Exploring named entity recognition and relation extraction for ontology and medical records integration
The available natural language data in electronic health records is of noteworthy interest to health research and development. Nevertheless, their manual analysis is not feasible and poses a challenge to accessing valuable information in these records. This paper presents an approach to automaticall...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914823002277 |
| _version_ | 1797401746790678528 |
|---|---|
| author | Diego Pinheiro da Silva William da Rosa Fröhlich Blanda Helena de Mello Renata Vieira Sandro José Rigo |
| author_facet | Diego Pinheiro da Silva William da Rosa Fröhlich Blanda Helena de Mello Renata Vieira Sandro José Rigo |
| author_sort | Diego Pinheiro da Silva |
| collection | DOAJ |
| description | The available natural language data in electronic health records is of noteworthy interest to health research and development. Nevertheless, their manual analysis is not feasible and poses a challenge to accessing valuable information in these records. This paper presents an approach to automatically extract information from these unstructured medical records using Domain Entity Recognition and Relation Extraction, structuring the results through a domain ontology. We developed our work in the oncology domain, an attention-demanding field. The main contribution of this work lies in integrating multiple resources in a complete methodology to accomplish this task. We developed a new entity and relation annotated dataset of medical evolutions in Brazilian Portuguese, containing 1622 documents, 146,769 entities, and 111,716 relations. We attained 78.24 % accuracy for entity and relation extraction in the exams domain. Healthcare specialists evaluated the approach regarding entity recognition and relation extraction positively and considered the methodology valuable to health professionals. |
| first_indexed | 2024-03-09T02:14:34Z |
| format | Article |
| id | doaj.art-4cfa9dda5c9c4794be8a331edb5f952b |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-03-09T02:14:34Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-4cfa9dda5c9c4794be8a331edb5f952b2023-12-07T05:29:11ZengElsevierInformatics in Medicine Unlocked2352-91482023-01-0143101381Exploring named entity recognition and relation extraction for ontology and medical records integrationDiego Pinheiro da Silva0William da Rosa Fröhlich1Blanda Helena de Mello2Renata Vieira3Sandro José Rigo4Universidade do Vale do Rio dos Sinos, Av. Unisinos, 950, Cristo Rei, São Leopoldo, 93022-750, Brazil; Corresponding author.Pontifícia Universidade Católica do Rio Grande do Sul, Porto Alegre, 90619-900, BrazilUniversidade do Vale do Rio dos Sinos, Av. Unisinos, 950, Cristo Rei, São Leopoldo, 93022-750, BrazilUniversidade de Évora, Largo dos Colegiais 2, 7004-516, Évora, PortugalUniversidade do Vale do Rio dos Sinos, Av. Unisinos, 950, Cristo Rei, São Leopoldo, 93022-750, BrazilThe available natural language data in electronic health records is of noteworthy interest to health research and development. Nevertheless, their manual analysis is not feasible and poses a challenge to accessing valuable information in these records. This paper presents an approach to automatically extract information from these unstructured medical records using Domain Entity Recognition and Relation Extraction, structuring the results through a domain ontology. We developed our work in the oncology domain, an attention-demanding field. The main contribution of this work lies in integrating multiple resources in a complete methodology to accomplish this task. We developed a new entity and relation annotated dataset of medical evolutions in Brazilian Portuguese, containing 1622 documents, 146,769 entities, and 111,716 relations. We attained 78.24 % accuracy for entity and relation extraction in the exams domain. Healthcare specialists evaluated the approach regarding entity recognition and relation extraction positively and considered the methodology valuable to health professionals.http://www.sciencedirect.com/science/article/pii/S2352914823002277Named entity recognitionDeep learningElectronic health recordRelation extractionNatural language processingOntology |
| spellingShingle | Diego Pinheiro da Silva William da Rosa Fröhlich Blanda Helena de Mello Renata Vieira Sandro José Rigo Exploring named entity recognition and relation extraction for ontology and medical records integration Informatics in Medicine Unlocked Named entity recognition Deep learning Electronic health record Relation extraction Natural language processing Ontology |
| title | Exploring named entity recognition and relation extraction for ontology and medical records integration |
| title_full | Exploring named entity recognition and relation extraction for ontology and medical records integration |
| title_fullStr | Exploring named entity recognition and relation extraction for ontology and medical records integration |
| title_full_unstemmed | Exploring named entity recognition and relation extraction for ontology and medical records integration |
| title_short | Exploring named entity recognition and relation extraction for ontology and medical records integration |
| title_sort | exploring named entity recognition and relation extraction for ontology and medical records integration |
| topic | Named entity recognition Deep learning Electronic health record Relation extraction Natural language processing Ontology |
| url | http://www.sciencedirect.com/science/article/pii/S2352914823002277 |
| work_keys_str_mv | AT diegopinheirodasilva exploringnamedentityrecognitionandrelationextractionforontologyandmedicalrecordsintegration AT williamdarosafrohlich exploringnamedentityrecognitionandrelationextractionforontologyandmedicalrecordsintegration AT blandahelenademello exploringnamedentityrecognitionandrelationextractionforontologyandmedicalrecordsintegration AT renatavieira exploringnamedentityrecognitionandrelationextractionforontologyandmedicalrecordsintegration AT sandrojoserigo exploringnamedentityrecognitionandrelationextractionforontologyandmedicalrecordsintegration |