Diagnosing contact dermatitis using machine learning: A review
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: Machine learning (ML) offers an opportunity in contact dermatitis (CD) research, where with full clinical picture, may support diagnosis and patch test accuracy. OBJECTIVE: This review aims to summarise the existing literature on how ML can be applied to CD in its entirety. METHODS: Embase, Medline, IEEE Xplore, and ACM Digital Library were searched from inception to February 7, 2024, for primary literature reporting on ML models in CD. RESULTS: 7834 articles were identified in the search, with 110 moving to full-text review, and six articles included. Two used ML to identify key biomarkers to help distinguish between allergic contact dermatitis (ACD) and irritant contact dermatitis (ICD), three used image data to distinguish between ACD and ICD, and one used clinical and demographical data to predict the risk of positive patch tests. All studies used supervision in their ML model training with a total of 49 704 patients across all data sets. There was sparse reporting of the accuracy of these models. CONCLUSIONS: Although the available research is still limited, there is evidence to suggest that ML has potential to support diagnostic outcomes in a clinical setting. Further research on the use of ML in clinical practice is recommended.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.007 | 0.003 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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