Development of cancer diagnosis and prediction algorithm using exhaled gas

• Project/Area Number: 17H01817
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Life / Health / Medical informatics
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Sakumura Yuichi 奈良先端科学技術大学院大学, 先端科学技術研究科, 准教授 (50324968)
• Co-Investigator(Kenkyū-buntansha): 池田 和司 奈良先端科学技術大学院大学, 先端科学技術研究科, 教授 (10262552) ; 申 ウソク 国立研究開発法人産業技術総合研究所, 材料・化学領域, 研究グループ長 (10357246) ; 宮内 睦美 広島大学, 医系科学研究科(歯), 教授 (50169265) ; 樋田 豊明 愛知県がんセンター(研究所), 分子腫瘍学分野, 研究員 (80250249) ; 伊藤 敏雄 国立研究開発法人産業技術総合研究所, 材料・化学領域, 主任研究員 (90377888) ; 赤松 貴文 国立研究開発法人産業技術総合研究所, 材料・化学領域, 主任研究員 (60635316)
• Project Period (FY): 2017-04-01 – 2020-03-31
• Project Status: Completed (Fiscal Year 2019)
• Budget Amount: ¥16,510,000 (Direct Cost: ¥12,700,000、Indirect Cost: ¥3,810,000); Fiscal Year 2019: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2018: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000); Fiscal Year 2017: ¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000)
• Keywords: 呼気ガス / 機械学習 / がん診断 / 疾病診断 / 呼気成分 / ガスセンサ / 非侵襲診断 / 呼気 / がん / 特徴選択 / AI

Outline of Final Research Achievements

Machine learning was applied to the components of exhaled gas to accurately diagnose healthy subjects and patients with multiple diseases. Each disease-specific exhalation component was extracted. These components may be candidates for novel biomarkers for each disease. In order to develop a simple gas component detector, we compared its diagnostic performance with that of gas chromatography, and found that it could provide the same level of performance. This indicates that the performance of the detection values by the simple detector is comparable to that of gas chromatography. The performance itself needs to be improved with high false positives and false negatives.

Academic Significance and Societal Importance of the Research Achievements

本研究課題の手法が確立されれば、様々な非侵襲データを統合することで、高い精度の健康診断が簡素に行うことが可能となる。その簡便性から医療現場の労力を大幅に削減できるだけでなく、被検者の観点では経済的・身体的・心的・時間的負担が大幅に軽減される。疾患・健常レベルを評価することは、疾病を速く（fast）診断するたけでなく、早い（early）段階で疾患可能性を潰す予防医学につなげることができる。予防医学が進めば我が国の医療費の削減に寄与するだけでなく、新たな産業の創出につながる可能性を秘めている。

Research Products

• [Journal Article] Diagnosis by Volatile Organic Compounds in Exhaled Breath from Lung Cancer Patients Using Support Vector Machine Algorithm (2017)
  • Author(s): Sakumura Yuichi、Koyama Yutaro、Tokutake Hiroaki、Hida Toyoaki、Sato Kazuo、Itoh Toshio、Akamatsu Takafumi、Shin Woosuck
  • Journal Title: Sensors Volume: 17 Issue: 2 Pages: 287-287
  • DOI: 10.3390/s17020287
  • NAID: 120006537399
  • Peer Reviewed / Open Access
• [Presentation] Machine learning diagnosis of multiple liver-related diseases by exhaled breath gas components (2019)
  • Author(s): Shingo Shirone, Mutsumi Miyauchi, Kazuhisa Ouhara, Hidemi Kurihara, Takashi Takata, Hideyuki Hyogo, Toshio Ito, Wosuck Shin, Akiko Tanaka, Kazuo Sato, Kazushi Ikeda and Yuichi Sakumura
  • Organizer: The 20th International Conference on Systems Biology
  • Int'l Joint Research
• [Presentation] Feature Selection using Distance from Classification Boundary and Monte Carlo Simulation (2018)
  • Author(s): Koyama Y, Ikeda K, Sakumura Y
  • Organizer: The 25th International Conference on Neural Information Processing
  • Int'l Joint Research