Reliability of Instant Messaging-Based Evaluation of Brain Imaging in Acute Stroke
Bibliographic record
Abstract
BACKGROUND: The use of instant messenger applications among physicians has become common in acute stroke management, especially in developing countries. Photos or video sequences of brain computed tomography (CT) scans are being sent to receive real-time support in assessing radiological findings. We analyzed whether instant messaging-based evaluation is precise enough to extract relevant information from the images. METHODS: In this prospective study, anonymized videos and photos of CT and CT angiography scans of patients with symptoms of acute stroke were recorded from the diagnostic monitor using a smartphone. Two neurologists and 2 neuroradiologists performed evaluation of the images using WhatsApp. The gold standard was set by 2 experienced neuroradiologists who evaluated the CT images with their full radiological equipment. Statistical analysis included the calculation of Cohen kappa (κ). RESULTS: A total of 104 brain images (derived from 81 patients) were included. All 4 raters performed with a perfect (κ=1) interobserver reliability in diagnosing intracerebral hemorrhage. For subarachnoid hemorrhage, interobserver reliability was slightly lower (raters 1, 2, and 3, κ=1; rater 4, κ=0.88). For diagnosing stroke mimics, interobserver reliability showed considerable variations (κ between 0.32 and 1). Alberta Stroke Program Early CT Score differences overall were comparable between raters and did not exceed 3 to 4 points without noticeable outliers. All raters performed with a moderate-to-substantial interobserver reliability for detecting large vessel occlusions (κ=0.48 in rater 1, κ=0.62 in rater 2, and κ=0.63 in raters 3 and 4). CONCLUSIONS: Stroke neurologists can reliably extract information on intracerebral hemorrhage from CT images recorded via smartphone and sent through instant messaging tools. Remote diagnosis of early infarct signs and stroke mimics was less reliable. We developed a standard for the acquisition of images, taking data protection into account.
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 | 0.025 | 0.075 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".