{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T10:04:51Z","timestamp":1756893891427},"reference-count":57,"publisher":"MIT Press","issue":"1","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>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) \u00d7 2 (fMRI and dMRI) \u00d7 246 (ROIs) \u00d7 246 (ROIs) to 275 (individuals) \u00d7 2 (fMRI and dMRI) \u00d7 6 (clusters) \u00d7 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.<\/jats:p>\n               <jats:p>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.<\/jats:p>","DOI":"10.1162\/neco_a_01623","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T22:29:19Z","timestamp":1701815359000},"page":"107-127","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":2,"title":["Cocaine Use Prediction With Tensor-Based Machine Learning on Multimodal MRI Connectome Data"],"prefix":"10.1162","volume":"36","author":[{"given":"Anru R.","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Bioinformatics and Department of Computer Science, Duke University, Durham, NC 27710, U.S.A. anru.zhang@duke.edu"}]},{"given":"Ryan P.","family":"Bell","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. rpbell@wakehealth.edu"}]},{"given":"Chen","family":"An","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Duke University, Durham, NC 27708, U.S.A. chen.an.nku@gmail.com"}]},{"given":"Runshi","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Wisconsin\u2013Madison, Madison, WI, U.S.A. rtang56@wisc.edu"}]},{"given":"Shana A.","family":"Hall","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. shana@limbix.com"}]},{"given":"Cliburn","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Bioinformatics, Duke University, Durham, NC 27710, U.S.A. cliburn.chan@duke.edu"}]},{"given":"Kareem","family":"Al-Khalil","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. kareem.alkhalil@duke.edu"}]},{"given":"Christina S.","family":"Meade","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC 27710, U.S.A. cmeade@wakehealth.edu"}]}],"member":"281","published-online":{"date-parts":[[2023,12,12]]},"reference":[{"issue":"4","key":"2023121400172694000_bib1","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","volume":"2","author":"Abdi","year":"2010","journal-title":"Wiley Interdisciplinary Reviews: Computational Statistics"},{"issue":"1","key":"2023121400172694000_bib2","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1038\/s42003-019-0611-3","article-title":"An improved neuroanatomical model of the default-mode network reconciles previous neuroimaging and neuropathological findings","volume":"2","author":"Alves","year":"2019","journal-title":"Communications Biology"},{"issue":"2","key":"2023121400172694000_bib3","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1016\/S1053-8119(03)00336-7","article-title":"How to correct susceptibility distortions in spin-echo echo-planar images: Application to diffusion tensor imaging","volume":"20","author":"Andersson","year":"2003","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib4","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1016\/j.neuroimage.2015.10.019","article-title":"An integrated approach to correction for off-resonance effects and subject movement in diffusion MR imaging","volume":"125","author":"Andersson","year":"2016","journal-title":"NeuroImage"},{"issue":"4","key":"2023121400172694000_bib5","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s12021-011-9109-y","article-title":"An open source multivariate framework for n-tissue segmentation with evaluation on public data","volume":"9","author":"Avants","year":"2011","journal-title":"Neuroinformatics"},{"issue":"4","key":"2023121400172694000_bib6","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1097\/WCO.0b013e32832d93dd","article-title":"Human brain networks in health and disease","volume":"22","author":"Bassett","year":"2009","journal-title":"Current Opinion in Neurology"},{"key":"2023121400172694000_bib7","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.drugalcdep.2019.03.023","article-title":"Regional differences in white matter integrity in stimulant use disorders: A meta-analysis of diffusion tensor imaging studies","volume":"201","author":"Beard","year":"2019","journal-title":"Drug and Alcohol Dependence"},{"key":"2023121400172694000_bib8","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.neuropharm.2013.02.018","article-title":"Intact inhibitory control processes in abstinent drug abusers (I): A functional neuroimaging study in former cocaine addicts","volume":"82","author":"Bell","year":"2014","journal-title":"Neuropharmacology"},{"key":"2023121400172694000_bib9","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.bbr.2017.01.002","article-title":"Resting state brain connectivity patterns before eventual relapse into cocaine abuse","volume":"327","author":"Berlingeri","year":"2017","journal-title":"Behavioural Brain Research"},{"key":"2023121400172694000_bib10","author":"Brown","year":"2016","journal-title":"Machine learning on human connectome data from MRI."},{"key":"2023121400172694000_bib11","doi-asserted-by":"publisher","first-page":"116443","DOI":"10.1016\/j.neuroimage.2019.116443","article-title":"The effect of network thresholding and weighting on structural brain networks in the UK biobank","volume":"211","author":"Buchanan","year":"2020","journal-title":"NeuroImage"},{"issue":"3","key":"2023121400172694000_bib12","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.bpsc.2015.12.005","article-title":"Multimodal fusion of brain imaging data: A key to finding the missing link(s) in complex mental illness","volume":"1","author":"Calhoun","year":"2016","journal-title":"Biological Psychiatry: Cognitive Neuroscience and Neuroimaging"},{"key":"2023121400172694000_bib13","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.mri.2021.06.012","article-title":"On the down-sampling of diffusion MRI data along the angular dimension","volume":"82","author":"Chen","year":"2021","journal-title":"Magnetic Resonance Imaging"},{"key":"2023121400172694000_bib14","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: A scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"2023121400172694000_bib15","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1145\/1143844.1143874","article-title":"The relationship between precision-recall and ROC curves","volume-title":"Proceedings of the 23rd International Conference on Machine Learning","author":"Davis","year":"2006"},{"issue":"8","key":"2023121400172694000_bib16","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1038\/s41386-019-0370-3","article-title":"Multimodal neurocognitive markers of interoceptive tuning in smoked cocaine","volume":"44","author":"de la Fuente","year":"2019","journal-title":"Neuropsychopharmacology"},{"issue":"4","key":"2023121400172694000_bib17","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1137\/S0895479896305696","article-title":"A multilinear singular value decomposition","volume":"21","author":"De Lathauwer","year":"2000","journal-title":"SIAM Journal on Matrix Analysis and Applications"},{"key":"2023121400172694000_bib18","article-title":"Unsupervised 3-tissue response function estimation from single-shell or multi-shell diffusion MR data without a coregistered T1 image","volume-title":"Proceedings of the ISMRM Workshop on Breaking the Barriers of Diffusion MRI","author":"Dhollander","year":"2016"},{"key":"2023121400172694000_bib19","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1146\/annurev-psych-122414-033457","article-title":"Drug addiction: Updating actions to habits to compulsions ten years on","volume":"67","author":"Everitt","year":"2016","journal-title":"Annual Review of Psychology"},{"issue":"8","key":"2023121400172694000_bib20","doi-asserted-by":"publisher","first-page":"3508","DOI":"10.1093\/cercor\/bhw157","article-title":"The human Brainnetome atlas: A new brain atlas based on connectional architecture","volume":"26","author":"Fan","year":"2016","journal-title":"Cerebral Cortex"},{"key":"2023121400172694000_bib21","article-title":"Structured clinical interview for DSM-IV axis I disorders research version (SCID-I)","author":"First","year":"1996"},{"key":"2023121400172694000_bib22","first-page":"129","article-title":"Case studies in the use of ROC curve analysis for sensor-based estimates in human computer interaction","volume-title":"Proceedings of Graphics Interface 2005","author":"Fogarty","year":"2005"},{"key":"2023121400172694000_bib23","first-page":"1","article-title":"Whole-brain white matter abnormalities in human cocaine and heroin use disorders: Association with craving, recency, and cumulative use","author":"Gaudreault","year":"2022","journal-title":"Molecular Psychiatry"},{"key":"2023121400172694000_bib24","doi-asserted-by":"publisher","first-page":"101676","DOI":"10.1016\/j.nicl.2019.101676","article-title":"Using neuroimaging to predict relapse in stimulant dependence: A comparison of linear and machine learning models","volume":"21","author":"Gowin","year":"2019","journal-title":"NeuroImage: Clinical"},{"issue":"15","key":"2023121400172694000_bib25","doi-asserted-by":"publisher","first-page":"4958","DOI":"10.1002\/hbm.25592","article-title":"Human immunodeficiency virus-related decreases in corpus callosal integrity and corresponding increases in functional connectivity","volume":"42","author":"Hall","year":"2021","journal-title":"Human Brain Mapping"},{"key":"2023121400172694000_bib26","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12547","article-title":"Exact clustering in tensor block model: Statistical optimality and computational limit","volume":"84","author":"Han","year":"2022","journal-title":"Journal of Royal Statistical Society, Series B"},{"key":"2023121400172694000_bib27","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.drugalcdep.2018.09.013","article-title":"Reward and executive control network resting-state functional connectivity is associated with impulsivity during reward-based decision making for cocaine users","volume":"194","author":"Hobkirk","year":"2019","journal-title":"Drug and Alcohol Dependence"},{"key":"2023121400172694000_bib28","doi-asserted-by":"publisher","first-page":"108833","DOI":"10.1016\/j.drugalcdep.2021.108833","article-title":"Inhibitory failures in cocaine use disorder: Not paying attention when there is a need to be cautious","volume":"226","author":"Howlett","year":"2021","journal-title":"Drug and Alcohol Dependence"},{"issue":"6","key":"2023121400172694000_bib29","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1001\/jamapsychiatry.2015.1","article-title":"Impaired functional connectivity within and between frontostriatal circuits and its association with compulsive drug use and trait impulsivity in cocaine addiction","volume":"72","author":"Hu","year":"2015","journal-title":"JAMA Psychiatry"},{"issue":"2","key":"2023121400172694000_bib30","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.neuroimage.2011.09.015","volume":"62","author":"Jenkinson","year":"2012","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib31","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Advances in neural information processing systems","author":"Ke","year":"2017"},{"key":"2023121400172694000_bib32","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.brainres.2015.02.002","article-title":"Effects of chronic and acute stimulants on brain functional connectivity hubs","volume":"1628","author":"Konova","year":"2015","journal-title":"Brain Research"},{"issue":"21","key":"2023121400172694000_bib33","doi-asserted-by":"publisher","first-page":"8081","DOI":"10.1523\/JNEUROSCI.3188-14.2015","article-title":"Interactions between the salience and default-mode networks are disrupted in cocaine addiction","volume":"35","author":"Liang","year":"2015","journal-title":"Journal of Neuroscience"},{"issue":"3","key":"2023121400172694000_bib34","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s40708-015-0019-x","article-title":"Multimodal neuroimaging computing: A review of the applications in neuropsychiatric disorders","volume":"2","author":"Liu","year":"2015","journal-title":"Brain Informatics"},{"issue":"2","key":"2023121400172694000_bib35","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Transactions on Information Theory"},{"issue":"11","key":"2023121400172694000_bib36","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1021\/acschemneuro.3c00265","article-title":"Brain imaging databases","volume":"14","author":"Mandal","year":"2023","journal-title":"ACS Chemical Neuroscience"},{"issue":"6","key":"2023121400172694000_bib37","doi-asserted-by":"publisher","first-page":"424","DOI":"10.3109\/00952990.2013.847446","article-title":"Striatal-insula circuits in cocaine addiction: Implications for impulsivity and relapse risk","volume":"39","author":"McHugh","year":"2013","journal-title":"American Journal of Drug and Alcohol Abuse"},{"issue":"1","key":"2023121400172694000_bib38","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1111\/nyas.12415","article-title":"The insula: A critical neural substrate for craving and drug seeking under conflict and risk","volume":"1316","author":"Naqvi","year":"2014","journal-title":"Annals of the New York Academy of Sciences"},{"issue":"3","key":"2023121400172694000_bib39","doi-asserted-by":"publisher","first-page":"2142","DOI":"10.1016\/j.neuroimage.2011.10.018","article-title":"Spurious but systematic correlations in functional connectivity MRI networks arise from subject motion","volume":"59","author":"Power","year":"2012","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib40","author":"Prokhorenkova","year":"2017","journal-title":"CatBoost: Unbiased boosting with categorical features."},{"key":"2023121400172694000_bib41","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.neuroimage.2015.02.064","article-title":"ICA-AROMA: A robust ICA-based strategy for removing motion artifacts from fMRI data","volume":"112","author":"Pruim","year":"2015","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib42","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.neuroimage.2016.09.053","article-title":"Consistency-based thresholding of the human connectome","volume":"145","author":"Roberts","year":"2017","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib43","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.mri.2019.05.008","article-title":"Synthesized b0 for diffusion distortion correction (Synb0-DisCo)","volume":"64","author":"Schilling","year":"2019","journal-title":"Magnetic Resonance Imaging"},{"issue":"3","key":"2023121400172694000_bib44","doi-asserted-by":"publisher","first-page":"1924","DOI":"10.1016\/j.neuroimage.2012.06.005","article-title":"Anatomically-constrained tractography: Improved diffusion MRI streamlines tractography through effective use of anatomical information","volume":"62","author":"Smith","year":"2012","journal-title":"NeuroImage"},{"issue":"3","key":"2023121400172694000_bib45","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1002\/hbm.10062","article-title":"Fast robust automated brain extraction","volume":"17","author":"Smith","year":"2002","journal-title":"Human Brain Mapping"},{"key":"2023121400172694000_bib46","doi-asserted-by":"crossref","first-page":"S208\u2013S219","DOI":"10.1016\/j.neuroimage.2004.07.051","article-title":"Advances in functional and structural MR image analysis and implementation as FSL","volume":"23","author":"Smith","year":"2004","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib47","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.neuroimage.2013.03.023","article-title":"The human connectome: Origins and challenges","volume":"80","author":"Sporns","year":"2013","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib48","volume-title":"Results from the 2018 National Survey on Drug Use and Health: Detailed Tables","author":"Substance Abuse and Mental Health Services Administration","year":"2019"},{"issue":"2","key":"2023121400172694000_bib49","doi-asserted-by":"publisher","first-page":"e12902","DOI":"10.1111\/adb.12902","article-title":"A meta-analysis of tract-based spatial statistics studies examining white matter integrity in cocaine use disorder","volume":"26","author":"Suchting","year":"2021","journal-title":"Addiction Biology"},{"issue":"2","key":"2023121400172694000_bib50","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1080\/10550490500528316","article-title":"The Addiction Severity Index at 25: Origins, contributions and transitions","volume":"15","author":"Thomas McLellan","year":"2006","journal-title":"American Journal on Addictions"},{"key":"2023121400172694000_bib51","doi-asserted-by":"publisher","first-page":"116137","DOI":"10.1016\/j.neuroimage.2019.116137","article-title":"MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation","volume":"202","author":"Tournier","year":"2019","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib52","volume-title":"World Drug Report 2021","author":"United Nations Office on Drugs and Crime","year":"2021"},{"key":"2023121400172694000_bib53","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/j.neuroimage.2016.08.016","article-title":"Denoising of diffusion MRI using random matrix theory","volume":"142","author":"Veraart","year":"2016","journal-title":"NeuroImage"},{"issue":"3","key":"2023121400172694000_bib54","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1016\/j.neuroimage.2011.01.006","article-title":"A learning-based wrapper method to correct systematic errors in automatic image segmentation: Consistently improved performance in hippocampus, cortex and brain segmentation","volume":"55","author":"Wang","year":"2011","journal-title":"NeuroImage"},{"key":"2023121400172694000_bib55","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.neuroimage.2013.10.046","article-title":"Estimates of segregation and overlap of functional connectivity networks in the human cerebral cortex","volume":"88","author":"Yeo","year":"2014","journal-title":"NeuroImage"},{"issue":"2","key":"2023121400172694000_bib56","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1176\/appi.ajp.2018.17101147","article-title":"Connectome-based prediction of cocaine abstinence","volume":"176","author":"Yip","year":"2019","journal-title":"American Journal of Psychiatry"},{"issue":"6","key":"2023121400172694000_bib57","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1016\/j.bpsc.2022.08.010","article-title":"Disrupted dynamic interactions between large-scale brain networks in cocaine users are associated with dependence severity","volume":"8","author":"Zhai","year":"2022","journal-title":"Biological Psychiatry: Cognitive Neuroscience and Neuroimaging"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/1\/107\/2195555\/neco_a_01623.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/1\/107\/2195555\/neco_a_01623.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:18:02Z","timestamp":1702513082000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/36\/1\/107\/118263\/Cocaine-Use-Prediction-With-Tensor-Based-Machine"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,12]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12,12]]},"published-print":{"date-parts":[[2023,12,12]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01623","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,1]]},"published":{"date-parts":[[2023,12,12]]}}}