Development of an artificial intelligence algorithm for the diagnosis of infantile hemangiomas.

Zhang, April J; Lindberg, Nick; Chamlin, Sarah L; Haggstrom, Anita N; Mancini, Anthony J; Siegel, Dawn H; Drolet, Beth A

Zhang, April J; Lindberg, Nick; Chamlin, Sarah L; Haggstrom, Anita N; Mancini, Anthony J; Siegel, Dawn H; Drolet, Beth A.

Afiliação

Zhang AJ; Department of Dermatology, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.
Lindberg N; Engage Computing LLC, Milwaukee, Wisconsin, USA.
Chamlin SL; Department of Pediatrics and Dermatology, Northwestern University Feinberg School of Medicine/Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Illinois, USA.
Haggstrom AN; Department of Pediatrics and Dermatology, Indiana University, Indianapolis, Indiana, USA.
Mancini AJ; Department of Pediatrics and Dermatology, Northwestern University Feinberg School of Medicine/Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Illinois, USA.
Siegel DH; Department of Dermatology, and by courtesy, Pediatrics, Stanford University School of Medicine, Stanford, California, USA.
Drolet BA; Department of Dermatology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA.

Pediatr Dermatol ; 39(6): 934-936, 2022 Nov.

Article em En | MEDLINE | ID: mdl-36164801

ABSTRACT

ABSTRACT

Prompt and accurate diagnosis of infantile hemangiomas is essential to prevent potential complications. This can be difficult due to high rates of misdiagnosis and poor access to pediatric dermatologists. In this study, we trained an artificial intelligence algorithm to diagnose infantile hemangiomas based on clinical images. Our algorithm achieved a 91.7% overall accuracy in the diagnosis of facial infantile hemangiomas.

Assuntos

Hemangioma Capilar; Hemangioma; Neoplasias Cutâneas; Criança; Humanos; Inteligência Artificial; Neoplasias Cutâneas/diagnóstico; Hemangioma Capilar/diagnóstico; Hemangioma/diagnóstico; Algoritmos

Palavras-chave

artificial intelligence; hemangioma; infants; machine learning; neoplasms; vascular tissue

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Neoplasias Cutâneas / Hemangioma Capilar / Hemangioma Tipo de estudo: Diagnostic_studies / Prognostic_studies Limite: Child / Humans Idioma: En Revista: Pediatr Dermatol Ano de publicação: 2022 Tipo de documento: Article País de afiliação: Estados Unidos

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google