平衡行为:可穿戴传感器和人工智能改变平衡评估

工程，研究人员，工程与计算机科学学院，学生

Using wearable sensors and advanced machine learning algorithms, 研究人员已经开发出一种新的方法，可以彻底改变平衡评估实践. (Photo by Alex Dolce)

By gisele galoustian | 6/26/2024

Balance can be impacted by various factors, including diseases such as Parkinson’s disease, acute and chronic injuries to the nervous system, and the natural aging process. 准确评估患者的平衡对于识别和管理影响协调和稳定性的条件非常重要. Balance assessments also play a key role in preventing falls, understanding movement disorders, 并针对不同年龄组和医疗条件设计适当的治疗干预措施.

However, 用于评估平衡的传统方法往往具有主观性, are not comprehensive enough and cannot be administered remotely. Moreover, these assessments rely on expensive, 在所有临床环境中可能不容易获得的专门设备，并取决于临床医生的专业知识, which can lead to variability in results. 在平衡评价中，迫切需要更客观、更全面的评价工具.

利用可穿戴传感器和先进的机器学习算法，来自 Florida Atlantic University’s College of Engineering and Computer Science 开发了一种新颖的方法，解决了平衡评估方面的关键差距，并为可穿戴技术和机器学习在医疗保健领域的应用树立了新的基准. 这种方法是客观平衡评价的重大进步, 尤其适用于居家或护理场所的远程监控, potentially transforming balance disorder management.

For the study, 研究人员使用了平衡感相互作用改良临床测试(m-CTSIB), 广泛用于医疗保健，评估一个人在不同感官条件下保持平衡的能力. Wearable sensors were placed on study participants’ ankle, lumbar (lower back), sternum, wrist and arm.

Researchers collected comprehensive motion data from the participants under four different sensory conditions of m-CTSIB: balance performance with eyes open and closed on a stable surface; and eyes open and closed on a foam surface. 每个测试条件持续约11秒，不间断，以模拟持续的平衡挑战并简化评估过程. 研究人员使用惯性测量单元(IMU)传感器和一个专门的系统来评估地面真值m-CTSIB平衡分数.

然后对数据进行预处理，提取大量特征以供分析. To estimate the m-CTSIB scores, researchers applied Multiple Linear Regression, Support Vector Regression and XGBOOST algorithms. 可穿戴传感器的数据作为机器学习模型的输入, and the corresponding m-CTSIB scores from Falltrak II, one of the leading tools in fall prevention, 作为模型训练和验证的基础真值标签. 然后开发了多个机器学习模型，从可穿戴传感器数据中估计m-CTSIB分数. 研究人员还探索了最有效的传感器位置，以优化平衡分析.

Results of the study, published in the journal Frontiers in Digital Health, 强调这种方法的高准确性和与地面真实平衡分数的强相关性, 表明该方法是一种有效、可靠的平衡估算方法. 腰椎和主要脚踝传感器的数据表明，平衡评分估计的性能最高, 强调战略性传感器放置的重要性，以捕捉相关的平衡调整和运动.

“可穿戴传感器为捕获详细的运动数据提供了一种实用且经济高效的解决方案, which is essential for balance analysis,” said Behnaz Ghoraani, Ph.D., senior author, an associate professor, FAU Department of Electrical Engineering and Computer Science , co-director of the FAU Center for SMART Health, and a fellow, 传感与嵌入式网络系统工程研究所(I-SENSE). “Positioned on areas like the lower back and lower limbs, these sensors provide insights into 3D movement dynamics, 对于不同人群的跌倒风险评估等应用至关重要. Coupled with the evolution of machine learning, these sensor-derived datasets transform into objective, quantifiable balance metrics, using an array of machine learning techniques.”

结果为具体动作的意义提供了重要的见解, feature selection and sensor placement in estimating balance. Notably, the XGBOOST model, utilizing the lumbar sensor data, 两种交叉验证方法均取得了优异的结果，具有较高的相关性和较低的平均绝对误差, indicating consistent performance.

“这项重要研究的结果表明，这种新方法有可能彻底改变平衡评估实践, 特别是在传统方法不切实际或无法使用的情况下,” said Stella Batalama, Ph.D., dean, FAU College of Engineering and Computer Science. “This approach is more accessible, cost-effective and capable of remote administration, which could have significant implications for health care, rehabilitation, 运动科学或其他平衡评估很重要的领域.”

这项研究的目的是认识到需要先进的工具来捕捉不同感官输入对平衡的细微影响.

“传统的平衡评估通常缺乏全面剖析这些影响的粒度, 导致我们对平衡障碍的理解和管理存在差距,” said Ghoraani. “Moreover, wearables support remote monitoring, 使医疗保健专业人员能够远程评估患者的平衡, which is particularly useful in diverse health care scenarios.”

Study co-authors are Marjan Nassajpour, a Ph.D. student and research assistant; Mustafa Shuqair, a Ph.D. student; both within the FAU Department of Electrical Engineering and Computer Science; Amie Rosenfeld, Magdalena Tolea, Ph.D., and James E. Galvin, M.D., professor of neurology, chief, Division of Cognitive Neurology, 也是脑健康综合中心和路易体痴呆卓越研究中心的主任, all with the University of Miami Miller School of Medicine.

这项工作得到了佛罗里达州卫生部Ed和Ethel Moore阿尔茨海默病研究项目和国家科学基金会的支持.

-FAU-