A5022875177- Topic Modeling
- Natural Language Processing Techniques
- Biomedical Text Mining and Ontologies
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Data-Driven Disease Surveillance
Hospital do Coração
2012-2024
Universidade de São Paulo
2004
Universidade Estadual de Campinas (UNICAMP)
2004
Contextual word embeddings and the Transformers architecture have reached state-of-the-art results in many natural language processing (NLP) tasks improved adaptation of models for multiple domains. Despite improvement reuse construction models, few resources are still developed Portuguese language, especially health domain. Furthermore, clinical available not representative enough all medical specialties. This work explores deep contextual embedding to support NLP tasks. We transferred...
The Primary Care Information System (SIAB) concentrates basic healthcare information from all different regions of Brazil. is collected by primary care teams on a paper-based procedure that degrades the quality provided to authorities and slows down process decision making. To overcome these problems we propose new data gathering application uses mobile device connected 3G network GPS be used for collecting families' data. A prototype was developed in which digital version one SIAB form made...
The goal of the current study is to describe experience Heart Institute (InCor) in implementation a patient-oriented Hospital Information System (HIS) integrated with Radiology (RIS) and Picture Archiving Communication (PACS) an open-source three-tier architecture. system was designed modules that permits patient admission, discharge transfer (ADT), registration medical activities, diagnoses therapy, order entry access all data, including vital signals, images lab tests. are single Web-based...
Objetivos: A desidentificação de narrativas clínicas é essencial para proteger a privacidade dos pacientes e garantir conformidade com as regulamentações. No entanto, uma tarefa complexa devido aos distintos tipos entidades serem desidentificadas à necessidade processar os textos localmente, por questões segurança privacidade. Métodos: Este artigo apresenta um estudo experimental sobre utilizando modelos generativos código aberto, que podem ser executados localmente. Resultados: Avaliamos...