An Effective Method of Detecting Characteristic Points of Impedance Cardiogram Verified in the Clinical Pilot Study

Karpiel, Ilona; Richter, Monika; Feige, Daniel; Gacek, Adam; Sobotnicki, Aleksander

doi:10.3390/s22249872

Cited by 9 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms are finally used to classify each heartbeat and identify the characteristic points B, C, and X. The effectiveness of the proposed method has been confirmed in clinical pilot studies, demonstrating high accuracy and reliability in identifying the characteristic points of the ICG signal [106]. The technique may improve the accuracy of diagnostics in patients with heart failure, leading to better management and treatment of this condition.…”

Section: Integration Of Ecg Data With Other Modalitiesmentioning

confidence: 90%

Current and Future Use of Artificial Intelligence in Electrocardiography

Sellés

Marina-Breysse

2023

JCDD

View full text Add to dashboard Cite

Artificial intelligence (AI) is increasingly used in electrocardiography (ECG) to assist in diagnosis, stratification, and management. AI algorithms can help clinicians in the following areas: (1) interpretation and detection of arrhythmias, ST-segment changes, QT prolongation, and other ECG abnormalities; (2) risk prediction integrated with or without clinical variables (to predict arrhythmias, sudden cardiac death, stroke, and other cardiovascular events); (3) monitoring ECG signals from cardiac implantable electronic devices and wearable devices in real time and alerting clinicians or patients when significant changes occur according to timing, duration, and situation; (4) signal processing, improving ECG quality and accuracy by removing noise/artifacts/interference, and extracting features not visible to the human eye (heart rate variability, beat-to-beat intervals, wavelet transforms, sample-level resolution, etc.); (5) therapy guidance, assisting in patient selection, optimizing treatments, improving symptom-to-treatment times, and cost effectiveness (earlier activation of code infarction in patients with ST-segment elevation, predicting the response to antiarrhythmic drugs or cardiac implantable devices therapies, reducing the risk of cardiac toxicity, etc.); (6) facilitating the integration of ECG data with other modalities (imaging, genomics, proteomics, biomarkers, etc.). In the future, AI is expected to play an increasingly important role in ECG diagnosis and management, as more data become available and more sophisticated algorithms are developed.

show abstract

Section: Integration Of Ecg Data With Other Modalitiesmentioning

confidence: 90%

Current and Future Use of Artificial Intelligence in Electrocardiography

Sellés

Marina-Breysse

2023

JCDD

View full text Add to dashboard Cite

show abstract

“…Historically, the application of ICG has stagnated in comparison to the ECG mostly due to the lack of standardization and costly apparatuses. However, advances in affordable technology and signal processing techniques led to an increase in both research and clinical utilization of ICG (Karpiel et al, 2022;Sherwood et al, 1990). The rapid development of signal processing methods allows for the detection of previously inaccessible information inside both ECG and ICG that could relate to human behavior and individuality which influenced the promotion of multidisciplinary research and collaboration of domain experts (Merdjanovska & Rashkovska, 2022;Welch et al, 2009).…”

Section: Introductionmentioning

confidence: 99%

CardioPRINT: Biometric identification based on the individual characteristics derived from cardiogram

Tanasković,

Lazarevic,

Knezevic

et al. 2023

Preprint

View full text Add to dashboard Cite

Objective: This paper investigates the potential of cardiogram-derived traits from electrocardiogram (ECG) and impedance cardiogram (ICG) for biometric identification. Additionally, the influence of induced emotions on cardiogram attributes and their impact on identification accuracy is explored.Method: We conduct a comparative evaluation of 7 machine learning classifiers using dataset gathered from 202 individuals to identify the highest-performing classifiers. Subsequently, we analyze three different feature sets employing (ECG-only, ICG-only, and both ECG and ICG). Additionally, we investigate the performance of classifiers under altered emotional states to assess classifiers’ robustness.Results: The analysis demonstrates that models employed with both ECG and ICG have the highest accuracies that are statistically significant. The best-performing Random Forest (RF) model using both ECG and ICG achieves an average accuracy of 97.2%. All models reveal a decrease in classification accuracies (~13%) when they are not trained and tested under identical emotional conditions. Conclusion: Our findings suggest that integration of ECG and ICG-based features could increase the accuracy of identification compared to a single-signal-based approach. Although certain models show slight robustness to altered emotional state, the effect of the emotion is evident and future selection of cardiogram-based features, as well as biometric models, should consider emotional responses.

show abstract

“…The electrical cardiometry (EC) has been proposed as a non-invasive, safe, simple, readily available, user friendly, prompt and non-operator dependent real-time monitor for hemodynamic monitoring in children and infants (5). It relies on the theory that the thorax is a cylinder filled with blood and that there is an inverse relation between the volume of blood and its resistance (impedance) to an electric current therefore this technique delivers a high-frequency, lowmagnitude, alternative current and relies on alterations in thoracic electrical bio-impedance during the cardiac cycle to measure various cardiac parameters that allows for real-time monitoring (6,7). EC technology estimates blood flow and measures cardiac output (CO), cardiac index (CI) (CO normalized for body surface area), stroke volume (SV), and stroke index (SI) (SV normalized for body surface area).…”

Section: Introductionmentioning

confidence: 99%

Electric Cardiometry is not Predictive of Outcome in Full-term Newborns with Respiratory Distress: A Single Center Study

Elmazzahy

El-Houchi

Khater

et al. 2023

Pediatric Sciences Journal

View full text Add to dashboard Cite

Background: Prompt management of respiratory distress (RD) among neonates is lifesaving. Electric cardiometry (EC) is not suitable for diagnosis, but its value in monitoring changes in cardiac parameters over time is in need of verification. Aim of the Work:To study EC hemodynamic parameters predictive ability of outcome in fullterm newborns with RD. Materials and Methods: using electric cardiometry (EC) hemodynamic parameters were studied among 30 full term neonates with RD within the first 10 minutes of life and 2 hours later compared to another 30 without RD. The studied parameters were heart rate variability (HRV), cardiac output (CO), cardiac index (CI), stroke volume (SV), stroke index (SI), thoracic fluid content (TFC), stroke volume variation (SVV), index of contractility (ICON), left ventricular (LV) pre-ejection period (PEP), ejection time (ET), and systemic vascular resistance (SVR). Results: The mean ± SD gestational age of the studied group was 38.20 ± 1.19 weeks, weight was 3.03 ± 0.51 kilogram, females were 15 (50%), and males were 15 (50%) which was comparable to the control group (p=0.584), (p=0.284) and (p=0.436) respectively. The mean Apgar score was less among the RD group; at one minute it was 6 and at 5 minutes was 8 (p=0.0001) and (p=0.002). Initial HRV, CO, CI, SV, SI, TFC, SVV, ICON, LV, PEP, ET, and SVR were not different among both groups but there was a significant decrease in CI (p=0.033), HRV (p=0.030), SI (p = 0.017), and SV (p= 0.016) in the RD group after 2 hours. Those with RD, 20 (66.6%) improved and 10 (33.3%) were admitted to the neonatal intensive unit. Both groups with RD had comparable HRV, CI, CO, SV, SI, TFC, SVV, PEP, ICON, LVET, or SVR in initial and the 2 hour of life assessment (p= 0.860), (p= 0.071), (p= 0.932), (p= 0.260), (p= 0.548), (p= 0.338), (p= 0.744), (p= 0.488), (p= 0.392), (p= 0.983), (p= 0.066) respectively. Conclusion: Hemodynamic parameters assessed by electric cardiometry of full term neonates within 10 minutes of birth was not different among those with RD and those without. Electric cardiometry at 2 hours of life of those with RD was not predictive of outcome.

show abstract

An Effective Method of Detecting Characteristic Points of Impedance Cardiogram Verified in the Clinical Pilot Study

Cited by 9 publications

References 38 publications

Current and Future Use of Artificial Intelligence in Electrocardiography

Current and Future Use of Artificial Intelligence in Electrocardiography

CardioPRINT: Biometric identification based on the individual characteristics derived from cardiogram

Electric Cardiometry is not Predictive of Outcome in Full-term Newborns with Respiratory Distress: A Single Center Study

Contact Info

Product

Resources

About