Cargando…

Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis

Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clini...

Descripción completa

Detalles Bibliográficos
Autores principales: ZAAR, Oscar, LARSON, Alexander, POLESIE, Sam, SALEH, Karim, TARSTEDT, Mikael, OLIVES, Antonio, SUAREZ, Andrea, GILLSTEDT, Martin, NEITTAANMÄKI, Noora
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Society for Publication of Acta Dermato-Venereologica 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9234984/
https://www.ncbi.nlm.nih.gov/pubmed/32852557
http://dx.doi.org/10.2340/00015555-3624
_version_ 1784736206133657600
author ZAAR, Oscar
LARSON, Alexander
POLESIE, Sam
SALEH, Karim
TARSTEDT, Mikael
OLIVES, Antonio
SUAREZ, Andrea
GILLSTEDT, Martin
NEITTAANMÄKI, Noora
author_facet ZAAR, Oscar
LARSON, Alexander
POLESIE, Sam
SALEH, Karim
TARSTEDT, Mikael
OLIVES, Antonio
SUAREZ, Andrea
GILLSTEDT, Martin
NEITTAANMÄKI, Noora
author_sort ZAAR, Oscar
collection PubMed
description Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clinical images including tumours, infective and inflammatory skin diseases were collected at the Department of Dermatology at the Sahlgrenska University Hospital and uploaded for classification by the online application. The AI algorithm classified the images giving 5 differential diagnoses, which were then compared to the diagnoses made clinically by the dermatologists and/or histologically. We included 521 images portraying 26 diagnoses. The diagnostic accuracy was 56.4% for the top 5 suggested diagnoses and 22.8% when only considering the most probable diagnosis. The level of diagnostic accuracy varied considerably for diagnostic groups. The online application demonstrated low diagnostic accuracy compared to a dermatologist evaluation and needs further development.
format Online
Article
Text
id pubmed-9234984
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Society for Publication of Acta Dermato-Venereologica
record_format MEDLINE/PubMed
spelling pubmed-92349842022-10-20 Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis ZAAR, Oscar LARSON, Alexander POLESIE, Sam SALEH, Karim TARSTEDT, Mikael OLIVES, Antonio SUAREZ, Andrea GILLSTEDT, Martin NEITTAANMÄKI, Noora Acta Derm Venereol Investigative Report Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clinical images including tumours, infective and inflammatory skin diseases were collected at the Department of Dermatology at the Sahlgrenska University Hospital and uploaded for classification by the online application. The AI algorithm classified the images giving 5 differential diagnoses, which were then compared to the diagnoses made clinically by the dermatologists and/or histologically. We included 521 images portraying 26 diagnoses. The diagnostic accuracy was 56.4% for the top 5 suggested diagnoses and 22.8% when only considering the most probable diagnosis. The level of diagnostic accuracy varied considerably for diagnostic groups. The online application demonstrated low diagnostic accuracy compared to a dermatologist evaluation and needs further development. Society for Publication of Acta Dermato-Venereologica 2020-09-16 /pmc/articles/PMC9234984/ /pubmed/32852557 http://dx.doi.org/10.2340/00015555-3624 Text en © 2020 Acta Dermato-Venereologica https://creativecommons.org/licenses/by-nc/4.0/This is an open access article under the CC BY-NC license
spellingShingle Investigative Report
ZAAR, Oscar
LARSON, Alexander
POLESIE, Sam
SALEH, Karim
TARSTEDT, Mikael
OLIVES, Antonio
SUAREZ, Andrea
GILLSTEDT, Martin
NEITTAANMÄKI, Noora
Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis
title Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis
title_full Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis
title_fullStr Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis
title_full_unstemmed Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis
title_short Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis
title_sort evaluation of the diagnostic accuracy of an online artificial intelligence application for skin disease diagnosis
topic Investigative Report
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9234984/
https://www.ncbi.nlm.nih.gov/pubmed/32852557
http://dx.doi.org/10.2340/00015555-3624
work_keys_str_mv AT zaaroscar evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT larsonalexander evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT polesiesam evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT salehkarim evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT tarstedtmikael evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT olivesantonio evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT suarezandrea evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT gillstedtmartin evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis
AT neittaanmakinoora evaluationofthediagnosticaccuracyofanonlineartificialintelligenceapplicationforskindiseasediagnosis