TY  - JOUR
AU  - Sugimoto, Kento
AU  - Wada, Shoya
AU  - Konishi, Shozo
AU  - Okada, Katsuki
AU  - Manabe, Shirou
AU  - Matsumura, Yasushi
AU  - Takeda, Toshihiro
PY  - 2023
DA  - 2023/11/14
TI  - Extracting Clinical Information From Japanese Radiology Reports Using a 2-Stage Deep Learning Approach: Algorithm Development and Validation
JO  - JMIR Med Inform
SP  - e49041
VL  - 11
KW  - natural language processing
KW  - radiology report
KW  - information extraction
KW  - deep learning
KW  - machine learning
KW  - radiology
KW  - report
KW  - reports
KW  - NLP
KW  - free text
KW  - unstructured
KW  - named entity recognition
KW  - relation extraction
AB  - Background: Radiology reports are usually written in a free-text format, which makes it challenging to reuse the reports. Objective: For secondary use, we developed a 2-stage deep learning system for extracting clinical information and converting it into a structured format. Methods: Our system mainly consists of 2 deep learning modules: entity extraction and relation extraction. For each module, state-of-the-art deep learning models were applied. We trained and evaluated the models using 1040 in-house Japanese computed tomography (CT) reports annotated by medical experts. We also evaluated the performance of the entire pipeline of our system. In addition, the ratio of annotated entities in the reports was measured to validate the coverage of the clinical information with our information model. Results: The microaveragedF1-scores of our best-performing model for entity extraction and relation extraction were 96.1% and 97.4%, respectively. The microaveragedF1-score of the 2-stage system, which is a measure of the performance of the entire pipeline of our system, was 91.9%. Our system showed encouraging results for the conversion of free-text radiology reports into a structured format. The coverage of clinical information in the reports was 96.2% (6595/6853). Conclusions: Our 2-stage deep system can extract clinical information from chest and abdomen CT reports accurately and comprehensively. 
SN  - 2291-9694
UR  - https://medinform.jmir.org/2023/1/e49041
UR  - https://doi.org/10.2196/49041
UR  - http://www.ncbi.nlm.nih.gov/pubmed/37991979
DO  - 10.2196/49041
ID  - info:doi/10.2196/49041
ER  -