ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Comparison of humans versus mobile phone-powered artificial intelligence for the diagnosis and management of pigmented skin cancer in secondary care: a multicentre, prospective, diagnostic, clinical trial

Menzies, Scott W.*; Sinz, Christoph; Menzies, Michelle; Lo, Serigne N.; Yolland, William; Lingohr, Johann; Razmara, Majid; Tschandl, Philipp; Guitera, Pascale; Scolyer, Richard A.; Boltz, Florentina; Borik-Heil, Liliane; Chan, Hsien Herbert; Chromy, David; Coker, David J.; Collgros, Helena; Eghtedari, Maryam; Forteza, Marina Corral; Forward, Emily; Gallo, Bruna; Geisler, Stephanie; Gibson, Matthew; Hampel, Amelie; Ho, Genevieve; Junez, Laura; Kienzl, Philipp; Martin, Arthur
Lancet Digital Health2023-10DOI: 10.1016/S2589-7500(23)00130-9
16被引4阅读
引用收藏
分享

摘要

Background Diagnosis of skin cancer requires medical expertise, which is scarce. Mobile phone-powered artificial intelligence (AI) could aid diagnosis, but it is unclear how this technology performs in a clinical scenario. Our primary aim was to test in the clinic whether there was equivalence between AI algorithms and clinicians for the diagnosis and management of pigmented skin lesions. Methods In this multicentre, prospective, diagnostic, clinical trial, we included specialist and novice clinicians and patients from two tertiary referral centres in Australia and Austria. Specialists had a specialist medical qualification related to diagnosing and managing pigmented skin lesions, whereas novices were dermatology junior doctors or registrars in trainee positions who had experience in examining and managing these lesions. Eligible patients were aged 18-99 years and had a modified Fitzpatrick I-III skin type; those in the diagnostic trial were undergoing routine excision or biopsy of one or more suspicious pigmented skin lesions bigger than 3 mm in the longest diameter, and those in the management trial had baseline total-body photographs taken within 1-4 years. We used two mobile phonepowered AI instruments incorporating a simple optical attachment: a new 7-class AI algorithm and the International Skin Imaging Collaboration (ISIC) AI algorithm, which was previously tested in a large online reader study. The reference standard for excised lesions in the diagnostic trial was histopathological examination; in the management trial, the reference standard was a descending hierarchy based on histopathological examination, comparison of baseline total-body photographs, digital monitoring, and telediagnosis. The main outcome of this study was to compare the accuracy of expert and novice diagnostic and management decisions with the two AI instruments. Possible decisions in the management trial were dismissal, biopsy, or 3-month monitoring. Decisions to monitor were considered equivalent to dismissal (scenario A) or biopsy of malignant lesions (scenario B). The trial was registered at the Australian New Zealand Clinical Trials Registry ACTRN12620000695909 (Universal trial number U1111-1251-8995). Findings The diagnostic study included 172 suspicious pigmented lesions (84 malignant) from 124 patients and the management study included 5696 pigmented lesions (18 malignant) from the whole body of 66 high-risk patients. The diagnoses of the 7-class AI algorithm were equivalent to the specialists' diagnoses (absolute accuracy difference 1 center dot 2% [95% CI -6 center dot 9 to 9 center dot 2]) and significantly superior to the novices' ones (21 center dot 5% [13 center dot 1 to 30 center dot 0]). The diagnoses of the ISIC AI algorithm were significantly inferior to the specialists' diagnoses (-11 center dot 6% [-20 center dot 3 to -3 center dot 0]) but significantly superior to the novices' ones (8 center dot 7% [-0 center dot 5 to 18 center dot 0]). The best 7-class management AI was significantly inferior to specialists' management (absolute accuracy difference in correct management decision -0 center dot 5% [95% CI -0 center dot 7 to -0 center dot 2] in scenario A and -0 center dot 4% [-0 center dot 8 to -0 center dot 05] in scenario B). Compared with the novices' management, the 7-class management AI was significantly inferior (-0 center dot 4% [-0 center dot 6 to -0 center dot 2]) in scenario A but significantly superior (0 center dot 4% [0 center dot 0 to 0 center dot 9]) in scenario B. Interpretation The mobile phone-powered AI technology is simple, practical, and accurate for the diagnosis of suspicious pigmented skin cancer in patients presenting to a specialist setting, although its usage for management decisions requires more careful execution. An AI algorithm that was superior in experimental studies was significantly inferior to specialists in a real-world scenario, suggesting that caution is needed when extrapolating results of experimental studies to clinical practice.

学科与关键词

关键词
CONVOLUTIONAL NEURAL-NETWORKNON-INFERIORITYLESIONSDERMATOLOGISTSCLASSIFICATIONPERFORMANCEEQUIVALENCEDERMOSCOPY
相关
加载中…
  • New AI-algorithms on smartphones to detect skin cancer in a clinical setting-A validation study
    Kraenke, Teresa; Tripolt-Droschl, Katharina; Roed, Lukas; Hofmann-Wellenhof, Rainer; Koppitz, Michael; Tripolt, MichaelPLoS One, 2023, 18(2): e0280670.被引 10
  • Accuracy of a Smartphone-Based Artificial Intelligence Application for Classification of Melanomas, Melanocytic Nevi, and Seborrheic Keratoses
    Liutkus, Jokubas; Kriukas, Arturas; Stragyte, Dominyka; Mazeika, Erikas; Raudonis, Vidas; Galetzka, Wolfgang; Stang, Andreas; Valiukeviciene, Skaidra*Diagnostics, 2023, 13(13): 2139.被引 2
  • Accuracy of commercially available smartphone applications for the detection of melanoma
    Sun, M. D.; Kentley, J.; Mehta, P.; Dusza, S.; Halpern, A. C.*; Rotemberg, V.British Journal of Dermatology, 2022, 186(4): 744-746.被引 18
查看全部 →

发表信息

论文状态
公开发表
期刊
Lancet Digital Health
发表日期
2023-10
卷期
第 5 卷, 第 10 期
页码
E679-E691
DOI
10.1016/S2589-7500(23)00130-9
成果收录
SCIE
资助标注
MetaOptima Technology

作者

  • M

    Menzies, Scott W. (通讯) (第一作者)

  • S

    Sinz, Christoph

查看全部 41 位作者收起作者
  • M

    Menzies, Michelle

  • L

    Lo, Serigne N.

  • Y

    Yolland, William

  • L

    Lingohr, Johann

  • R

    Razmara, Majid

  • T

    Tschandl, Philipp

  • G

    Guitera, Pascale

  • S

    Scolyer, Richard A.

  • B

    Boltz, Florentina

  • B

    Borik-Heil, Liliane

  • C

    Chan, Hsien Herbert

  • C

    Chromy, David

  • C

    Coker, David J.

  • C

    Collgros, Helena

  • E

    Eghtedari, Maryam

  • F

    Forteza, Marina Corral

  • F

    Forward, Emily

  • G

    Gallo, Bruna

  • G

    Geisler, Stephanie

  • G

    Gibson, Matthew

  • H

    Hampel, Amelie

  • H

    Ho, Genevieve

  • J

    Junez, Laura

  • K

    Kienzl, Philipp

  • M

    Martin, Arthur

  • M

    Moloney, Fergal J.

  • P

    Pereira, Amanda Regio

  • R

    Ressler, Julia Maria

  • R

    Richter, Susanne

  • S

    Silic, Katharina

  • S

    Silly, Thomas

  • S

    Skoll, Michael

  • T

    Tittes, Julia

  • W

    Weber, Philipp

  • W

    Weninger, Wolfgang

  • W

    Weiss, Doris

  • W

    Woo-Sampson, Ping

  • Z

    Zilberg, Catherine

  • K

    Kittler, Harald

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417