AI and machine learning algorithms demonstrated areas under the curve between 0.80 and 0.93 for predicting post-CABG atrial fibrillation, exceeding traditional clinical risk scores.
Do artificial intelligence and machine learning models improve the prediction of postoperative atrial fibrillation in patients undergoing CABG compared to traditional risk scores?
AI and machine learning models integrating multimodal data show promising predictive accuracy for post-CABG atrial fibrillation, outperforming traditional risk scores, though external validation is still needed.
Postoperative atrial fibrillation (POAF) remains one of the most frequent and consequential complications following coronary artery bypass grafting (CABG), occurring in 15–30% of patients and contributing to increased morbidity, prolonged hospitalization, and higher long-term mortality. Despite decades of investigation, traditional risk models have shown limited predictive accuracy due to the multifactorial nature of POAF. Recent advances in artificial intelligence (AI), machine learning (ML), and biomarker discovery have begun to transform predictive modeling, enabling integration of complex, multimodal datasets. This review synthesizes the emerging evidence from recent studies applying AI and ML approaches for POAF prediction, with focus on clinical, biochemical, genomic, and molecular dimensions. Across studies, modern algorithms demonstrate areas under the curve (AUCs) between 0.80 and 0.93, with performance exceeding that reported for traditional clinical risk scores. However, external validation, model calibration, and biases remain to be fully addressed before clinical translation is considered. The convergence of interpretable AI, metabolic and genetic biomarkers, and clinical data offers a promising path toward individualized risk stratification and targeted postoperative management.
Ghani et al. (Mon,) conducted a review in Postoperative atrial fibrillation (POAF) following CABG. Artificial intelligence and machine learning predictive models vs. Traditional clinical risk scores was evaluated on Predictive accuracy (AUC) for POAF. AI and machine learning algorithms demonstrated areas under the curve between 0.80 and 0.93 for predicting post-CABG atrial fibrillation, exceeding traditional clinical risk scores.