Development of a Personalized Optimal Transplantation Procedure Proposal System using Machine Learning for Allogeneic Hematopoietic Cell Transplantation

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K17386
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 54010:Hematology and medical oncology-related
• Research Institution: Osaka Metropolitan University (2022-2023); Osaka City University (2020-2021)
• Principal Investigator: Okamura Hiroshi 大阪公立大学, 大学院医学研究科, 講師 (00803149)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: 機械学習 / 造血幹細胞移植 / 予後予測

Outline of Final Research Achievements

In this study, a machine learning survival prediction model was developed based on the data obtained from allogeneic hematopoietic stem cell transplantation. Furthermore, an algorithm and a web application were developed to propose an optimal transplantation procedure considering an individual patient's disease characteristics and situation. The clinical value of this algorithm was retrospectively evaluated. Consistency between the transplantation procedure proposed by the machine learning model and the transplantation procedure actually used was shown to be a favorable prognostic factor for the clinical outcome. In the future, it will be desirable to evaluate the clinical value of this algorithm through prospective studies for clinical applications.

Free Research Field

医学

Academic Significance and Societal Importance of the Research Achievements

本研究の結果から、機械学習モデルによって提案される患者個別の病状や状況に応じた移植法を臨床判断に活用することで、移植予後の改善が得られる可能性があることが示された。今後、従来治療群と本アルゴリズムを臨床活用した群の移植予後を比較するランダム化比較試験を行い本アルゴリズムの臨床的意義を示すことにより、移植領域における情報薬という新たな治療モダリティの社会実装が期待される。