Peer-Reviewed Publication
Neural Comput2023;36(1):107-127.December 12, 2023Journal Article
Cocaine Use Prediction With Tensor-Based Machine Learning on Multimodal MRI Connectome Data.
Anru R Zhang1, Ryan P Bell2, Chen An3, Runshi Tang4, Shana A Hall5, Cliburn Chan6, Kareem Al-Khalil7, Christina S Meade8
1Department of Biostatistics and Bioinformatics and Department of Computer Science, Duke University, Durham, NC 27710, U.S.A. anru.zhang@duke.edu.
2Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. rpbell@wakehealth.edu.
3Department of Mathematics, Duke University, Durham, NC 27708, U.S.A. chen.an.nku@gmail.com.
4Department of Statistics, University of Wisconsin-Madison, Madison, WI, U.S.A. rtang56@wisc.edu.
5Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. shana@limbix.com.
6Department of Biostatistics and Bioinformatics, Duke University, Durham, NC 27710, U.S.A. cliburn.chan@duke.edu.
7Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. kareem.alkhalil@duke.edu.
8Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. cmeade@wakehealth.edu.
Abstract
This letter considers the use of machine learning algorithms for predicting cocaine use based on magnetic resonance imaging (MRI) connectomic data. The study used functional MRI (fMRI) and diffusion MRI (dMRI) data collected from 275 individuals, which was then parcellated into 246 regions of interest (ROIs) using the Brainnetome atlas. After data preprocessing, the data sets were transformed into…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans