Key result
The LightGBM machine learning model accurately predicted acute kidney injury after coronary artery bypass grafting, achieving an area under the curve of 0.8027 in internal validation and up to 0.8798 in external validation.
Why the study?
Acute kidney injury after CABG is associated with poor outcomes, prompting the application of machine learning methods to establish AKI prediction models.
Cohort (n=4,831)
Yes
Effect estimate: AUC 0.8027 (95% CI 0.7511-0.8542)
A LightGBM machine learning model using perioperative clinical features can accurately predict the risk of acute kidney injury following isolated CABG surgery, potentially aiding in early identification of high-risk patients.
ML models may aid post-CABG AKI risk stratification; leaves open prospective validation before clinical use.
Background Acute kidney injury (AKI) after coronary artery bypass grafting (CABG) surgery is associated with poor outcomes. The objective of this study was to apply a new machine learning (ML) method to establish prediction models of AKI after CABG. Methods Totally 2780 patients from two medical centers in East China who underwent primary isolated CABG were enrolled. Then the dataset was randomly divided for model training (80%) and model testing (20%). Four ML models based on LightGBM, Support vector machine (SVM), Softmax and random forest (RF) algorithms respectively were established on Python. A total of 2051 patients from two other medical centers were assigned to an external validation group to verify the performances of the ML prediction models. The models were evaluated using the area under the receiver operating characteristics curve (AUC), Hosmer-Lemeshow goodness-of-fit statistic, Bland-Altman plots, and decision curve analysis. The outcome of the LightGBM model was interpreted using SHapley Additive exPlanations (SHAP). Results The incidence of postoperative AKI in the modeling group was 13.4%. Similarly, the incidence of postoperative AKI of the two medical centers in the external validation group was 8.2% and 13.6% respectively. LightGBM performed the best in predicting, with an AUC of 0.8027 in internal validation group and 0.8798 and 0.7801 in the external validation group. The SHAP revealed the top 20 predictors of postoperative AKI ranked according to the importance, and the top three features on prediction were the serum creatinine in the first 24h after operation, the last preoperative Scr level, and body surface area. Conclusion This study provides a LightGBM predictive model that can make accurate predictions for AKI after CABG surgery. This ML model shows good predictive ability in both internal and external validation. It can help cardiac surgeons identify high-risk patients who may experience AKI after CABG surgery.
No takes yet. Share an insight, caveat, or question.
Jia et al. (2023) conducted a cohort in Acute kidney injury after coronary artery bypass grafting (n=4,831). LightGBM machine learning model vs. SVM, Softmax, and Random Forest models was evaluated on Prediction of postoperative AKI (Area Under the Curve in internal validation) (AUC 0.8027, 95% CI 0.7511-0.8542). The LightGBM machine learning model accurately predicted acute kidney injury after coronary artery bypass grafting, achieving an area under the curve of 0.8027 in internal validation and up to 0.8798 in external validation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: