Patients undergoing open heart surgery. The following patients were excluded: heart transplant recipients; those who required preoperative dialysis, preoperative extracorporeal membrane oxygenation, preoperative tracheostomy, or mechanical ventilation; patients who underwent procedures for automated implantable cardioverter-defibrillator, left ventricular assist devices, or sternal work.
Overall assessment: Pending.

Prediction accuracy: Good (c-statistic 0.81 in randomly selected internal validation set and 0.82 in development set).

Risk to reproducibility: Low. The model has demonstrated good performance in several external validation studies.

Risk of data reporting bias: Pending

Risk to transportability: Low. The model has demonstrated good performance in several external validation studies and has been used prospectively to select high-risk patients for clinical trials.