biostudies-literatureDeng LRBLRD VANIDCR NIH HHSNIBIB NIH HHSNICHD NIH HHSNCATS NIH HHSNCRR NIH HHSNIDA NIH HHSNIMH NIH HHSNational Institutes of Health Office of the DirectorNational Institutes of HealthUS Department of Veterans AffairsNLM NIH HHSNINDS NIH HHSRoy J. Carver Charitable TrustNCI NIH HHSNational Institute of Mental HealthNational Institute on Drug AbuseNIH HHS448-460https://www.ebi.ac.uk/biostudies/studies/S-EPMC11560692biostudies-literatureUnknown368<h4>Background</h4>Bipolar disorder (BD) is a chronic psychiatric mood disorder that is solely diagnosed based on clinical symptoms. These symptoms often overlap with other psychiatric disorders. Efforts to use machine learning (ML) to create predictive models for BD based on data from brain imaging are expanding but have often been limited using only a single modality and the exclusion of the cerebellum, which may be relevant in BD.<h4>Methods</h4>In this study, we sought to improve ML classification of BD by combining information from structural, functional, and diffusion-weighted imaging. Participants (108 BD I, 78 control) with BD type I and matched controls were recruited into an imaging study. This dataset was randomly divided into training and testing sets. For each of the three modJournal of affective disordersMachine learning with multiple modalities of brain magnetic resonance imaging data to identify the presence of bipolar disorder.PMC11560692R01 DA052953UM1 TR004403RL1MH083268RL1MH083269RL1 DA024853R01MH125838PL1 NS062410UL1 TR002537IO1BX004440R01 EB031169R01MH111578T32 MH019113I01 BX004440P30 CA086862S10OD025025RL1 MH083270P50HD103556RL1LM009833S10RR028821RL1 LM009833S10 OD030220R01 MH125838KL2TR002537R01 MH111578RL1MH083270UL1 DE019580PL1 MH083271T32MH019113RL1 MH083268R01DA052953RL1DA024853P50 HD103556RL1 MH083269UL1DE019580PL1NS062410S10 RR028821S10 OD025025UM1TR004403PL1MH083271Magnotta VAWilliams AJBarsotti EJFiedorowicz JGRivera-Dompenciel AMRichards JGSathyaputri LXu JDeng LRMani MAbdolmotalleby HSaleem AWemmie JAChristensen GEVoss MWShaffer JJHarmata GISfalseMachine learning with multiple modalities of brain magnetic resonance imaging data to identify the presence of bipolar disorder.<h4>Background</h4>Bipolar disorder (BD) is a chronic psychiatric mood disorder that is solely diagnosed based on clinical symptoms. These symptoms often overlap with other psychiatric disorders. Efforts to use machine learning (ML) to create predictive models for BD based on data from brain imaging are expanding but have often been limited using only a single modality and the exclusion of the cerebellum, which may be relevant in BD.<h4>Methods</h4>In this study, we sought to improve ML classification of BD by combining information from structural, functional, and diffusion-weighted imaging. Participants (108 BD I, 78 control) with BD type I and matched controls were recruited into an imaging study. This dataset was randomly divided into training and testing sets. For each of the three mod2025-01-01T00:00:00Z2025 Jan2026-06-06T17:27:47.551Z2026-06-03T03:10:37.803ZS-EPMC115606923927846910.1016/j.jad.2024.09.025