AI-powered shoes detecting early signs of neurodegenerative diseases

Decoding Gait: How AI-Powered Shoe Sensors Could Predict Neurodegenerative Diseases

Samir D’Costa in Health & Wellness August 2025 • 4 min read.

"New research explores using force-sensitive resistors in shoes, coupled with AI, to detect early signs of Parkinson's, Huntington's, and ALS diseases through gait analysis."

Everyday activities like walking, shopping, and simply moving around are often taken for granted. However, for individuals suffering from neurodegenerative diseases (NDDs) such as Parkinson's Disease (PD), Huntington's Disease (HD), and Amyotrophic Lateral Sclerosis (ALS), these simple actions can become significant challenges. These diseases often affect motor neurons, leading to changes in gait, or walking patterns.

Traditionally, clinical gait analysis, as described by Baker et al., involves recording biomechanical movements during walking to assess a patient's condition. This method allows clinicians to identify deviations from normal patterns and adjust treatment plans accordingly. However, new technologies offer the potential for more continuous and unobtrusive monitoring of gait.

One promising technology involves the use of force-sensitive resistors (FSRs). These sensors can be placed in shoes to measure the force and pressure exerted between the foot and the shoe during walking, providing detailed information about gait dynamics. Coupled with artificial intelligence (AI), this data can be analyzed to detect subtle changes in gait patterns that may indicate the presence or progression of neurodegenerative diseases.

How Do Force-Sensitive Resistors Work in Gait Analysis?

AI-powered shoes detecting early signs of neurodegenerative diseases

Force-sensitive resistors (FSRs) are sensors that change their resistance in response to applied force. When placed in the insole of a shoe, these sensors measure the pressure distribution across the foot during different phases of the gait cycle. As force is applied to the sensor, its resistance decreases, and this change is converted into a voltage signal that can be recorded and analyzed.

The gait cycle is typically divided into two main phases: stance and swing. The stance phase refers to the period when the foot is in contact with the ground, while the swing phase is when the foot is lifted and moving forward. Within the stance phase, there are several sub-phases, including heel strike, mid-stance, and toe-off. FSRs can capture the pressure variations during each of these sub-phases, providing a detailed picture of how the foot interacts with the ground.

Stance Interval: The time when the foot is in contact with the ground, from heel strike to toe-off.
Swing Interval: The time when the foot is not touching the ground, as it moves forward for the next step.
Double Support: The period when both feet are simultaneously in contact with the ground.

By analyzing the data from FSRs, researchers and clinicians can identify subtle changes in gait parameters, such as stride length, step time, and pressure distribution. These changes may be indicative of underlying neurological conditions, even before other symptoms become apparent. The use of AI algorithms further enhances the ability to detect these subtle patterns and differentiate between healthy individuals and those with NDDs.

The Future of Gait Analysis and Neurodegenerative Disease Prediction

The research outlined in this paper demonstrates the potential of using force-sensitive resistors and AI to predict neurodegenerative diseases based on gait analysis. While the current study shows promising results, there are several avenues for future research. These include incorporating data from multiple sensors, increasing the size and diversity of patient datasets, and refining the AI algorithms used for classification. As technology advances, wearable sensors and AI-powered analysis could play an increasingly important role in early disease detection and management, ultimately improving the lives of individuals affected by these debilitating conditions.

About this Article -

This article was crafted using a human-AI hybrid and collaborative approach. AI assisted our team with initial drafting, research insights, identifying key questions, and image generation. Our human editors guided topic selection, defined the angle, structured the content, ensured factual accuracy and relevance, refined the tone, and conducted thorough editing to deliver helpful, high-quality information.See our About page for more information.

This article is based on research published under:

DOI-LINK: 10.1109/lsc.2018.8572063, Alternate LINK

Title: Neurodegenerative Disease Prediction Based On Gait Analysis Signals Acquired With Force-Sensitive Resistors

Journal: 2018 IEEE Life Sciences Conference (LSC)

Publisher: IEEE

Authors: Roger Selzler, James R. Green, Rafik Goubran

Published: 2018-10-01

Everything You Need To Know

How do force-sensitive resistors work in shoes to capture gait data, and what specific information do they provide?

Force-sensitive resistors, or FSRs, are sensors used in shoes to measure the pressure distribution across the foot during walking. As force is applied, the FSR's resistance decreases, and this change is converted into a voltage signal. This data captures pressure variations during phases like heel strike, mid-stance, and toe-off, providing a detailed picture of how the foot interacts with the ground. While the text describes the functionality of FSRs it doesn't cover the calibration process of force sensors, which is crucial for ensuring accuracy in gait analysis. Understanding how these sensors are calibrated and maintained would provide a more complete view of their practical application.

Can you explain the difference between the stance and swing phases of the gait cycle, and why are they important in gait analysis using shoe sensors?

The stance phase is the period when the foot is in contact with the ground, starting from heel strike and ending at toe-off. The swing phase is when the foot is lifted and moving forward. Within the stance phase, sub-phases like heel strike, mid-stance, and toe-off provide detailed information on how the foot interacts with the ground. The period when both feet are simultaneously in contact with the ground is called double support. The text doesn't explain how specific gait parameters, like cadence or step length, are extracted and quantified from stance and swing phase data. This extraction and quantification are essential steps in translating raw sensor data into clinically meaningful information.

In what specific ways does AI improve the analysis of gait data collected from force-sensitive resistors, particularly in detecting neurodegenerative diseases?

AI enhances gait analysis by detecting subtle changes in gait patterns indicative of neurodegenerative diseases. By analyzing data from force-sensitive resistors, AI algorithms can differentiate between healthy individuals and those with conditions such as Parkinson's, Huntington's, and ALS, even before other symptoms are apparent. The text mentions refining AI algorithms but doesn't delve into specific types of AI, like deep learning or machine learning, or how these algorithms are trained and validated using gait data. A deeper explanation of the AI methodologies employed would clarify how these systems learn and improve their predictive accuracy.

What are the potential benefits of using AI-powered shoe sensors for predicting neurodegenerative diseases, and how could this technology impact patient care?

The use of force-sensitive resistors and AI can potentially lead to earlier diagnosis and treatment of neurodegenerative diseases like Parkinson's, Huntington's, and ALS. This technology offers a more continuous and unobtrusive monitoring of gait, allowing for the detection of subtle changes that may indicate the presence or progression of these diseases. However, the information doesn't mention the ethical considerations of using AI in medical diagnostics, particularly regarding data privacy, algorithmic bias, and the potential for misdiagnosis. Addressing these ethical aspects would provide a more balanced perspective on the responsible implementation of this technology.

Beyond what's already being researched, what further advancements or integrations could enhance the accuracy and applicability of using gait analysis for disease prediction?

Future research involves incorporating data from multiple sensors, increasing the size and diversity of patient datasets, and refining the AI algorithms used for classification. Wearable sensors and AI-powered analysis could play a crucial role in early disease detection and management. The text doesn't specify how the integration of data from other sensors, such as accelerometers or gyroscopes, could complement the data from force-sensitive resistors. Furthermore, a discussion on how these integrated data streams can provide a more comprehensive assessment of gait and overall motor function would enhance the understanding of future research directions.