Ms. Anderson is from The University of Texas Health Science Center at San Antonio. Ms. Anderson also is from and Dr. Moy is from Moy, Fincher, Chipps Facial Plastics & Dermatology, Los Angeles, California. Mr. Tejani, Mr. Jarmain, and Dr. Kellett are from Triage Technologies Inc, Toronto, Ontario, Canada.
Cutis. 2023 May;111(5):254-258. doi: 10.12788/cutis.0764.
Early diagnosis of melanoma drastically reduces morbidity and mortality; however, most skin lesions are not initially evaluated by dermatologists, and some patients may require a referral. This study sought to determine the performance of an artificial intelligence (AI) application in classifying lesions as benign or malignant to determine whether AI could assist in screening potential melanoma cases. One hundred dermoscopic images (80 benign nevi and 20 biopsy-verified malignant melanomas) were assessed by an AI application as well as 23 dermatologists, 7 family physicians, and 12 primary care mid-level providers. The AI's high accuracy and positive predictive value (PPV) demonstrate that this AI application could be a reliable melanoma screening tool for providers.
早期诊断黑色素瘤可显著降低发病率和死亡率;然而,大多数皮肤病变最初并非由皮肤科医生评估,且一些患者可能需要转诊。本研究旨在评估人工智能(AI)应用程序在分类病变为良性或恶性方面的性能,以确定 AI 是否有助于筛选潜在的黑色素瘤病例。一百张皮肤镜图像(80 个良性痣和 20 个经活检证实的恶性黑色素瘤)由 AI 应用程序以及 23 名皮肤科医生、7 名家庭医生和 12 名初级保健中级提供者进行评估。AI 的高准确性和阳性预测值(PPV)表明,该 AI 应用程序可为提供者提供一种可靠的黑色素瘤筛查工具。