International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Detection of Cognitive Disorders Using Eye Tracking and Machine Learning |
|---|---|
| ABSTRACT | Cognitive health conditions such as Alzheimer's disease, Attention Deficit Hyperactivity Disorder (ADHD), and early-onset dementia affect tens of millions of people globally, yet early-stage detection remains a persistent challenge in clinical practice. Conventional screening approaches often depend on patient-reported symptoms, lengthy paper-based assessments, or costly neuroimaging procedures, all of which introduce delays, human bias, or accessibility barriers. The core objective of this paper is to investigate a non-invasive, cost-effective alternative that leverages eye-movement data in combination with supervised machine learning algorithms to flag potential cognitive impairment before visible behavioral symptoms emerge. The human eye, when engaged in visual tasks, produces quantifiable movement patterns that are tightly regulated by underlying neural activity. In cognitively impaired individuals, subtle yet consistent deviations appear in metrics such as fixation stability, the speed of rapid gaze transitions (saccades), and the way the pupil responds to changing luminance. These deviations are often imperceptible to clinicians observing a patient in conversation, but they become statistically distinguishable when collected systematically and processed by a trained classifier. This work proposes a complete pipeline that begins with data capture via an infrared eye-tracking camera, moves through noise filtering and coordinate normalization, proceeds into feature extraction, and concludes with classification using two prominent models: Support Vector Machine (SVM) and Random Forest. The Random Forest classifier with 100 decision trees achieved a classification accuracy of 93.4% on the test set, outperforming the SVM (RBF kernel) model at 87.6%. Experimental evaluation was performed on a dataset of 120 subject sessions, balanced evenly between cognitively healthy participants and those with documented mild cognitive impairment (MCI). The proposed system demonstrates that clinically meaningful cognitive assessment can be conducted in under three minutes using hardware that costs significantly less than conventional diagnostic tools, making it a viable candidate for integration into primary healthcare settings, especially in resource-limited environments. Future work will focus on expanding the disorder taxonomy and experimenting with deep learning-based sequence models to capture temporal patterns in gaze data. |
| AUTHOR | PROF.MANJULA P, VIJAYALAXMI U M, VIDYA D B, KAVYA PUJAR, SAHANA H K, VANDANA N Assistant Professor, Department of CSE, Jain Institute of Technology, Davangere, Karnataka, India UG Students, Department of CSE, Jain Institute of Technology, Davangere, Karnataka, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406051 |
| pdf/51_Detection of Cognitive Disorders Using Eye Tracking and Machine Learning.pdf | |
| KEYWORDS | |
| References | [1] Molitor, R. J., Ko, P. C., & Ally, B. A. (2015). Eye movements in Alzheimer's disease: An integrative review with insights into the influence of reading paradigms on fixation behavior. Neuropsychology Review, 25(3), 240–258. [2] Fried, M., Tsitsiashvili, E., Bonneh, Y. S., Sterkin, A., Wygnanski-Jaffe, T., Epstein, T., & Polat, U. (2014). ADHD subjects fail to suppress eye blinks and reflexive saccades to no-go signals. Vision Research, 101, 93–105. [3] Crawford, T. J., Higham, S., Renvoize, T., Patel, J., Dale, M., Suriya, A., & Tetley, S. (2005). Inhibitory control of saccadic eye movements and the diagnosis of dementia. Psychological Medicine, 35(8), 1123–1132. [4] Granholm, E., & Steinhauer, S. R. (2004). Pupillometric measures of cognitive and emotional processes. International Journal of Psychophysiology, 52(1), 1–6. [5] Thabtah, F., Peebles, D., & Ramsay, K. (2019). A new machine learning model applied to clinical data for early detection of autism spectrum disorder. Journal of Medical Systems, 43(9), 303. [6] Wilcockson, T. D. W., Mardanbegi, D., Xia, B., Taylor, S., Sawyer, P., Gellersen, H. W., Leroi, I., Killick, R., & Crawford, T. J. (2019). Abnormalities of saccadic eye movements in dementia due to Alzheimer's disease and mild cognitive impairment. Aging, 11(15), 5389–5397. [7] Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. [8] Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. |
