Efficacy of current approaches to non-invasive diagnosis of skin cancer and the potential impact of artificial intelligence: A systematic review and meta-analysis.
Laura Awad, Samrhuddi Tagalpallewar, Sunil Parthiban et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review and meta-analysis evaluated the efficacy of non-invasive skin cancer diagnostic methods, focusing on artificial intelligence (AI) tools. The study analyzed 208 articles and found that AI demonstrated high sensitivity for melanoma diagnosis compared to clinician assessments. AI's performance in diagnosing basal cell carcinoma and squamous cell carcinoma remains uncertain.
Key findings
- AI interpretation of dermatoscopic images showed high sensitivity for melanoma diagnosis compared to clinician assessments.
- The diagnostic performance of AI was superior to dermatoscopic assessment alone.
- Reflectance confocal microscopy has high sensitivity for diagnosing cutaneous malignancy.
Why it matters
The findings highlight the potential of AI to enhance diagnostic accuracy in skin cancer, which could alleviate the burden on healthcare resources and improve patient outcomes, especially in primary care settings.