Personalized wearable systems for real-time ECG classification and healthcare interoperability: Real-time ECG classification and FHIR interoperability

Abstract

Abstract-Continuous monitoring of an individual's health using wearable biomedical devices is becoming a norm these days with a large number of wearable kits becoming easily available. Modern wearable health monitoring devices have become easily available in the consumer market, however, realtime analyses and prediction along with alerts and alarms about a health hazard are not adequately addressed in such devices. Taking ECG monitoring as a case study the research paper focusses on signal processing, arrhythmia detection and classification and at the same time focusses on updating the electronic health records database in realtime such that the concerned medical practitioners become aware of an emergent situation the patient being monitored might face. Also, heart rate variability (HRV) analysis is usually considered as a basis for arrhythmia classification which largely depends on the morphology of the ECG waveforms and the sensitivity of the biopotential measurements of the ECG kits, so it may not yield accurate results. Initially, the ECG readings from the 3-Lead ECG analog front-end were de-noised, zero-offset corrected, filtered using recursive least square adaptive filter and smoothed using Savitzky-Golay filter and subsequently passed to the data analysis component with a unique feature extraction method to increase the accuracy of classification. The machine learning models trained on MITDB arrhythmia database (MIT-BIH Physionet) showed more than 97% accuracy using kNN classifiers. Neuralnet fitting models showed mean-squared error of as low as 0.0085 and regression value as high as 0.99. ECG abnormalities based on annotations in MITDB could be classified and these ECG observations could be logged to a server implementation based on FHIR standards. The instruments were networked using IoT (Internet of Things) devices and ECG event observations were coded according to SNOMED coding system and could be accessed in Electronic Health Record by the concerned medic to take appropriate and timely decisions. The system emphasizes on 'preventive care rather than remedial cure' as the next generation personalized health-care monitoring devices become available.

Composite and Wearable Sensor Kit for Location Aware Healthcare Monitoring and Real-Time Trauma Scoring for Survival Prediction.

“…Fast Health Interoperability Resources FHIR is an HL7 standard that provides interoperability specifications for web services and EHR databases and by modelling the trauma scores into FHIR 'Observations' and 'Bundles' of information payload the trauma specific information could be logged into EHR databases for future decision support and to prepare for emergency procedures ahead of time. [34] It was observed that since the analysis was performed on datasets of patients that were admitted to the ICU wards, the NEWS score, the RTS scores and the prediction of survival scores agreed with their health status. The NEWS and the RTS severity scores less than 4 indicated the patients were under severe trauma and this helped to accept the hypothesis.…”

“…Fast Health Interoperability Resources FHIR is an HL7 standard that provides interoperability specifications for web services and EHR databases. [34] A very important application for wearable IoT healthcare monitoring devices is to be able to locate the individual when the trauma related events take place. With the availability of low cost wearable Global Positioning System (GPS) and Global System for Mobile communication / General Packet Radio Service (GSM/GPRS) receivers, which can be embedded into the wearable kits, such a provision can made available.…”

Binary Classifiers for Data Integrity Detection in Wearable IoT Edge Devices

“…5. k-NN has been used for real-time ECG classification as discussed in [14]. In this experiment, the k-NN feature space is 6 dimensional and populated with 512 objects (number of training examples) during the training phase.…”

A Composite and Wearable Sensor Kit for Location-Aware Healthcare Monitoring and Real-Time Trauma Scoring for Survival Prediction

“…The ICD injury matrices are frameworks that are designed to organize ICD-coded injury data into meaningful groupings that are agreed upon by the global medical community. The matrices were developed specifically to facilitate national and international comparability in the presentation of injury statistics [32].…”