TOPIC 425: POSTURE ANALYSIS THROUGH MACHINE LEARNING (PATHML) PHASE II

主题 425：通过机器学习 (PATHML) 进行姿势分析第二阶段

• 批准号: 10915803
• 负责人: VADIM KAGAN
• 金额: $ 204.96万
• 依托单位: SENTIMETRIX, INC.
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10915803
• 关键词: Address; Aging; Amputees; Architecture; Behavior; COVID-19 pandemic; Clinical; Clinical Trials; Computer Vision Systems; Computer software; Data; Data Collection; Data Set; Environment; Feedback; Future; Goals; Health; Home; Hour; Infrastructure; Machine Learning; Marketing; Measures; Modeling; Movement Disorders; Outcome; Patients; Performance; Phase; Physical Function; Physical Performance; Physical activity; Physical assessment; Population; Posture; Research; Research Personnel; Software Tools; System; Taxonomy; Testing; Time; Training; Visit; Walking; acceptability and feasibility; cancer rehabilitation; clinical outcome assessment; clinically relevant; cohort; cost; health application; improved; innovation; insight; machine learning model; novel; prototype; telehealth; tool; trend; usability

The availability of low-cost video has tremendous potential to provide new insight into how physical behavior is associated with health, define clinical trial outcomes, and assess physical function within the home, research and clinical environments. The COVID-19 pandemic required a rapid shift to incorporate video-based data collection and clinical visits, establishing the feasibility of using video for clinical outcome assessments (COA). However, there is a lack of software tools to automate and incorporate video into health-related applications. Our Phase I project resulted in a proof-of-concept PathML software prototype that included several sufficiently accurate machine learning models to annotate posture, physical activity intensity, and features of the environment. The Phase II project has two goals. The first goal is to enhance the functionality of the Phase I PathML prototype through innovative machine learning approaches to annotate relevant to physical behavior research taxonomies and UX enhancements that will result in a market-ready tool addressing the needs of physical behavior researchers. Additionally, this project seeks to extend the software to include automatic identification and scoring of clinically relevant COA’s (e.g., 30 second sit-stand test, two-minute walk test), partnering with clinical researchers with expertise in aging, movement disorders, amputees, and cancer rehabilitation.

低成本视频的可用性具有巨大的潜力，可以为身体行为如何与健康相关提供新的见解，定义临床试验结果，并评估家庭内的身体功能， 研究和临床环境。2019冠状病毒病大流行需要迅速转变，将基于视频的数据收集和临床访视结合起来，确立了使用视频进行临床结局评估（COA）的可行性。然而，缺乏软件工具来自动化视频并将其纳入与健康有关的应用程序。我们的第一阶段项目产生了一个概念验证的PathML软件原型 这包括几个足够准确的机器学习模型来注释姿势，身体活动强度和环境特征。第二阶段有两个目标。第一个目标是通过创新的机器学习方法来增强第一阶段PathML原型的功能，以注释与物理行为研究分类和UX增强相关的内容，从而实现 满足身体行为研究人员需求的市场就绪工具。此外，该项目旨在扩展软件，以包括临床相关COA的自动识别和评分（例如，30 第二次坐立测试，两分钟步行测试），与在衰老，运动障碍，截肢者和癌症康复方面具有专业知识的临床研究人员合作。