Prediction of recurrence and functional status in young ischemic stroke patients: Comparison of machine learning and traditional statistical methods
Bibliographic record
Abstract
Abstract Introduction Ischemic stroke in young adults is a significant social and economic burden. Machine learning (ML) techniques can potentially predict the outcomes of recurrence and functional status after a stroke more accurately than traditional statistical methods. We sought to predict these outcomes in young individuals with stroke with machine learning and compare that with traditional statistical methods. Methods This study is part of Global Outcome Assessment Lifelong After Stroke in Young Adults (GOAL) initiative, which collects individual patient data from hospital-based young stroke (18-50 years) cohorts from 29 countries covering all continents worldwide. We compared several common machine learning models with traditional logistic regression to investigate the best models for predicting functional outcome, as measured by the modified Rankin scale at three months post-stroke, and stroke recurrence during follow-up. Results Functional outcome was available for 7937 patients, and stroke recurrence for 9366 patients. Poor functional outcomes post-stroke occurred in 27.0% of cases, and stroke recurrence in 10.1% of cases during a median follow-up time of 75 months. For functional outcome, multilayer perceptron model achieved the highest mean area under the receiver operating characteristic curve (AUC) at 0.92±0.08. Random forest model attained the highest AUC (0.68±0.03) for predicting stroke recurrence. However, their results were not statistically significantly higher than those for logistic regression. Conclusion Our work explored the use machine learning to predict outcomes in young stroke patients. However, in our cohort, ML methods provided only moderate added value compared to logistic regression for predicting stroke recurrence and functional outcome.
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 | 0.007 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| 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".