Deep Learning-Based Non-invasive Fetal Cardiac Arrhythmia Detection

Sharma, Kamakshi; Masood, Sarfaraz

doi:10.1007/978-981-16-3067-5_38

Cited by 11 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, the group from Children’s National described a new frequency-based technique for attenuating the maternal ECG to enhance and extract the fECG [ 118 ]. Ongoing efforts utilize artificial intelligence, including artificial neural networks and deep learning models, to detect fetal arrhythmias [ 119 , 120 , 121 , 122 ].…”

Section: Diagnostic Toolsmentioning

confidence: 99%

Diagnosis and Management of Fetal Arrhythmias in the Current Era

Killen,

Strasburger

2024

JCDD

View full text Add to dashboard Cite

Diagnosis and management of fetal arrhythmias have changed over the past 40–50 years since propranolol was first used to treat fetal tachycardia in 1975 and when first attempts were made at in utero pacing for complete heart block in 1986. Ongoing clinical trials, including the FAST therapy trial for fetal tachycardia and the STOP-BLOQ trial for anti-Ro-mediated fetal heart block, are working to improve diagnosis and management of fetal arrhythmias for both mother and fetus. We are also learning more about how “silent arrhythmias”, like long QT syndrome and other inherited channelopathies, may be identified by recognizing “subtle” abnormalities in fetal heart rate, and while echocardiography yet remains the primary tool for diagnosing fetal arrhythmias, research efforts continue to advance the clinical envelope for fetal electrocardiography and fetal magnetocardiography. Pharmacologic management of fetal arrhythmias remains one of the most successful achievements of fetal intervention. Patience, vigilance, and multidisciplinary collaboration are key to successful diagnosis and treatment.

show abstract

Section: Diagnostic Toolsmentioning

confidence: 99%

Diagnosis and Management of Fetal Arrhythmias in the Current Era

Killen,

Strasburger

2024

JCDD

View full text Add to dashboard Cite

show abstract

“…With significant advancements in deep learning technologies, numerous studies have used neural networks to extract fetal ECG signals without separating the maternal ECG [22][23]. Zhong et al employed a one-dimensional convolutional neural network (CNN) to detect fetal QRS complexes without removing the maternal ECG signal, aiming for a similar goal as this study, achieving an accuracy of 75.33%, a recall rate of 80.54%, and an F-1 score of 77.85% [24].…”

Section: Introductionmentioning

confidence: 96%

A Non-Invasive Fetal QRS Complex Detection Method Based on a Multi-Feature Fusion Neural Network

Huang,

Yu,

Shan

et al. 2024

Preprint

View full text Add to dashboard Cite

Fetal heart monitoring, as a crucial part of fetal monitoring, can timely and accurately reflect the fetus's health status. To address the issues of high computational cost, inability to observe fetal heart morphology, and insufficient accuracy associated with the traditional method of calculating fetal heart rate using a four-channel maternal electrocardiogram (ECG), a method for extracting fetal QRS complexes from a single-channel non-invasive fetal ECG based on a multi-feature fusion neural network is proposed. Firstly, a signal entropy data quality detection algorithm based on the blind source separation method is designed to select maternal ECG signals that meet the quality requirements from all channel ECG data, followed by data preprocessing operations such as denoising and normalization on the signals. After being segmented by the sliding window method, the maternal ECG signals are calculated as data in four modes: time domain, frequency domain, time-frequency domain, and data eigenvalues. Finally, the deep neural network using three multi-feature fusion strategies—feature-level fusion, decision-level fusion, and model-level fusion—achieves the effect of quickly identifying fetal QRS complexes. Among the proposed networks, the one with the best performance has an accuracy of 95.85%, sensitivity of 97%, specificity of 95%, and PPV (Positive Predictive Value) of 95%. This method, employing the sliding window technique and lightweight deep neural networks, can quickly and accurately identify fetal QRS complexes from single-channel maternal ECG signals, laying the foundation for home-based fetal QRS shape recognition and fetal risk prediction.

show abstract