Using the Natural Language Processing System Medical Named Entity Recognition-Japanese to Analyze Pharmaceutical Care Records:Natural Language Processing Analysis

被引：4

作者：

Ohno, Yukiko ^{[1
]}

Kato, Riri ^{[1
]}

Ishikawa, Haruki ^{[1
]}

Nishiyama, Tomohiro ^{[2
]}

Isawa, Minae ^{[1
]}

Mochizuki, Mayumi ^{[1
]}

Aramaki, Eiji ^{[2
]}

Aomori, Tohru ^{[3
]}

机构：

[1] Keio Univ, Fac Pharm, Tokyo, Japan

[2] Nara Inst Sci & Technol, Ikoma, Nara, Japan

[3] Takasaki Univ Hlth & Welfare, Fac Pharm, 37-1 Nakaorui machi, Takasaki, Gunma 370-0033, Japan

来源：

JMIR FORMATIVE RESEARCH | 2024年 / 8卷

基金：

日本科学技术振兴机构;

关键词：

natural language processing; NLP; named entity recognition; pharmaceutical care records; machine learning; cefazolin sodium; electronic medical record; EMR; extraction; Japanese;

D O I：

10.2196/55798

中图分类号：

R19 [保健组织与事业（卫生事业管理）];

学科分类号：

摘要：

Background: Large language models have propelled recent advances in artificial intelligence technology, facilitating theextraction of medical information from unstructured data such as medical records. Although named entity recognition (NER) isused to extract data from physicians'records, it has yet to be widely applied to pharmaceutical care records. Objective: In this study, we aimed to investigate the feasibility of automatic extraction of the information regarding patients'diseases and symptoms from pharmaceutical care records. The verification was performed using Medical Named EntityRecognition-Japanese (MedNER-J), a Japanese disease-extraction system designed for physicians'records. Methods: MedNER-J was applied to subjective, objective, assessment, and plan data from the care records of 49 patients whoreceived cefazolin sodium injection at Keio University Hospital between April 2018 and March 2019. The performance ofMedNER-J was evaluated in terms of precision, recall, and F1-score. Results: The F1-scores of NER for subjective, objective, assessment, and plan data were 0.46, 0.70, 0.76, and 0.35, respectively.In NER and positive-negative classification, the F1-scores were 0.28, 0.39, 0.64, and 0.077, respectively. The F1-scores of NERfor objective (0.70) and assessment data (0.76) were higher than those for subjective and plan data, which supported the superiorityof NER performance for objective and assessment data. This might be because objective and assessment data contained manytechnical terms, similar to the training data for MedNER-J. Meanwhile, the F1-score of NER and positive-negative classificationwas high for assessment data alone (F1-score=0.64), which was attributed to the similarity of its description format and contentsto those of the training data. Conclusions: MedNER-J successfully read pharmaceutical care records and showed the best performance for assessment data.However, challenges remain in analyzing records other than assessment data. Therefore, it will be necessary to reinforce thetraining data for subjective data in order to apply the system to pharmaceutical care records

引用

页数：13

共 18 条

[1]

Aramaki Eiji, 2022, Yearb Med Inform, V31, P243, DOI 10.1055/s-0042-1742510

[2] MedEx/J: A One-Scan Simple and Fast NLP Tool for Japanese Clinical Texts [J].

Aramaki, Eiji ;

Yano, Ken ;

Wakamiya, Shoko .

MEDINFO 2017: PRECISION HEALTHCARE THROUGH INFORMATICS, 2017, 245 :285-288

[3] A COEFFICIENT OF AGREEMENT FOR NOMINAL SCALES [J].

COHEN, J .

EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1960, 20 (01) :37-46

[4]

Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171

[5] A systematic review of natural language processing and text mining of symptoms from electronic patient-authored text data [J].