Scholarlink

<p>Spinal Sagittal Imbalance (SSI) is identified as abnormal alignment of the spine in the sagittal plane resulting in functional limitations. This misalignment can lead to chronic pain, and impaired mobility in the lower limbs. Understanding the kinematic patterns of low back pain patients with SSI is important in proper diagnosis and treatment. In this study, we investigated the walking condition of 60 low back pain patients with SSI and compared them to 60 controls. We used Inertial measurement unit (IMU) data and machine learning (ML) models to gather and analyze the data. The support vector machine (SVM) model achieved an accuracy of over 97% in classifying the two groups data, outperforming other classification methods. Statistical comparison of the IMU data of the two groups also showed a significant difference (p&lt;0.05). This study demonstrated ML-based IMU gait analysis as a non-invasive and efficient tool for preoperative performance assessment in SSI patients and identified the most important parameters influencing classification and diagnosis. According to the results, ML accurately measures and examines lower limb variability for each patient before surgery, which can enhance surgical planning and patient classification.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Preoperative lower limb kinematic analysis in spinal sagittal imbalance using machine learning and IMU sensors

  • 期刊论文

  • 发表日期：

    2025年5月28日

查看全文
  • Sadegh Madadi,
  • Mostafa Rostami,
  • Hadi Farahani,
  • Farshad Nikouee,
  • Mohammad Samadian,
  • Ram Haddas

摘要

Spinal Sagittal Imbalance (SSI) is identified as abnormal alignment of the spine in the sagittal plane resulting in functional limitations. This misalignment can lead to chronic pain, and impaired mobility in the lower limbs. Understanding the kinematic patterns of low back pain patients with SSI is important in proper diagnosis and treatment. In this study, we investigated the walking condition of 60 low back pain patients with SSI and compared them to 60 controls. We used Inertial measurement unit (IMU) data and machine learning (ML) models to gather and analyze the data. The support vector machine (SVM) model achieved an accuracy of over 97% in classifying the two groups data, outperforming other classification methods. Statistical comparison of the IMU data of the two groups also showed a significant difference (p<0.05). This study demonstrated ML-based IMU gait analysis as a non-invasive and efficient tool for preoperative performance assessment in SSI patients and identified the most important parameters influencing classification and diagnosis. According to the results, ML accurately measures and examines lower limb variability for each patient before surgery, which can enhance surgical planning and patient classification.