Trainingn = 412
- Validationn = 176
- Outcome
- Best-performing model (XGBoost) performance
Methodological detailssingle-centre, machine learning prediction model, Lasso feature selection, fivefold cross-validation
- Single-centre
- Machine learning prediction model
- Lasso feature selection
- Fivefold cross-validation
Main finding
As reported in the abstract
| Group | AUC | Accuracy | Sensitivity | Specificity | F1 | Area under the precision-recall curve (AUPRC) |
|---|---|---|---|---|---|---|
| XGBoost | 0.96 | 0.96 | 0.93 | 0.96 | 0.79 | 0.83 |
XGBoost
AUC0.96
Accuracy0.96
Sensitivity0.93
Specificity0.96
F10.79
Area under the precision-recall curve (AUPRC)0.83
Observational data: associations, not effects.
Further findings
Key predictors (Lasso regression)
- Peak intraoperative lactate, blood transfusion volume, renal artery involvement, myoglobin, cystatin C, creatine kinase MB
Most significant predictor (SHapley Additive exPlanations analysis)
- Peak intraoperative lactate
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Machine Learning in Risk Prediction of Continuous Renal Replacement Therapy After Surgical Repair of Acute Type A Aortic Dissection. J Cardiothorac Vasc Anesth. Published 18 June 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →