Cho Sang Wouk, Cho Sung Joon, Park Eun-Young, Park Na-Rae, Han Sookyeong, Rhee Yumie, Hong Namki
Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, 03722, Korea.
Institute for Innovation in Digital Healthcare (IIDH), Yonsei University Health System, Seoul, 03722, Korea.
Osteoporos Int. 2025 May 15. doi: 10.1007/s00198-025-07515-z.
Video-estimated peak jump power (vJP) using deep learning showed strong agreement with ground truth jump power (gJP). vJP was associated with sarcopenia, age, and muscle parameters in adults, with providing a proof-of-concept that markerless monitoring of peak jump power could be feasible in daily life space.
Low peak countermovement jump power measured by ground force plate (GFP) is associated with sarcopenia, impaired physical function, and elevated risk of fracture in older adults. GFP is available at research setting yet, limiting its clinical applicability. Video-based estimation of peak jump power could enhance clinical applicability of jump power measurement over research setting.
Data were collected prospectively in osteoporosis clinic of Severance Hospital, Korea, between March and August 2022. Individuals performed three jump attempts on GFP (ground truth, gJP) under video recording, along with measurement of handgrip strength (HGS), 5-time chair rise (CRT) test, and appendicular lean mass (ALM). Open source deep learning pose estimation and machine learning algorithms were used to estimate video-estimated peak jump power (vJP) in 80% train set. Sarcopenia was defined by Korean Working Group for Sarcopenia 2023 definition.
A total of 658 jump motion data from 220 patients (mean age 62 years; 77% women; sarcopenia 19%) were analyzed. In test set (20% hold-out set), average difference between predicted and actual jump power was 0.27 W/kg (95% limit of agreement - 5.01 to + 5.54 W/kg; correlation coefficient 0.93). vJP detected gJP-defined low jump power with 81.8% sensitivity and 91.3% specificity. vJP showed a steep decline across age like gJP, with modest to strong correlation with HGS and CRT. Eight landmarks (both shoulders, hip, knee joints, and ears) were the most contributing features to vJP estimation. vJP was associated with the presence of sarcopenia (unadjusted and adjusted, - 3.95 and - 2.30 W/kg), HGS (- 3.69 and - 1.96 W/kg per 1 SD decrement), and CRT performance (- 2.79 and - 1.87 W/kg per 1 SD decrement in log-CRT) similar to that of gJP.
vJP was associated with sarcopenia, age, and muscle parameters in adults, with good agreement with ground truth jump power.
使用深度学习的视频估计峰值跳跃功率(vJP)与地面真实跳跃功率(gJP)显示出高度一致性。vJP与成年人的肌肉减少症、年龄和肌肉参数相关,这为无标记监测日常生活空间中的峰值跳跃功率提供了概念验证,证明其具有可行性。
通过地面力板(GFP)测量的低峰值反向运动跳跃功率与老年人的肌肉减少症、身体功能受损和骨折风险升高相关。然而,GFP仅在研究环境中可用,限制了其临床适用性。基于视频的峰值跳跃功率估计可以提高跳跃功率测量在临床环境中的适用性,而不仅仅局限于研究环境。
于2022年3月至8月在韩国Severance医院的骨质疏松门诊进行前瞻性数据收集。受试者在视频记录下在GFP上进行三次跳跃尝试(地面真实值,gJP),同时测量握力(HGS)、5次从椅子上起身(CRT)测试和四肢瘦体重(ALM)。使用开源深度学习姿态估计和机器学习算法在80%的训练集中估计视频估计峰值跳跃功率(vJP)。肌肉减少症根据2023年韩国肌肉减少症工作组的定义来确定。
共分析了来自220名患者(平均年龄62岁;77%为女性;肌肉减少症患者占19%)的658次跳跃运动数据。在测试集(20%的留出集)中,预测跳跃功率与实际跳跃功率的平均差异为0.27W/kg(95%一致性界限为-5.01至+5.54W/kg;相关系数为0.93)。vJP检测gJP定义的低跳跃功率的灵敏度为81.8%,特异性为91.3%。vJP与gJP一样,随年龄增长呈急剧下降趋势,与HGS和CRT呈中度至高度相关。八个地标(双肩、髋、膝关节和耳朵)是vJP估计中贡献最大的特征。vJP与肌肉减少症的存在相关(未调整和调整后分别为-3.95和-2.30W/kg),与HGS相关(每降低1个标准差分别为-3.69和-1.96W/kg),与CRT表现相关(log-CRT每降低1个标准差分别为-2.79和-1.87W/kg),与gJP相似。
vJP与成年人的肌肉减少症、年龄和肌肉参数相关,与地面真实跳跃功率具有良好的一致性。