PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
January 17, 2024Jurnal Teknologi Terapan G-TechOpen Access

Enhancing Cardiac Anomaly Detection through Deep Learning Autoencoder: An In-Depth Analysis Using the PTB Diagnostic ECG Database

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Cardiovascular diseases are the leading cause of mortality worldwide, necessitating advancements in early anomaly detection from electrocardiogram signals.

Does a CNN-based autoencoder improve the detection of ECG anomalies compared to traditional MLP models in the PTB Diagnostic ECG Database?

Population

ECG signals from the PTB Diagnostic ECG Database

Comparison

CNN-based autoencoder architecture vs traditional MLP models

Authors

GAGregorius Airlangga

Discussion

Loading...

Member takes

Overview

CNN autoencoder may aid ECG anomaly research; leaves open clinical adoption without prospective validation.

Structured PICO

Does a CNN-based autoencoder improve the detection of ECG anomalies compared to traditional MLP models in the PTB Diagnostic ECG Database?

P
Population
ECG signals from the PTB Diagnostic ECG Database
I
Intervention
Convolutional neural network (CNN)-based autoencoder architecture with a refined thresholding strategy
C
Comparator
Traditional Multi-Layer Perceptron (MLP) models
O
Outcome
Detection of ECG anomalies (accuracy and F1 score)surrogate

A novel CNN-based autoencoder architecture demonstrates 71.16% accuracy and 73% F1 score in detecting ECG anomalies, outperforming traditional MLP models.

Cite This Study

Gregorius Airlangga (2024) studied this question.

synapsesocial.com/papers/6a8a8ff506e1858e55de9651https://doi.org/10.33379/gtech.v8i1.3921
View Full Paper
Ask AI
Bookmark
Share