NEWS

Researchers at Tel Aviv University and Ichilov’s Tel Aviv Sourasky Medical Center led a multidisciplinary international study in which an innovative model based on machine learning was developed to accurately estimate step length. The new model can be integrated into a wearable device that is attached (with “skin tape”) to the lower back and enables continuous monitoring of steps in a patient’s everyday life. "Step length is a sensitive measure of a wide range of problems and diseases, from cognitive decline and aging to Parkinson's. The conventional measuring devices that exist today are stationary and cumbersome and are only found in specialized clinics and laboratories. The model we developed enables accurate measurement in a patient's natural environment throughout the day, using a wearable sensor", according to the researchers.

The study was led by Assaf Zadka, a graduate student in the Department of Biomedical Engineering at Tel Aviv University; Prof. Jeffrey Hausdorff from the Department of Physical Therapy at the Faculty of Medical and Health Sciences and the Sagol School of Neuroscience at Tel Aviv University, as well as from the Department of Neurology, Tel Aviv Sourasky Medical Center (TASMC); and Prof. Neta Rabin from the Department of Industrial Engineering at the Fleischman Faculty of Engineering at Tel Aviv University. Also participating in the study were Eran Gazit from TASMC, Prof. Anat Mirelman from the Faculty of Medical and Health Sciences and the Sagol School of Neuroscience at Tel Aviv University and TASMC, as well as researchers from Belgium, England, Italy, Holland, and the USA. The research was supported by the Center for AI and Data Science of Tel Aviv University. An article describing the research was published in the journal Digital Medicine.

A person walking in a state-of-the-art gait lab, with a wearable sensor positioned on his lower back. He is walking over a gait mat embedded with force-sensitive sensors. The gait mat provides highly accurate measures of the person's step length and is used to provide reference values for "training" and testing of the machine learning model described in this study. In the background, specialized motion capture cameras can also be seen. The gait mat and cameras very accurately measure a subject's walking pattern, over a few steps. However, these tools cannot be used in the real-world, everyday setting. In contrast, the wearable sensor is small, lightweight, and waterproof, can be held in place using skin tape, and can measure step length throughout the day, informing the evaluation of real-world walking and functional abilities.

Can Our Steps Reveal Neurological Health?

Prof. Hausdorff, an expert in the fields of walking, aging, and neurology, explains: "Step length is a very sensitive and non-invasive measure for evaluating a wide variety of conditions and diseases, including aging, deterioration as a result of neurological and neurodegenerative diseases, cognitive decline, Alzheimer's, Parkinson's, multiple sclerosis, and more. 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. Daily living walking may be influenced by a patient’s level of fatigue, mood, and medications, for example. Continuous, 24/7 monitoring like that enabled by this new model of step length can capture this real-world walking behavior".

Smart Sensors for Accurate Steps

Prof. Rabin, an expert in machine learning, adds: "To solve the problem, we sought to harness IMU (inertial measurement unit) systems - light and relatively cheap sensors currently installed in every phone and smart-watch, and measure parameters associated with walking. Previous studies have examined IMU-based wearable devices to assess step length, but these experiments were only performed on healthy subjects without walking difficulties, were based on a small sample size that did not allow for generalization, and the devices themselves were not comfortable to wear and sometimes several sensors were needed. 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".

To develop the algorithm, the researchers used IMU sensor-based gait data, in addition to step length data measured conventionally in a previous study, from 472 subjects with different conditions, such as Parkinson's, people with mild cognitive impairment, healthy elderly subjects, as well as younger, healthy adults and people with multiple sclerosis. An accurate and diverse database consisting of 83,569 steps was collected in this way. The researchers used this data and machine learning methods to train several computer models that translated the IMU data into an estimate of step length. To test the robustness of the models the researchers then determined to what extent the various models could accurately analyze new data that was not used in the training process – an ability known as generalization.

New Model Improves Step Length Precision

Assaf Zadka: "We found that the model called XGBoost is the most accurate, and is 3.5 times more accurate than the most advanced biomechanical model currently used to estimate step length. For a single step, the average error of our model was 6 cm - compared to 21 cm predicted by the conventional model. When we evaluated an average of 10 steps, we arrived at an error of less than 5 cm - a threshold known in the professional literature as 'the minimum difference that has clinical importance', which allows identifying a significant improvement or decrease in the subject's condition. In other words, our model is robust and reliable, and can be used to analyze sensor data from subjects, some with walking difficulties, who were not included in the original training set".

Prof. Hausdorff concludes: "In our research, we collaborated with researchers in diverse fields around the world, and the multi-disciplinary effort led to promising results. We developed a machine learning model that can be integrated with a wearable and easy-to-use sensor, which gives an accurate estimate of the patient's step length during daily life. The data collected in this way enables continuous, remote, and long-term monitoring of a patient’s condition, and can also be used in clinical trials to examine the effectiveness of medications. Based on our encouraging results, we are looking into whether it is possible to develop similar models based on data from sensors in smart-watches, which would further improve the comfort of the subject".

A new study from Tel Aviv University identified the earliest appearance worldwide of special stone tools, used 400,000 years ago to process fallow deer. The tools, called Quina scrapers (after the site in France where they were first discovered), were unearthed at the prehistoric sites of Jaljulia and Qesem Cave. They are characterized by a sharp working edge shaped as scales, enabling users to butcher their prey and also process its hides.

The researchers explain that after the elephants disappeared from the region, the ancient hunters were forced to make technological adaptations enabling them to hunt, butcher, and process much smaller and quicker game - fallow deer. The study also found that the unique tools were made of non-local flint procured from the Mountains of Samaria, which probably also served as the fallow deers' calving area, about 20km east of Jaljulia and Qesem Cave. Consequently, the researchers hypothesize that Mounts Ebal and Gerizim (near Nablus of today) were considered a source of plenty and held sacred by prehistoric hunters as early as the Paleolithic period.

The study was led by Vlad Litov and Prof. Ran Barkai of Tel Aviv University’s Jacob M. Alkow Department of Archaeology and Ancient Near Eastern Cultures. The paper was published in Archaeologies.

Prof. Ran Barkai

The researchers explain that for about a million years, starting 1.5 million years ago, early humans used stone tools called scrapers to process hides and scrape the flesh off the bones of mostly large game. In the Levant, they mainly hunted elephants and other large herbivores that provided most of the calories they needed. The study found, however, that about 400,000 years ago, following the elephants' disappearance, hunters turned to a different kind of prey, considerably smaller and quicker than elephants - fallow deer.

How Changing Diets Shaped Prehistoric Tools

Litov explains: "In this study, we tried to understand why stone tools changed during prehistoric times, with a focus on a technological change in scrapers in the Lower Paleolithic, about 400,000 years ago. We found a dramatic change in the human diet during this period, probably resulting from a change in the available fauna: the large game, particularly elephants, had disappeared, and humans were forced to hunt smaller animals, especially fallow deer. Clearly, butchering a large elephant is one thing, and processing a much smaller and more delicate fallow deer is quite a different challenge. Systematic processing of numerous fallow deer to compensate for a single elephant was a complex and demanding task that required the development of new implements. Consequently, we see the emergence of the new Quina scrapers, with a better-shaped, sharper, more uniform working edge compared to the simple scrapers used previously".

A close look at a Quina-like scraper from Jaljulia.

The study relies on findings from an excavation at the Jaljulia prehistoric site next to Highway 6 in central Israel, probably inhabited by humans of the homo erectus species, as well as evidence from the nearby Qesem Cave. At both sites the excavators discovered many scrapers of the new type, made of non-local flint whose nearest sources are the western slopes of Samaria, to the east of the excavated sites, or today's Ben Shemen Forest to the south.

Prof. Barkai adds: "In this study we identified links between technological developments and changes in the fauna hunted and consumed by early humans. For many years researchers believed that the changes in stone tools resulted from biological and cognitive changes in humans. We demonstrate a double connection, both practical and perceptual. On the one hand, humans started making more sophisticated tools because they had to hunt and butcher smaller, faster, thinner game. On the other, we identify a perceptual connection: Mounts Ebal and Gerizim in Samaria, about 20km east of Jaljulia, were a home range of fallow deer and thus considered a source of plenty. We found a connection between the plentiful source of fallow deer and the source of flint used to butcher them, and we believe that this link held perceptual significance for these prehistoric hunters. They knew where the fallow deer came from and made special efforts to use flint from the same area to make tools for butchering this prey. This behavior is familiar from many other places worldwide and is still widely practiced by native hunter-gatherer communities".

Samaria’s Sacred Role in Early Tool Evolution

Litov concludes: "We believe that the Mountains of Samaria were sacred to the prehistoric people of Qesem Cave and Jaljulia because that's where the fallow deer came from. It's important to note that in Jaljulia we also found numerous other tools made of different kinds of locally-procured stones. When the locals realized that the elephant population was dwindling, they gradually shifted their focus to fallow deer. Identifying the deer's plentiful source, they began to develop the unique scrapers in the same place. This is the earliest instance of a phenomenon that later spread throughout the world. The new scrapers first appeared at Jaljulia on a small scale, about 500,000 years ago, and a short time later, 400,000 to 200,000 years ago, on a much larger scale at Qesem Cave. The Samarian highlands east of Jaljulia and Qesem Cave were likely the home range of a fallow deer population, as evidenced by bone remains recovered from local archaeological sites throughout the Pleistocene and Holocene. Many fallow deer bones were also found at the altar site on Mount Gerizim, attributed in the Old Testament to Joshua bin Nun, and identified by some traditions as the place of Abraham's Covenant of the Pieces described in the Book of Genesis. Apparently, the Mountains of Samaria gained a prominent, or even sacred status as early as the Paleolithic period and retained their unique cultural position for hundreds of thousands of years".