医工情報学
医工情報研究領域

医工情報学
医工情報研究領域

准教授

今井　健

1.研究概要

医工情報学部門では、医療・工学・情報学が密接に関わる境界領域、とりわけ医用人工知能システムの開発と臨床応用を中心に研究しています。具体的には臨床知識データベースに基づいた知識推論手法と、機械学習や大規模言語モデルベースの自然言語処理といった情報処理技術をハイブリッドに組み合わせ、コンピュータを用いた診断・診療支援や、医療安全支援、大規模臨床データベースからの医学知識発見と利活用、医療情報の標準化などの研究を展開しています。また本学医学系研究科 医療情報学分野/ 附属病院企画情報運営部と密接に連携し、実臨床データの 2次利用の推進と成果の臨床現場へのフィードバックを目標としています。

これまでに臨床医学知識データベースの構築と利活用、内科領域の診断支援システムの開発、自然言語処理を用いた医用文書の自動構造化と知識発見、深層学習による心電図解析の高精度化、メンタルヘルスケアへの AI 応用などに取り組んでいます。また医療 AI の開発では研究成果の社会還元も重要な視点となりますが、成果をサービスとして公開し実際にユーザーに使ってもらうための社会実装にも積極的に取り組んでいます。

また研究基盤部門 医工情報研究領域としては、研究科情報ネットワーク基盤の管理、Web・メール・DNS等各種サーバー管理、医学部CERTとしてセキュリティ・インシデント対応、IPアドレス管理、医学図書館の実習用端末の整備などの情報化推進室の業務を通じ、医学部・医学系研究科全体の情報インフラ管理と医学研究支援を行っています。

2.研究開発の目標

  • 医用大規模言語モデルと診断・診療支援への応用手法の開発
  • 臨床医学オントロジーの構築と理論的基盤の整備
  • 自然言語処理による診療テキスト情報解析と知識発見・知識構造化手法の開発
  • 知識推論技術の診断支援システムへの応用手法の開発
  • 深層学習とオントロジーを活用した診療情報の解析技術の開発
  • 医療情報モデルの開発と標準化

関連ページ(医療情報学分野) # 更新ストップ中

3.業績

  1. Tsukiji Y, Kataoka S, Itokazu M, Nagai R, Imai T. Evaluating Encoder and Decoder Models for Extended Clinical Concept Recognition in Japanese Clinical Texts: A Comparative Study with Weighted Soft Matching. J Med Internet Res (forthcoming). doi:10.2196/78681, 2026. http://dx.doi.org/10.2196/78681
  2. Ogasawara R, Imai T, Takeda K, Nakagome K. Machine-Learning-Based Prediction of Suicide Risk Using Preliminary Questionnaire and Consultation Text. Stud Health Technol Inform. 2025 Aug 7;329:861-865. doi: 10.3233/SHTI250962. PMID: 40775980.
  3. Tanaka T, Katayama T, Imai T. Predicting the effects of drugs and unveiling their mechanisms of action using an Interpretable Pharmacodynamic Mechanism Knowledge Graph (IPM-KG). Computers in Biology and Medicine, Epub 2024 November. doi: https://doi.org/10.1016/j.compbiomed.2024.109419.
  4. Cai C, Imai T, Hasumi E, Fujiu K. One-shot screening: Utilization of a two-dimensional convolutional neural network for automatic detection of left ventricular hypertrophy using electrocardiograms. Comput Methods Programs Biomed. 2024 Feb 25;247:108097. doi: 10.1016/j.cmpb.2024.108097. Epub ahead of print. PMID: 38428250.
  5. Yokota S, Doi S, Fukuhara M, Mitani T, Nagashima S, Gonoi W, Imai T, Ohe K. Application program to detect unrecognized information regarding malignant tumors in radiology reports. Health and Technology, Epub 2022 Dec. doi: https://doi.org/10.1007/s12553-022-00724-0
  6. Shiokawa Y, Mori N, Sakusabe T, Imai T, Watanabe H, Kimura M. Medical Image Sharing in Japan. J Digit Imaging. 2022 Aug;35(4):772-784. doi: 10.1007/s10278- 022-00675-y. Epub 2022 Aug 22. PMID: 35995897; PMCID: PMC9395812.
  7. Aoki M, Yokota S, Kagawa R, Shinohara E, Imai T, Ohe K. Automatic Classification of Electronic Nursing Narrative Records Based on Japanese Standard Terminology for Nursing. Comput Inform Nurs. 2021 May 12;39(11):828-834.
  8. Ma X, Imai T, Shinohara E, Kasai S, Kato K, Kagawa R, Ohe K. EHR2CCAS: A framework for mapping EHR to disease knowledge presenting causal chain of disorders – chronic kidney disease example. J Biomed Inform. 2021 Mar;115:103692. doi: 10.1016/j.jbi.2021.103692. Epub 2021 Feb 4. PMID: 33548543.
  9. Iwai S, Mitani T, Hayakawa J, Shinohara E, Imai T, Kawazoe Y, Ohe K. Development of Graph-Based Algorithm for Differentiating Pathophysiological Conditions. Applied Medical Informatics. 2020;42(2):107-117.
  10. Mitani T, Doi S, Yokota S, Imai T, Ohe K. Highly accurate and explainable detection of specimen mix-up using a machine learning model. Clin Chem Lab Med. 2020 Feb 25;58(3):375-383.
  11. Hayakawa M, Imai T, Kawazoe Y, Kozaki K, Ohe K. Auto-Generated Physiological Chain Data for an Ontological Framework for Pharmacology and Mechanism of Action to Determine Suspected Drugs in Cases of Dysuria. Drug Saf. 2019 Sep;42(9):1055-1069.
  12. Kagawa R, Shinohara E, Imai T, Kawazoe Y, Ohe K. Bias of Inaccurate Disease Mentions in Electronic Health Record-based Phenotyping. Int J Med Inform. 2019 Apr;124:90-96.
  13. Ishihara S, Fujiu K, Imai T. An analysis of one-shot screening methods of ECG with different types of 2-D CNN. Journal of Neuroscience and Biomedical Engineering, 2019, 1(1): 1-9.
  14. Ma X, Imai T, Shinohara E, Sakurai R, Kozaki K, Ohe K. A Semi-Automatic Framework to Identify Abnormal States in EHR Narratives. Stud Health Technol Inform. 2017;245:910-914.
  15. Kagawa R, Kawazoe Y, Shinohara E, Imai T, Ohe K. The Impact of “Possible Patients” on Phenotyping Algorithms: Electronic Phenotype Algorithms Can Only Be Reproduced by Sharing Detailed Annotation Criteria. Stud Health Technol Inform. 2017;245:432-436.
  16. Iwai S, Kawazoe Y, Imai T, Ohe K. Effects of Implementing a Tree Model of Diagnosis into a Bayesian Diagnostic Inference System. Stud Health Technol Inform. 2017;245:882-886.
  17. Kozaki K, Yamagata Y, Mizoguchi R, Imai T, Ohe K. Disease Compass- a navigation system for disease knowledge based on ontology and linked data techniques. J Biomed Semantics. 2017 Jun 19;8(1):22. doi: 10.1186/s13326-017-0132-2.
  18. Kagawa R, Kawazoe Y, Ida Y, Shinohara E, Tanaka K, Imai T, Ohe K. Development of Type 2 Diabetes Mellitus Phenotyping Framework Using Expert Knowledge and Machine Learning Approach. J Diabetes Sci Technol. 2017 Jul;11(4):791-799. doi: 10.1177/1932296816681584. Epub 2016 Dec 7.
  19. Imai T, Shinohara E, Kajino M, Sakurai R, Ohe K, Kozaki K, Mizoguchi R. An Ontological Framework for Representing Topological Information in Human Anatomy. In Proc. of International Conference on Biomedical Ontology and BioCreative (ICBO-BioCreative 2016), Corvallis, USA, August 1-4, 2016. CEUR Workshop Proceedings, ISSN 1613-0073, available online at CEUR-WS.org/Vol-1747/, 2016.
  20. Kawazoe Y, Imai T, Ohe K, A Querying Method over RDF-ized Health Level Seven v2.5 Messages Using Life Science Knowledge Resources, JMIR Med Inform 2016;4(2):e12.
  21. Kozaki K, Yamagata Y, Mizoguchi R, Imai T and Ohe K. Disease Compass – Navigation System for Disease Knowledge based on Ontology and Linked Data Techniques. In Proc. of International Conference on Biomedical Ontology (ICBO 2015), Lisbon, Portugal, pp.77-81, July 27-30, 2015.
  22. Yamagata Y, Kozaki K, Imai T, Ohe K, Mizoguchi R. Towards the Integration of Abnormality in Diseases. In Proc. of the 5th International Conference on Biomedical Ontology (ICBO2014), Houston, USA, pp.7-12, October 6-9, 2014.
  23. Kozaki K, Yamagata Y, Imai T, Ohe K, Mizoguchi R. Publishing a Disease Ontologies as Linked Data. In Proc. of Third Joint International Semantic Technology Conference (JIST2013), South Korea, November 28-30, 2013. Lecture Notes in Computer Science Volume 8388, 2014, pp. 110-128.
  24. Yamagata Y, Kozaki K, Imai T, Ohe K, Mizoguchi R. An ontological modeling approach for abnormal states and its application in the medical domain. J Biomed Semantics. 2014 May 21;5:23. doi: 10.1186/2041-1480-5-23. eCollection 2014.
  25. Yamagata Y, Kou H, Kozaki K, Mizoguchi R, Imai T, Ohe K. Ontological Model of Abnormal States and its Application in the Medical Domain. In Proc. of the 4th International Conference on Biomedical Ontology (ICBO 2013), Montreal, Qc, Canada, pp.22-27, July 8-9, 2013.
  26. Imai T, Hayakawa M, Ohe K. Development of Description Framework of Pharmacodynamics Ontology and Its Application to Possible Drug-drug Interaction Reasoning. Stud Health Technol Inform. 2013;192:567-71.
  27. Yoshida Y, Imai T, Ohe K. The trends in EMR and CPOE adoption in Japan under the national strategy. Int J Med Inform. 2013 Oct;82(10):1004-11.
  28. Shinohara EY, Aramaki E, Imai T, Miura Y, Tonoike M, Ohkuma T, Masuichi H, Ohe K. An easily implemented method for abbreviation expansion for the medical domain in Japanese text. A preliminary study. Methods Inf Med. 2013;52(1):51-61.
  29. Yamagata Y, Kou H, Kozaki K, Mizoguchi R, Imai T, Ohe K. Ontological Modeling of Interoperable Abnormal States. In Proc. of Second Joint International Semantic Technology Conference (JIST 2012), Nara, Japan, December 2-4, 2012. Lecture Notes in Computer Science Volume 7774, 2013, pp 33-48.
  30. Kozaki K, Mizoguchi R, Imai T, Ohe K. Identity Tracking of a Disease as a Causal Chain. In Proc. of the 3rd International Conference on Biomedical Ontology (ICBO 2012), KR-MED Series, July 21-25, 2012, Graz, Austria, Ronald Cornet ans Robert Stevens (eds.), CEUR Workshop Proceedings, ISSN 1613-0073, available online at CEUR-WS.org/Vol-897/,pp.131-136, 2012.
  31. Kozaki K, Mizoguchi R, Imai T, Ohe K. A Consideration on Identity of Diseases. Proc. of the Fifth Interdisciplinary Ontology Meeting, pp.75-80, Tokyo, Japan, February 23-24, 2012.
  32. Mizoguchi R, Kozaki K, Kou H, Yamagata Y, Imai T, Waki K, Ohe K. River Flow Model of Diseases. Proc. of International Conference on Biomedical Ontology 2011 (ICBO2011), pp.63-70, 2011.
  33. Kou H, Ohta M, Zhou J, Kozaki K, Mizoguchi R, Imai T, Ohe K. Development of Fundamental Technologies for Better Understanding of Clinical Medical Ontologies. Proc. of International Conference on Knowledge Engineering and Ontology Development (KEOD 2010),pp.235-240, 2010.
  34. Imai T, Kajino M, Sato M, Ohe K. Development of structured ICD-10 and its application to computer-assisted ICD coding. Stud Health Technol Inform. 2010;160(Pt 2):1080-4.
  35. Yamada E, Aramaki E, Imai T, Ohe K. Internal structure of a disease name and its application for ICD coding. Stud Health Technol Inform. 2010;160(Pt 2):1010-4.
  36. Imai T, Kou H, Zhou J, Kozaki K, Mizoguchi R, Ohe K. Japan Medical Ontology Development Project for Advanced Clinical Information Systems. Proc. Of 10th International HL7 Interoperability Conference 2009 (IHIC2009), pp.42-46, 2009.
  37. Mizoguchi R, Kou H, Zhou J, Kozaki K, Imai T, Ohe K. An Advanced Clinical Ontology. Proc. Of International Conference on Biomedical Ontology 2009 (ICBO2009), pp.119-122, 2009.
  38. Aramaki E, Imai T, Miyo K, Ohe K. Orthographic Disambiguation Incorporating Transliterated Probability. Proc. of International Joint Conference on Natural Language Processing (IJCNLP2008), pp.48-55, 2008.
  39. Aramaki E, Imai T, Miyo K, Ohe K. Support Vector Machine Based Orthographic Disambiguation. Proc. of the Conference on Theoretical and Methodological Issues in Machine Translation (TMI2007). pp.21-30, 2007.
  40. Aramaki E, Imai T, Miyo K, Ohe K. UTH: Semantic Relation Classification using Physical Sizes. The Association for Computational Linguistics (ACL2007) Workshop on Semantic Evaluations (SemEval 2007). pp.464-7, 2007.
  41. Imai T, Aramaki E, Kajino M, Miyo K, Onogi Y, Ohe K. Finding malignant findings from radiological reports using medical attributes and syntactic information. Stud Health Technol Inform. 2007;129(Pt 1):540-4.
  42. Aramaki E, Imai T, Kajino M, Miyo K, Ohe K. Statistical selector of the best multiple ICD-coding method. Stud Health Technol Inform. 2007;129(Pt 1):645-9.
  43. Aramaki E, Imai T, Miyo K, Ohe K. Automatic Deidentification by using Sentence Features and Label Consistency. Proceedings i2b2 Workshop on Challenges in Natural Language Processing for Clinical Data, 2006.
  44. Aramaki E, Imai T, Miyo K, Ohe K. Patient Status Classification by using Rule based Sentence Extraction and BM25-kNN based Classifier. Proceedings i2b2 Workshop on Challenges in Natural Language Processing for Clinical Data, 2006.
  45. Aramaki E, Imai T, Kashiwagi M, Kajino M, Miyo K, Ohe K. Toward Medical Ontology using Natural Language Processing. Proc. of OntoLex2005, IJCNLP’05. pp.53-8, 2005.
  46. Imai T, Onogi Y. Extracting Numerical Measurements and Temporal Coordinates from Japanese Radiological Reports. Proc. of SPIE Medical Imaging 2004;5371: pp.268-76, 2004.

 

研究倫理関連の開示

  1. 漢方の特性を利用したエビデンス創出と適正使用支援システムの構築(審査番号:11662)

研究室サイトはこちら