Hemodynamic determinants of postoperative neurocognitive impairment using Random Forest analysis and partial...

This study investigated the effect of hemodynamic data during cardiopulmonary bypass (CPB) on neurocognitive impairment in patients undergoing coronary artery bypass graft (CABG) surgery using machine learning algorithms. Twenty-eight CABG patients were included in the study. Systolic and diastolic blood pressure, pulse (PLS), and SpO₂ were recorded at 2.4-second intervals, yielding 730,870 data points (450,548 after artefact removal). Data were analyzed using Random Forest classification and Partial Dependence Plots (PDPs) to evaluate the collective and individual effects of parameters on neurocognitive outcomes. Separate analyses were conducted for the surgery period, bypass, and cross-clamp periods. Cognitive impairment was assessed using the Montreal Cognitive Assessment (MoCA), with a decrease of ≥ 2 points considered indicative of impairment. The highest classification accuracy (86%) was achieved during the bypass period when all parameters were analyzed together. Parameter importance varied by surgical phase: PLS was most significant during the surgery period and bypass periods. PDPs revealed specific optimal parameter ranges for each surgical phase. This study highlights the complex and dynamic role of hemodynamic parameters in preserving neurocognitive function during CABG surgery. Findings suggest that monitoring specific combinations of parameters during different surgical phases could help reduce neurocognitive risks. The significant importance of PLS data and its relationship with mean arterial pressure (MAP) values indicates that pulsatile flow may play a crucial role in neurocognitive protection. Future research should validate these findings in larger cohorts and develop phase-specific monitoring strategies for clinical implementation.