Artificial intelligence vs. dermoscopy for malignancy risk stratification of pigmented skin lesions: a systematic review and meta-analysis for public health

Ming Diao, Yaxi Zhu, Hailing Tang · 2026

Read Artificial intelligence vs. dermoscopy for malignancy risk stratification of pigmented skin lesions: a systematic review and meta-analysis for public health by Ming Diao, Yaxi Zhu, Hailing Tang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13457125.txt.

Description

Ming Diao, Yaxi Zhu, and Hailing Tang compare, in a 2026 meta-analysis, artificial intelligence against the dermatologist's magnifier for judging whether a pigmented skin spot may be malignant. Sorting such spots well catches melanoma early and spares healthy skin needless cutting. The team searched four databases and kept ten studies with seventeen test arms.

Performance overlapped heavily. Dermoscopy sensitivity ranged from about 42 to 97 percent across studies, and AI landed in a similar span. AI specificity likewise overlapped the clinicians' range. In the single study of clinicians aided by AI, sensitivity was perfect and specificity solid, a hint that partnership may beat either alone. Spread between studies was wide, reflecting varied algorithms and settings. No publication bias showed. The authors conclude that today's AI matches standard dermoscopy on average, with consistency, not peak skill, as the open problem.

Catalog record

CREATORMing Diao, Yaxi Zhu, Hailing Tang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE39 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13457125

Browse the full library · About the Tower of Babel