From Time to Tissue: The AI Revolution in Wake up Stroke
Bibliographic record
Abstract
Wake-up stroke (WUS), representing about 25% of ischemic strokes, presents a major therapeutic challenge due to the unknown time of symptom onset. The shift towards a tissue-based treatment paradigm, reliant on advanced neuroimaging, creates a pressing need for rapid and accurate image analysis. This review systematically synthesizes and appraises the current evidence on artificial intelligence (AI) for the diagnosis, triage, and management of WUS. Following PRISMA guidelines, a comprehensive literature search was conducted across PubMed, Scopus, and Web of Science from inception through March 2024 for studies developing or validating AI models in WUS or late-window stroke. Analysis of 42 included studies demonstrates that AI models, particularly deep learning applied to non-contrast CT (NCCT) and MRI, achieve high diagnostic accuracy (AUCs often 0.89–0.95) in detecting early ischemia, quantifying infarct core and penumbra, and identifying the DWI-FLAIR mismatch. Commercial AI tools now automate these assessments, providing objective, trial-aligned eligibility criteria. Emerging multimodal models show promise for predicting functional outcomes and complications like hemorrhagic transformation. In conclusion, AI integration enables a data-driven, tissue-based approach that can expand treatment access in WUS. For routine clinical adoption, challenges regarding generalizability, interpretability, and the need for robust prospective validation to prove patient outcome benefits must be addressed.
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 | 0.006 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".