Hemodynamics, fluids & transfusion
Potential Predictors for Deterioration of Renal Function After Transfusion
Authors' conclusion
Surprisingly, only the recipients' characteristics played a decisive role in AKI prediction.
Study context
- Population
- Transfusion episodes of packed red blood cells at a university hospital, October 31, 2016 to August 31, 2020
- Participants
- 3,366 transfusion episodes
- Outcome
- Prediction of posttransfusion AKI (modified Kidney Disease Improving Global Outcomes (KDIGO) criterion)
Methodological detailsmachine learning (random forest), single-centre
- Machine learning (random forest)
- Single-centre
Main finding
As reported in the abstract
Prediction of posttransfusion AKI (modified KDIGO)
Area under the curve of the receiver operating characteristic (AUC-ROC)
0.73 ± 0.02
NPV
0.90 ± 0.02
PPV
0.32 ± 0.03
Observational data: associations, not effects.
Further findings
Predictors of posttransfusion acute kidney injury (AKI) (feature importance, relative risk)
- Donor features far less important than recipient features
Original publication
Potential Predictors for Deterioration of Renal Function After Transfusion. Anesth Analg. Published 16 February 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →