Literature DB >> 33037709

Performance of a deep neural network in teledermatology: a single-centre prospective diagnostic study.

C Muñoz-López1, C Ramírez-Cornejo1, M A Marchetti2, S S Han3, P Del Barrio-Díaz1, A Jaque1, P Uribe1,4, D Majerson1, M Curi1, C Del Puerto1, F Reyes-Baraona1, R Meza-Romero1, J Parra-Cares1, P Araneda-Ortega1, M Guzmán1, R Millán-Apablaza1, M Nuñez-Mora1, K Liopyris5, C Vera-Kellet1, C Navarrete-Dechent1,4.   

Abstract

BACKGROUND: The use of artificial intelligence (AI) algorithms for the diagnosis of skin diseases has shown promise in experimental settings but has not been yet tested in real-life conditions.
OBJECTIVE: To assess the diagnostic performance and potential clinical utility of a 174-multiclass AI algorithm in a real-life telemedicine setting.
METHODS: Prospective, diagnostic accuracy study including consecutive patients who submitted images for teledermatology evaluation. The treating dermatologist chose a single image to upload to a web application during teleconsultation. A follow-up reader study including nine healthcare providers (3 dermatologists, 3 dermatology residents and 3 general practitioners) was performed.
RESULTS: A total of 340 cases from 281 patients met study inclusion criteria. The mean (SD) age of patients was 33.7 (17.5) years; 63% (n = 177) were female. Exposure to the AI algorithm results was considered useful in 11.8% of visits (n = 40) and the teledermatologist correctly modified the real-time diagnosis in 0.6% (n = 2) of cases. The overall top-1 accuracy of the algorithm (41.2%) was lower than that of the dermatologists (60.1%), residents (57.8%) and general practitioners (49.3%) (all comparisons P < 0.05, in the reader study). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained, the balanced top-1 accuracy of the algorithm (47.6%) was comparable to the dermatologists (49.7%) and residents (47.7%) but superior to the general practitioners (39.7%; P = 0.049). Algorithm performance was associated with patient skin type and image quality.
CONCLUSIONS: A 174-disease class AI algorithm appears to be a promising tool in the triage and evaluation of lesions with patient-taken photographs via telemedicine.
© 2020 European Academy of Dermatology and Venereology.

Entities:  

Mesh:

Year:  2020        PMID: 33037709      PMCID: PMC8274350          DOI: 10.1111/jdv.16979

Source DB:  PubMed          Journal:  J Eur Acad Dermatol Venereol        ISSN: 0926-9959            Impact factor:   6.166


  25 in total

1.  A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task.

Authors:  Titus J Brinker; Achim Hekler; Alexander H Enk; Joachim Klode; Axel Hauschild; Carola Berking; Bastian Schilling; Sebastian Haferkamp; Dirk Schadendorf; Stefan Fröhling; Jochen S Utikal; Christof von Kalle
Journal:  Eur J Cancer       Date:  2019-03-08       Impact factor: 9.162

2.  Artificial intelligence in dermato-oncology: a joint clinical and data science perspective.

Authors:  Eva Hulstaert; Lars Hulstaert
Journal:  Int J Dermatol       Date:  2019-05-31       Impact factor: 2.736

Review 3.  Machine Learning and Health Care Disparities in Dermatology.

Authors:  Adewole S Adamson; Avery Smith
Journal:  JAMA Dermatol       Date:  2018-11-01       Impact factor: 10.282

4.  Teledermatology: a useful tool to fight COVID-19.

Authors:  Alessia Villani; Massimiliano Scalvenzi; Gabriella Fabbrocini
Journal:  J Dermatolog Treat       Date:  2020-04-13       Impact factor: 3.359

Review 5.  Teledermatology: A Review and Update.

Authors:  Jonathan J Lee; Joseph C English
Journal:  Am J Clin Dermatol       Date:  2018-04       Impact factor: 7.403

6.  Human-computer collaboration for skin cancer recognition.

Authors:  Philipp Tschandl; Christoph Rinner; Zoe Apalla; Giuseppe Argenziano; Noel Codella; Allan Halpern; Monika Janda; Aimilios Lallas; Caterina Longo; Josep Malvehy; John Paoli; Susana Puig; Cliff Rosendahl; H Peter Soyer; Iris Zalaudek; Harald Kittler
Journal:  Nat Med       Date:  2020-06-22       Impact factor: 53.440

7.  Dermatologist-level classification of skin cancer with deep neural networks.

Authors:  Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun
Journal:  Nature       Date:  2017-01-25       Impact factor: 49.962

Review 8.  Teledermatology: from historical perspective to emerging techniques of the modern era: part I: History, rationale, and current practice.

Authors:  Sarah J Coates; Joseph Kvedar; Richard D Granstein
Journal:  J Am Acad Dermatol       Date:  2015-04       Impact factor: 11.527

9.  Virtual health care in the era of COVID-19.

Authors:  Paul Webster
Journal:  Lancet       Date:  2020-04-11       Impact factor: 79.321

Review 10.  Artificial Intelligence Applications in Dermatology: Where Do We Stand?

Authors:  Arieh Gomolin; Elena Netchiporouk; Robert Gniadecki; Ivan V Litvinov
Journal:  Front Med (Lausanne)       Date:  2020-03-31
View more
  10 in total

Review 1.  Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review.

Authors:  Roxana Daneshjou; Mary P Smith; Mary D Sun; Veronica Rotemberg; James Zou
Journal:  JAMA Dermatol       Date:  2021-11-01       Impact factor: 11.816

2.  SMD-YOLO: An efficient and lightweight detection method for mask wearing status during the COVID-19 pandemic.

Authors:  Zhenggong Han; Haisong Huang; Qingsong Fan; Yiting Li; Yuqin Li; Xingran Chen
Journal:  Comput Methods Programs Biomed       Date:  2022-05-13       Impact factor: 7.027

Review 3.  Teledermatology During COVID-19: An Updated Review.

Authors:  Morgan A Farr; Madeleine Duvic; Tejas P Joshi
Journal:  Am J Clin Dermatol       Date:  2021-04-09       Impact factor: 6.233

Review 4.  Machine and cognitive intelligence for human health: systematic review.

Authors:  Xieling Chen; Gary Cheng; Fu Lee Wang; Xiaohui Tao; Haoran Xie; Lingling Xu
Journal:  Brain Inform       Date:  2022-02-12

5.  Comparison of Convolutional Neural Network Architectures for Robustness Against Common Artefacts in Dermatoscopic Images.

Authors:  Florian Katsch; Christoph Rinner; Philipp Tschandl
Journal:  Dermatol Pract Concept       Date:  2022-07-01

6.  The degradation of performance of a state-of-the-art skin image classifier when applied to patient-driven internet search.

Authors:  Seung Seog Han; Cristian Navarrete-Dechent; Konstantinos Liopyris; Myoung Shin Kim; Gyeong Hun Park; Sang Seok Woo; Juhyun Park; Jung Won Shin; Bo Ri Kim; Min Jae Kim; Francisca Donoso; Francisco Villanueva; Cristian Ramirez; Sung Eun Chang; Allan Halpern; Seong Hwan Kim; Jung-Im Na
Journal:  Sci Rep       Date:  2022-09-28       Impact factor: 4.996

7.  Retrospective study of nail telemedicine visits during the COVID-19 pandemic.

Authors:  Michelle J Chang; Claire R Stewart; Shari R Lipner
Journal:  Dermatol Ther       Date:  2020-12-13       Impact factor: 3.858

8.  The Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks.

Authors:  Federica Veronese; Francesco Branciforti; Elisa Zavattaro; Vanessa Tarantino; Valentina Romano; Kristen M Meiburger; Massimo Salvi; Silvia Seoni; Paola Savoia
Journal:  Diagnostics (Basel)       Date:  2021-03-05

9.  Augmenting the accuracy of trainee doctors in diagnosing skin lesions suspected of skin neoplasms in a real-world setting: A prospective controlled before-and-after study.

Authors:  Young Jae Kim; Jung-Im Na; Seung Seog Han; Chong Hyun Won; Mi Woo Lee; Jung-Won Shin; Chang-Hun Huh; Sung Eun Chang
Journal:  PLoS One       Date:  2022-01-21       Impact factor: 3.240

10.  Perilesional sun damage as a diagnostic clue for pigmented actinic keratosis and Bowen's disease.

Authors:  P Weber; C Sinz; C Rinner; H Kittler; P Tschandl
Journal:  J Eur Acad Dermatol Venereol       Date:  2021-07-03       Impact factor: 6.166

  10 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.