← Back to all news
arXiv AI

The Entropy Triangle Method (ETM): A novel framework for the prevention of cardiac arrhythmia with a review of more than 10,000 patients

The Entropy Triangle Method (ETM) is a new framework designed to predict cardiac arrhythmias. It combines feature engineering, entropy triangle oversampling, and disease prediction, and was tested on a 12‑lead ECG database of 10,646 patients with 11 heart rhythm categories. The study reports that the method achieves over 85% accuracy for non‑sinus rhythms, with support vector classifiers and a novel oversampling technique termed "shark scent" yielding the best performance.

Related stories

arXiv Machine Learning
Aug 20

Transforming Heart Disease Prediction with Advanced Machine Learning Techniques

The study evaluates several machine‑learning classifiers for predicting heart disease using two public datasets, each with 14 health‑related attributes. Performance metrics such as MAE, RAE, accuracy, precision, recall, and F‑measure were used, revealing that SVM performed best on the UCI data while Simple Cart excelled on the Kaggle data. The authors conclude that well‑tuned ML models can aid early heart‑disease diagnosis and suggest future work on hybrid methods and newer datasets.

By Sami Ullah, Muhammad Mohsin Khan
More like this →
arXiv AI
Sep 7

A Hybrid Predictive Ensemble of Machine Learning and Deep Neural Networks for Early Cardiovascular Disease Risk Assessment

The paper presents a hybrid predictive ensemble that merges machine learning and deep neural network techniques to detect and prognosticate cardiovascular disease early. It processes real‑time physiological data from IoMT devices, applying preprocessing, feature selection, and optimized classifiers (SVM, Random Forest, XGBoost) within an ensemble architecture. The cloud‑based system achieves higher accuracy, fewer false positives, and consistent performance on real‑world datasets, supporting continuous patient monitoring and clinical decision support.

By Balaji Venkateswaran
More like this →
arXiv Machine Learning
Sep 14

A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients

The paper presents a new labelled ICU dataset and benchmarks for detecting atrial fibrillation (AF) from electrocardiograms (ECGs). It compares three AI approaches—feature‑based classifiers, deep learning, and ECG foundation models—across Canadian ICU data and the 2021 PhysioNet challenge, finding that ECG foundation models with transfer learning achieve the highest F1 score (0.89). The study demonstrates the feasibility of automated AF monitoring in ICU settings and provides resources for further research.

By Sarah Nassar, Nooshin Maghsoodi, Sophia Mannina, Shamel Addas, Stephanie Sibley, Gabor Fichtinger, David Pichora, David Maslove, Purang Abolmaesumi, Parvin Mousavi
fine-tuningbenchmarks
More like this →
arXiv AI
Aug 12

LVCG: Learning ECG Representations in the Latent Vectorcardiogram Space

arXiv:2605. 31249v2 Announce Type: replace-cross Abstract: Electrocardiography (ECG) is a cornerstone of cardiac assessment, making the learning of informative ECG representations fundamental to tasks ranging from disease diagnosis to clinical report generation.

By Bosong Huang, Panzhen Zhao, Zengxiang Li, Patricia Lee, Wei Jin, Alan Wee-Chung Liew, Ming Jin, Shirui Pan
diffusion
More like this →
arXiv Machine Learning
Jul 28

Beyond Local Inspection: Global, Guideline-Grounded Evaluation of Post-hoc XAI Methods for ECG Classification

arXiv:2607. 24035v1 Announce Type: cross Abstract: Explainable AI (XAI) is used to assess whether artificial intelligence models rely on meaningful patterns, yet explanations that appear plausible for individual predictions may systematically misrepresent model behavior.

By Nils Gumpfer, Michael Guckert, Samuel Sossalla, Birgit A{\ss}mus, Jennifer Hannig
computer-vision
More like this →