I-Cops: AI-based Heart Sound Screening for Early-Stage Heart Disease

I-Cops：基于人工智能的早期心脏病心音筛查

• 批准号: 2042851
• 负责人: Joshua Hutcheson
• 金额: $ 5万
• 依托单位: Florida International University
• 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: 2020-08-01 至 2022-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2042851&HistoricalAwards=false
• 关键词: Cops; AI; based; Heart; Sound

The broader impact/commercial potential of this I-Corps project is the development of a non-invasive screening tool that will allow physicians to accurately and objectively screen for cardiovascular diseases, regardless of symptom presence. Cardiovascular diseases are often only diagnosed in late stages after heart function is severely diminished. Early detection of asymptomatic patients could lead to less invasive or earlier treatment to prevent disease progression and identify new late-stage patients in need of life-saving procedures. The proposed technology discriminates between abnormal and normal sounds, using artificial intelligence for improved efficiency and accuracy in cardiovascular screening. This I-Corps project is based on the development of an artificial intelligence-based diagnostic algorithm that uses heart sounds recorded from a digital stethoscope, similar to the devices currently used by doctors during routine physical exams, to classify cardiovascular disease stage. The proposed technology uses a database that correlates heart sounds to disease stage and cardiac function. In addition, the proposed technology standardizes and analyzes descriptors of sound to reduce user-dependent disease classification error.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I-Corps项目的更广泛的影响/商业潜力是开发一种非侵入性筛查工具，使医生能够准确客观地筛查心血管疾病，无论是否存在症状。心血管疾病通常只有在心脏功能严重下降后的晚期才能被诊断出来。早期发现无症状患者可能导致侵入性较小或早期治疗，以防止疾病进展并确定需要挽救生命的新晚期患者。该技术可以区分异常和正常声音，使用人工智能来提高心血管筛查的效率和准确性。 这个I-Corps项目是基于开发一种基于人工智能的诊断算法，该算法使用数字听诊器记录的心音，类似于医生目前在常规体检中使用的设备，对心血管疾病阶段进行分类。这项技术使用了一个数据库，将心音与疾病阶段和心脏功能联系起来。 此外，拟议中的技术，语音识别和分析的声音，以减少用户依赖的疾病分类错误的描述符。这一奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。