Evaluation of machine learning algorithms and structural features for optimal MRI-based diagnostic prediction in psychosis.
Por:
Salvador R, Radua J, Canales-Rodríguez EJ, Solanes A, Sarró S, Goikolea JM, Valiente A, Monté GC, Natividad MDC, Guerrero-Pedraza A, Moro N, Fernández-Corcuera P, Amann BL, Maristany M, Vieta E, McKenna PJ and Pomarol-Clotet E
Publicada:
20 abr 2017
Ahead of Print:
20 abr 2017
Resumen:
A relatively large number of studies have investigated the power of structural magnetic resonance imaging (sMRI) data to discriminate patients with schizophrenia from healthy controls. However, very few of them have also included patients with bipolar disorder, allowing the clinically relevant discrimination between both psychotic diagnostics. To assess the efficacy of sMRI data for diagnostic prediction in psychosis we objectively evaluated the discriminative power of a wide range of commonly used machine learning algorithms (ridge, lasso, elastic net and L0 norm regularized logistic regressions, a support vector classifier, regularized discriminant analysis, random forests and a Gaussian process classifier) on main sMRI features including grey and white matter voxel-based morphometry (VBM), vertex-based cortical thickness and volume, region of interest volumetric measures and wavelet-based morphometry (WBM) maps. All possible combinations of algorithms and data features were considered in pairwise classifications of matched samples of healthy controls (N = 127), patients with schizophrenia (N = 128) and patients with bipolar disorder (N = 128). Results show that the selection of feature type is important, with grey matter VBM (without data reduction) delivering the best diagnostic prediction rates (averaging over classifiers: schizophrenia vs. healthy 75%, bipolar disorder vs. healthy 63% and schizophrenia vs. bipolar disorder 62%) whereas algorithms usually yielded very similar results. Indeed, those grey matter VBM accuracy rates were not even improved by combining all feature types in a single prediction model. Further multi-class classifications considering the three groups simultaneously made evident a lack of predictive power for the bipolar group, probably due to its intermediate anatomical features, located between those observed in healthy controls and those found in patients with schizophrenia. Finally, we provide MRIPredict (https://www.nitrc.org/projects/mripredict/), a free tool for SPM, FSL and R, to easily carry out voxelwise predictions based on VBM images.
Filiaciones:
Salvador R:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Radua J:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Institute of Psychiatry, Psychology and Neuroscience, King's College, London, United Kingdom
Center for Psychiatry Research, Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
Canales-Rodríguez EJ:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Solanes A:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
University of Barcelona, Barcelona, Spain
Sarró S:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Goikolea JM:
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Hospital Clínic, University of Barcelona, IDIBAPS, Barcelona, Spain
Valiente A:
Hospital Benito Menni - CASM, Sant Boi de Llobregat, Spain
Monté GC:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Hospital Clínic, University of Barcelona, IDIBAPS, Barcelona, Spain
Natividad MDC:
Hospital Mare de Déu de la Mercè, Barcelona, Spain
Guerrero-Pedraza A:
Hospital Benito Menni - CASM, Sant Boi de Llobregat, Spain
Moro N:
Hospital Benito Menni - CASM, Sant Boi de Llobregat, Spain
Fernández-Corcuera P:
Hospital Benito Menni - CASM, Sant Boi de Llobregat, Spain
Amann BL:
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Institut de Neuropsiquiatria i Addiccions, Centre Fòrum Research Unit, Parc de Salut Mar, Barcelona, Spain
IMIM (Hospital del Mar Medical Research Institute), Barcelona, Spain
Department of Psychiatry, Autonomous University of Barcelona, Barcelona, Spain
Maristany M:
Hospital Sant Joan de Déu, Esplugues de Llobregat, Spain
Vieta E:
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Hospital Clínic, University of Barcelona, IDIBAPS, Barcelona, Spain
McKenna PJ:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
Pomarol-Clotet E:
FIDMAG - Germanes Hospitalaries, Barcelona, Spain
Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Barcelona, Spain
|