Machine-learning model incorporating perioperative hemodynamics predicts moderate-to-severe AKI after heart transplantation
Key result: A machine-learning model incorporating perioperative hemodynamic indices (pulmonary artery systolic pressure, mean arterial pressure, central venous pressure) predicted postoperative stage 2-3 AKI after heart transplant with an AUC of 0.898.
Incidence: 21.9% (25/114) of recipients developed moderate-to-severe AKI.
Best model: Light gradient boosting machine outperformed other algorithms in discrimination and calibration.
Clinical implication: The model may guide early hemodynamic optimization to reduce AKI risk, but requires external validation.
Design | Retrospective cohort study |
|---|---|
Setting | Single center in China |
Population | 114 orthotopic heart transplant recipients |
Outcome | Postoperative stage 2-3 acute kidney injury (KDIGO criteria) within 7 days |
Predictors | 8 factors including pulmonary artery systolic pressure, mean arterial pressure, central venous pressure, and preoperative creatinine |
Model performance | LightGBM: AUC 0.898, AUPRC 0.802, Brier score 0.106 |
Funding | Not reported in source |
Why This Study Matters
Sign in free to continue reading
Create or use your MedXY account to unlock the complete article.
This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication.