Breakthrough in Cancer Detection: AI-Enabled Device Improves Diagnosis and Management
Researchers at the University of North Carolina have made a significant breakthrough in cancer detection using an artificial intelligence-enabled device. The study, published in the Journal of Primary Care & Community Health, found that the device, employing Elastic Scattering Spectroscopy (ESS), improved diagnostic sensitivity and management performance in primary care physicians (PCPs) when detecting skin cancer.
Key Takeaways:
- The ESS device, enabled with an AI algorithm, distinguished between benign and malignant tissue in vivo without the need for a surgical biopsy.
- The device aided PCPs in their management of lesions suspicious for skin cancer, increasing diagnostic sensitivity from 71.1% to 81.7% and referral sensitivity from 82.0% to 91.4%.
- Device-aided diagnostic specificity decreased from 60.9% to 54.7%, and referral specificity decreased from 44.2% to 32.4%.
- The overall management performance (AUC) increased from 0.708 to 0.762, and from 0.567 to 0.682 for lesions where physicians reported low confidence in their unassisted management decision.
- The study concluded that the use of the ESS device output by PCPs significantly improved their diagnostic and management sensitivities as well as their overall management performance.
Statistics:
- Diagnostic sensitivity increased significantly from 71.1% to 81.7% (P = .0085) with the use of the ESS device.
- Referral sensitivity increased significantly from 82.0% to 91.4% (P = .0027) with the use of the ESS device.
- Device-aided diagnostic specificity decreased from 60.9% to 54.7% (P = .1896).
- Referral specificity decreased from 44.2% to 32.4% (P = .0256).
- Overall management performance (AUC) increased from 0.708 to 0.762 with the use of the ESS device.
Sources:
- DERM-SUCCESS FDA Pivotal Study: A Multi-Reader Multi-Case Evaluation of Primary Care Physicians' Skin Cancer Detection Using AI-Enabled Elastic Scattering Spectroscopy. Journal of Primary Care & Community Health, 2025,16.
- University of North Carolina
- Dermasensor Inc.