Study: Perceptions Rank Favorably for AI Use in Dermatology Practices

As artificial intelligence use grows in the field of dermatology, and the potential of it getting integrated into the clinical practice becomes a reality, many may wonder how dermatologists feel about this advancement.

Researchers in the Journal of Drugs in Dermatology created an IRB-approved 18-question survey to poll dermatologists on their perceptions of artificial intelligence (AI) in the dermatology practice.

Overall, 90 responders fully completed the survey, and were stratified by age to analyze the statistical differences between the perceptions. There were 54 survey takers (60%) who were slightly familiar with AI, and 73 responders (81.1%) who have not incorporated AI into their clinical practice. A portion of the responders (27.8%) perceived AI as superior to a human provider’s experience in some instances.

Most of the survey takers (94.4%)reported that they would at least use AI for certain scenarios and 65.6% of respondents believed that AI would help patients with analyzing and managing electronic health records. Less than half of respondents (38.9%) predict that AI will not decrease or increase the need for dermatologists and 51.6% of respondents felt that AI will at least somewhat enhance the dermatologists’ ability to screen skin lesions.

The 3 dermatology areas that AI was perceived to most beneficial were malignant skin lesions, benign skin lesions, and pigmentation disorders, according to the article. Additionally, the age of respondents did not have any significant impact on the perceptions of AI.

“Our results show that the dermatologists surveyed were generally positive toward embracing AI integration into clinical practice,” researchers concluded. “Further studies should be conducted to confirm these findings.”

Reference:

Wei C, Adusumilli N, Friedman A, Patel V. Perceptions of artificial intelligence integration into dermatology clinical practice: a cross-sectional survey study. J Drugs Dermatol. 2022;21(2):135-140. doi:10.36849/jdd.6398