Newly identified electromagnetic problems with medical telemetry systems

Hanada, Eisuke; Ishida, Kai; Kudou, Takato

doi:10.15199/48.2018.02.06

Cited by 15 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Problems with such implementations are related to establishing the connection, maintaining the communication channel, and packet losses. Even at home, if the distance between the transmitter and receiver is large, or there are fences or other sources of signals in the same frequency range, communication may not be possible [ 92 ]. Furthermore, Bluetooth has some security issues while data are transferring [ 93 ].…”

Section: Discussionmentioning

confidence: 99%

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: Discussionmentioning

confidence: 99%

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

show abstract

“…However, electrical devices, especially switched-mode power supplies installed in light-emitting diode (LED) devices, may radiate unwanted emissions and increase BGN [5]. In addition, to promote the safe introduction and operation of WMT, it is necessary to consider effective frequency allocation, range of access, invasive radio waves from out of hospitals, and interference by intermodulation [6][7][8]. Moreover, other wireless communication systems, such as realtime detection systems for dementia, may interfere with WMT because these devices use the same frequency band of WMT and are widely introduced in hospitals [9].…”

Section: Introductionmentioning

confidence: 99%

Novel Estimation Technique for the Carrier-to-Noise Ratio of Wireless Medical Telemetry Using Software-Defined Radio with Machine-Learning

Ishida

2022

Preprint

View full text Add to dashboard Cite

In this study, we developed a novel machine-learning model to estimate the carrier-to-noise ratio (CNR) of wireless medical telemetry (WMT) using time-domain waveform data measured by a low-cost software-defined radio. If the CNR can be estimated automatically, the management of the electromagnetic environment of WMT can be easier. Therefore, we proposed a machine-learning method for estimating CNR. According to the performance evaluation results by 5-segment cross-validation on 704 types of measured data, CNR was estimated with 99.5% R-square and 0.844 dB mean absolute error using a gradient boosting regression tree. The gradient boosting decision tree classifiers predicted whether the CNR exceeded 30 dB with 99.5% accuracy. The proposed method is effective for investigating electromagnetic environments in clinical settings.

show abstract

“…In previous research, although the electromagnetic interference between the WMTS and equipment such as a light-emitting diode (LED) has been demonstrated, the results presented did not represent a performance evaluation of the WMTT itself [3,4,5]. In addition, another report measured the reception limit distance to determine whether a signal can be received [6].…”

Section: Introductionmentioning

confidence: 99%

Fundamental Study of Quantitative Evaluation of Radio Wave Output of Wireless Medical Telemetry Transmitters Operable in Medical Field

Fujii¹,

Kishimoto²,

Inoue³

2020

GJMR

View full text Add to dashboard Cite

Wireless medical telemetry systems (WMTSs) are important medical equipment for monitoring of biological information such as the electrocardiogram of a patient in a remote location in real time. However, because WMTSs have characteristically used channels that are unique to the radio wave spectrum, many institutions have not previously managed WMTSs. Therefore, we examined a method for quantitative evaluation of the radio wave output of a wireless medical telemetry transmitter (WMTT) that can even be implemented in the medical field. In the experiments, we demonstrated the possibility of use of the method for quantitative evaluation of WMTT radio wave output in the medical field using two types of radio wave propagation model: a free-space propagation model and a two-ray ground reflection model. To determine the reference threshold value for use of each model, a breakpoint was found to be important to grasp the change point between short distance and long distance. It was indicated that the measured value was lower than the theoretical value below the breakpoint, while the measured value was slightly higher than the theoretical value beyond the breakpoint.

show abstract

Newly identified electromagnetic problems with medical telemetry systems

Cited by 15 publications

References 3 publications

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

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

Novel Estimation Technique for the Carrier-to-Noise Ratio of Wireless Medical Telemetry Using Software-Defined Radio with Machine-Learning

Fundamental Study of Quantitative Evaluation of Radio Wave Output of Wireless Medical Telemetry Transmitters Operable in Medical Field

Contact Info

Product

Resources

About