딥러닝 기반 임상 관계 학습을 통한 질병 예측
Disease Prediction By Learning Clinical Concept Relations
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 임상 의사 결정 지원을 위하여 의학 지식을 통해 임상 관계를 추출하고 딥러닝 모델을 이용하여 질병을 예측하는 방법을 제안한다. 의학 사전인 UMLS(Unified Medical Language System)와 암 관련 의학 지식에 포함된 임상 용어를 5가지로 분류한다. 분류된 임상 용어들을 사용하여 위키피디아 의학 문서를 추출한다. 추출한 위키피디아 의학 문서와 추출한 임상 용어를 매칭하여 임상 관계를 구축한다. 구축한 임상 관계를이용하여 딥러닝 학습을 진행한 후 질의에서 표현된 의학 용어를 바탕으로 질의와 연관된 질병을 예측한다. 이후, 예측한 질병과 관계가 있는의학 용어를 확장 질의로 선택한 뒤 질의를 확장한다. 제안 방법의 유효성을 검증하기 위해 TREC Clinical Decision Support(CDS), TREC PrecisionMedicine(PM) 테스트 컬렉션에 대해 비교 평가한다.
Abstract
In this paper, we propose a method of constructing clinical knowledge with clinical concept relations and predicting diseases basedon a deep learning model to support clinical decision-making. Clinical terms in UMLS(Unified Medical Language System) and cancer-relatedmedical knowledge are classified into five categories. Medical related documents in Wikipedia are extracted using the classified clinicalterms. Clinical concept relations are established by matching the extracted medical related documents with the extracted clinical terms. After deep learning using clinical knowledge, a disease is predicted based on medical terms expressed in a query. Thereafter, medicalterms related to the predicted disease are selected as an extended query for clinical document retrieval. To validate our method, wehave experimented on TREC Clinical Decision Support (CDS) and TREC Precision Medicine (PM) test collections.
참고문헌 (17)
- J. Lee, "BioBERT : a pre-trained biomedical language representation model for biomedical text mining", Bioinformatics, 36(4), pp.1234~1240 (2020)
- 박철수, "Machine learning in biomedical engineering", Biomedical Engineering Letters (BMEL), 8(1), pp.1~3 (2018), 대한의용생체공학회[DOI]
- K. Roberts, "Overview of the TREC 2016clinical decision support track", Proceedings of the Text Retrieval Conference 2016 (2016)
- K. Roberts, "Overview of the TREC 2020precision medicine track", Proceedings of the Text Retrieval Conference 2020 (2020)
- K. B. Cohen, "Stronger biomedical NLP in the face of COVID-19", Proceedings of the 20th Workshop on Biomedical Language Processing (2020)
- M. Hassan, "Extracting disease-symptom relationships by learning syntactic patterns from dependency graphs", Proceedings of the 2015 Workshop on Biomedical Natural Language Processing (BioNLP 2015), pp.71~80 (2015)
- L. Yao, "Relationship extraction from biomedical literature using Maximum Entropy based on rich features", Proceedings of the Ninth Internation al Conference on Machine Learning and Cybernetics(ICMLC’10), pp.3358~3361 (2010)
- L. Soldaini, "Query Reformulation for Clinical Decision Support Search", proceedings of the Text Retrieval Conference 2014 (2014)
- F. Hu, "Learning from medical summaries : The university of michigan at TREC 2015 clinical decision support track", Proceedings of the Text Retrieval Conference 2015 (2015)
- J. Stober, "Concept based information retrieval for clinical case summaries", Proceedings of the Text Retrieval Conference 2015 (2015)
- R. You, "FDUMedSearch at TREC 2015 clinical decision support track", Proceedings of the Text Retrieval Conference 2015 (2015)
- "Atlas of Genetics and Cytogenetics in Oncology and Haematology"[URL]
- "1000 Genomes Project in Sanger Data Directory"[URL]
- T. Strohman, "Indri:A language model-based search engine for complex queries", Proceedings of the International Conference on Intelligence Analysis (2005)
- X. Lium, "SCUT-CCNL at TREC 2019 Precision Medicine Track", Proceedings of the Text Retreival Conference 2019 (2019)
- S. H. Jo, "CBNU at TREC 2019 precision medicine track", Proceedings of the Text Retrieval Conference 2019 (2019)
- S. H. Jo, "CBNU at TREC 2015 clinical decision support track", Proceedings of the Text Retrieval Conference 2015 (2015)