Development of a Flexible Smart Wearable Oximeter Insole for Monitoring SpO2 Levels of Diabetics’ Foot Ulcer

Abstract

This work presents the development of a fully functional prototype of a wearable smart shoe insole that can monitor arterial oxygen saturation (SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) levels at the foot of a diabetic patient using photoplethysmography (PPG) signals. Continuous monitoring of SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> levels at foot in patients with diabetic foot ulcer (DFU) can provide critical information on the severity of the ulcer, the wound healing process, and alerting clinicians for critical limb ischemia. The developed oximetry system seamlessly integrates the Internet of things (IoT) via a custom-developed Android mobile application, thus enabling “at-home” monitoring. Twenty healthy subjects were tested, and the insole oximeter was able to successfully estimate SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> levels at the toe. An average error of ≈ 2.6% was calculated for the measured/estimated SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> levels at the subjects’ toe when compared to a reference oximeter attached to the finger. Perfusion Index (PI) - which represents the blood flow/supply in tissues - was used as a method for validating the oximeter readings. It was observed that fingers (index fingers) generally have larger PI values when compared to the toe, while PI results of both monitoring sites were in the acceptable range. In addition, a dataset was formed for the twenty test subjects, and machine learning (ML) techniques were applied to predict the SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> level and the site of measurement (Finger or Toe), using multiple linear regression and classification methods. The ML results show that AC components of the PPG signals have a more significant contribution to the SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> estimations when compared to the DC components. In addition, KNN (K=1) classifier, was able to successfully predict the monitoring sites, with a test accuracy of 96.86%.