Researchers from Florida Atlantic University have developed a balance assessment method that uses strategically placed sensors.
“Wearable sensors offer a practical and cost-effective solution for capturing detailed movement data,” said Behnaz Ghoraani, PhD, senior author and associate professor at FAU. “Positioned on areas like the lower back and lower limbs, these sensors provide insights into 3D movement dynamics, essential for applications such as fall risk assessment.”
Traditional balance assessment methods often lack objectivity, are not comprehensive and cannot be administered remotely. They rely on expensive, specialized equipment and the clinician’s expertise, which can skew results. By using wearable sensors to collect detailed motion data and machine learning algorithms to analyze it, this new approach overcomes these limitations.
Investigators used the Modified Clinical Test of Sensory Interaction on Balance, a widely used method in healthcare. Wearable sensors were placed on participants’ ankles, lower back, sternum, wrist and arm to collect motion data under different sensory conditions. Those conditions included balancing with eyes open and closed on both stable and foam surfaces, each for about 11 seconds.
The collected data then were preprocessed, and features were extracted for analysis. Multiple machine learning models, including Multiple Linear Regression, Support Vector Regression and XGBOOST algorithms, were applied to estimate m-CTSIB scores from the sensor data. The results, published in the journal Frontiers in Digital Health, showed high accuracy and strong correlation with ground truth balance scores.
The study highlighted the importance of strategic sensor placement, with data from lumbar and dominant ankle sensors demonstrating the highest performance in balance score estimation. This finding is particularly relevant for long-term care providers looking to implement practical and effective fall risk assessment tools.
Balance, a key aspect of mobility and stability, can be affected by various factors such as the aging process, nervous system injuries or Parkinson’s disease.
Accurate balance assessment is essential for identifying and managing conditions that impact coordination and stability. It also plays a significant role in preventing falls, understanding movement disorders, and designing appropriate therapeutic interventions for older adults and those with chronic conditions.
“Findings from this important research suggest that this novel method has the potential to revolutionize balance assessment practices, especially in situations where traditional methods are impractical or inaccessible,” said Stella Batalama, PhD, dean of FAU’s College of Engineering and Computer Science.
The McKnight’s Tech Daily is an e-newsletter for the audiences of McKnight’s Long-Term Care News, McKnight’s Senior Living and McKnight’s Home Care.
