RESUMO
PURPOSE: This study aims to compare artificial intelligence (AI) systems applied in diabetic retinopathy (DR) teleophthalmology screening, currently deployed systems, fairness initiatives and the challenges for implementation. METHODS: The review included articles retrieved from PubMed/Medline/EMBASE literature search strategy regarding telemedicine, DR and AI. The screening criteria included human articles in English, Portuguese or Spanish and related to telemedicine and AI for DR screening. The author's affiliations and the study's population income group were classified according to the World Bank Country and Lending Groups. RESULTS: The literature search yielded a total of 132 articles, and nine were included after full-text assessment. The selected articles were published between 2004 and 2020 and were grouped as telemedicine systems, algorithms, economic analysis and image quality assessment. Four telemedicine systems that perform a quality assessment, image preprocessing and pathological screening were reviewed. A data and post-deployment bias assessment are not performed in any of the algorithms, and none of the studies evaluate the social impact implementations. There is a lack of representativeness in the reviewed articles, with most authors and target populations from high-income countries and no low-income country representation. CONCLUSIONS: Telemedicine and AI hold great promise for augmenting decision-making in medical care, expanding patient access and enhancing cost-effectiveness. Economic studies and social science analysis are crucial to support the implementation of AI in teleophthalmology screening programs. Promoting fairness and generalizability in automated systems combined with telemedicine screening programs is not straightforward. Improving data representativeness, reducing biases and promoting equity in deployment and post-deployment studies are all critical steps in model development.
Assuntos
Diabetes Mellitus , Retinopatia Diabética , Oftalmologia , Telemedicina , Humanos , Inteligência Artificial , Retinopatia Diabética/diagnóstico , AlgoritmosRESUMO
Este trabalho tem como objetivo investigar a associação entreo o uso dos cigarros eletrônicos e doenças pulmonares em adolescentes. Foi realizada uma revisão sistemática na base de dados PubMed. Os termos Mesh incluídos na busca foram "Electronic Nicotine Delivery Systems" e "Lung Diseases" e sinônimos no título e abstract, com o filtro de idade "child: birth - 18 years", para buscar artigos relacionados ao uso de cigarros eletrônicos e doenças pulmonares em adolescentes. Os critérios de elegibilidade consistiram em: usuários adolescentes, exposição ao cigarro eletrônico e doença pulmonar como desfecho. Os artigos foram selecionados por uma revisão pareada de maneira independente, primeiramente com a leitura dos títulos e resumos, seguida da leitura integral dos artigos selecionados, os quais foram analisados pela ferramenta New Castle-Ottawa quanto sua qualidade, e receberam entre 5 e 7 estrelas. Os dados encontrados foram extraídos para a realização da metanálise. Inicialmente foram encontrados 61 artigos, sendo seis considerados elegíveis, todos transversais e com aplicação de questionários. Na metanálise foi encontrada uma associação significativa entre o uso de cigarro eletrônico e exacerbação de asma (OR ajustado 1,44; IC 95% 1,171,76). Não foram encontrados estudos que avaliassem a associação do cigarro eletrônico e outras doenças pulmonares, incluindo EVALI (E-cigarette or Vaping product use-Associated Lung Injury), em adolescentes. Na metanálise foi encontrada uma associação significativa entre exacerbações de asma e uso de cigarros eletrônicos em adolescentes com asma crônica e nos previamente hígidos.
This study aims to investigate the association between electronic cigarette use and lung disease in adolescents. A systematic review was conducted in PubMed. We used the MeSH terms "Electronic Nicotine Delivery Systems" and "Lung Diseases" as well as synonyms in the title and abstract, with the age filter "child: birth - 18 years" to search for articles related to electronic cigarette use and lung disease in adolescents. The eligibility criteria consisted of adolescent users and exposure to e-cigarettes that resulted in lung disease. The articles were selected by independent assessment, reading first the titles and abstracts, then the full text of the selected articles. The Newcastle-Ottawa Scale was used to assess study quality, and the included studies received between 5 and 7 stars. Finally, the data were extracted for meta-analysis. Initially, 61 articles were found and 6 were considered eligible, all of which were cross-sectional and applied questionnaires. The meta-analysis found a significant association between electronic cigarette use and asthma exacerbation (adjusted OR 1.44 95% CI 1.17 - 1.76). However, no studies evaluated the association with other lung diseases, including electronic cigarette or vaping product use-associated lung injury in adolescents. The metaanalysis revealed a significant association between e-cigarette use and asthma exacerbation among adolescents with chronic asthma, as well as among their previously healthy peers.
