Abstract TP308: Predictive model for Stroke Mimics during Code Stroke Evaluation
Bibliographic record
Abstract
Introduction: A common approach at differentiating acute ischemic stroke (AIS) from stroke mimics (SM) is medical history and clinical presentation. However, combination of certain clinical symptoms and signs are more associated with SM than with AIS. Identifying these clinical features during “Code Stroke “would help clinicians to raise high suspicion to identify SM and thus prevent futile IV thrombolysis. Hypothesis: A predictive model will identify a combination of signs and symptoms associated with SM. Methods: A retrospective cohort over a 4-year period was used to construct a predictive model with recursive partitioning. Results: During the study period, out of 1467 “Code Stroke” activations, 508 patients were eligible for IV thrombolysis. After initial analysis of 43 “Code Stroke” clinical features, we identified 11 signs and symptoms that were significantly different in AIS and SM patients: age, systolic blood pressure, atrial fibrillation (AF), being on antithrombotic at presentation, similar admissions in the past, seizure at onset, headache at presentation, encephalopathy, focal neurological symptoms, NIHSS and old stroke on head CT. Using a predictive model analysis, headache at presentation, absence of focal symptoms, and seizure at onset significantly predicted of SM. A high predictive value of 92%, (CI: 88-95%) for SM included: i) headache at presentation, ii) no headache without focal symptoms, iii) no headache with at least one focal symptom and seizure at onset. While a low SM predictive value of 29% (CI: 23-35%) included no headache at presentation with at least one focal symptom and no seizure at onset. Conclusion: Our study found that among other symptoms, headache, absence of focal symptoms, and seizure at onset have strongest association with SM during “Code Stroke”. Study results further need to be validated in prospective cohort.
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 | 0.005 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".