Accuracy of mobile devices for acute stroke head CT interpretation among Neurologists in training. (P1.083)
Bibliographic record
Abstract
Objective: To test accuracy of mobile devices (iPad and iPhone) in the interpretation of Head CT compared to standard Picture Archiving and Communication System (PACs) Radiology station among Neurologists in training. Background: Advances in technology has allowed physicians access to radiological images remotely facilitating their rapid interpretation. The diagnostic performance of this approach for acute stroke head CT scan interpretation among neurologists in training has not been evaluated. Design/ Methods: 9 readers (3 vascular neurology fellows, 3 PGY-4 and 3 PGY-3 neurology residents) independently interpreted 20 preselected acute stroke CTs. Images were viewed on iPad 2(1024x768 pixels) and iPhone 4 (960x640 pixels) using (ResMD® software (, Calgary Scientific, Calgary, CanadaA), and Radiology PACS station (gold standard). Readers recorded CT findings iIncluding Acute Ischemic Signs (AIS), Non-Acute Ischemic Signs (NAIS) and Hyperdense MCA (HMCA). A generalized, mixed linear model was constructed. Model-generated estimates of sensitivity & specificity (with 95[percnt] confidence intervals) were calculated. Results: For AIS, iPad had sensitivity of 83[percnt] (95[percnt]CI 69-92) and specificity of 60[percnt], (95[percnt]CI 41-76) compared to iPhone [sensitivity 79[percnt] (95[percnt]CI 60-90); specificity 58[percnt] (95[percnt]CI 36-77)]. For NAIS iPad sensitivity was 63[percnt] (95[percnt]CI 24-90) and specificity 77[percnt] (95[percnt]CI 37-95). iPhone sensitivity was 75[percnt] (95[percnt]CI 53-89) and specificity was 73[percnt] (95[percnt]CI 48-89). HMCA identification sensitivity on the iPad was 58[percnt] (95[percnt]CI 36-77) and specificity was 93[percnt] (95[percnt]CI 86-96) and iPhone sensitivity was 52[percnt] (95[percnt]CI 29-74) and specificity 90[percnt] (95[percnt]CI 81-95). Conclusions: Among neurologists in training (residents and stroke fellows) mobile devices had good to excellent sensitivity for identification of AIS. Mobile devices also has good to excellent specificity for the identification of the HMCA. Larger studies testing newer generation mobile devices and a greater breadth of findings are needed for comparison with traditional PACs interpretation prior to routine clinical practice.
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 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".