Hemodynamic determinants of postoperative neurocognitive impairment using Random Forest analysis and partial dependence plots
Bibliographic record
Abstract
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 SpO 2 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".