Safety and Efficacy Results for DERM-ASSESS II Prospective, Multi-Centre Study
Study reported no adverse events as well as no significant difference between DermaSensor's and dermatologists' sensitivity and specificity
DermaSensor's sensitivity for melanoma was 100.0%* while the study dermatologists' was 90.9%. For BCC and SCC, also known as Non-Melanoma Skin Cancer (NMSC), DermaSensor's sensitivity was 93.3% and the dermatologists'. was 98.3%
- There were no adverse events, confirming the safety of this light-based, non-invasive device.
- There was no statistical difference between the sensitivity of DermaSensor (94.3%) and dermatologists' (97.2%) nor between their specificity (27.8% and 31.1%, respectively) for lesions biopsied in the study. DermaSensor's specificity for unbiopsied benign lesions** in the study was 41.5%, and the overall specificity (including biopsied and unbiopsied lesions) was 32.1%.
- As reported in Nature in 20191 "... most skin lesions are diagnosed by primary care doctors, and problems with inaccuracy have been underscored; if AI can be reliably shown to simulate experienced dermatologists, that would represent a significant advance."
- Literature suggests the range of Dermatologists' sensitivity for skin cancer is 82-100% 2 according to study design, with the middle of that range being 91%; PCPs sensitivity range is 54-88% 2,3 according to study design, with the middle of that range being 71%.
- With DermaSensor's overall sensitivity of 94.3%, DermaSensor correctly detects cancer approximately 23.3% more than a typical GP from literature.
Note: All clinical performance results referenced above are evidenced in data on file unless otherwise noted. Results are from study data provided on subjects enrolled through February 2020. For biopsied lesions, performance for Dermatologist In-Person Assessment is based on the study dermatologists' binary assessment of biopsied lesions as being malignant or benign, prior to receiving pathology results.
*Melanoma sensitivity includes lesions diagnosed as melanoma and as highly atypical nevi.
**For unbiopsied lesions the dermatologists' clinical determination of the lesion as benign was used as the reference standard.
2Chen SC, et al. A comparison of dermatologists' and primary care physicians' accuracy in diagnosing melanoma: a systematic review. Arch Dermatol. 2001;137(12):1627-1634.
3Argenziano G, et al. Dermoscopy improves accuracy of primary care physicians to triage lesions suggestive of skin cancer. J Clin Oncol. 2006;24(12):1877-1882.
DermaSensor ESS Technology Performance Across Different Studies
- Sensitivity for detecting all common skin cancer is 94.3% 1 to 94.4% 2
- Sensitivity for detecting melanoma has consistently been 100% 1-3
- Sensitivity for detecting non-melanoma skin cancer (NMSC) is 93.3% 1 to 93.8% 2
- Overall specificity for all benign lesions ranges from to 32.1% 1 to 36.4% 2
- Specificity for lesions which dermatologists decided merit biopsy ranges from 27.8% 1 to 31.1% 2
- Specificity for unbiopsied lesions that dermatologists clinically diagnosed as benign, but that they deemed suspicious to a lesser dermatologically trained healthcare practitioner, ranges from 41.5% 1 to 42.2% 2
1Clinical data on file
2Publication on a previous device version using DermaSensor's spectroscopy and machine learning technology. Rodriguez-Diaz E, et al. Optical Spectroscopy as a Method for Skin Cancer Risk Assessment. Photochem Photobiol. 2019;95(6):1441-1445.
3Published melanoma sensitivity for in situ and invasive melanomas, does not include highly atypical melanocytic lesions
DermaSensor Reader Study And Clinical Model Suggest That Physicians’ Use Of DermaSensor Improves Positive Predictive Value
49% Increase In True Positives
- 11.44% of lesions (~1 out of 9) that a physician refers/biopsies will be malignant with use of DermaSensor versus 7.70% of lesions (~1 out of 13) currently
- Accordingly, the relative likelihood that a physician’s referral/biopsy of a lesion is positive for cancer increases by 49%
Notes: Unpublished statistical model developed with and validated by a third-party biostatistician. Positive Predictive Value (PPV) is the probability that subjects with a positive screening test truly have the disease. PPV model uses US prevalence rates from biopsies in published literature and these prevalence rates were modeled with reader study results to estimate physician PPV with and without use of DermaSensor.