Development of GSM Modem for Transfer of ECG Signals in Remote Patient Monitoring

Badarov, Dimiter; Iliev, Ivo; Tabakov, Serafim

doi:10.1109/et55967.2022.9920292

Cited by 1 publication

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lead-specific carrier frequencies are uniformly distributed in 300 Hz steps, fitting within the limited bandwidth (300–3000 Hz) of common GSM microphones. The bandwidth is in accordance with our previous experimental study for the audio characteristics of six mobile phones of different classes [ 46 ]. F D = 125 Hz: the frequency deviation, which has a constant value for all ECG leads.…”

Section: Methodssupporting

confidence: 84%

Section: Methodssupporting

confidence: 84%

“…Our team co-authored five of six studies we could find using a similar wireless interface that generates a sonified ECG stream and captures it with a GSM microphone [ 41 , 42 , 43 , 44 , 45 , 46 ], where all developments were designed for single-channel ECG processing: Remote recording of ECG between fingers with a commercial AliveCor device, found in a public database for screening of atrial fibrillation, including >12 k ECG recordings up to 60 s in duration, published for the PhysioNet/Computing in Cardiology Challenge 2017 [ 42 ]. Specifically, after the analogue-to-audio conversion of the ECG signal, the patient module transmitted acoustic data to a smartphone or tablet microphone, using a 19 kHz carrier frequency and a 200 Hz/mV modulation index.…”

Section: Methodsmentioning

confidence: 99%

“… Fully analogue hardware solution for sonification that could convert analogue ECG signals to an audio stream using a voltage-controlled oscillator [ 44 ]. Study of the audio characteristics of mobile phones [ 45 ] and development of a GSM modem [ 46 ] in the context of transmission of biosignals converted to sound [ 45 ]. …”

Section: Methodsmentioning

confidence: 99%

“…Study of the audio characteristics of mobile phones [ 45 ] and development of a GSM modem [ 46 ] in the context of transmission of biosignals converted to sound [ 45 ].…”

Section: Methodsmentioning

confidence: 99%

See 4 more Smart Citations

Application of Convolutional Neural Network for Decoding of 12-Lead Electrocardiogram from a Frequency-Modulated Audio Stream (Sonified ECG)

Krasteva,

Iliev,

Tabakov

2024

Sensors

View full text Add to dashboard Cite

Research of novel biosignal modalities with application to remote patient monitoring is a subject of state-of-the-art developments. This study is focused on sonified ECG modality, which can be transmitted as an acoustic wave and received by GSM (Global System for Mobile Communications) microphones. Thus, the wireless connection between the patient module and the cloud server can be provided over an audio channel, such as a standard telephone call or audio message. Patients, especially the elderly or visually impaired, can benefit from ECG sonification because the wireless interface is readily available, facilitating the communication and transmission of secure ECG data from the patient monitoring device to the remote server. The aim of this study is to develop an AI-driven algorithm for 12-lead ECG sonification to support diagnostic reliability in the signal processing chain of the audio ECG stream. Our methods present the design of two algorithms: (1) a transformer (ECG-to-Audio) based on the frequency modulation (FM) of eight independent ECG leads in the very low frequency band (300–2700 Hz); and (2) a transformer (Audio-to-ECG) based on a four-layer 1D convolutional neural network (CNN) to decode the audio ECG stream (10 s @ 11 kHz) to the original eight-lead ECG (10 s @ 250 Hz). The CNN model is trained in unsupervised regression mode, searching for the minimum error between the transformed and original ECG signals. The results are reported using the PTB-XL 12-lead ECG database (21,837 recordings), split 50:50 for training and test. The quality of FM-modulated ECG audio is monitored by short-time Fourier transform, and examples are illustrated in this paper and supplementary audio files. The errors of the reconstructed ECG are estimated by a popular ECG diagnostic toolbox. They are substantially low in all ECG leads: amplitude error (quartile range RMSE = 3–7 μV, PRD = 2–5.2%), QRS detector (Se, PPV > 99.7%), P-QRS-T fiducial points’ time deviation (<2 ms). Low errors generalized across diverse patients and arrhythmias are a testament to the efficacy of the developments. They support 12-lead ECG sonification as a wireless interface to provide reliable data for diagnostic measurements by automated tools or medical experts.

show abstract

Section: Methodssupporting

confidence: 84%

Section: Methodssupporting

confidence: 84%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…Study of the audio characteristics of mobile phones [ 45 ] and development of a GSM modem [ 46 ] in the context of transmission of biosignals converted to sound [ 45 ].…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations