Produção Nacional
Revisado por pares
Multiple Holdouts With Stability: Improving the Generalizability of Machine Learning Analyses of Brain–Behavior Relationships
2019; Elsevier BV; Volume: 87; Issue: 4 Linguagem: Inglês
10.1016/j.biopsych.2019.12.001
ISSN1873-2402
AutoresÁgoston Mihalik, Fábio S. Ferreira, Michael Moutoussis, Gabriel Ziegler, Rick A. Adams, Maria João Rosa, Gita Prabhu, Letícia Oliveira, Mirtes Garcia Pereira, Edward T. Bullmore, Peter Fonagy, Ian M. Goodyer, Peter B. Jones, John Shawe‐Taylor, Raymond J. Dolan, Janaı́na Mourão-Miranda, Tobias U. Hauser, Sharon Neufeld, Rafael Romero-García, Michelle St Clair, Petra E. Vértes, Kirstie Whitaker, Becky Inkster, Cinly Ooi, Umar Toseeb, Barry Widmer, Junaid Bhatti, Laura Villis, Ayesha Alrumaithi, Sarah Birt, Aislinn Bowler, Kalia Cleridou, Hina Dadabhoy, Emma Davies, Ashlyn Firkins, Sian Granville, Elizabeth Harding, Alexandra Hopkins, Daniel Isaacs, Janchai King, Danae Kokorikou, Christina Maurice, Cleo McIntosh, Jessica Memarzia, Harriet L. Mills, Ciara O’Donnell, Sara Pantaleone, Jenny Scott, Pasco Fearon, John Suckling, Anne‐Laura van Harmelen, Rogier Kievit,
Tópico(s)Functional Brain Connectivity Studies
ResumoIn 2009, the National Institute of Mental Health launched the Research Domain Criteria, an attempt to move beyond diagnostic categories and ground psychiatry within neurobiological constructs that combine different levels of measures (e.g., brain imaging and behavior). Statistical methods that can integrate such multimodal data, however, are often vulnerable to overfitting, poor generalization, and difficulties in interpreting the results.We propose an innovative machine learning framework combining multiple holdouts and a stability criterion with regularized multivariate techniques, such as sparse partial least squares and kernel canonical correlation analysis, for identifying hidden dimensions of cross-modality relationships. To illustrate the approach, we investigated structural brain-behavior associations in an extensively phenotyped developmental sample of 345 participants (312 healthy and 33 with clinical depression). The brain data consisted of whole-brain voxel-based gray matter volumes, and the behavioral data included item-level self-report questionnaires and IQ and demographic measures.Both sparse partial least squares and kernel canonical correlation analysis captured two hidden dimensions of brain-behavior relationships: one related to age and drinking and the other one related to depression. The applied machine learning framework indicates that these results are stable and generalize well to new data. Indeed, the identified brain-behavior associations are in agreement with previous findings in the literature concerning age, alcohol use, and depression-related changes in brain volume.Multivariate techniques (such as sparse partial least squares and kernel canonical correlation analysis) embedded in our novel framework are promising tools to link behavior and/or symptoms to neurobiology and thus have great potential to contribute to a biologically grounded definition of psychiatric disorders.
Referência(s)