AI-Powered Detection and Rehabilitation Support for Brain Wellness

Concussion diagnosis remains a complex and resource-intensive process, yet early detection is essential to reducing the risk of long-term neurological impairment. This feasibility study explores a cost-effective, portable solution lever-aging the ubiquity of smartphones. Unlike previous approaches that relied on virtual reality environments, our method adapts established assessment techniques to a more accessible platform by utilizing front-facing sensors and integrated eye-tracking capabilities available in modern mobile devices. Specifically, we investigate the feasibility of combining ARKit-based gaze estimation with lightweight electroencephalography (EEG) sensors to measure saccades, fixation, reaction time, and neural activity. Through multi-modal data fusion and machine learning, we assess the system’s ability to reliably identify potential concussion symptoms and provide timely, on-site screening prior to formal clinical evaluation. This work does not replace medical diagnosis but establishes the foundation for an accessible mobile health tool aimed at improving the speed and reach of concussion screening.

• Publication year

  2025

• Venue

  2025 International Conference on Machine Learning, Computational Intelligence and Pattern Recognition (MLCIPR)

• Publication date

  2025-12-19

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/MLCIPR68329.2025.11407331
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Lifetime Traumatic Brain Injury and Cognitive Domain Deficits in Late Life: The PROTECT-TBI Cohort Study

  2023cited by this paper
• Towards Preventing Gaps in Health Care Systems through Smartphone Use: Analysis of ARKit for Accurate Measurement of Facial Distances in Different Angles

  2023cited by this paper
• Early vs. delayed evaluation and persisting concussion symptoms during recovery in adults

  2022cited by this paper
• Eye tracking for classification of concussion in adults and pediatrics

  2022influential reference
• Traumatic brain injury: progress and challenges in prevention, clinical care, and research

  2022cited by this paper
• Multimodal EEG and Eye Tracking Feature Fusion Approaches for Attention Classification in Hybrid BCIs

  2022cited by this paper
• Cybersickness and Its Severity Arising from Virtual Reality Content: A Comprehensive Study

  2022cited by this paper
• Early injury evaluation following concussion is associated with improved recovery time in children and adolescents.

  2021cited by this paper
• Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors

  2021cited by this paper
• StimulEye: A Computer Vision Based Concussion Detector

  2020cited by this paper
• Oculomotor Behavior as a Biomarker for Differentiating Pediatric Patients With Mild Traumatic Brain Injury and Age Matched Controls

  2020cited by this paper
• Predictive Modeling of Sports-Related Concussions using Clinical Assessment Metrics

  2020cited by this paper
• BIE-PInCS: Brain injury evaluation with pupillometer based on infrared camera system

  2017cited by this paper
• The visual system as a proxy for evaluation of brain function

  2016cited by this paper
• Long-Term Consequences of Traumatic Brain Injury: Current Status of Potential Mechanisms of Injury and Neurological Outcomes

  2015cited by this paper
• The pathophysiology of traumatic brain injury at a glance

  2013cited by this paper
• The Prevalence of Undiagnosed Concussions in Athletes

  2013cited by this paper
• Traumatic Brain Injury in Sports: A Review

  2012influential reference
• Behavioral testing for TBI: Present and future perspectives

  2010cited by this paper
• Early clinical characteristics of patients with persistent post-concussion symptoms: A prospective study

  2009cited by this paper

• No citing papers are available for this paper.