A Web-based System to Assist With Etiology Differential Diagnosis in Children With Arterial Ischemic Stroke
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND AND PURPOSE: The diagnosis of childhood arteriopathy is complex. We present a Web-based, evidence-backed classification system to return the most likely cause(s) of a pediatric arterial ischemic stroke. This tool incorporates a decision-making algorithm that considers a patient's clinical and imaging features before returning a differential diagnosis, including the likelihood of various arteriopathy subtypes. METHODS: The Vascular Effects of Infection in Pediatric Stroke study prospectively enrolled 355 children with arterial ischemic stroke (2010-2014). Previously, a central panel of experts classified the stroke etiology. To create this tool, we used the 174 patients with definite arteriopathy and spontaneous cardioembolic stroke as the "derivation cohort" and the 34 with "possible" arteriopathy as the "test cohort." Using logistic regression models of clinical and imaging characteristics associated with each arteriopathy subtype in the derivation cohort, we built a decision framework that we integrated into a Web interface specifically designed to create a probabilistic differential diagnosis. We applied the Web-based tool to the "test cohort." RESULTS: The differential diagnosis returned by our tool was in complete agreement with the experts' opinions in 20.6% of patients. We observed a partial agreement in 41.2% of patients and an overlap in 29.4% of patients. The tool disagreed with the experts on the diagnoses of 3 patients (8.8%). CONCLUSIONS: Our tool yielded an overlapping differential diagnosis in most patients that defied definitive classification by experts. Although it needs to be validated in an independent cohort, it helps facilitate high-quality, and timely diagnoses of arteriopathy in pediatric patients.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it