Machine Learning for Predicting Neurosurgical Postoperative Cognitive Decline
Bibliographic record
Abstract
Background: Postoperative cognitive decline (POCD) in common in neurosurgical patients and significantly impacts functional independence. Several factors correlate to exacerbated POCD, including age, preoperative brain activity, and anesthesia type. However, little research has explored the use of artificial intelligence (AI) to predict POCD, which may personalize and improve patient treatment. This study aims to develop an AI tool which predicts POCD from neurosurgical patients based on patient and procedure characteristics for improved treatment outcomes. Hypothesis: We hypothesize that an AI tool trained on patient characteristics before and after surgery, along with procedure factors, may predict POCD. Methods: An AI tool will be trained and validated on neurosurgical case data to predict POCD risk and cognitive score (n = 200). Training data will include patient factors (demographics, blood test results, cognitive scores, lesion type) and procedure factors (anesthesia type, neurosurgical intervention). Cognitive score will be assessed using standard MoCA and MMSE tests. The tool will predict 7- and 30-day post-operative MoCA and MMSE score. We will validate the tool using a subset of patients (n = 50) and will assess model accuracy. Implications: AI-driven POCD prediction offers a cost-effective approach to personalized patient care. Integrating these tools into clinical workflows may better equip healthcare service providers to identify high risk patients, assess surgical risk, and adjust management, ultimately improving patient outcomes.
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 | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 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) | 0.002 | 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".