Performance of automated CT ASPECTS in comparison to physicians at different levels on evaluating acute ischemic stroke at a single institution in China
Bibliographic record
Abstract
BACKGROUND: Our aim was to evaluate the sensitivity and specificity of the automated computer-based Alberta Stroke Program Early CT Score (e-ASPECTS) for acute stroke patients and compare the result with physicians at different levels. METHODS: In our center, e-ASPECTS and 9 physicians at different levels retrospectively and blindly assessed baseline computed tomography (CT) images of 55 patients. Sensitivity, specificity, receiver-operating characteristic curves, Bland-Altman plots with mean score error, and Matthews correlation coefficients were calculated. Comparisons were made between the scores by physicians and e-ASPECTS with diffusion-weighted imaging (DWI) being the ground truth. Two methods for clustered data were used to estimate sensitivity and specificity in the region-based analysis. RESULTS: In total, 1100 (55 patients × 20 regions per patient) ASPECTS regions were scored. In the region-based analysis, sensitivity of e-ASPECTS was better than junior doctors and residents (0.576 vs 0.165 and 0.111, p < 0.05) but inferior to senior doctors (0.576 vs 0.617). Specificity was lower than junior doctors and residents (0.883 vs 0.971 and 0.914) but higher than senior doctors (0.883 vs 0.809, p < 0.05). E-ASPECTS had the best Matthews correlation coefficient of 0.529, compared to senior doctors, junior doctors, and residents (0.463, 0.251, and 0.087, respectively). CONCLUSIONS: e-ASPECTS showed a similar performance to that of senior physicians in the assessment of brain CT of acute ischemic stroke patients with the Alberta Stroke Program Early CT score method.
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 | 0.009 |
| 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 | 0.000 | 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".