Rabinovitz, Harold

Background: Patients with skin lesions suspicious for skin cancer or atypical melanocytic nevi of uncertain malignant potential often present to dermatologists, who may have variable dermoscopy triage clinical experience. 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 dermatologists. Methods: Thirty-six United States board-certified dermatologists evaluated 50 clinical images and 50 digital dermoscopy images of the same skin lesions (25 malignant and 25 benign), first without and then with knowledge of the DDI-AI device output. Participants indicated whether they thought the lesion was likely benign (unremarkable) or malignant (suspicious). Results: The management sensitivity of dermatologists using the DDI-AI device was 91.1%, compared to 84.3% with DDI, and 70.0% with clinical images. The management specificity was 71.0%, compared to 68.4% and 64.9%, respectively. The diagnostic sensitivity of dermatologists using the DDI-AI device was 86.1%, compared to 78.8% with DDI, and 63.4% with clinical images. Diagnostic specificity using the DDI-AI device increased to 80.7%, compared to 75.9% and 73.6%, respectively. Conclusion: The use of the DDI-AI device may quickly, safely, and effectively improve dermoscopy performance, skin cancer diagnosis, and management when used by dermatologists, independent of training and experience.

AbstractBackgroundDiagnosis of suspected basal cell carcinoma (BCC) is typically confirmed with incisional biopsy before referral to final surgery.ObjectiveTo investigate the clinical confidence and accuracy of physicians making a diagnosis of BCC based on dermoscopic and reflectance confocal microscopy (RCM) features.MethodsThis study was designed as a simulation to determine the certainty and willingness to refer to surgery without previous biopsy confirmation of BCC. Study subjects were identified with suspected BCC. Dermoscopic and RCM lesion images were obtained before biopsy. Eight clinicians with various expertise levels blindly interpreted these images and chose among four hypothetical treatment options: definite BCC, refer directly to surgery without biopsy; other malignancy, perform biopsy for diagnosis; uncertain diagnosis, perform biopsy; benign, do not biopsy. Decisions for treatment were based on dermoscopic images alone and, subsequently, on dermoscopic and RCM images combined.ResultsThe sensitivity for referral to surgery without biopsy was 67.6% with the use of dermoscopy; the positive predictive value (PPV) was 97.0%. Adding RCM increased the sensitivity to 76.5% and the PPV to 98.6%.ConclusionsDermoscopy provides a high PPV for BCC. The addition of RCM to dermoscopy increases diagnostic sensitivity, particularly in less experienced dermoscopists. Physician behavior might be different if actual referrals were made for surgery without biopsy.