Embedding Anatomical or Functional Knowledge in Whole-Brain Multiple Kernel Learning Models
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14376
- Type
- D - Journal article
- DOI
-
10.1007/s12021-017-9347-8
- Title of journal
- Neuroinformatics
- Article number
- 1
- First page
- 1
- Volume
- 16
- Issue
- 1
- ISSN
- 1539-2791
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 21
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposed a new framework based on Multiple Kernel Learning (MKL) to improve the interpretability of whole brain predictive models. The proposed framework learns the contribution of each brain region, defined by an atlas, to the predictive model. The framework has been implemented in the open source software PRoNTo which is being used by hundreds of neuroscience and clinical neuroscience labs around the world. The advantages of the framework has been recently demonstrated to identify brain regions predictive of bipolar disorder risk in young adults (Oliveira L et al. Biol Psychiatry Cogn Neurosci Neuroimaging. 2019).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -