Transforming Seismocardiograms Into Electrocardiograms by Applying Convolutional Autoencoders

Haescher, Marian; Höpfner, Florian; Chodan, Wencke; Kraft, Dimitri; Aehnelt, Mario; Urban, Bodo

doi:10.1109/icassp40776.2020.9053130

Cited by 8 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To provide this surplus of oxygen, the breathing rate and the heart rate increase. Empirical knowledge and experiences in handling data from biomedical parameters gathered with wearable devices has been accumulated in prior studies [18][19][20]. Especially the heart rate and heart rate variability have been identified as valid stress markers [21,22].…”

Section: Physiological Stress Modelmentioning

confidence: 99%

A clinical field study aimed at Digitally identifying and minimizing stressors at the Palliative care workplace by measuring stress continuously through wearable sensors (DiPa): Study Design (Preprint)

Chodan,

Seehausen,

Höpfner

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND Nursing in palliative medicine combines primary patient care with the special challenges of this medical field, e.g., handling the processes of dying, grief, and death. These cause high stress levels and burden on the nursing staff, fostering early drop-outs of working life because of physical or psychological disorders like burnout. OBJECTIVE DiPa is a prospective study which investigates the feasibility of measuring the burden and its causes in palliative care using methods of subjective and objective stress detection. Based on these results, stress-reducing interventions are to be deduced and evaluated. In this paper, we present our study protocol. METHODS The nursing staff of an inpatient university palliative hospital ward gathered data over 6 weeks. Each was equipped with a smart wrist band and a smartphone which continuously measures physiological and ambient parameters throughout their working days. These objective data were enriched by subjective measurements: a questionnaire at the beginning of the study, which assessed multiple potential stressful situations and constellations in the private and working environment, and ecological momentary assessments (EMA) during the workday, which were prompted by scanning near-field communication (NFC) tags placed at different locations on the ward. The ongoing data analyses will be processed by using computer algorithms partly programmed specifically for this study and partly drawn from existing libraries, such as toolboxes for neurophysiological signal processing for Python. Comparisons between subjective and objective measures and group comparisons between variables of interest will be made using inferential statistics, including regression analyses and analyses of variance. Data analysis using machine learning algorithms will be implemented once sufficient data will have been gathered. RESULTS As of April 2024, 12 of 18 nurses of the Palliative Care Unit consented to participate in our study. CONCLUSIONS The DiPa study aims at testing the feasibility of measuring and merging subjective and objective stress parameters in a palliative care nurses. CLINICALTRIAL The DiPa study has been registered in the German Register for Clinical Studies on February 10th, 2021 (DRKS, ID DRKS00024425A).

show abstract

Section: Physiological Stress Modelmentioning

confidence: 99%

A clinical field study aimed at Digitally identifying and minimizing stressors at the Palliative care workplace by measuring stress continuously through wearable sensors (DiPa): Study Design (Preprint)

Chodan,

Seehausen,

Höpfner

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Mora et al [20] explored the application of unsupervised learning on SCG signals through the use of a variational autoencoder which was used to extract user information from their corresponding SCG waveforms. Haescher et al [21] proposed a strategy which aims to transform SCG signals into ECG signals using a convolutional autoencoder. This was followed by the use of the Pan Tompkins algorithm [22] for R-peak detection on the resultant of the transformation.…”

Section: Related Workmentioning

confidence: 99%

End-to-End Deep Learning for Reliable Cardiac Activity Monitoring using Seismocardiograms

Suresh¹,

Pranav²,

Vijayaraghavan³

2020

Preprint

View full text Add to dashboard Cite

Continuous monitoring of cardiac activity is paramount to understanding the functioning of the heart in addition to identifying precursors to conditions such as Atrial Fibrillation. Through continuous cardiac monitoring, early indications of any potential disorder can be detected before the actual event, allowing timely preventive measures to be taken. Electrocardiography (ECG) is an established standard for monitoring the function of the heart for clinical and non-clinical applications, but its electrode-based implementation makes it cumbersome, especially for uninterrupted monitoring. Hence we propose SeismoNet, a Deep Convolutional Neural Network which aims to provide an end-to-end solution to robustly observe heart activity from Seismocardiogram (SCG) signals. These SCG signals are motion-based and can be acquired in an easy, user-friendly fashion. Furthermore, the use of deep learning enables the detection of R-peaks directly from SCG signals in spite of their noise-ridden morphology and obviates the need for extracting hand-crafted features. SeismoNet was modelled on the publicly available CEBS dataset and achieved a high overall Sensitivity and Positive Predictive Value of 0.98 and 0.98 respectively.

show abstract

“…The application of unsupervised learning on SCG signals was explored by Mora et al [48] using variational autoencoder to extract user heart conditions from corresponding SCG waveforms. Haescher et al [49] has used convolutional autoencoder to transform SCG signals into ECG signals and used the Pan Tompkins algorithm [50] for detecting the R-peak of the signal resulted from the transformation. This algorithm has been applied on ECG signal with noise [51].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Lightweight 1D CNN-LSTM Architecture for Automated ECG Beat-Wise Classification

Obeidat¹,

Alqudah²

2021

View full text Add to dashboard Cite

In this paper we have utilized a hybrid lightweight 1D deep learning model that combines convolutional neural network (CNN) and long short-term memory (LSTM) methods for accurate, fast, and automated beat-wise ECG classification. The CNN and LSTM models were designed separately to compare with the hybrid CNN-LSTM model in terms of accuracy, number of parameters, and the time required for classification. The hybrid CNN-LSTM system provides an automated deep feature extraction and classification for six ECG beats classes including Normal Sinus Rhythm (NSR), atrial fibrillation (AFIB), atrial flutter (AFL), atrial premature beat (APB), left bundle branch block (LBBB), and right bundle branch block (RBBB). The hybrid model uses the CNN blocks for deep feature extraction and selection from the ECG beat. While the LSTM layer will learn how to extract contextual time information. The results show that the proposed hybrid CNN-LSTM model achieves high accuracy and sensitivity of 98.22% and 98.23% respectively. This model is light and fast in classifying ECG beats and superior to other previously used models which makes it very suitable for embedded systems designs that can be used in clinical applications for monitoring heart diseases in faster and more efficient manner.

show abstract

Transforming Seismocardiograms Into Electrocardiograms by Applying Convolutional Autoencoders

Cited by 8 publications

References 42 publications

A clinical field study aimed at Digitally identifying and minimizing stressors at the Palliative care workplace by measuring stress continuously through wearable sensors (DiPa): Study Design (Preprint)

A clinical field study aimed at Digitally identifying and minimizing stressors at the Palliative care workplace by measuring stress continuously through wearable sensors (DiPa): Study Design (Preprint)

End-to-End Deep Learning for Reliable Cardiac Activity Monitoring using Seismocardiograms

A Hybrid Lightweight 1D CNN-LSTM Architecture for Automated ECG Beat-Wise Classification

Contact Info

Product

Resources

About