Improving prediction accuracy of adverse events in radiation therapy using machine learning

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K16708
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 52040:Radiological sciences-related
• Research Institution: Keio University
• Principal Investigator: Fukata Kyohei 慶應義塾大学, 医学部(信濃町), 共同研究員 (00647266)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: 放射線治療

Outline of Final Research Achievements

If we can use machine learning to accurately predict adverse events that occur during radiation therapy, we believe that it will be possible to formulate treatment plans that avoid them. We clarified the relationship between the radiation dose to the heart and adverse events in patients who had undergone treatment for the esophagus in the past. We also used a machine learning-based model to examine the influence of rectal dose during heavy ion radiotherapy to the prostate on rectal adverse events.

Free Research Field

放射線治療

Academic Significance and Societal Importance of the Research Achievements

放射線治療を行う上で、有害事象の一定確率での発生は避けることができないのが事実である。本研究では、放射線治療の線量分布に基づく有害事象の予測確率を示した。今後は有害事象の確率を下げるにはどのように治療計画を行えばよいのか、といった議論が期待される。