Detecting cognitive impairment by eye movement analysis using automatic classification algorithms

• Published in: Journal of neuroscience methods Vol. 201; no. 1; pp. 196 - 203
• Main Authors: Lagun, Dmitry, Manzanares, Cecelia, Zola, Stuart M., Buffalo, Elizabeth A., Agichtein, Eugene
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 30.09.2011
• Subjects: Aged; Aged, 80 and over; Algorithms; Alzheimer Disease - diagnosis; Alzheimer Disease - physiopathology; Alzheimer's disease; Behavioral test; Cognition Disorders - diagnosis; Cognition Disorders - physiopathology; Cognitive Dysfunction - diagnosis; Cognitive Dysfunction - physiopathology; Eye movement; Eye Movements - physiology; Female; Humans; Male; Photic Stimulation - methods; Psychomotor Performance - physiology; Recognition memory; Recognition memory; Behavioral test; Eye movement; Alzheimer's disease
• DOI: 10.1016/j.jneumeth.2011.06.027
• ISSN: 0165-0270; 1872-678X

► A novel application of automatic classification methods from computer science to improve the accuracy of detecting Mild Cognitive Impairment during the Visual Paired Comparison task. ► An effective representation of eye movement characteristics such as fixations, saccades, and re-fixations as features for automatic classification algorithms. ► Our techniques allow to automatically distinguish age-matched normal control subjects from MCI subjects with 87% accuracy, 96% sensitivity and 77% specificity, compared to the best classification performance of 67% accuracy, 60% sensitivity, and 73% with previous techniques over VPC data. The Visual Paired Comparison (VPC) task is a recognition memory test that has shown promise for the detection of memory impairments associated with mild cognitive impairment (MCI). Because patients with MCI often progress to Alzheimer's Disease (AD), the VPC may be useful in predicting the onset of AD. VPC uses noninvasive eye tracking to identify how subjects view novel and repeated visual stimuli. Healthy control subjects demonstrate memory for the repeated stimuli by spending more time looking at the novel images, i.e., novelty preference. Here, we report an application of machine learning methods from computer science to improve the accuracy of detecting MCI by modeling eye movement characteristics such as fixations, saccades, and re-fixations during the VPC task. These characteristics are represented as features provided to automatic classification algorithms such as Support Vector Machines (SVMs). Using the SVM classification algorithm, in tandem with modeling the patterns of fixations, saccade orientation, and regression patterns, our algorithm was able to automatically distinguish age-matched normal control subjects from MCI subjects with 87% accuracy, 97% sensitivity and 77% specificity, compared to the best available classification performance of 67% accuracy, 60% sensitivity, and 73% specificity when using only the novelty preference information. These results demonstrate the effectiveness of applying machine-learning techniques to the detection of MCI, and suggest a promising approach for detection of cognitive impairments associated with other disorders.