Severe illness getting noticed sooner – SIGNS-for-Kids: developing an illness recognition tool to connect home and hospital
Bibliographic record
Abstract
Background: Delays to definitive treatment for time-sensitive acute paediatric illnesses continue to be a cause of death and disability in the Canadian healthcare system. Our aim was to develop the SIGNS-for-Kids illness recognition tool to empower parents and other community caregivers to recognise the signs and symptoms of severe illness in infants and children. The goal of the tool is improved detection and reduced time to treatment of acute conditions that require emergent medical attention. Methods: A single-day consensus workshop consisting of a 17-member panel of parents and multidisciplinary healthcare experts with content expertise and/or experience managing children with severe acute illnesses was held. An a priori agreement of ≥85% was planned for the final iteration SIGNS-for-Kids tool elements by the end of the workshop. Results: One hundred percent consensus was achieved on a five-item tool distilled from 20 initial items at the beginning of the consensus workshop. The final items included four child-based items consisting of: (1) behaviour, (2) breathing, (3) skin, and (4) fluids, and one context-based item and (5) response to rescue treatments. Conclusions: Specific cues of urgent child illness were identified as part of this initial development phase. These cues were integrated into a comprehensive tool designed for parents and other lay caregivers to recognise the signs of serious acute illness and initiate medical attention in an undifferentiated population of infants and children. Future validation and optimisation of the tool are planned.
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
Direct model labels (unvalidated)
Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.
| Model arm | Categories | Study design | Confidence |
|---|---|---|---|
| gemma | no category Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Other design | low |
| gpt | no category Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Other design | low |
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 | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedLabeled directly by 2 models reading the full record.
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".