Validation of Various Prediction Scores for Cardiac Surgery-Associated Acute Kidney Injury

Alhulaibi, Anwar Abdullatif; Alruwaili, Abdulrahman Mashatel; Alotaibi, Abdullah Saad; Alshakhs​, ​Fatima Nabih; Alramadhan, Habib Samir; Koudieh, ​Mohammed Salman

doi:10.37616/2212-5043.1322

Cited by 4 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Across Caucasian populations, the SRI and BRT had AUCs between 0.7-0.88 (24, 33-35, 41, 46, 49, 50) . SRI discrimination fell and was unacceptable in Asian populations (11,18,31) , with the exclusion of Wang et al (50) . The BRS was evaluated in one Chinese population with acceptable discrimination (31) .…”

Section: Risk Of Biasmentioning

confidence: 96%

“…35 studies introduced bias into outcome determination. 28 resulted from prior knowledge of predictor information (11-14, 16-18, 22, 25, 27, 28, 30, 31, 33-36, 39, 41, 42, 44, 46-52, 54) , 12 inappropriately determined/insu ciently described the outcome de nition (11,17,19,22,25,28,34,36,45,49,51,52) , whilst 12 did not determine the outcome equally for all (18,19,22,23,25,33,35,36,45,47,49,50) . 41 studies introduced signi cant bias through statistical analysis.…”

Section: Risk Of Biasmentioning

confidence: 99%

“…Calibration was not performed. Of the externally validated papers, 15 were validated for dialysis (11,16,18,21,22,24,28,31,33,35,41,43,46,49,50) . The remainder were validated for Any-Stage AKI, composite outcome AKI or speci c severity AKI.…”

Section: Risk Of Biasmentioning

confidence: 99%

“…Calibration was acceptable. The AKICS tool was externally validated in studies which validated for Any-Stage AKI (11,31) and 1 which validated for speci c stages of AKI as de ned by the RIFLE criteria (33) and 1 which validated it for composite outcome of Stage 2 or more AKI and dialysis as de ned by KDIGO (17) . Kiers et al found that AKICS had acceptable but inferior discrimination for milder forms of AKI and excellent discrimination for dialysis with an AUC of 0.84.…”

Section: Pre- Intra-and Post-operative Variable Modelsmentioning

confidence: 99%

“…Che et al's validation of composite outcomes yielded inferior but acceptable discrimination with an AUC of 0.74 (17) . For Any-Stage AKI, discrimination was poor with AUCs between 0.610 and 0.689 (11,31) . (39) .…”

Section: Pre- Intra-and Post-operative Variable Modelsmentioning

confidence: 99%

See 4 more Smart Citations

Renal Risk Prediction in Cardiac Surgery using traditional Methods of Acute Kidney Injury prediction: A Systematic Review

Jolliffe,

Sharma,

Thungathurthi

et al. 2024

Preprint

View full text Add to dashboard Cite

Objectives Acute Kidney Injury following Cardiac Surgery (CS-AKI) remains a significant cause of morbidity and mortality. To assist early recognition, risk prediction models have been developed over the last two decades. This review evaluates the current body of evidence for non-machine learning renal risk prediction models. Methodology A systematic review of 4 databases was undertaken according to PRISMA guidelines. Included studies were those that had derived and validated a renal risk prediction model in cardiac surgery patients. Machine learning models were excluded. Outcomes measured were pre, intra or post-operative variable use within the models and metrics for prediction. The PROBAST was used to evaluate for risk of bias. Results 44 studies were finally selected in a pooled population of 907,993. 24 developed renal risk prediction models whilst 31 externally validated these. When externally validated In Caucasian populations (N= 19), pre-operative prediction models offered reliable prediction for dialysis and severe AKI with area under the receiver operating curve (AUC) between 0.7-0.93. Models using intra-operative or post-operative variables (N=14) had acceptable prediction of severe stage AKI and dialysis with AUCs between 0.7-0.81. Pre-operative predictor models were the most externally validated. AKI prediction worsened with reducing severity of AKI. Validation of non-Caucasian populations was limited with 11 (25%) of studies undertaken in this group. Conclusion Pre-operative renal risk prediction models offer the most validated, accurate prediction for dialysis and severe CS-AKI. External validation of prediction tools for less-severe AKI and in non-Caucasian populations is required.

show abstract