Abstract

With the advances in the microfabrication of analogue front-end devices, and embedded and signal processing technology, it has now become possible to devise miniaturized health monitoring kits for non-invasive real time monitoring at any location. The current commonly available kits only measure singleton physiological parameters, and a composite analysis that covers all vital signs and trauma scores seems to be missing with these kits. The research aims at using vital signs and other physiological parameters to calculate trauma scores National Early Warning Score (NEWS), Revised Trauma Score (RTS), Trauma Score - Injury Severity Score (TRISS) and Prediction of survival (Ps), and to log the trauma event to electronic health records using standard coding schemes. The signal processing algorithms were implemented in MATLAB and could be ported to TI AM335x using MATLAB/Embedded Coder. Motion artefacts were removed using a level ‘5’ stationary wavelet transform and a ‘sym4’ wavelet, which yielded a signal-to-noise ratio of 27.83 dB. To demonstrate the operation of the device, an existing Physionet, MIMIC II Numerics dataset was used to calculate NEWS and RTS scores, and to generate the correlation and regression models for a clinical class of patients with respiratory failure and admitted to Intensive Care Unit (ICU). Parameters such as age, heart rate, Systolic Blood Pressure (SysBP), respiratory rate, and Oxygen Saturation (SpO2) as predictors to Ps, showed significant positive regressions of 93% at p < 0.001. The NEWS and RTS scores showed no significant correlation (r = 0.25, p < 0.001) amongst themselves; however, the NEWS and RTS together showed significant correlations with Ps (blunt) (r = 0.70, p < 0.001). RTS and Ps (blunt) scores showed some correlations (r = 0.63, p < 0.001), and the NEWS score showed significant correlation (r = 0.79, p < 0.001) with Ps (blunt) scores. Global Positioning System (GPS) system was built into the kit to locate the individual and to calculate the shortest path to the nearest healthcare center using the Quantum Geographical Information System (QGIS) Network Analysis tool. The physiological parameters from the sensors, along with the calculated trauma scores, were encoded according to a standard Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) coding system, and the trauma information was logged to electronic health records using Fast Health Interoperability Resources (FHIR) servers. The FHIR servers provided interoperable web services to log the trauma event information in real time and to prepare for medical emergencies.

Highlights

  • This research begins with a literature review on various wearable monitoring equipment used in healthcare, emphasizing on the need for a composite sensor kit

  • Several wearable health monitoring kits currently exist in the market that focus on individual physiological parameter monitoring, such as the Electrocardiograph (ECG), Electromyography (EMG), the Galvanic Skin Response (GSR), with very common ones being the ‘AliveCor’ and ‘Shimmer’ sensing kits [1,2,3]

  • Other vital signs such as the blood pressure and respiratory rate are not measured by these kits, and they are measured after the patient is admitted to the Intensive Care Unit (ICU) after the trauma episode has occurred, which could cause a delay in treating the patient

Read more

Summary

Introduction

This research begins with a literature review on various wearable monitoring equipment used in healthcare, emphasizing on the need for a composite sensor kit. E.g., an ECG module, can only measure the biopotential, as a composite sensor; with additional modules such as the Pulse Oximeter sensor, other physiological parameters from a human subject can be measured simultaneously These readings, collectively, can be used to calculate trauma scores in real-time and they can be used to estimate the prediction of survival in patients. Several wearable health monitoring kits currently exist in the market that focus on individual physiological parameter monitoring, such as the Electrocardiograph (ECG), Electromyography (EMG), the Galvanic Skin Response (GSR), with very common ones being the ‘AliveCor’ and ‘Shimmer’ sensing kits [1,2,3]. Location awareness is built into the device, which locates the nearest healthcare service provider and calculates the shortest path to reaching the healthcare provider

Objectives
Methods
Findings
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call