Display options
Share it on

IEEE Sens J. 2021 Jul 01;21(13):14281-14289. doi: 10.1109/jsen.2020.3022273. Epub 2020 Nov 03.

Detection of Low Cardiac Index using a Polyvinylidene Fluoride-Based Wearable Ring and Convolutional Neural Networks.

IEEE sensors journal

Sardar Ansari, Jessica R Golbus, Mohamad H Tiba, Brendan McCracken, Lu Wang, Keith D Aaronson, Kevin R Ward, Kayvan Najarian, Kenn R Oldham

Affiliations

  1. Department of Emergency Medicine, University of Michigan, Ann Arbor, MI, 48109 USA.
  2. Department of Internal Medicine, University of Michigan, Ann Arbor, MI 48109 USA.
  3. Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109 USA.
  4. Department of Emergency Medicine and the Biomedical Engineering Department, University of Michigan, Ann Arbor, MI, 48109 USA.
  5. Department of Computational Medicine and Bioinformatics, the Department of Emergency Medicine and the Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI, 48109 USA.

PMID: 34504397 PMCID: PMC8423366 DOI: 10.1109/jsen.2020.3022273

Abstract

This study investigated the use of a wearable ring made of polyvinylidene fluoride film to identify a low cardiac index (≤2 L/min). The waveform generated by the ring contains patterns that may be indicative of low blood pressure and/or high vascular resistance, both of which are markers of a low cardiac index. In particular, the waveform contains reflection waves whose timing and amplitude are correlated with pulse travel time and vascular resistance, respectively. Hence, the pattern of the waveform is expected to vary in response to changes in blood pressure and vascular resistance. By analyzing the morphology of the waveform, our aim was to create a tool to identify patients with low cardiac index. This was done using a convolutional neural network which was trained on data from animal models. The model was then tested on waveforms that were collected from patients undergoing pulmonary artery catheterization. The results indicate high accuracy in classifying patients with a low cardiac index, achieving an area under the receiver operating characteristics and precision-recall curves of 0.88 and 0.71, respectively.

Keywords: Cardiac index; cardiac output; convolutional neural networks; polyvinylidene fluoride; wearable monitoring

References

  1. J Cardiothorac Vasc Anesth. 2011 Dec;25(6):1044-50 - PubMed
  2. Crit Care Med. 2015 Jan;43(1):177-85 - PubMed
  3. Curr Heart Fail Rep. 2006 Sep;3(3):107-13 - PubMed
  4. Br J Anaesth. 2015 Aug;115(2):322-3 - PubMed
  5. Anesth Analg. 2012 Apr;114(4):771-5 - PubMed
  6. World J Cardiol. 2014 Sep 26;6(9):1022-9 - PubMed
  7. J Clin Monit Comput. 2013 Dec;27(6):647-57 - PubMed
  8. Am Heart J. 2009 Aug;158(2):217-23 - PubMed
  9. Sensors (Basel). 2015 Jul 31;15(8):18801-12 - PubMed
  10. Ultrason Imaging. 1979 Oct;1(4):356-67 - PubMed
  11. J Cardiothorac Vasc Anesth. 2011 Oct;25(5):776-9 - PubMed
  12. Anesth Analg. 2011 Oct;113(4):766-76 - PubMed
  13. Adv Mater. 2016 Jun;28(22):4283-305 - PubMed
  14. Anesthesiology. 1998 Dec;89(6):1592-5 - PubMed
  15. Br J Clin Pharmacol. 2011 Mar;71(3):316-30 - PubMed

Publication Types

Grant support