2024
Data leakage inflates prediction performance in connectome-based machine learning models
Rosenblatt M, Tejavibulya L, Jiang R, Noble S, Scheinost D. Data leakage inflates prediction performance in connectome-based machine learning models. Nature Communications 2024, 15: 1829. PMID: 38418819, PMCID: PMC10901797, DOI: 10.1038/s41467-024-46150-w.Peer-Reviewed Original Research
2022
Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer
Scheinost D, Pollatou A, Dufford A, Jiang R, Farruggia M, Rosenblatt M, Peterson H, Rodriguez R, Dadashkarimi J, Liang Q, Dai W, Foster M, Camp C, Tejavibulya L, Adkinson B, Sun H, Ye J, Cheng Q, Spann M, Rolison M, Noble S, Westwater M. Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer. Biological Psychiatry 2022, 93: 893-904. PMID: 36759257, PMCID: PMC10259670, DOI: 10.1016/j.biopsych.2022.10.014.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsPredicting the future of neuroimaging predictive models in mental health
Tejavibulya L, Rolison M, Gao S, Liang Q, Peterson H, Dadashkarimi J, Farruggia MC, Hahn CA, Noble S, Lichenstein SD, Pollatou A, Dufford AJ, Scheinost D. Predicting the future of neuroimaging predictive models in mental health. Molecular Psychiatry 2022, 27: 3129-3137. PMID: 35697759, PMCID: PMC9708554, DOI: 10.1038/s41380-022-01635-2.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus Statements
2019
Toward Addiction Prediction: An Overview of Cross-Validated Predictive Modeling Findings and Considerations for Future Neuroimaging Research
Yip SW, Kiluk B, Scheinost D. Toward Addiction Prediction: An Overview of Cross-Validated Predictive Modeling Findings and Considerations for Future Neuroimaging Research. Biological Psychiatry Cognitive Neuroscience And Neuroimaging 2019, 5: 748-758. PMID: 31932230, PMCID: PMC8274215, DOI: 10.1016/j.bpsc.2019.11.001.Peer-Reviewed Original ResearchConceptsIndividual differencesBrain-behavior modelsFuture neuroimaging researchLikelihood of replicationEvidence-based treatmentsNeuroimaging researchEffect size estimatesSubstance useDirection of associationAnatomical locusBrain functionTreatment outcomesModeling findingsClinical samplesNovel subjectRelapse rateClinical outcomesPredictive modeling approachUnsuccessful treatmentLeading causeIndividualsClinical settingParticular riskSize estimatesOutcomesAn information network flow approach for measuring functional connectivity and predicting behavior
Kumar S, Yoo K, Rosenberg MD, Scheinost D, Constable RT, Zhang S, Li C, Chun MM. An information network flow approach for measuring functional connectivity and predicting behavior. Brain And Behavior 2019, 9: e01346. PMID: 31286688, PMCID: PMC6710195, DOI: 10.1002/brb3.1346.Peer-Reviewed Original ResearchConceptsFunctional brain connectivityFunctional magnetic resonance imagingFMRI time coursesIndividual differencesTask performanceMeasures of attentionSustained attention taskAttention task performanceResting-state fMRI dataSample of individualsAttention taskFMRI dataFunctional connectivityFC patternsBrain connectivityPearson correlationInformation theory statisticsInformation flowMachine-learning modelsMeasuresMagnetic resonance imagingAttentionNetwork flow approachTime courseDifferent datasetsTen simple rules for predictive modeling of individual differences in neuroimaging
Scheinost D, Noble S, Horien C, Greene AS, Lake EM, Salehi M, Gao S, Shen X, O’Connor D, Barron DS, Yip SW, Rosenberg MD, Constable RT. Ten simple rules for predictive modeling of individual differences in neuroimaging. NeuroImage 2019, 193: 35-45. PMID: 30831310, PMCID: PMC6521850, DOI: 10.1016/j.neuroimage.2019.02.057.Peer-Reviewed Original ResearchMeSH KeywordsBrainConnectomeHumansMachine LearningMagnetic Resonance ImagingModels, NeurologicalNeuroimagingConceptsBrain-behavior associationsConnectome-Based Prediction of Cocaine Abstinence
Yip SW, Scheinost D, Potenza MN, Carroll KM. Connectome-Based Prediction of Cocaine Abstinence. American Journal Of Psychiatry 2019, 176: 156-164. PMID: 30606049, PMCID: PMC6481181, DOI: 10.1176/appi.ajp.2018.17101147.Peer-Reviewed Original ResearchMeSH KeywordsAdultBehavior TherapyBrainCholinesterase InhibitorsCocaine-Related DisordersCognitionConnectomeExecutive FunctionFemaleFunctional NeuroimagingGalantamineHumansIndividualityMachine LearningMagnetic Resonance ImagingMaleMiddle AgedNeural PathwaysOpiate Substitution TreatmentOpioid-Related DisordersPrognosisRewardTreatment OutcomeConceptsConnectome-based predictive modelingCocaine use disorderUse disordersBrain-based predictorsLarge-scale neural networksFunctional MRI dataCocaine abstinenceExecutive controlReward responsivenessIndividual differencesBaseline cocaine usePosttreatment assessmentConnectivity strengthHeterogeneous sampleAbstinenceIndependent samplesNovel interventionsCanonical networksSpecific behaviorsCocaine useSignificant correspondenceDisordersTreatment outcomesNetwork strengthMRI data