Dataset Information

Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group.

ABSTRACT: Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI?=?63.47-67.00, ROC-AUC?=?71.49%, 95% CI?=?69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI?=?56.70-60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen's Kappa?=?0.83, 95% CI?=?0.829-0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.

SUBMITTER: Nunes A

PROVIDER: S-EPMC7473838 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group.

Nunes Abraham A Schnack Hugo G HG Ching Christopher R K CRK Agartz Ingrid I Akudjedu Theophilus N TN Alda Martin M Alnæs Dag D Alonso-Lana Silvia S Bauer Jochen J Baune Bernhard T BT Bøen Erlend E Bonnin Caterina Del Mar CDM Busatto Geraldo F GF Canales-Rodríguez Erick J EJ Cannon Dara M DM Caseras Xavier X Chaim-Avancini Tiffany M TM Dannlowski Udo U Díaz-Zuluaga Ana M AM Dietsche Bruno B Doan Nhat Trung NT Duchesnay Edouard E Elvsåshagen Torbjørn T Emden Daniel D Eyler Lisa T LT Fatjó-Vilas Mar M Favre Pauline P Foley Sonya F SF Fullerton Janice M JM Glahn David C DC Goikolea Jose M JM Grotegerd Dominik D Hahn Tim T Henry Chantal C Hibar Derrek P DP Houenou Josselin J Howells Fleur M FM Jahanshad Neda N Kaufmann Tobias T Kenney Joanne J Kircher Tilo T J TTJ Krug Axel A Lagerberg Trine V TV Lenroot Rhoshel K RK López-Jaramillo Carlos C Machado-Vieira Rodrigo R Malt Ulrik F UF McDonald Colm C Mitchell Philip B PB Mwangi Benson B Nabulsi Leila L Opel Nils N Overs Bronwyn J BJ Pineda-Zapata Julian A JA Pomarol-Clotet Edith E Redlich Ronny R Roberts Gloria G Rosa Pedro G PG Salvador Raymond R Satterthwaite Theodore D TD Soares Jair C JC Stein Dan J DJ Temmingh Henk S HS Trappenberg Thomas T Uhlmann Anne A van Haren Neeltje E M NEM Vieta Eduard E Westlye Lars T LT Wolf Daniel H DH Yüksel Dilara D Zanetti Marcus V MV Andreassen Ole A OA Thompson Paul M PM Hajek Tomas T

Molecular psychiatry 20180831 9

Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, su ...[more]

PMID: 30171211

Similar Datasets

Project description:ObjectiveNeuroimaging studies show structural differences in both cortical and subcortical brain regions in children and adults with autism spectrum disorder (ASD) compared with healthy subjects. Findings are inconsistent, however, and it is unclear how differences develop across the lifespan. The authors investigated brain morphometry differences between individuals with ASD and healthy subjects, cross-sectionally across the lifespan, in a large multinational sample from the Enhancing Neuroimaging Genetics Through Meta-Analysis (ENIGMA) ASD working group.MethodThe sample comprised 1,571 patients with ASD and 1,651 healthy control subjects (age range, 2-64 years) from 49 participating sites. MRI scans were preprocessed at individual sites with a harmonized protocol based on a validated automated-segmentation software program. Mega-analyses were used to test for case-control differences in subcortical volumes, cortical thickness, and surface area. Development of brain morphometry over the lifespan was modeled using a fractional polynomial approach.ResultsThe case-control mega-analysis demonstrated that ASD was associated with smaller subcortical volumes of the pallidum, putamen, amygdala, and nucleus accumbens (effect sizes [Cohen's d], 0.13 to -0.13), as well as increased cortical thickness in the frontal cortex and decreased thickness in the temporal cortex (effect sizes, -0.21 to 0.20). Analyses of age effects indicate that the development of cortical thickness is altered in ASD, with the largest differences occurring around adolescence. No age-by-ASD interactions were observed in the subcortical partitions.ConclusionsThe ENIGMA ASD working group provides the largest study of brain morphometry differences in ASD to date, using a well-established, validated, publicly available analysis pipeline. ASD patients showed altered morphometry in the cognitive and affective parts of the striatum, frontal cortex, and temporal cortex. Complex developmental trajectories were observed for the different regions, with a developmental peak around adolescence. These findings suggest an interplay in the abnormal development of the striatal, frontal, and temporal regions in ASD across the lifespan.

Dataset Information

Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group.

Publications

Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets