Predicting the Prognosis of Patients with Coronary Artery Disease Using Optical Coherence Tomography and Machine Learning

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K17117
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 53020:Cardiology-related
• Research Institution: Osaka University
• Principal Investigator: Nakamura Daisuke 大阪大学, 医学部附属病院, 特任助教(常勤) (30869970)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: 冠動脈疾患

Outline of Final Research Achievements

We conducted a machine learning analysis on 102 cases of OCT-guided PCI performed at Osaka University Hospital, analyzing OCT images before and after stent placement. The analysis of OCT findings pre- and post-PCI suggested a relationship between post-stent expansion failure and clinical outcomes, specifically regarding revascularization. Furthermore, we examined the relationship between stent expansion failure and pre-placement calcification, finding that the thickness and length of calcification were associated with post-placement expansion failure. It is crucial to determine whether this machine learning-based calcification analysis is clinically useful. For it to be clinically valuable, a system that provides immediate analysis results after OCT imaging is necessary. We plan to prospectively collect OCT images and conduct further analyses in the future.

Free Research Field

循環器内科学

Academic Significance and Societal Importance of the Research Achievements

厚生労働省が発表した2018年の人口動態統計月報年計（概数）の結果では、日本人の死 因の第2位は心疾患であり、今後の高齢化社会を考慮すると罹患率の上昇は確実であるその中でも虚血性疾患の罹患率は高く、冠 動脈疾患への治療成績の向上、それに伴う予後の改善は必至である。OCTによって心血管予後の予測が可能であれば、より詳細,より正確な治療方針の決定 が可能になり、またそれによって患者の心血管予後、生命予後の改善が期待できる