Researchers in Israel 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 important indicators for clinicians evaluating the progression of many such conditions.

Camera-based systems can make precise measurements and identify subtle changes. But they’re confined to specialized clinics and only provide a snapshot, which may be influenced by the time of the day, fatigue, medication or “white coat syndrome.”

The new device, developed by a team from Tel Aviv University (TAU) and Tel Aviv Sourasky Medical Center, is taped to the patient’s lower back and allows continuous and precise monitoring of steps, around the clock, in everyday life.

It’s based on the cheap sensors in every smartphone and smartwatch that count steps and measure the distance covered – but which are notoriously inaccurate. 

The researchers developed an algorithm that interprets the raw data to provide step measurements that are accurate to within 5 centimeters over 10 steps, which is well within the parameters needed by clinicians.

The team collected data from more than 83,000 steps walked by 472 people with different conditions, such as Parkinson’s disease or mild cognitive impairment, along with healthy elderly subjects, younger adults and people with multiple sclerosis.  

They then used machine-learning methods to train computer models to accurately estimate step length.

Efficient, convenient

Prof. Neta Rabin, an expert in machine learning at TAU’s Department of Industrial Engineering, said: “We sought to harness IMU [inertial measurement unit] systems — light and relatively cheap sensors that are currently installed in every phone and smartwatch — and measure parameters associated with walking.

“We sought to develop an efficient and convenient solution that would suit people with walking problems, such as the sick and the elderly, and would allow quantifying and collecting data on step length, throughout the day, in an environment familiar to the patient. 

“The goal was to develop an algorithm that is capable of translating the IMU data into an accurate assessment of step length, which can be integrated into a wearable and comfortable device.”

“Step length is a very sensitive and noninvasive measure for evaluating a wide variety of conditions and diseases” including aging and deterioration as a result of neurological and neurodegenerative diseases such as Alzheimer’s and Parkinson’s, said Prof. Jeffrey Hausdorff from TAU’s Department of Physical Therapy.

“Today it is common to measure step length using devices found in specialized laboratories and clinics, which are based on cameras and measuring devices like force-sensitive gait mats. While these tests are accurate, they provide only a snapshot view of a person’s walking that likely does not fully reflect real-world, actual functioning,” he said.

“Continuous, 24/7 monitoring like that enabled by this new model of step length can capture this real-world walking behavior.”

The study was led by Assaf Zadka, a graduate student at TAU’s Department of Biomedical Engineering. The results have been published in the journal Nature.