| Co-Investigator(Kenkyū-buntansha) |
結城 賢弥 慶應義塾大学, 医学部(信濃町), その他 (00365347)
松浦 将人 東京大学, 医学部附属病院, 特任研究員 (00768351)
藤野 友里 島根大学, 医学部, 医療技術職員 (20768254)
村田 博史 国立研究開発法人国立国際医療研究センター, センター病院, 眼科 医師 (80635748)
谷戸 正樹 島根大学, 学術研究院医学・看護学系, 教授 (30284037)
平澤 一法 北里大学, 医学部, 講師 (80724343)
|
|---|
| Budget Amount *help |
¥17,940,000 (Direct Cost: ¥13,800,000、Indirect Cost: ¥4,140,000)
Fiscal Year 2023: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2022: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2021: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2020: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2019: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2018: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
|
|---|
| Outline of Final Research Achievements |
Data from 439 participants of the United Kingdom Glaucoma Treatment Study (UKGTS) were obtained and used for analysis. Using the initial visual field data, we applied variational Bayesian linear regression to predict the final visual field, and evaluated the prediction accuracy. The predictive performance was assessed using leave-one-out cross-validation and calculated as the root mean square error (RMSE) of the sensitivity at each test point. The resulting RMSE was 5.0 ± 3.0 dB. Subsequently, we used the predicted values from this method along with the initial optical coherence tomography (OCT) measurements;specifically, the peripapillary retinal nerve fiber layer (pRNFL) thickness;to predict the final visual field using the Gradient Boosting method. As a result, the RMSE decreased significantly to 4.6 plusminus 2.3 dB.
|
