GAIT-BASED EARLY COGNITIVE DECLINE DETECTOR (MCI Screening) Using a Single Camera

The Gait-Based Early Cognitive Decline Detector (MCI Screening) Using a Single Camera is an AI-driven healthcare system designed to detect early signs of Mild Cognitive Impairment (MCI) through automated gait analysis.

Mild Cognitive Impairment is an early stage of cognitive decline that may progress to Alzheimer’s disease or other forms of dementia. Early diagnosis plays a crucial role in enabling timely intervention, cognitive therapy, and preventive care. However, traditional diagnostic methods such as neuropsychological testing and brain imaging are expensive, time-consuming, and not easily accessible in rural or low-resource healthcare settings.

Research studies show that subtle changes in walking patterns—such as reduced gait speed, stride variability, balance instability, and asymmetry—can serve as early indicators of cognitive decline. This project leverages computer vision and machine learning techniques to analyze gait patterns using a single RGB camera.

The system captures video of a person walking in a controlled environment and applies pose estimation algorithms to extract body keypoints such as hips, knees, ankles, shoulders, and head positions. From these keypoints, relevant gait features including step length, stride time, walking speed, and posture stability are computed. These features are then processed using machine learning classification models to predict whether the individual is normal, at risk, or showing high risk of cognitive impairment.

The proposed solution is non-invasive, cost-effective, and scalable. It eliminates the need for wearable sensors or complex motion capture systems, making it suitable for primary healthcare centers, elderly care facilities, and telemedicine applications. The system aims to support healthcare professionals by providing an automated screening tool for early detection of cognitive decline.