Incidence of early postoperative cognitive dysfunction and overall patient and surgical risks in older patients undergoing cardiac surgery

duration and blood loss, and the eXtreme Gradient Boosting model for postoperative patient placement predictions.Results: The tool achieved an adjusted R 2 of 0.92 (CI 0.909e0.939) in predicting surgical duration (Fig. 1), adjusted R 2 of 0.66 (CI 0.649e0.671)for operative blood loss, and a receiver operating characteristic area under the curve of 0.83 (CI 0.819e0.841)for predicting postoperative ward placement.The model also includes a feedback loop from patient outcomes, ensuring continuous improvement and refinement of the tool.Important predictors of an extended surgical duration were BMI (odds ratio [OR] 5.54, CI 5.42e5.65),international normalized ratio (OR 4.74, CI 4.65e4.84),heart failure (OR 1.41, CI 1.32e1.50).Conclusions: The Pre-Anesthesia AI Tool has been developed to serve as a Software as Medical Device (SaMD) for physicians, aiding in the preoperative planning process.We believe that this ISO 13485 certified tool will contribute to improved patient outcomes and operational efficiency.