Connectome-based machine learning models are vulnerable to subtle data manipulations.

Saved in:
Bibliographic Details
Title: Connectome-based machine learning models are vulnerable to subtle data manipulations.
Authors: Rosenblatt M; Department of Biomedical Engineering, Yale School of Engineering and Applied Science, New Haven, CT 06510, USA., Rodriguez RX; Interdepartmental Neuroscience Program, Yale School of Medicine, New Haven, CT 06510, USA., Westwater ML; Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT 06510, USA., Dai W; Department of Biostatistics, Yale School of Public Health, New Haven, CT 06510, USA., Horien C; Interdepartmental Neuroscience Program, Yale School of Medicine, New Haven, CT 06510, USA., Greene AS; Interdepartmental Neuroscience Program, Yale School of Medicine, New Haven, CT 06510, USA., Constable RT; Department of Biomedical Engineering, Yale School of Engineering and Applied Science, New Haven, CT 06510, USA.; Interdepartmental Neuroscience Program, Yale School of Medicine, New Haven, CT 06510, USA.; Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT 06510, USA.; Department of Neurosurgery, Yale School of Medicine, New Haven, CT 06510, USA., Noble S; Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT 06510, USA., Scheinost D; Department of Biomedical Engineering, Yale School of Engineering and Applied Science, New Haven, CT 06510, USA.; Interdepartmental Neuroscience Program, Yale School of Medicine, New Haven, CT 06510, USA.; Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT 06510, USA.; Department of Statistics & Data Science, Yale University, New Haven, CT 06510, USA.; Child Study Center, Yale School of Medicine, New Haven, CT 06510, USA.; Wu Tsai Institute, Yale University, New Haven, CT 06510, USA.
Source: Patterns (New York, N.Y.) [Patterns (N Y)] 2023 May 15; Vol. 4 (7), pp. 100756. Date of Electronic Publication: 2023 May 15 (Print Publication: 2023).
Publication Type: Journal Article
Journal Info: Publisher: Elsevier Inc Country of Publication: United States NLM ID: 101767765 Publication Model: eCollection Cited Medium: Internet ISSN: 2666-3899 (Electronic) Linking ISSN: 26663899 NLM ISO Abbreviation: Patterns (N Y) Subsets: PubMed not MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:2666-3899
DOI:10.1016/j.patter.2023.100756