{"doi":"10.1093/psyrad/kkae005","title":"Transcriptomic and neuroimaging data integration enhances machine learning classification of schizophrenia","abstract":"<jats:title>Abstract</jats:title>\n               <jats:sec>\n                  <jats:title>Background</jats:title>\n                  <jats:p>Schizophrenia is a polygenic disorder associated with changes in brain structure and function. Integrating macroscale brain features with microscale genetic data may provide a more complete overview of the disease etiology and may serve as potential diagnostic markers for schizophrenia.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Objective</jats:title>\n                  <jats:p>We aim to systematically evaluate the impact of multi-scale neuroimaging and transcriptomic data fusion in schizophrenia classification models.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Methods</jats:title>\n                  <jats:p>We collected brain imaging data and blood RNA sequencing data from 43 patients with schizophrenia and 60 age- and gender-matched healthy controls, and we extracted multi-omics features of macroscale brain morphology, brain structural and functional connectivity, and gene transcription of schizophrenia risk genes. Multi-scale data fusion was performed using a machine learning integration framework, together with several conventional machine learning methods and neural networks for patient classification.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Results</jats:title>\n                  <jats:p>We found that multi-omics data fusion in conventional machine learning models achieved the highest accuracy (AUC ~0.76–0.92) in contrast to the single-modality models, with AUC improvements of 8.88 to 22.64%. Similar findings were observed for the neural network, showing an increase of 16.57% for the multimodal classification model (accuracy 71.43%) compared to the single-modal average. In addition, we identified several brain regions in the left posterior cingulate and right frontal pole that made a major contribution to disease classification.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion</jats:title>\n                  <jats:p>We provide empirical evidence for the increased accuracy achieved by imaging genetic data integration in schizophrenia classification. Multi-scale data fusion holds promise for enhancing diagnostic precision, facilitating early detection and personalizing treatment regimens in schizophrenia.</jats:p>\n               </jats:sec>","journal":"Psychoradiology","year":2024,"id":598846,"datarank":0.4636563680037475,"base_score":3.091042453358316,"endowment":3.091042453358316,"self_citation_contribution":0.4636563680037475,"citation_network_contribution":0.0,"self_endowment_contribution":0.4636563680037475,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":21,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1534732,"name":"Shu-Wan Zhao","orcid":null,"position":1,"is_corresponding":false},{"id":495234,"name":"Di Wu","orcid":"0000-0002-3238-6388","position":2,"is_corresponding":false},{"id":1534733,"name":"Ya-Hong Zhang","orcid":null,"position":3,"is_corresponding":false},{"id":1534735,"name":"Yan-Kun Han","orcid":null,"position":4,"is_corresponding":false},{"id":1489368,"name":"Kun Zhao","orcid":"0009-0007-7497-1773","position":5,"is_corresponding":false},{"id":81228,"name":"Ting Qi","orcid":"0000-0001-5868-0799","position":6,"is_corresponding":false},{"id":267096,"name":"Yong Liu","orcid":"0000-0002-1862-3121","position":7,"is_corresponding":false},{"id":1534736,"name":"Long-Biao Cui","orcid":null,"position":8,"is_corresponding":false},{"id":272063,"name":"Yongbin Wei","orcid":"0000-0002-8044-7667","position":9,"is_corresponding":false},{"id":719107,"name":"Mengya Wang","orcid":"0000-0003-0300-4245","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Transcriptomic and neuroimaging data integration enhances machine learning classification of schizophrenia","abstract":"<jats:title>Abstract</jats:title>\n               <jats:sec>\n                  <jats:title>Background</jats:title>\n                  <jats:p>Schizophrenia is a polygenic disorder associated with changes in brain structure and function. Integrating macroscale brain features with microscale genetic data may provide a more complete overview of the disease etiology and may serve as potential diagnostic markers for schizophrenia.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Objective</jats:title>\n                  <jats:p>We aim to systematically evaluate the impact of multi-scale neuroimaging and transcriptomic data fusion in schizophrenia classification models.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Methods</jats:title>\n                  <jats:p>We collected brain imaging data and blood RNA sequencing data from 43 patients with schizophrenia and 60 age- and gender-matched healthy controls, and we extracted multi-omics features of macroscale brain morphology, brain structural and functional connectivity, and gene transcription of schizophrenia risk genes. Multi-scale data fusion was performed using a machine learning integration framework, together with several conventional machine learning methods and neural networks for patient classification.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Results</jats:title>\n                  <jats:p>We found that multi-omics data fusion in conventional machine learning models achieved the highest accuracy (AUC ~0.76–0.92) in contrast to the single-modality models, with AUC improvements of 8.88 to 22.64%. Similar findings were observed for the neural network, showing an increase of 16.57% for the multimodal classification model (accuracy 71.43%) compared to the single-modal average. In addition, we identified several brain regions in the left posterior cingulate and right frontal pole that made a major contribution to disease classification.</jats:p>\n               </jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion</jats:title>\n                  <jats:p>We provide empirical evidence for the increased accuracy achieved by imaging genetic data integration in schizophrenia classification. Multi-scale data fusion holds promise for enhancing diagnostic precision, facilitating early detection and personalizing treatment regimens in schizophrenia.</jats:p>\n               </jats:sec>","is_dataset_classified":null,"base_score":0.0,"endowment":0.0,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"38694267","pmcid":null,"openalex_id":null,"authors":[],"funders":[{"funder_name":"Beijing Municipal Natural Science Foundation","grant_id":"7232341","title":null},{"funder_name":"National Natural Science Foundation of China","grant_id":"82202264","title":null},{"funder_name":"National Natural Science Foundation of China","grant_id":"82271949","title":null},{"funder_name":"Key Research and Development Program of Shaanxi Province","grant_id":"2023-YBSF-444","title":null}],"total_grants":4,"fwci":null,"citation_percentile":null,"influential_citations":0,"citation_trend":[],"oa_status":"gold","license":"cc-by-nc","oa_locations":[{"url":"https://academic.oup.com/psyrad/advance-article-pdf/doi/10.1093/psyrad/kkae005/57097953/kkae005.pdf","host_type":"publisher"},{"url":"https://academic.oup.com/psyrad/article-pdf/doi/10.1093/psyrad/kkae005/60806713/kkae005.pdf","host_type":"publisher"},{"url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11061866/pdf/kkae005.pdf","host_type":"repository"}],"fields_of_study":[],"mesh_terms":[],"keywords":["genomics","machine learning","multi-omics","schizophrenia","transcriptomics"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-07-28T16:19:15.221794Z","pmid":null,"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":[]}