{"doi":"10.1002/hbm.25574","title":"Improving the predictive potential of diffusion <scp>MRI</scp> in schizophrenia using normative models—Towards subject‐level classification","abstract":"Diffusion MRI studies consistently report group differences in white matter between individuals diagnosed with schizophrenia and healthy controls. Nevertheless, the abnormalities found at the group-level are often not observed at the individual level. Among the different approaches aiming to study white matter abnormalities at the subject level, normative modeling analysis takes a step towards subject-level predictions by identifying affected brain locations in individual subjects based on extreme deviations from a normative range. Here, we leveraged a large harmonized diffusion MRI dataset from 512 healthy controls and 601 individuals diagnosed with schizophrenia, to study whether normative modeling can improve subject-level predictions from a binary classifier. To this aim, individual deviations from a normative model of standard (fractional anisotropy) and advanced (free-water) dMRI measures, were calculated by means of age and sex-adjusted z-scores relative to control data, in 18 white matter regions. Even though larger effect sizes are found when testing for group differences in z-scores than are found with raw values (p < .001), predictions based on summary z-score measures achieved low predictive power (AUC < 0.63). Instead, we find that combining information from the different white matter tracts, while using multiple imaging measures simultaneously, improves prediction performance (the best predictor achieved AUC = 0.726). Our findings suggest that extreme deviations from a normative model are not optimal features for prediction. However, including the complete distribution of deviations across multiple imaging measures improves prediction, and could aid in subject-level classification.","journal":"Human Brain Mapping","year":2021,"id":165022,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":37,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9569,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":484800,"name":"Suheyla Cetin‐Karayumak","orcid":"0000-0002-3315-5821","position":1,"is_corresponding":false},{"id":273468,"name":"Fan Zhang","orcid":"0000-0002-5032-6039","position":2,"is_corresponding":false},{"id":243223,"name":"Kang Ik K. Cho","orcid":"0000-0001-7135-3848","position":3,"is_corresponding":false},{"id":398318,"name":"Amanda E. Lyall","orcid":"0000-0001-8049-516X","position":4,"is_corresponding":false},{"id":687753,"name":"Johanna Seitz‐Holland","orcid":"0000-0002-1815-2681","position":5,"is_corresponding":false},{"id":687754,"name":"Rami Ben‐Ari","orcid":"0000-0001-7162-7351","position":6,"is_corresponding":false},{"id":236953,"name":"Godfrey D. Pearlson","orcid":"0000-0002-7525-5185","position":7,"is_corresponding":false},{"id":314834,"name":"Carol A. Tamminga","orcid":"0000-0002-6366-5697","position":8,"is_corresponding":false},{"id":344413,"name":"John A. Sweeney","orcid":"0000-0003-1752-2828","position":9,"is_corresponding":false},{"id":322984,"name":"Brett A. Clementz","orcid":"0000-0002-2563-9594","position":10,"is_corresponding":false},{"id":355944,"name":"David J. Schretlen","orcid":"0000-0003-3992-5601","position":11,"is_corresponding":false},{"id":507488,"name":"Petra Viher","orcid":null,"position":12,"is_corresponding":false},{"id":427705,"name":"Katharina Stegmayer","orcid":"0000-0002-4611-8966","position":13,"is_corresponding":false},{"id":316463,"name":"Sebastian Walther","orcid":"0000-0003-4026-3561","position":14,"is_corresponding":false},{"id":506522,"name":"Jung Sun Lee","orcid":"0000-0003-2171-2720","position":15,"is_corresponding":false},{"id":507489,"name":"Tim Crow","orcid":null,"position":16,"is_corresponding":false},{"id":22029,"name":"Anthony James","orcid":"0000-0002-2742-8328","position":17,"is_corresponding":false},{"id":230416,"name":"Aristotle N. Voineskos","orcid":"0000-0003-0156-0395","position":18,"is_corresponding":false},{"id":507490,"name":"Robert W. Buchanan","orcid":null,"position":19,"is_corresponding":false},{"id":298356,"name":"Philip R. Szeszko","orcid":"0000-0002-6383-6142","position":20,"is_corresponding":false},{"id":37375,"name":"Anil K. Malhotra","orcid":"0000-0001-9664-4182","position":21,"is_corresponding":false},{"id":322986,"name":"Matcheri S. Keshavan","orcid":"0000-0002-5945-888X","position":22,"is_corresponding":false},{"id":274933,"name":"Martha E. Shenton","orcid":"0000-0003-4235-7879","position":23,"is_corresponding":false},{"id":273470,"name":"Yogesh Rathi","orcid":"0000-0002-9946-2314","position":24,"is_corresponding":false},{"id":432469,"name":"Sylvain Bouix","orcid":"0000-0003-1326-6054","position":25,"is_corresponding":false},{"id":687755,"name":"Nir Sochen","orcid":"0000-0001-7805-5560","position":26,"is_corresponding":false},{"id":398316,"name":"Marek Kubicki","orcid":"0000-0002-3989-8212","position":27,"is_corresponding":false},{"id":311510,"name":"Ofer Pasternak","orcid":"0000-0002-7078-6446","position":28,"is_corresponding":false},{"id":687752,"name":"Doron Elad","orcid":"0000-0002-5985-9835","position":0,"is_corresponding":true}],"reference_count":69,"raw_metadata":null,"created_at":"2026-07-18T23:45:36.425208Z","pmid":"34322947","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}