Real-World Comparison of Human and Software Image Assessment in Acute Ischemic Stroke Patients’ Qualification for Reperfusion Treatment
Bibliographic record
Abstract
Our aim was to compare human and computer accuracy in reading medical images of acute stroke patients. We analyzed data of patients who underwent assessment of Alberta Stroke Program Early CT Score (ASPECTS) and CT Perfusion (CTP) via Rapid Processing of Perfusion and Diffusion (RAPID) software RAPID ASPECTS, and RAPID CTP), compared to radiologist reports and manual measurements. We compared volumes calculated by RAPID CTP software with those selected by scanner-equipped software (GE). For reference, follow-up images were manually assessed in accordance with the Alberta Stroke Program Early CT Score (ASPECTS) territories retrospectively. Although exact ASPECTS score agreement between the automatic and manual methods, and between each method and follow-up, was poor, crossing of the threshold for reperfusion therapy was characterized by an 80% match. CT perfusion analyses yielded only slight agreement (kappa = 0.193) in the qualification of patients for therapy. Either automatic or manual scoring methods of non-contrast images imply similar clinical decisions in real-world circumstances. However, volume measurements performed by fully automatic and manually assisted systems are not comparable. Thresholds devised and validated for computer algorithms are not compatible with measurements performed manually using other software and should not be applied to setups other than those with which they were developed.
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 | 0.036 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".