SOC underrepresentation in dermatology AI hinders lesion identification. Addressing dataset biases vital for equitable patient care. Explore full study implications.
(HealthDay News) — Challenges relating to artificial intelligence (AI) in dermatology and its application to skin of color (SOC) are partly due to underrepresentation of SOC in datasets, according to research published online March 6 in the International Journal of Dermatology.
Rebecca Fliorent, from the Rowan-Virtua School of Osteopathic Medicine in Stratford, New Jersey, and colleagues analyzed recent literature to assess current AI programs in use for dermatologic purposes to identify challenges with application of this technology to SOC. Literature from the last 10 years through October 2023 was analyzed.
The researchers note that challenges relating to AI and its application to SOC come from the underrepresentation of SOC in datasets, as well as issues with quality and standardization of images. Current AI programs are worse at identifying lesions in SOC because of these issues. Furthermore, only 30 percent of the programs identified in the literature reported on their use in dermatology, specifically in SOC. For an accurate depiction of darker skin tone images in datasets, significant development of these applications is needed.
“Although the mentioned AI programs do not constitute a comprehensive list, many of these programs show promise in supporting clinical decision-making; however, they require modification to become reliable diagnostic aids for SOC patients,” the authors write.
Abstract/Full Text (subscription or payment may be required)
By subscribing, you consent to receive emails from BlackDoctor.pro You may unsubscribe at any time. Privacy Policy & Terms of Service.
Are you a healthcare professional? Register with us today!