Análise de um Fluxo Completo Automatizado de Etapas Voltado ao Reconhecimento de Texto em Imagens de Prescrições Médicas Manuscritas

• Ano de defesa: 2024
• Autor(a) principal: Corrêa, André Pires
• Orientador(a): Nascimento, Hugo Alexandre Dantas do
• Banca de defesa: Nascimento, Hugo Alexandre Dantas do, Costa, Ronaldo Martins da, Pedrini, Hélio, Lima, Eliomar Araújo de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Goiás
• Programa de Pós-Graduação: Programa de Pós-graduação em Ciência da Computação (INF)
• Departamento: Instituto de Informática - INF (RMG)
• País: Brasil
• Palavras-chave em Português: Prescrições médicas; Reconhecimento de texto manuscrito; Aprendizado de máquina
• Palavras-chave em Inglês: Medical prescriptions; Handwritten text recognition; Machine learning
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: http://repositorio.bc.ufg.br/tede/handle/tede/13759

Compounding pharmacies deal with large volumes of medical prescriptions on a daily basis, whose data needs to be manually inputted into information management systems to properly process their customers’ orders. A considerable portion of these prescriptions tend to be written by doctors with poorly legible handwriting, which can make decoding them an arduous and time-consuming process. Previous works have investigated the use of machine learning for medical prescription recognition. However, the accuracy rates in these works are still fairly low and their approaches tend to be rather limited, as they typically utilize small datasets, focus only on specific steps of the automated analysis pipeline or use proprietary tools, which makes it difficult to replicate and analyse their results. The present work contributes towards filling this gap by presenting an end-toend process for automated data extraction from handwritten medical prescriptions, from text segmentation, to recognition and post-processing. The approach was built based on an evaluation and adaptation of multiple existing methods for each step of the pipeline. The methods were evaluated on a dataset of 993 images of medical prescriptions with 27,933 annotated words, produced with the support of a compounding pharmacy that participated in the project. The results obtained by the best performing methods indicate that the developed approach is reasonably effective, reaching an accuracy of 68% in the segmentation step, and a character accuracy rate of 86.8% in the text recognition step.