Researchers have developed a wearable step sensor to monitor the wellbeing of the elderly and patients with cognitive decline or neurological diseases. Reductions in step length are crucial indicators for clinicians evaluating the progression of these conditions. Traditional camera-based systems can make precise measurements and identify subtle changes but are confined to specialized clinics and only provide limited snapshots.
The new device, developed by a team from Tel Aviv University (TAU) and Tel Aviv Sourasky Medical Center, is attached to the patient’s lower back and allows continuous and precise monitoring of steps around the clock in everyday life. It utilizes common smartphone and smartwatch sensors, known for their inaccuracy, but the research team developed an algorithm to interpret the raw data, achieving step measurements accurate to within 5 centimeters over 10 steps.
The researchers collected data from more than 83,000 steps walked by 472 people with various conditions, such as Parkinson’s disease and mild cognitive impairment, as well as healthy elderly subjects, younger adults, and people with multiple sclerosis. They used machine-learning methods to train computer models to estimate step length accurately.
Professor Neta Rabin, an expert in machine learning at TAU’s Department of Industrial Engineering, stated that the goal was to harness light and relatively inexpensive IMU (inertial measurement unit) systems found in phones and smartwatches to measure walking parameters. The aim was to develop an efficient and convenient solution for people with walking problems that would allow quantifying and collecting step length data throughout the day in a familiar environment.
Professor Jeffrey Hausdorff from TAU’s Department of Physical Therapy emphasized that step length is a sensitive and noninvasive measure for evaluating a wide range of conditions, including aging and neurodegenerative diseases like Alzheimer’s and Parkinson’s. He highlighted that while current measurements in specialized labs are accurate, they only provide a snapshot that may not fully reflect real-world walking behavior. Continuous 24/7 monitoring, as enabled by this new device, can capture real-world walking behavior.
The study, led by Assaf Zadka, a graduate student at TAU’s Department of Biomedical Engineering, has been published in the journal Nature.
Article written by John Jeffay
21/07/2024
Source:
Israel 21C
https://www.israel21c.org/step-length-sensor-monitors-neurological-disease-progression/