TOPIC 425 - COMPUTER VISION-BASED ANALYSIS OF GAIT FOR THE ASSESSMENT OF GERIATRIC CANCER

老年癌症患者在手术前后以及化疗前和化疗期间接受详细的临床评估。研究表明，虚弱（由虚弱指数量化）和各种步态 诸如步态速度的特征或诸如计时加速（TUG）的测试是外科老年癌症患者死亡率的预测因子。此外，与某些化疗药物相关的神经毒性可能对老年患者的移动性和平衡性产生显著影响，增加跌倒相关损伤的风险，因此，作为综合老年评估（CGA）的一部分，对患者平衡性进行客观评估可能与癌症相关结局相关。然而，由于肿瘤诊所的时间限制，许多肿瘤学家没有评估老年癌症患者的步态和平衡。在这项研究中，我们建议在我们早期工作的基础上，开发一种易于使用的床旁技术，用于使用计算机视觉对老年癌症患者进行客观的步态评估。作为这一进程的一部分，将开发一个访问控制的公共视频库，以促进步态评估计算机视觉技术的发展。

Older patients with cancer undergo detailed clinical assessment prior to and after surgery as well as prior to and during chemotherapy. Studies show that frailty (quantified by the frailty index) and various gait characteristics such as gait speed or tests such as timed up and go (TUG) are predictors of mortality for surgical geriatric cancer patients. In addition, the neurotoxicity associated with some of the chemotherapy drugs can have a significant impact on the mobility and balance of the older patient increasing the risk of fall-related injuries, and hence, an objective assessment of patient's balance as part of a comprehensive geriatric assessment (CGA) may be associated with cancer-related outcomes. However, given the time constraints in oncology clinics, many oncologists do not assess gait and balance of older adults with cancer. In this study, we propose to build on our earlier work to develop an easy-to-use point-of-care technology for objective gait assessment in geriatric cancer patients using computer vision. As part of the process, an access-controlled public repository of videos will be developed to cultivate development of computer vision techniques for gait assessment.