WEKO3
アイテム
Resting-state functional-connectivity investigation of the neural substrates of psychiatric disorders
https://repo.qst.go.jp/records/76674
https://repo.qst.go.jp/records/766741b33283b-cf97-43fd-ba5e-e073506a8048
| Item type | 会議発表用資料 / Presentation(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2019-09-05 | |||||
| タイトル | ||||||
| タイトル | Resting-state functional-connectivity investigation of the neural substrates of psychiatric disorders | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_c94f | |||||
| 資源タイプ | conference object | |||||
| アクセス権 | ||||||
| アクセス権 | metadata only access | |||||
| アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
| 著者 |
Yahata, Noriaki
× Yahata, Noriaki× Yahata, Noriaki |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | The interest in using resting-state functional connectivity (FC) to quantitatively delineate the neural mechanisms underlying mental disorders is growing. In particular, application of various machine-learning techniques has enabled data-driven identification of disorder-specific patterns of FC, the use of which has led to automated case-control classification of individuals, with an accuracy of 80-90%. However, previous classification systems have largely suffered from overfitting and the effect of nuisance variables (NVs), thus limiting the generalization of the schemes in an independent cohort, and subsequently, their clinical applications. Here, using multi-site data set from Japan, we have developed an autism spectrum disorder (ASD) classifier by focusing on abnormal FCs in ASD, as indicated by resting-state functional connectivity magnetic resonance imaging (rs-fcMRI). To overcome the difficulties associated with overfitting and NVs, we developed a novel machine-learning algorithm that automatically and objectively identified a small number of abnormal FCs in ASD (0.2% of all FCs considered). This classifier provided diagnostic accuracy for predicting ASD in individuals in this dataset, and could also be generalized to a second cohort consisting of a different ethnic population in the USA. Furthermore, the same set of FCs in the classifier accurately predicted the communication domain score on the standard diagnostic instrument. Thus, we have established a reliable rs-fcMRI-based biomarker for ASD that reveals a direct association between the underlying neural mechanisms and the behavioral characteristics of ASD. Finally, we examined the specificity of the ASD classifier for ASD by investigating its generalizability to other psychiatric disorders. We found that our classifier did not distinguish individuals with major depressive disorder or attention-deficit hyperactivity disorder from controls, but had a moderate ability to distinguish patients with schizophrenia from controls. Our findings support that exploring neuroimaging-based dimensions that quantify the multiple-disorder spectrum may contribute to more biologically oriented diagnostic systems in clinical psychiatry. | |||||
| 会議概要（会議名, 開催地, 会期, 主催者等） | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | 第42回日本神経科学大会（NEURO2019） | |||||
| 発表年月日 | ||||||
| 日付 | 2019-07-25 | |||||
| 日付タイプ | Issued | |||||
