Clinical utility of a digital dermoscopy image-based artificial intelligence device in the diagnosis and management of skin cancer by dermatology health care providers, primary care providers, and nondermatology specialized physicians
Bibliographic record
Abstract
Background: Patients with skin lesions suspicious of skin cancer or atypical nevi frequently present to dermatology health care providers (DHPs), primary care providers (PCPs), and nondermatology specialized physicians (NDSPs) who have variable training in the triage and diagnosis of skin cancers and atypical melanocytic nevi. Objective: To evaluate the clinical utility of a digital dermoscopy image-based artificial intelligence algorithm (DDI-AI device) on the diagnosis and management of skin cancers by DHPs, PCPs, and NDSPs. Study Design: Forty-three United States licensed DHPs, PCPs, and NDSPs evaluated 50 clinical images and 50 digital dermoscopy images (DDIs) of the same skin lesions (25 malignant and 25 benign), first without and then with knowledge of the DDI-AI device output. Participants selected whether they thought the lesion was likely benign or malignant. Results: The overall management sensitivity for participants was 94.2% with the DDI-AI device, 84.1% with DDI, and 72.9% with clinical images; overall diagnostic sensitivity for participants was 87.0%, 79.6%, and 64.7%, respectively. Diagnostic specificity increased over baseline to 75.0% with the DDI-AI device, while no significant difference was observed in management specificity. DHPs had a statistically significantly higher baseline clinical (68.5% sensitivity vs. 59.6%) and dermoscopy (84.3% sensitivity vs. 73.3%) performance than PCPs and NDSPs. DHPs also achieved the highest diagnostic performance (87.7% sensitivity vs. 86.2%) when using the DDI-AI device. Conclusions: The use of the DDI-AI device may quickly, safely, and effectively improve skin cancer management and diagnosis when used by DHPs, PCPs, and NDSPs, independent of variable training and clinical experience.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".