Cocaine Use Prediction With Tensor-Based Machine Learning on Multimodal MRI Connectome Data.

Autor:	Zhang AR; Department of Biostatistics and Bioinformatics and Department of Computer Science, Duke University, Durham, NC 27710, U.S.A. anru.zhang@duke.edu., Bell RP; Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. rpbell@wakehealth.edu., An C; Department of Mathematics, Duke University, Durham, NC 27708, U.S.A. chen.an.nku@gmail.com., Tang R; Department of Statistics, University of Wisconsin-Madison, Madison, WI, U.S.A. rtang56@wisc.edu., Hall SA; Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. shana@limbix.com., Chan C; Department of Biostatistics and Bioinformatics, Duke University, Durham, NC 27710, U.S.A. cliburn.chan@duke.edu., Al-Khalil K; Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. kareem.alkhalil@duke.edu., Meade CS; Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. cmeade@wakehealth.edu.
Jazyk:	angličtina
Zdroj:	Neural computation [Neural Comput] 2023 Dec 12; Vol. 36 (1), pp. 107-127.
DOI:	10.1162/neco_a_01623
Abstrakt:	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 tensor form. We developed a tensor-based unsupervised machine learning algorithm to reduce the size of the data tensor from 275 (individuals) × 2 (fMRI and dMRI) × 246 (ROIs) × 246 (ROIs) to 275 (individuals) × 2 (fMRI and dMRI) × 6 (clusters) × 6 (clusters). This was achieved by applying the high-order Lloyd algorithm to group the ROI data into six clusters. Features were extracted from the reduced tensor and combined with demographic features (age, gender, race, and HIV status). The resulting data set was used to train a Catboost model using subsampling and nested cross-validation techniques, which achieved a prediction accuracy of 0.857 for identifying cocaine users. The model was also compared with other models, and the feature importance of the model was presented. Overall, this study highlights the potential for using tensor-based machine learning algorithms to predict cocaine use based on MRI connectomic data and presents a promising approach for identifying individuals at risk of substance abuse. (© 2023 Massachusetts Institute of Technology.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu