Mitigating diagnostic performance bias in a skin‐tone balanced dermatology curriculum
Bibliographic record
Abstract
INTRODUCTION: Individuals with skin of colour (SoC) have delayed diagnosis and poorer outcomes when presenting with some dermatologic conditions when compared to individuals with light skin (LS). The objective of this study was to determine if diagnostic performance bias can be mitigated by a skin-tone balanced dermatology curriculum. METHODOLOGY: A prospective randomised intervention study occurred over 2 weeks in 2020 at a Canadian medical school. A convenience sample of all first-year medical students (n = 167) was chosen. In week 1, all participants had access to dermatology podcasts and were randomly allocated to receive non-analytic training (NAT; online patient 'cards') on either SoC cases or LS cases. In week 2, all participants received combined training (CT; NAT and analytic training through workshops on how to apply dermatology diagnostic rules for all skin tones). Participating students completed two formative assessments after weeks 1 and 2. RESULTS: Ninety-two students participated in the study. After week 1, both groups had a lower diagnostic performance on SoC (p = 0.0002 and p = 0.002 for students who trained on LS 'cards' and SoC 'cards', respectively). There was a significant decrease in mean skin tone difference in both groups after week 2 (initial training on SoC: 5.8% (SD 12.2) pre, -1.4% (14.7) post, p = 0.007; initial training on LS: 7.8% (15.4) pre, -4.0% (11.8%) post, p = 0.0001). Five students participated in a post-study survey in 2023, and all found the curriculum enhanced their diagnostic skills in SoC. CONCLUSIONS: SoC performance biases of medical students disappeared after CT in a skin tone-balanced dermatology curriculum.
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 | 0.007 | 0.020 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".