Incorporating demographics into a skin cancer diagnosis algorithm for Raman spectroscopy improves diagnostic specificity (Conference Presentation)
Bibliographic record
Abstract
Background & objective: Skin cancer is a very common malignancy that occurs more frequently in fair skin and older individuals. Raman spectroscopy is a non-invasive optical technique that can be used as an adjunct for skin cancer diagnosis. The objective of this study is to evaluate whether incorporating patient demographics can improve skin cancer diagnosis based on Raman spectroscopy. Patients & Methods: Raman spectra of 731 lesions and their respective adjacent normal skin were measured in vivo using a real-time Raman spectrometer. The lesions were divided into skin cancers (including malignant melanoma, basal cell carcinoma, squamous cell carcinoma and precancerous lesion - actinic keratosis, n = 340) and benign skin lesions (including pigmented nevi and seborrheic keratosis, n = 391). Patient age, gender, skin type and location of the lesion were incorporated into the analysis. Multivariate statistical analysis including principal component and general discriminant analysis (PC-GDA) and partial least squares (PLS) are used for skin cancer discrimination based on leave-one-out cross-validation. Results: The posterior probability of being a cancer is significantly dependent on gender, age and location of the lesion (p<0.05) but independent of skin type (p>0.05). The area under the receiver operating characteristic curve (ROC) is increased from 0.905 (95%CI: 0.884-0.927) to 0.932 (95%CI: 0.919-0.945) after taking into account demographics. Correspondingly, the specificity is increased from 43.2% to 50.1% at sensitivity of 99%; and from 73.4% to 77.5% at sensitivity of 90%. Conclusions: The specificity is increased after incorporating demographics into the algorithm for skin cancer diagnosis based on Raman spectroscopy.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".