人工知能を用いた肥大型心筋症患者の収縮能低下および拡張相移行への予測
| Project/Area Number |
21K08138
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 53020:Cardiology-related
|
|---|
| Research Institution | Nippon Medical School |
|---|
Principal Investigator |
高野 仁司 日本医科大学, 医学部, 准教授 (90277533)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
時田 祐吉 日本医科大学, 医学部, 講師 (20386189)
松田 淳也 日本医科大学, 医学部, 助教 (10714735)
|
|---|
| Project Period (FY) |
2021-04-01 – 2023-03-31
|
| Project Status |
Discontinued (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2025: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2024: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2023: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 肥大型心筋症 / 心不全 / 人工知能 / 自動診断 |
|---|
| Outline of Research at the Start |
一部の肥大型心筋症患者では収縮能が徐々に低下し拡張相肥大型心筋症へ移行、致死性不整脈が増し心不全治療にも抵抗するより予後が悪い病態へ変化する。しかし、その予測因子や介入による予防方法は確立されておらず、本疾患治療の重要な課題である。本研究では、肥大型心筋症患者の12誘導心電図の経時的変化を基本として、さらにベースラインでの心エコー所見・心臓磁気共鳴画像所見、経時的に得られる心筋マーカーの数値、拡張相肥大型心筋症移行の家族歴などを加味し、収縮能低下および拡張相への移行確率を両方向性長・短期記憶を用いた長期ニューラルネットワークによる人工知能を用いた予測方法を確立する。
|
| Outline of Annual Research Achievements |
Background: Some patients with hypertrophic cardiomyopathy (HCM) progress to the dilated phase of HCM (DHCM). We aimed to identify the predictive factors for the development of DHCM (left ventricular ejection fraction (LVEF) < 50%) or declined LV contraction (LVEF < 60%) in patients with HCM.
Methods: We analyzed the data of 291 patients who were enrolled in our hospital’s HCM registry. The patients were divided into three groups based on their LVEF at the end of the study (LVEF remained > 60%, LVEF 50-60%, and DHCM < 50%). We evaluated the predictive factors of LVEF less than 50% and 60%. We also looked at how percutaneous transluminal septal myocardial ablation (PTSMA) affected long-term systolic LV function and DHCM development.
Results: During the follow-up period (mean, 71.8 months), LVEF remained > 60% in 239 patients, fell within the range of 50%-60% in 33 patients, and declined below 50% in 19 patients. Multivariate analyses indicated baseline atrial fibrillation (AF), non-sustained ventricular tachycardia (NSVT), left ventricular diameter at end-systole (LVDs) and C-reactive protein (CRP) as the significant predictors of DHCM and reduced estimated glomerular filtration rate as a nearly significant predictor for the declined LV contraction. PTSMA, performed in 78 HCM patients, did not significantly affect the long-term LVEF changes or the development of DHCM.
Conclusion: We concluded that AF, NSVT, LVDs and CRP are significant predictors of DHCM development. However, a validation study with a larger population is warranted.
|
Report
(2 results)
Research Products
(2 results)
