Machine learning algorithms on eye tracking trajectories to classify patients with spatial neglect.

Autor: Franceschiello B; The LINE (Laboratory for Investigative Neurophysiology), Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.; CIBM Center for Biomedical Imaging, Lausanne, Switzerland; Department of Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland; The Sense Innovation and Research Center, Lausanne and Sion, Switzerland; School of Engineering, Institute of Systems Engineering, HES-SO Valais-Wallis, Route de L'industrie 23, Sion, Switzerland., Noto TD; Department of Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland., Bourgeois A; Laboratory of Cognitive Neurorehabilitation, Faculty of Medicine, University of Geneva, Geneva, Switzerland., Murray MM; The LINE (Laboratory for Investigative Neurophysiology), Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.; Department of Ophthalmology, Fondation Asile des Aveugles and University of Lausanne, Lausanne, Switzerland; CIBM Center for Biomedical Imaging, Lausanne, Switzerland; Department of Hearing and Speech Sciences, Vanderbilt University, Nashville, TN, USA; The Sense Innovation and Research Center, Lausanne and Sion, Switzerland., Minier A; The LINE (Laboratory for Investigative Neurophysiology), Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.; Department of Ophthalmology, Fondation Asile des Aveugles and University of Lausanne, Lausanne, Switzerland., Pouget P; Laboratory of Cognitive Neurorehabilitation, Faculty of Medicine, University of Geneva, Geneva, Switzerland., Richiardi J; Department of Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland; The Sense Innovation and Research Center, Lausanne and Sion, Switzerland., Bartolomeo P; Sorbonne Universite, Inserm, CNRS, Institut du Cerveau - Paris Brain Institute, ICM, Hopital de la Pitie-Salpetriere, Paris, France., Anselmi F; Center for Neuroscience and Artificial Intelligence, Department of Neuroscience, Baylor College of Medicine, Houston, TX, USA; Center for Brains, Minds, and Machines, McGovern Institute for Brain Research at MIT, Cambridge, MA, USA. Electronic address: fabio.anselmi@bcm.edu.
Jazyk: angličtina
Zdroj: Computer methods and programs in biomedicine [Comput Methods Programs Biomed] 2022 Jun; Vol. 221, pp. 106929. Date of Electronic Publication: 2022 Jun 01.
DOI: 10.1016/j.cmpb.2022.106929
Abstrakt: Background and Objective: Eye-movement trajectories are rich behavioral data, providing a window on how the brain processes information. We address the challenge of characterizing signs of visuo-spatial neglect from saccadic eye trajectories recorded in brain-damaged patients with spatial neglect as well as in healthy controls during a visual search task.
Methods: We establish a standardized pre-processing pipeline adaptable to other task-based eye-tracker measurements. We use traditional machine learning algorithms together with deep convolutional networks (both 1D and 2D) to automatically analyze eye trajectories.
Results: Our top-performing machine learning models classified neglect patients vs. healthy individuals with an Area Under the ROC curve (AUC) ranging from 0.83 to 0.86. Moreover, the 1D convolutional neural network scores correlated with the degree of severity of neglect behavior as estimated with standardized paper-and-pencil tests and with the integrity of white matter tracts measured from Diffusion Tensor Imaging (DTI). Interestingly, the latter showed a clear correlation with the third branch of the superior longitudinal fasciculus (SLF), especially damaged in neglect.
Conclusions: The study introduces new methods for both the pre-processing and the classification of eye-movement trajectories in patients with neglect syndrome. The proposed methods can likely be applied to other types of neurological diseases opening the possibility of new computer-aided, precise, sensitive and non-invasive diagnostic tools.
Competing Interests: Declaration of Competing Interest The authors certify that they have no financial and personal relationships with other people or organisations that could inappropriately influence the present work. Manuscript title: “Machine learning algorithms on eye tracking trajectories to classify patients with spatial neglect” The authors (Benedetta Franceschiello, Tommaso Di Noto, Alexia Bourgeois, Micah M. Murray, Astrid Minier, Pierre Pouget, Jonas Richiardi, Paolo Bartolomeo, Fabio Anselmi) certify that they have no financial and personal relationships with other people or organisations that could inappropriately influence the present work.
(Copyright © 2022 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: