Safety and Efficacy Results for DERM-ASSESS II Prospective, Multi-Centre Study
Overall study performance summary: 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% while the study dermatologists' was 90%. For non-melanoma skin cancer (NMSC), i.e. BCC and SCC, DermaSensor's performance was 93% and the dermatologists' was 98%.
DermaSensor and Dermatologist Sensitivity For Skin Cancers
- 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 (93%) and dermatologists' (96%) nor between their specificity (32% and 37%, respectively) for lesions biopsied by the dermatologists per their standard of care.
- DermaSensor's specificity was 47% for benign lesions assessed by the study dermatologists as being suggestive of skin cancer to non-specialist healthcare professionals.1
- DermaSensor's sensitivity results for melanoma, SCC and BCC were 100%, 94% and 92%, respectively. Dermatologists' sensitivity results were 90%, 96% and 100%, respectively.
- As reported in Nature in 2019 2 "... 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."
- In a randomized, prospective study of DermaSensor utility with 57 GPs, these physicians made over 5,000 assessments of skin lesions. The study results showed that physicians’ correctly referred or biopsied cancerous lesions 13 percent more when the DermaSensor output was available to them, compared to their evaluations with no device output.
- DermaSensor increased physicians’ cancer detection sensitivity from 81% to 94%, and this improvement was statistically significant (p = .0009). There was no statistically significant change in the GP’s specificity, or false positive rate, for benign lesions (p = .3558).
Note: All study results referenced above are evidenced in data on file unless otherwise noted. For lesions biopsied in DERM-ASSESS II, dermatologist performance (i.e. dermatologist sensitivity and specificity) is based on the study dermatologists' in-person binary assessment of biopsied lesions as being malignant or benign, prior to receiving pathology results
1For unbiopsied lesions the dermatologists' clinical determination of the lesion as benign was used as the reference standard; however, for the dermatologists' clinical assessment there was no reference standard since no biopsies were performed and accordingly no specificity is reported for their evaluations.
2Topol E. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine. 2019;25:44-66.
3Data on file for DERM-ASSESS II clinical study and publication 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.
DermaSensor ESS Technology Performance Across Different Studies
- Sensitivity for detecting all common skin cancer is 93% 1,2 to 94% 3
- Sensitivity for detecting melanoma has consistently been 100%, which includes in situ and invasive melanomas 1-3
- Sensitivity for detecting non-melanoma skin cancer (NMSC) is 93% 1,2 to 94% 3
- Overall specificity for all benign lesions ranges from to 36% 3 to 37% 1,2
- Specificity for lesions which dermatologists decided merit biopsy ranges from 31% 3 to 32% 1,2
- Specificity for unbiopsied lesions that dermatologists clinically diagnosed as benign, but that they deemed suspicious to a lesser dermatologically trained healthcare professional, ranges from 42% 3 to 47% 1,2
1Clinical data on file
2Poster presentation on preliminary DERM-ASSESS II results. Benvenuto-Andrade et al. (2020) Safety and Effectiveness of Elastic Scattering Spectroscopy and Machine Learning in the Evaluation of Skin Lesions for Cancer. 8th World Congress of of Teledermatology, Imaging, an AI for Skin Diseases
3Publication 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.
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.
