A Spatially Sensitive Kernel to Predict Cognitive Performance from Short-Term Changes in Neural Structure
Abstract
This paper introduces a novel framework for performing machine learning onlongitudinal neuroimaging datasets. These datasets are characterized by theirsize, particularly their width (millions of features per data input). Specifically, we address the problem of detecting subtle, short-term changes inneural structure that are indicative of cognitive change and correlate withrisk factors for Alzheimer's disease. We introduce a new spatially-sensitivekernel that allows us to reason about individuals, as opposed to populations. In doing so, this paper presents the first evidence demonstrating that verysmall changes in white matter structure over a two year period can predictchange in cognitive function in healthy adults.
Cite
Text
Ansari et al. "A Spatially Sensitive Kernel to Predict Cognitive Performance from Short-Term Changes in Neural Structure." AAAI Conference on Artificial Intelligence, 2014. doi:10.1609/AAAI.V28I1.8925Markdown
[Ansari et al. "A Spatially Sensitive Kernel to Predict Cognitive Performance from Short-Term Changes in Neural Structure." AAAI Conference on Artificial Intelligence, 2014.](https://mlanthology.org/aaai/2014/ansari2014aaai-spatially/) doi:10.1609/AAAI.V28I1.8925BibTeX
@inproceedings{ansari2014aaai-spatially,
title = {{A Spatially Sensitive Kernel to Predict Cognitive Performance from Short-Term Changes in Neural Structure}},
author = {Ansari, M. Hidayath and Coen, Michael H. and Bendlin, Barbara B. and Sager, Mark A. and Johnson, Sterling C.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2014},
pages = {1157-1163},
doi = {10.1609/AAAI.V28I1.8925},
url = {https://mlanthology.org/aaai/2014/ansari2014aaai-spatially/}
}