JMIR Publications

ABSTRACT

Background:

Abstract—Recently, there has been an increased interest in monitoring health using wearable sensors technologies however, few have focused on breathing. The ability to monitor breathing metrics may have indications both for general health as well as respiratory conditions such as asthma, where long-term monitoring of lung function has shown promising utility.

Objective:

In this paper we characterise a Long Short-Term Memory (LSTM) architecture and predict measures of inter-breath intervals, respiratory rate and the inspiration:expiration ratio from a photoplethsymogram signal.

Methods:

A pulse oximeter was mounted to the left index finger of nine healthy subjects who breathed at controlled respiratory rates. A respiratory band was used to collect a reference signal as a comparison.

Results:

Over a 40 second window the LSTM model predicted breathing metrics with a bias and 95% confidence interval for inspiration time 0.03 s (-1.14, 1.20), expiration time 0.05 s (-1.07, 0.96), respiratory rate 0.12 (-1.5,1.75), inter-breath intervals (-1.29, 1.16) and the I:E ratio 0.00 (-.45, 0.46).

Conclusions:

A trained LSTM model shows acceptable accuracy for deriving breathing metrics, and could be useful for long-term breathing monitoring in health. Its utility in respiratory disease, e.g. asthma warrants further investigation. Clinical Trial: Sydney Local Health District Human Research Ethics Committee (#LNR/16/HAWKE99 ethics approval).