Machine learning algorithms on eye tracking trajectories to classify patients with spatial neglect. (June 2022)

• Record Type: Journal Article
• Authors: Franceschiello, Benedetta; Noto, Tommaso Di; Bourgeois, Alexia; Murray, Micah M.; Minier, Astrid; Pouget, Pierre; Richiardi, Jonas; Bartolomeo, Paolo; Anselmi, Fabio
• Is Part Of: Computer methods and programs in biomedicine. Volume 221(2022)
• Publication Date: 2022-06
• Subjects: Neglect -- Bio-markers -- Eye-tracking -- Machine learning -- Deep networks -- Structural lesion -- Diffusion tensor imaging; 0000 -- 1111; 0000 -- 1111; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106929
• Languages: English
• ISSNs: 0169-2607

Abstract

Abstract : We identify signs of visuo-spatial neglect through an automated analysis of saccadic eye trajectories using a series of machine learning classifiers. We provide a standardized pre-processing pipeline adaptable to other task-based eye-tracker measurements. Patient-wise, we benchmark the predictions form a 1D convolutional neural network with standardized paper-and-pencil test results. We evaluate white matter tracts by using Diffusion Tensor Imaging (DTI) and find a clear correlation with the microstructure of the third branch of the superior longitudinal fasciculus. Machine learning methods can efficiently and non-invasively characterize left spatial neglect. Abstract: 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.