Development of an AI-based non-invasive Pulse AudioGram monitoring device for arrhythmia screening

Che Wei Lin, Yung Chang, Chou Ching K. Lin, Liang Miin Tsai, Ju Yi Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

An artificial intelligence-based (AI-based) noninvasive Pulse AudioGram (PAG) monitoring device with arrhythmia screening algorithm has been developed in this research study. The PAG monitoring device consists of four components, including an audiogram sensor, an analog-digital converter, a microprocessor, and a data storage unit. The main function of the proposed AI-based non-invasive PAG is to measure the audio signal in radial artery generated by hemodynamics. Hemodynamics under arrhythmia and sinus rhythm (SR) conditions might exhibit different patterns as the heart rhythm becomes irregular under arrhythmia condition. PAG signals of SR and other arrhythmia symptoms such as atrial fibrillation (AF), aortic regurgitation (AR), and congestive heart failure (CHF) were collected during this research. In the experiment results, the proposed method can achieve accuracy of 99.29% when discriminating SR and AF; the proposed method can achieve accuracy of 98.92% when discriminating SR, AF, AR, and CHF. In this study, we have successfully developed an AI-based non-invasive PAG monitoring device for arrhythmia screening, and have plan to use it in on large-scale screening for arrhythmia in the near future.

Original languageEnglish
Title of host publication2017 IEEE Healthcare Innovations and Point of Care Technologies, HI-POCT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages40-43
Number of pages4
ISBN (Electronic)9781538613924
DOIs
Publication statusPublished - 2017 Dec 19
Event2017 IEEE Healthcare Innovations and Point of Care Technologies, HI-POCT 2017 - Bethesda, United States
Duration: 2017 Nov 62017 Nov 8

Publication series

Name2017 IEEE Healthcare Innovations and Point of Care Technologies, HI-POCT 2017
Volume2017-December

Other

Other2017 IEEE Healthcare Innovations and Point of Care Technologies, HI-POCT 2017
Country/TerritoryUnited States
CityBethesda
Period17-11-0617-11-08

All Science Journal Classification (ASJC) codes

  • Health Informatics
  • Instrumentation
  • Health(social science)
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Development of an AI-based non-invasive Pulse AudioGram monitoring device for arrhythmia screening'. Together they form a unique fingerprint.

Cite this