SBIR Phase II: A Therapeutic Machine-Learned Triage Application For Early Detection and Triage of COPD Exacerbations

SBIR 第二阶段：用于早期检测和分诊 COPD 恶化的机器学习分诊治疗应用

• 批准号: 1950994
• 负责人: Sumanth Swaminathan
• 金额: $ 74.78万
• 依托单位: E-THERA, INC.
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-15 至 2022-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1950994&HistoricalAwards=false
• 关键词: SBIR; Phase; II; Therapeutic; Machine

The broader/commercial impact of SBIR Phase II project aims to reduce significant disease flare-ups in patients with Chronic Obstructive Pulmonary Disease (COPD), increase in-patient quality-of-life, and reduce expensive and unnecessary healthcare utilization. COPD is one of the leading chronic conditions driving potentially avoidable hospital admissions, accounting for an estimated $25 B in 2018 patient care costs. Current at-home care support for COPD patients is often completely missing or consists of action plans that fail to provide effective, individualized care. Integrating health management and a smart triage system offering instant healthcare guidance has the potential to reduce unnecessary COPD hospitalization and provide long-term maintenance treatment of COPD symptoms. The proposed project will develop an easy-to use, personalized triage application that catches disease degeneration early, tracks patient health history, and provides decision support to guide patients appropriately. Moreover, an easily accessible, highly accurate, convenient solution can empower patients to make better health decisions early. This SBIR Phase II project focuses on optimizing and deploying a triage application that provides personalized decision support and therapeutic benefit to patients with COPD. The proposed project will validate this application for a new population and test the integrated system. Specific technical tasks include the expansion of algorithms to include jointly diagnosed COPD-asthma patients, an important population at risk, as well as optimization of configurations for usability and performance.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.

SBIR II期项目的更广泛/商业影响旨在减少慢性阻塞性肺疾病（COPD）患者的重大疾病发作，提高住院患者的生活质量，并减少昂贵和不必要的医疗保健使用。COPD是导致可能避免的住院的主要慢性疾病之一，在2018年的患者护理费用中估计占25 B美元。目前对COPD患者的家庭护理支持通常完全缺失或由无法提供有效的个性化护理的行动计划组成。 整合健康管理和提供即时医疗指导的智能分诊系统有可能减少不必要的COPD住院治疗，并提供COPD症状的长期维持治疗。拟议的项目将开发一个易于使用的个性化分流应用程序，早期捕获疾病退化，跟踪患者健康史，并提供决策支持，以适当地指导患者。 此外，一个易于访问、高度准确、方便的解决方案可以使患者尽早做出更好的健康决策。SBIR第二阶段项目的重点是优化和部署一个分诊应用程序，为COPD患者提供个性化的决策支持和治疗益处。拟议的项目将为新的人口验证这一应用程序，并测试综合系统。 具体的技术任务包括将算法扩展到包括共同诊断的COPD-哮喘患者，一个重要的风险人群，以及优化配置的可用性和性能。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

A Machine Learning Methodology for Identification and Triage of Heart Failure Exacerbations.

• DOI: 10.1007/s12265-021-10151-7
• 发表时间: 2022-03
• 期刊: Journal of cardiovascular translational research
• 影响因子: 3.4
• 作者: Morrill J;Qirko K;Kelly J;Ambrosy A;Toro B;Smith T;Wysham N;Fudim M;Swaminathan S
• 通讯作者: Swaminathan S