Unmasking biases and navigating pitfalls in the ophthalmic artificial intelligence lifecycle: A narrative review

• Tipo: Outra Publicação em Revista Científica Internacional
• Data: 2024

Autores

Nakayama, LF (Autor) Outra; Matos, J (Autor) Outra; Quion, J (Autor) Outra; Novaes, F (Autor) Outra; Mitchell, WG (Autor) Outra; Mwavu, R (Autor) Outra; Hung, CJYJ (Autor) Outra; Santiago, APD (Autor) Outra; Phanphruk, W (Autor) Outra; Jaime S Cardoso (Autor) FEUP; Celi, LA (Autor) Outra

Revista

A Revista está pendente de validação pelos Serviços Administrativos.

Título: PLOS Digital Health

Vol. 3

ISSN: 2767-3170

Editora: Public Library of Science

Indexação

ISI Web of Knowledge - 1 Citação

Scopus - 0 Citações

Outras Informações

ID Authenticus: P-00Z-MX7

DOI: 10.1371/journal.pdig.0000618

Abstract (EN): Over the past 2 decades, exponential growth in data availability, computational power, and newly available modeling techniques has led to an expansion in interest, investment, and research in Artificial Intelligence (AI) applications. Ophthalmology is one of many fields that seek to benefit from AI given the advent of telemedicine screening programs and the use of ancillary imaging. However, before AI can be widely deployed, further work must be done to avoid the pitfalls within the AI lifecycle. This review article breaks down the AI lifecycle into seven steps-data collection; defining the model task; data preprocessing and labeling; model development; model evaluation and validation; deployment; and finally, post-deployment evaluation, monitoring, and system recalibration-and delves into the risks for harm at each step and strategies for mitigating them.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 14