Efficacy of a Photograph-Based Triage System Initiated During the COVID-19 Pandemic to Identify and Streamline Pediatric Foot and Ankle Referrals
Bibliographic record
Abstract
Background: The COVID-19 pandemic required hospitals to reduce in-person visits. Although most pediatric foot and ankle conditions do not require urgent consultation, clubfoot (CF) relies on early identification and treatment. To avoid unnecessary hospital visits for infants, we developed a triage system using standardized clinical photographs of the child’s feet taken by the parents for clinician review. This study assesses the efficacy of this triage system based on accuracy of the triage diagnosis (TDx) and time from referral to initial consultation (IC). Methods: This is a retrospective cohort review of patients referred to a tertiary care pediatric institution for a foot and ankle condition from 03/16/20 to 09/15/20 (onset of COVID-19), and from the same period in 2019 (prior to use of the triage system). Patients were identified by referring diagnosis (RDx). Patients were excluded if they missed their initial visit or the RDx was not clear. Chart review was performed to collect demographic data, clinical photographs, RDx, TDx, IC diagnosis, and time to IC. Diagnosis accuracy (DA) scores were assigned: 0 when RDx or TDx did not match diagnosis at IC, 0.5 if the diagnosis was partly correct, and 1 when diagnoses aligned. Results: Of the 118 patients included, 62 were referred for CF and 56 for other foot and ankle conditions (FA). In 2020, 23/27 CF and 11/12 FA patients sent photographs. The average time to IC for FA patients was similar in both years (142 days in 2019 vs 183 days in 2020, p= 0.24), while the average time to IC for CF decreased from 66 days in 2019 to 31 days in 2020 (p=0.08). Accuracy for TDx in 2020 was high for CF (0.98) and FA (0.92) patients (p=0.49). Conclusion: Triage diagnosis was accurate and time from referral to consultation decreased for clubfoot patients from 2019 to 2020 supporting that this novel photo-based triage system for pediatric foot and ankle referrals is effective in identifying urgent consults and ensuring timely assessment.
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 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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, unvalidatedMachine predicted; a candidate call from one teacher head, 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".