MétaCan
Menu
Back to cohort
Record W2754313597

DERMATOLOGICAL TRACKING OF CHRONIC ACNE

2014· article· en· W2754313597 on OpenAlexaffvenue
Sergiu Lucut, Michael Smith

Bibliographic record

VenueJournal of undergraduate research in Alberta · 2014
Typearticle
Languageen
FieldMedicine
TopicAcne and Rosacea Treatments and Effects
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsAcneSchematicTracking (education)Computer scienceCluster analysisMedicineRegion of interestArtificial intelligencePsychologyDermatology
DOInot available

Abstract

fetched live from OpenAlex

INTRODUCTION Acne is a condition with severe physical and psychological implications on chronic sufferers, affecting approximately 80 percent of people between the ages of 11 and 30, at some point in their lives. The purpose of the research was to create a prototype that has the potential track changes in the condition for a person suffering from acne, in order to provide an accurate and standardized tool of assessment. Such a tool would be useful in both clinical and research settings where qualitative and quantifiable results are needed [1]. These are normally hard to obtain due to the low reproducibility and high subjectivity of the assessment which often leads to high inter and intra variability in graders. METHODS Images of (20) patients with healthy skin, acne, and other conditions similar in appearance to acne were used to test the algorithm, LS-KMC, that is explained in the schematic in Figure 1. The left side outlines the previous method based on Ramli et al.’s work [2], RMH-KMC, for comparison. RESULTS The results show that LS-KMC outclasses the previous system, not just by its ability to automatically characterize the condition in the region of interest (ROI), but also by achieving higher scores across all relevant metrics in 19 of the 20 cases. DISCUSSION AND CONCLUSIONS We proposed a new acne recognition approach to extend the previous k-clustering method proposed by Ramli et al. to introduce a higher level of computer aided support for providing acne scores. The new algorithm includes a number of steps to automate the identification and classification of acne features. Previously used metrics failed to take into account the nature of the condition and lead to unrealistically high success rates. A new metric, Characterization Sensitivity , was proposed for identifying the relative success of acne recognition algorithms. The metric uses a weighted area technique with assigned coefficients to the areas of the lesions based on the Michaelson grading scale [3]. The results showed that the proposed Lucut-Smith k-clustering algorithm performs much better than the previous systems.

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.005
Threshold uncertainty score0.015

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0050.001

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.

Opus teacher head0.068
GPT teacher head0.394
Teacher spread0.327 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2014
Admission routes2
Has abstractyes

Explore more

Same venueJournal of undergraduate research in AlbertaSame topicAcne and Rosacea Treatments and EffectsFrench-language works237,207