Classification of Major Depressive Disorder via Multi-Site Weighted LASSO Model
Book chapter
Zhu, Dajiang, Riedel, Brandalyn C., Jahanshad, Neda, Groenewold, Nynke A., Stein, Dan J., Gotlib, Ian H., Dima, Danai, Cole, James H., Fu, C., Walter, Henrik, Veer, Ilya M., Frodl, Thomas, Schmaal, Lianne, Veltman, Dick J. and Thompson, Paul M. 2017. Classification of Major Depressive Disorder via Multi-Site Weighted LASSO Model. in: Descoteaux, Maxime, Maier-Hein, Lena, Franz, Alfred, Jannin, Pierre, Collins, D. Louis and Duchesne, Simon (ed.) Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017 Springer, Cham.
Authors | Zhu, Dajiang, Riedel, Brandalyn C., Jahanshad, Neda, Groenewold, Nynke A., Stein, Dan J., Gotlib, Ian H., Dima, Danai, Cole, James H., Fu, C., Walter, Henrik, Veer, Ilya M., Frodl, Thomas, Schmaal, Lianne, Veltman, Dick J. and Thompson, Paul M. |
---|---|
Editors | Descoteaux, Maxime, Maier-Hein, Lena, Franz, Alfred, Jannin, Pierre, Collins, D. Louis and Duchesne, Simon |
Abstract | Large-scale collaborative analysis of brain imaging data, in psychiatry and neurology, offers a new source of statistical power to discover features that boost accuracy in disease classification, differential diagnosis, and outcome prediction. However, due to data privacy regulations or limited accessibility to large datasets across the world, it is challenging to efficiently integrate distributed information. Here we propose a novel classification framework through multi-site weighted LASSO: each site performs an iterative weighted LASSO for feature selection separately. Within each iteration, the classification result and the selected features are collected to update the weighting parameters for each feature. This new weight is used to guide the LASSO process at the next iteration. Only the features that help to improve the classification accuracy are preserved. In tests on data from five sites (299 patients with major depressive disorder (MDD) and 258 normal controls), our method boosted classification accuracy for MDD by 4.9% on average. This result shows the potential of the proposed new strategy as an effective and practical collaborative platform for machine learning on large scale distributed imaging and biobank data. |
Keywords | MDD; weighted LASSO |
Book title | Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017 |
Year | 2017 |
Publisher | Springer, Cham |
Publication dates | |
Online | 04 Sep 2017 |
Publication process dates | |
Deposited | 05 Jun 2017 |
Accepted | 26 May 2017 |
Accepted | May 2017 |
Series | Lecture Notes in Computer Science |
Event | 20th International Conference on Medical Image Computing and Computer Assisted Intervention |
ISBN | 978-3-319-66178-0 |
978-3-319-66179-7 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-319-66179-7_19 |
Funder | National Institutes of Health |
National Institutes of Health | |
Web address (URL) | https://doi.org/10.1007/978-3-319-66179-7_19 |
https://arxiv.org/abs/1705.10312v1 | |
Additional information | The final authenticated version is available online at https://doi.org/10.1007/978-3-319-66179-7_19 |
Journal citation | 3, pp. 159-167 |
Accepted author manuscript |
https://repository.uel.ac.uk/item/84q9x
Download files
206
total views275
total downloads0
views this month1
downloads this month