Challenging functional connectivity data: machine learning application on essential tremor recognition.

Autor: Saccà V; Department of Medical and Surgical Sciences, University Magna Graecia, Catanzaro, Italy.; Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA., Novellino F; Department of Pharmacology and Toxicology, School of Medicine, Universidad Complutense de Madrid (UCM), Av. Complutense s/n, 28040, Madrid, Spain. fabiana.novellino@cnr.it.; Instituto de Investigación Neuroquímica (IUINQ-UCM), Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Instituto de Investigación Sanitaria Hospital, 12 de Octubre (Imas12), Madrid, Spain. fabiana.novellino@cnr.it.; Institute of Bioimaging and Molecular Physiology (IBFM), National Research Council, Catanzaro, Italy. fabiana.novellino@cnr.it., Salsone M; Institute of Molecular Bioimaging and Physiology, National Research Council, Milan, Italy.; Sleep Disorders Center, Division of Neuroscience, San Raffaele Scientific Institute, Milan, Italy., Abou Jaoude M; Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA., Quattrone A; Institute of Neurology, University Magna Graecia, Catanzaro, Italy.; Department of Clinical and Movement Neurosciences, UCL Queen Square Institute of Neurology, University College London, London, UK., Chiriaco C; Institute of Neurology, University Magna Graecia, Catanzaro, Italy., Madrigal JLM; Department of Pharmacology and Toxicology, School of Medicine, Universidad Complutense de Madrid (UCM), Av. Complutense s/n, 28040, Madrid, Spain.; Instituto de Investigación Neuroquímica (IUINQ-UCM), Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Instituto de Investigación Sanitaria Hospital, 12 de Octubre (Imas12), Madrid, Spain., Quattrone A; Institute of Bioimaging and Molecular Physiology (IBFM), National Research Council, Catanzaro, Italy. quattrone@unicz.it.; Neuroscience Research Center, Magna Graecia University, Catanzaro, Italy. quattrone@unicz.it.
Jazyk: angličtina
Zdroj: Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology [Neurol Sci] 2023 Jan; Vol. 44 (1), pp. 199-207. Date of Electronic Publication: 2022 Sep 20.
DOI: 10.1007/s10072-022-06400-5
Abstrakt: Background and Aims: This paper aimed to investigate the usefulness of applying machine learning on resting-state fMRI connectivity data to recognize the pattern of functional changes in essential tremor (ET), a disease characterized by slight brain abnormalities, often difficult to detect using univariate analysis.
Methods: We trained a support vector machine with a radial kernel on the mean signals extracted by 14 brain networks obtained from resting-state fMRI scans of 18 ET and 19 healthy control (CTRL) subjects. Classification performance between pathological and control subjects was evaluated using a tenfold cross-validation. Recursive feature elimination was performed to rank the importance of the extracted features. Moreover, univariate analysis using Mann-Whitney U test was also performed.
Results: The machine learning algorithm achieved an AUC of 0.75, with four networks (language, primary visual, cerebellum, and attention), which have an essential role in ET pathophysiology, being selected as the most important features for classification. By contrast, the univariate analysis was not able to find significant results among these two conditions.
Conclusion: The machine learning approach identifies the changes in functional connectivity of ET patients, representing a promising instrument to discriminate specific pathological conditions and find novel functional biomarkers in resting-state fMRI studies.
(© 2022. Fondazione Società Italiana di Neurologia.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje