SBIR Phase I: A Cloud-based, AI-enabled ECG Analysis Platform for More Efficient Arrhythmia Detection

SBIR 第一阶段：基于云、支持人工智能的心电图分析平台，可更有效地检测心律失常

• 批准号: 2025951
• 负责人: Peng Zhang
• 金额: $ 25.6万
• 依托单位: ZBEATS, 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: 2020-09-01 至 2021-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2025951&HistoricalAwards=false
• 关键词: SBIR; Phase; Cloud; based; AI

The broader impact /commercial potential of this Small Business Innovation Research (SBIR) Phase I project is help cardiologists with new tools for electrocardiogram (ECG) monitoring, classifying heartbeats and detecting irregular rhythms. This project will develop a system that uses machine learning to monitor heart condition and enable advanced, accurate detection of potential problems, saving lives and reducing health care costs. It will leverage novel algorithms and effective interactive tools to improve care.This Small Business Innovation Research (SBIR) Phase I project will develop machine learning algorithms and annotation tools to automate ECG analysis. Two machine learning (ML) algorithms will be developed. The first ML method will consist of two stages: 1) process single cardiac beat classification; and 2) cluster them into ECG waveform templates to detect and classify arrhythmia. Three tools will be developed for further disambiguation. Technical tasks include: (a) test the accuracy of the ML algorithms per ANSI/AAMI EC57:2012; (b) evaluate the effectiveness of interactive tools with clinical advisors and potential users.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.

这个小型企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力是帮助心脏病专家使用心电图（ECG）监测、心跳分类和检测不规则节律的新工具。 该项目将开发一个系统，使用机器学习来监测心脏状况，并实现对潜在问题的先进、准确检测，从而挽救生命并降低医疗成本。它将利用新的算法和有效的交互式工具来改善护理。这个小型企业创新研究（SBIR）第一阶段项目将开发机器学习算法和注释工具，以自动化ECG分析。 将开发两种机器学习（ML）算法。第一种ML方法将包括两个阶段：1）处理单次心跳分类;以及2）将它们聚类到ECG波形模板中以检测和分类心律失常。为进一步消除歧义，将开发三种工具。 技术任务包括：（a）根据ANSI/AAMI EC 57：2012测试ML算法的准确性;（B）与临床顾问和潜在用户一起评估交互工具的有效性。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。