Are We Missing Something? The Skin Lesions Not Seen in Teledermatology
Bibliographic record
Abstract
Background The suspected skin cancer electronic referral pathway was introduced in 2017. It requires general practitioners to add regional, close-up, and dermoscopic images to a lesion-specific referral template for a teledermatologist to review and advise on management. The virtual lesion clinic is a nurse-led clinic used since 2010 to obtain high-quality images for teledermoscopy assessment. A limitation of both services is the absence of a full-body examination. Objective This study aims to evaluate the number of skin cancers missed during teledermatology assessment. Methods This is a retrospective review of skin lesion referrals to dermatology. Suspected skin cancer referrals made in the latter half of 2020 were compared with referrals to the virtual lesion clinic during a similar time period in 2016. Results The study included 481 patients with 548 lesions in the 2020 suspected skin cancer cohort that were matched for age, sex, and ethnicity to 400 patients with 682 lesions in the 2016 virtual lesion clinic cohort. A total of 41 patients underwent subsequent specialist review in the suspected skin cancer cohort compared to 91 in the virtual lesion clinic cohort. A total of 20% of the suspected skin cancer cohort and 24% of the virtual lesion clinic cohort were found to have at least one additional lesion of concern. The majority of these were keratinocytic skin cancers; there were 2 and 0 additional melanomas or melanoma-in-situ, respectively. The virtual lesion clinic nurses identified additional lesions for imaging in 78 of 400 (20%) patients assessed in the virtual lesion clinic. The teledermatologist determined (author AO) that 73% of these additional lesions were malignant. Of the 548 lesions, 10 (2%) in the suspected skin cancer group were rereferred, none of which had a change in diagnosis. Out of 682 lesions, 16 (2%) in the virtual lesion clinic cohort were rereferred, 6 (1%) of which had a change in diagnosis. Conclusions Patients diagnosed with skin cancer often have multiple lesions of concern. Single-lesion teledermoscopy diagnoses have high concordance with in-person evaluation and histology; however, we have shown that in-person examination may reveal other suspicious lesions. The importance of a full-body skin examination should be emphasized to the referrer. Acknowledgments The Waikato Medical Research Foundation provided financial support for the study. Conflicts of Interest None declared.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| 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".