Abstract T P28: Diagnostic Accuracy of Mobile Devices for Remote Acute Stroke Neuroimaging Interpretation
Bibliographic record
Abstract
BACKGROUND: Advances in technology allow physicians’ access to radiological images remotely, virtually anytime, anywhere to streamline stroke management. OBJECTIVE: To compare the diagnostic accuracy of different mobile devices in interpretation of acute head CT for various ischemic stroke findings among various readers. METHODS: 20 selected acute stroke head CT were independently interpreted by 11 readers (7 Neurologists, 3 Neuroradiologists and 1 Radiologist) on 2 mobile devices, iPad® 2 (1024x768 pixels) and iPhone® 4 (960x640 pixels), and on the Picture Archiving and Communication System (PACS) workstation (1280x1024 pixels). Both mobile devices used a FDA-cleared ResolutionMD software (ResMD® Calgary Scientific, Calgary, Canada). Primary outcome measures included: any acute ischemic sign (AIS), any non acute ischemic sign (NAIS), and any hyperdense middle cerebral artery (HMCA) sign. For each outcome intra-rater inter-device accuracy, using a rater specific gold standard, were evaluated and estimated % Sensitivity (Sen) and % Specificity (Spe) with 95% Agrest-Coull Confidence Intervals (CIs) were reported from frequency tables. RESULTS: Across all 11 readers, for AIS: Sen = 76 (68, 82) and Spe = 75 (64, 83) on iPhone; Sen = 76 (69, 83), Spe = 71 (60, 80) on iPad. For for NAIS: Sen = 80 (72, 86) and Spe = 77 (67, 84) on iPhone and Sen = 75 (67, 82) and Spe = 80 (71, 87) on iPad. For HMCA Sen = 53 (39, 67) Spe = 97 (93, 99) on iPhone and Sen = 62 (48, 75) and Spe = 95 (91, 98) on iPad. CONCLUSIONS: This is the first study directly comparing the diagnostic accuracy of two different mobile devices for acute head CT ischemic stroke findings. Both iPhone and iPad have fair sensitivity for detection of AIS and NAIS, while poorer sensitivity for HMCA when read by readers from different specialties. Specificity was good to excellent for all 3 head CT ischemic stroke findings. iPhone and iPad have similarly good diagnostic accuracy for acute ischemic stroke head CT scan findings supporting their use for remote neuroimaging interpretation. Their validation in routine clinical practice needs to be confirmed in larger studies.
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 | 0.037 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| 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) | 0.004 | 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".