S&AS: INT: COLLAB: An Intelligence-Driven Patient Care Approach to Reduce Medical Errors (I-CARE)

S

• 批准号: 1849359
• 负责人: Hua Wang
• 金额: $ 45万
• 依托单位: Colorado School of Mines
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1849359&HistoricalAwards=false
• 关键词: S&AS; INT; COLLAB; Intelligence; Driven

Imagine that in the near future a patient needing surgery will swallow a small mobile robot that can autonomously perform the procedure without any external incisions or pain. Such robots have the potential to make state-of-the-art surgical concepts a reality by providing an unconstrained mobile platform to visualize, manipulate and surgically treat tissue. The project's strategy will also harness the excitement surrounding robotics and computer science, and leverage it with the investigators' exceptional infrastructure for education innovation and outreach to provide new, inspirational educational experiences for students. Finally, the project outcomes can broadly impact a number of other areas that would benefit from the developed novel methodologies, including search and rescue, construction and maintenance, and remote imaging, where the environment is dynamic or changes upon repeated inspection.The goal of this project is to gain a fundamental understanding of the cognition and adaptation needs of an intelligence-driven patient care approach to reduce medical errors. Realizing such an intelligent physical system would allow for augmenting physician capabilities. If one considers an operating room of the future, one can imagine scenarios where data is collected from, and shared with, all medical personnel including the surgeon, the supporting medical technicians, and anesthesiologists. In addition, artificial intelligence could be harnessed to look for unseen patterns in patient care. This operating room of the future will only be possible by establishing a new paradigm that includes medical devices with embedded smart and autonomous features. Such an intelligent physical system would gather knowledge from support personnel, sensors and diagnostics, and interpret physician intent and provide suggestions and diagnostic feedback in real-time. To provide real-world evaluation of this approach, the project will focus on robotic capsule endoscopy, with an intent to have immediate impact in conventional gastroenterology procedures. In pursuit of this goal, this project addresses three research objectives: the first objective focuses on robotic capsule endoscopy perception and control; the second objective formulates the perception and diagnostic support requirements to augment physician performance; and the third objective integrates multimodal, multi-label, temporal data analytics for intelligent physician support.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

想象一下，在不久的将来，一个需要手术的病人将吞下一个小型移动的机器人，这个机器人可以自动执行手术，没有任何外部切口或疼痛。这样的机器人有可能使国家的最先进的外科手术的概念成为现实，通过提供一个不受约束的移动的平台，以可视化，操纵和外科手术治疗组织。该项目的战略还将利用围绕机器人和计算机科学的兴奋，并利用研究人员的卓越基础设施进行教育创新和推广，为学生提供新的，鼓舞人心的教育体验。最后，该项目的成果可以广泛地影响其他一些领域，将受益于开发的新方法，包括搜索和救援，建设和维护，以及远程成像，其中环境是动态的或反复检查后发生变化。该项目的目标是获得一个基本的认知和适应需求的智能驱动的病人护理方法，以减少医疗错误的理解。实现这样的智能物理系统将允许增强医生的能力。如果考虑未来的手术室，可以想象从所有医务人员（包括外科医生、支持医疗技术人员和麻醉师）收集数据并与之共享的场景。此外，人工智能可以用来寻找病人护理中看不见的模式。未来的手术室只有通过建立一个新的范例才有可能，其中包括具有嵌入式智能和自主功能的医疗设备。这种智能物理系统将从支持人员、传感器和诊断中收集知识，并解释医生的意图，实时提供建议和诊断反馈。为了对这种方法进行真实世界的评估，该项目将重点关注机器人胶囊内窥镜，旨在对传统的胃肠病学程序产生直接影响。为了实现这一目标，本项目提出了三个研究目标：第一个目标侧重于机器人胶囊内窥镜的感知和控制;第二个目标制定感知和诊断支持要求，以增强医生的表现;第三个目标是将多模式，多标签，该奖项反映了NSF的法定使命，并通过使用基金会的学术价值和更广泛的影响审查标准。

项目成果

Learning Robust Distance Metric with Side Information via Ratio Minimization of Orthogonally Constrained L21-Norm Distances

• DOI: 10.24963/ijcai.2019/417
• 发表时间: 2019-08
• 作者: Kai Liu;Lodewijk Brand;Hua Wang;F. Nie

On Mean-Optimal Robust Linear Discriminant Analysis

• DOI: 10.1109/icdm54844.2022.00129
• 发表时间: 2022-11
• 期刊: 2022 IEEE International Conference on Data Mining (ICDM)
• 作者: Xiangyu Li;Hua Wang

Learning Robust Multilabel Sample Specific Distances for Identifying HIV-1 Drug Resistance

• DOI: 10.1089/cmb.2019.0329
• 发表时间: 2019-11-15
• 期刊: JOURNAL OF COMPUTATIONAL BIOLOGY
• 影响因子: 1.7
• 作者: Brand, Lodewijk;Yang, Xue;Nie, Feiping
• 通讯作者: Nie, Feiping

Learning Strictly Orthogonal p-Order Nonnegative Laplacian Embedding via Smoothed Iterative Reweighted Method

• DOI: 10.24963/ijcai.2019/561
• 发表时间: 2019-08
• 作者: Haoxuan Yang;Kai Liu;Hua Wang;F. Nie

Learning Semi-Supervised Representation Enrichment Using Longitudinal Imaging-Genetic Data

使用纵向成像遗传数据学习半监督表示丰富

• DOI: 10.1109/bibm49941.2020.9313310
• 发表时间: 2020
• 期刊: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM
• 作者: Seo, Hoon;Brand, Lodewijk;Wang, Hua
• 通讯作者: Wang, Hua