Dermatological tracking of chronic acne treatment effectiveness
Bibliographic record
Abstract
Acne can lead to severe physical and psychological implications on chronic sufferers if not treated promptly and properly. Ramli et al. proposed a k-means cluster based algorithm to provide computer-assisted support for the manual grading of digital images. We propose an improved, automated, and more objective, grading method which involves optimizing the k-means clustering algorithm by identifying the actual number of clusters rather than basing analysis on a fixed K= 3 assumption for all images. The Hough transform was used to further analyze the found acne cluster leading to an approach to more accurately automatically determine the number and type of lesions. A quantitative comparison of the two approaches showed that the new approach provided a better match to the stated specialist analysis. We found it inappropriate to use accuracy and specificity performance analysis metrics to compare the algorithms. A better matching of the algorithms' accuracy to the specialist's analysis of the skin condition was found by modifying the sensitivity metric to account for the Michelson acne grading scale. This robustness suggests that the tool might be a first-step towards patient self-monitoring between visits to a specialist; potentially reducing visits frequency, decreasing wait times, and lead to a definitive standardized assessment scale.
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 | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".