| 研究課題/領域番号 |
23K14813
|
|---|
| 研究種目 |
若手研究
|
| 配分区分 | 基金 |
|---|
| 審査区分 |
小区分52030:精神神経科学関連
|
|---|
| 研究機関 | 千葉大学 |
|---|
研究代表者 |
BhusalChhatkuli Ritu 千葉大学, 子どものこころの発達教育研究センター, 特任助教 (50836591)
|
|---|
| 研究期間 (年度) |
2023-04-01 – 2026-03-31
|
| 研究課題ステータス |
交付 (2024年度)
|
| 配分額 *注記 |
4,680千円 (直接経費: 3,600千円、間接経費: 1,080千円)
2025年度: 1,040千円 (直接経費: 800千円、間接経費: 240千円)
2024年度: 1,950千円 (直接経費: 1,500千円、間接経費: 450千円)
2023年度: 1,690千円 (直接経費: 1,300千円、間接経費: 390千円)
|
|---|
| キーワード | Anorexia Nervosa / Classification / Machine Learning / Harmonzation / Anorexia / MRI / Biomarkers / Machine learning / biomarkers |
|---|
| 研究開始時の研究の概要 |
We collect large number of MR datasets from healthy volunteers and anorexia patients in this multicenter study with an aim to classify patients from the healthy controls and its subtypes, by using different machine learning techniques to identify the neuroanatomical biomarker of anorexia.
|
| 研究実績の概要 |
Accurate classification of healthy controls (HC) and anorexia nervosa (AN) patients in the multi-site data set is challenging due to its clinical heterogeneity. However, it is important for disease-specific biomarker discovery. The objective is to evaluate machine learning-based classifier performance for the classification of AN, AN restricting type (AN-R), and binge purging type (AN-BP) from healthy controls, classify AN-R and AN-BP, using multi-site structural MR imaging parcellated datasets, and to identify the most significant brain regions that contribute to the classification. Machine learning-based analysis showed promising results for using structural MR imaging as a candidate to identify biomarkers in patients with AN.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
3: やや遅れている
理由
The research manuscript is already prepared however it is under major revision. Hence some re-analyses is being conducted.
|
| 今後の研究の推進方策 |
As per the reviews received from the reviewers some additional analyses needs to be conducted by separating one site as an unused data sets. Once the analysis is complete the result will be added to the manuscript and resubmitted.
|
