A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data
Source abstract
Abstract
In this paper, we propose a novel Machine Learning Model based on Bayesian Linear Regression intended to deal with the low sample-to-variable ratio typically found in neuroimaging studies and focusing on mental disorders. The proposed model combines feature selection capabilities with a formulation in the dual space which, in turn, enables efficient work with neuroimaging data. Thus, we have tested the proposed algorithm with real MRI data from an animal model of schizophrenia. The results show that our proposal efficiently predicts the diagnosis and, at the same time, detects regions which clearly match brain areas well-known to be related to schizophrenia.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gaussian Processes and Bayesian Inference · Functional Brain Connectivity Studies · Bayesian Methods and Mixture Models
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Signal Processing and Communications, University Carlos III of Madrid Leganés, 28911 Leganés, Spain
Department of Bioengineering and Aerospace Engineering, University Carlos III of Madrid Leganés, 28911 Leganés, Spain
CIBER of Mental Health (CIBERSAM), 28029 Madrid, Spain
Instituto de Investigación Sanitaria Gregorio Marañón, 28007 Madrid, Spain
Centro Nacional de Investigaciones Cardiovasculares (CNIC), 28029 Madrid, Spain
Funding
Spanish MINECO (Agencia Estatal de Investigación) · Community of Madrid through the "Excellence of University Teaching Staff" line of the Multi-year Agreement with UC3M (EPUC3M27), within the framework of the V PRICIT · Ministerio de Ciencia, Innovación y Universidades, Instituto de Salud Carlos III · Delegación del Gobierno para el Plan Nacional sobre Drogas · Fundación Mapfre · Fundación Alicia Koplowitz · Ministerio de Ciencia e Innovación (MCIN) and Insituto de Salud Carlos III (ISCIII) · The CNIC is supported by the ISCIII, the MCIN and the Pro CNIC Foundation, and is a Severo Ochoa Center of Excellence (SEV-2015-0505).
References (52)
Show source-provided references
1. Evidence-based umbrella review of 162 peripheral biomarkers for major mental disorders10.1038/s41398-020-0835-5 ↗
2. Symptom Profiles in Psychotic Disorder Not Otherwise Specified10.3389/fpsyt.2020.580444 ↗
3. Correll, C.U., Brevig, T., and Brain, C. (2019). Patient characteristics, burden and pharmacotherapy of treatment-resistant schizophrenia: Results from a survey of 204 US psychiatrists. BMC Psychiatry, 19.10.1186/s12888-019-2318-x ↗
4. New tests, new tools: Mobile and connected technologies in advancing psychiatric diagnosis10.1038/s41746-017-0006-0 ↗
5. Deep learning based automatic diagnosis of first-episode psychosis, bipolar disorder and healthy controls10.1016/j.compmedimag.2021.101882 ↗
6. Machine learning in schizophrenia genomics, a case-control study using 5090 exomes10.1002/ajmg.b.32638 ↗
7. Classification of suicide attempters in schizophrenia using sociocultural and clinical features: A machine learning approach10.1016/j.genhosppsych.2017.03.001 ↗
8. Support vector machine-based classification of first episode drug-naïve schizophrenia patients and healthy controls using structural MRI10.1016/j.schres.2017.11.037 ↗
9. Guo, Y., Qiu, J., and Lu, W. (2020). Support Vector Machine-Based Schizophrenia Classification Using Morphological Information from Amygdaloid and Hippocampal Subregions. Brain Sci., 10.10.3390/brainsci10080562 ↗
10. Automated detection of schizophrenia using nonlinear signal processing methods10.1016/j.artmed.2019.07.006 ↗
11. Brownlee, J. (2020, May 25). Recursive Feature Elimination (RFE) for Feature Selection in Python. Machine Learning Mastery. Available online: https://machinelearningmastery.com/rfe-feature-selection-in-python/.
12. Random forests10.1023/A:1010933404324 ↗
13. Building auto-encoder intrusion detection system based on random forest feature selection10.1016/j.cose.2020.101851 ↗
14. Regularization and variable selection via the elastic net10.1111/j.1467-9868.2005.00503.x ↗
15. A two-layer feature selection method using genetic algorithm and elastic net10.1016/j.eswa.2020.114072 ↗
16. Shen, L., Qi, Y., Kim, S., Nho, K., Wan, J., Risacher, S.L., and Saykin, A.J. (2010, January 20–24). Sparse bayesian learning for identifying imaging biomarkers in AD prediction. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Beijing, China.10.1007/978-3-642-15711-0_76 ↗
17. The relevance voxel machine (RVoxM): A self-tuning Bayesian model for informative image-based prediction10.1109/TMI.2012.2216543 ↗
18. Sabuncu, M.R. (2015, January 5–9). A sparse Bayesian learning algorithm for longitudinal image data. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_49 ↗
19. Discovering brain regions relevant to obsessive–compulsive disorder identification through bagging and transduction10.1016/j.media.2014.01.006 ↗
20. Sign-consistency based variable importance for machine learning in brain imaging10.1007/s12021-019-9415-3 ↗
21. Regularized Bagged Canonical Component Analysis for Multiclass Learning in Brain Imaging10.1007/s12021-020-09470-y ↗
22. Acute ketamine challenge increases resting state prefrontal-hippocampal connectivity in both humans and rats10.1007/s00213-015-4022-y ↗
23. Using a maternal immune stimulation model of schizophrenia to study behavioral and neurobiological alterations over the developmental course10.1016/j.schres.2015.05.010 ↗
24. A Characterization of the Effects of Minocycline Treatment During Adolescence on Structural, Metabolic, and Oxidative Stress Parameters in a Maternal Immune Stimulation Model of Neurodevelopmental Brain Disorders10.1093/ijnp/pyab036 ↗
25. Immune activation during pregnancy in mice leads to dopaminergic hyperfunction and cognitive impairment in the offspring: A neurodevelopmental animal model of schizophrenia10.1016/j.biopsych.2005.07.031 ↗
26. Minocycline alleviates behavioral deficits and inhibits microglial activation in the offspring of pregnant mice after administration of polyriboinosinic–polyribocytidilic acid10.1016/j.psychres.2014.06.046 ↗
27. To poly (I: C) or not to poly (I: C): Advancing preclinical schizophrenia research through the use of prenatal immune activation models10.1016/j.neuropharm.2011.01.009 ↗
28. Risperidone administered during adolescence induced metabolic, anatomical and inflammatory/oxidative changes in adult brain: A pet and mri study in the maternal immune stimulation animal model10.1016/j.euroneuro.2019.05.002 ↗
29. An in vivo MRI template set for morphometry, tissue segmentation, and fMRI localization in rats
30. Bishop, C.M. (1999). Bayesian PCA. Advances in Neural Information Processing Systems, The MIT Press.
31. Bayesian canonical correlation analysis
32. Pattern recognition
33. Schölkopf, B., Herbrich, R., and Smola, A.J. (2001, January 16–19). A generalized representer theorem. Proceedings of the International Conference on Computational Learning Theory, Amsterdam, The Netherlands.10.1007/3-540-44581-1_27 ↗
34. Variational Inference: A Review for Statisticians10.1080/01621459.2017.1285773 ↗
35. Rasmussen, C.E. (2003). Gaussian processes in machine learning. Summer School on Machine Learning, Springer.10.1007/978-3-540-28650-9_4 ↗
36. Steinwart, I., and Christmann, A. (2008). Support Vector Machines, Springer Science & Business Media.
37. Scikit-learn: Machine Learning in Python
38. Sparse semi-supervised heterogeneous interbattery bayesian analysis10.1016/j.patcog.2021.108141 ↗
39. Sevilla-Salcedo, C., Guerrero-López, A., Olmos, P.M., and Gómez-Verdejo, V. (2020). Bayesian Sparse Factor Analysis with Kernelized Observations. arXiv.
40. Morphometric analysis of lateral ventricles in schizophrenia and healthy controls regarding genetic and disease-specific factors10.1073/pnas.0501117102 ↗
41. Rapado-Castro, M., Villar-Arenzana, M., Janssen, J., Fraguas, D., Bombin, I., Castro-Fornieles, J., Mayoral, M., González-Pinto, A., de la Serna, E., and Parellada, M. (2021). Fronto-Parietal Gray Matter Volume Loss Is Associated with Decreased Working Memory Performance in Adolescents with a First Episode of Psychosis. J. Clin. Med., 10.10.3390/jcm10173929 ↗
42. Abnormality of subcortical volume and resting functional connectivity in adolescents with early-onset and prodromal schizophrenia10.1016/j.jpsychires.2021.05.052 ↗
43. Brain-wide functional inter-hemispheric disconnection is a potential biomarker for schizophrenia and distinguishes it from depression10.1016/j.nicl.2013.06.008 ↗
44. Schizophrenia, brain asymmetry development, and twinning: Cellular relationship with etiological and possibly prognostic implications
45. Omega-3 fatty acids during adolescence prevent schizophrenia-related behavioural deficits: Neurophysiological evidences from the prenatal viral infection with PolyI: C10.1016/j.euroneuro.2021.02.001 ↗
46. Medial septum activation produces opposite effects on dopamine neuron activity in the ventral tegmental area and substantia nigra in MAM vs. normal rats10.1038/s41537-018-0059-3 ↗
47. The medial septum as a potential target for treating brain disorders associated with oscillopathies10.3389/fncir.2021.701080 ↗
48. Dorsal hippocampus drives context-induced cocaine seeking via inputs to lateral septum10.1038/npp.2017.144 ↗
49. Lateral septum inhibition reduces motivation for cocaine: Reversal by diazepam10.1111/adb.12742 ↗
50. Vasopressin in the lateral septum decreases conditioned place preference to amphetamine and nucleus accumbens dopamine release10.1111/adb.12851 ↗
51. Cognitive deficits and white matter abnormalities in never-treated first-episode schizophrenia10.1038/s41398-020-01049-0 ↗
52. Impaired cerebro-cerebellar white matter connectivity and its associations with cognitive function in patients with schizophrenia10.1038/s41537-021-00169-w ↗