The study by Ma et. al, strives to create accessible AI-based equipment that effectively predicts the risk of new-onset postoperative atrial fibrillation (NOAF) in patients that recently went through coronary artery bypass grafting (CABG). The researchers collected data from 2994 patients that recently went through CABG over the course of March 2015 to July 2024. In total, the researchers evaluated 77 characteristics that could impact NOAF. To analyze the collected data, a stacking model of 11 base learners was created and SHAPley Additive exPlanations values (SHAP) were collected and plotted based on the characteristics. From this, the results from the developed stacking model were found to be exceptional, with the AUC value (area under curve) and F1 score to be .931 and .797 respectively. Additionally, the researchers utilized the calculated SHAP values to evaluate the influence that certain factors have on predicting NOAF, with brain natriuretic peptide (BNP) being the most important and smoking status the least. With aid from the stacking model results, the researchers created a more accessible bedside tool for NOAF risk prediction. Overall, the developed AI-based model for predicting NOAF after undergoing CABG and the bedside equipment were found to be not only successful but superior to other tools.