首页|Georgia Institute of Technology and Emory University Reports Findings in Alzheim er Disease (Multimodal active subspace analysis for computing assessment oriente d subspaces from neuroimaging data)
Georgia Institute of Technology and Emory University Reports Findings in Alzheim er Disease (Multimodal active subspace analysis for computing assessment oriente d subspaces from neuroimaging data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Neurodegenerative Dise ases and Conditions - Alzheimer Disease is the subject of a report. According to news reporting originating from Atlanta, United States, by NewsRx correspondent s, research stated, "For successful biomarker discovery, it is essential to deve lop computational frameworks that summarize high-dimensional neuroimaging data i n terms of involved sub-systems of the brain, while also revealing underlying he terogeneous functional and structural changes covarying with specific cognitive and biological traits. However, unsupervised decompositions do not inculcate cli nical assessment information, while supervised approaches extract only individua l feature importance, thereby impeding qualitative interpretation at the level o f subspaces." Our news editors obtained a quote from the research from the Georgia Institute o f Technology and Emory University, "We present a novel framework to extract robu st multimodal brain subspaces associated with changes in a given cognitive or bi ological trait. Our approach involves active subspace learning on the gradients of a trained machine learning model followed by clustering to extract and summar ize the most salient and consistent subspaces associated with the target variabl e. Through a rigorous cross-validation procedure on an Alzheimer's disease (AD) dataset, our framework successfully extracts multimodal subspaces specific to a given clinical assessment (e.g., memory and other cognitive skills), and also re tains predictive performance in standard machine learning algorithms. We also sh ow that the salient active subspace directions occur consistently across randoml y sub-sampled repetitions of the analysis. Compared to existing unsupervised dec ompositions based on principle component analysis, the subspace components in ou r framework retain higher predictive information."
AtlantaUnited StatesNorth and Centra l AmericaAlzheimer DiseaseBiomarkersCyborgsDiagnostics and ScreeningEm erging TechnologiesHealth and MedicineMachine LearningNeurodegenerative Di seases and ConditionsNeuroimaging
NETL
NSTL
