System and Method for Predicting Fall Risk in Elderly Patients Using Video Game-Based Assessment

Simple SummaryContent extracted from patent full text and abstract with AI.

This invention describes a system and method for assessing the fall risk of elderly individuals, particularly those with chronic conditions like diabetes, using a combination of sensor-equipped insoles embedded in gaming slippers and a video game application. The insoles measure precise foot pressure during gameplay, and the data is analyzed using advanced machine learning models to evaluate balance, reaction time, and other relevant motor and cognitive skills. The system then classifies users into low/no risk or high risk of falls, supporting more accurate and engaging fall risk screening than traditional clinical methods.

Use CasesContent extracted from patent full text and abstract with AI.

• Routine fall risk assessment in elderly care homes or clinics to identify individuals at risk and adapt care plans accordingly.
• Self-monitoring tool for elderly individuals to track their fall risk at home, possibly integrated into telemedicine or home health monitoring programs.
• Rehabilitation and physiotherapy support by providing objective feedback and motivation through engaging games for balance and motor skills improvement.
• Clinical trials and research studies evaluating mobility, balance, interventions, or new treatments in geriatric or diabetic populations.
• Early detection of deteriorating physical functions in chronic disease patients, enabling timely preventive interventions.

BenefitsContent extracted from patent full text and abstract with AI.

• Significantly higher predictive accuracy (up to 88.6%) for fall risk compared to standard assessment tools.
• User engagement and compliance are enhanced due to the game-based, interactive nature of the assessment.
• Non-invasive, real-time measurement of multiple risk factors including balance, reaction time, sensation, endurance, and strength.
• Customizable for both seated and standing users, increasing accessibility for frail or immobile individuals.
• Supports data-driven, individualized interventions by using advanced machine learning to extract subtle risk patterns.
• Provides immediate feedback and visualizations, which can improve motivation for functional improvement and facilitate preventive care.
• Can be implemented in various settings such as clinics, rehabilitation centers, or users’ homes for flexible monitoring.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The present disclosure provides a video game-based fall risk assessment system (100) designed for individuals (120). The system comprises sensor-equipped insoles (102) embedded in gaming slippers, featuring pressure sensors to monitor plantar foot pressure at key locations. An electronic control unit (104) processes this data and a video gaming application on a smart device (106) uses real-time pressure data to facilitate gameplay, evaluating skills relevant to fall prevention, such as balance and reaction time. A server (108) receives gameplay data, extract specific performance parameters (including reaction time and success rate) using a machine learning model (116), and analyze these parameters to assess the individual's balance and stability. The machine learning model (116) evaluates fall risk based on seated or a combination of seated/standing data, employing statistical analysis techniques. Finally, the system classifies individuals into "no/low risk of falls" or "high risk of falls" categories, considering posture-specific risks for accurate fall risk assessment.