Publicação

Development of an innovative and transparent symptom checker with a focus on multi-label classification

Ver documento

Detalhes bibliográficos
Resumo:This paper presents the creation of a medical symptom checker with state-of-the-art machine and deep learning technologies. It examines the use and development of speech-to-text, natural language processing, and classification models, which are trained on medical datasets. All models are discussed, highlighting their advantages and disadvantages for the study. Moreover, the paper introduces a web application which provides a user-friendly interface, allowing users to interact with the models and showcase the results. Finally, the paper offers an outlook on the future use cases of the application and how it may improve healthcare outcomes.
Autores principais:Petry, Hannah
Assunto:Deep learning Machine learning Classification Speech to text Natural language processing Medical symptom checker Streamlit
Ano:2023
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
Descrição
Resumo:This paper presents the creation of a medical symptom checker with state-of-the-art machine and deep learning technologies. It examines the use and development of speech-to-text, natural language processing, and classification models, which are trained on medical datasets. All models are discussed, highlighting their advantages and disadvantages for the study. Moreover, the paper introduces a web application which provides a user-friendly interface, allowing users to interact with the models and showcase the results. Finally, the paper offers an outlook on the future use cases of the application and how it may improve healthcare outcomes.