Enhancing Atrial Fibrillation Detection Through Hyperparameter Optimization

Sara Gjorgjieva; Ilinka Ivanoska; Marjan Gusev

cs.LGOct 29, 2026

Enhancing Atrial Fibrillation Detection Through Hyperparameter Optimization

Authors: Sara Gjorgjieva, Ilinka Ivanoska, Marjan Gusev

Organizations: Innovation Dooel, Skopje, North Macedonia · Ss. Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering, North Macedonia

Abstract

This study explores the role of hyperparameter optimization (HPO) in enhancing the detection of Atrial Fibrillation (AF) using both machine learning and deep learning models. We evaluated a range of standard classifiers - Decision Tree, Random Forest, and XGBoost classifiers, alongside deep learning architectures including Recurrent Neural Networks, Deep Neural Networks, and Siamese Neural Networks. To fine-tune these models, we applied four HPO methods: Genetic Algorithm, Hyperband, Optuna, and SMAC3. The experiments were conducted using inter-patient and intra- patient data splits to assess model generalization and robustness in the presence of class imbalance, which is reflective of real-world AF occurrence. Our results, based on PhysioNet electrocardiogram datasets, showed that the Hyperband-optimized XGBoost model outperformed all others, achieving a peak F1 score of 96.95%. These findings highlight the critical role of suitable HPO strategies in enhancing the accuracy and robustness of AF classification outcomes in clinical settings.

Figures & tables

Figure 1: Overview of the HPO-supported ML model development

Exp.	Train	Test	Evaluation	Split
E11	MITDB	MITDB	intra-patient	80/20
E12	MITDB	LTAFDB	inter-patient	dataset
E21	LTAFDB	MITDB	inter-patient	dataset
E22	LTAFDB	LTAFDB	intra-patient	80/20

Table 1: Specification of experiments

Optimizer	Parameter	Value
	factor	3
Hyperband	max resources	100
	min resources	20
	max epoch	20
Optuna	trials	50
	population	[10,30,70]

Table 2: HPO Models Configurations

Figure 2: Visual representation for the execution time(s) for different HPO

Optimizer	Model	Acc	PPV	Sen	F1
GA	XGB	98.35	97.02	96.53	96.77
Hyperband	XGB	98.43	97.11	96.80	96.95
Optuna	XGB	98.34	96.96	96.57	96.77
SMAC3	XGB	98.37	96.99	96.66	96.83

Table 5: The best results for E22

Panel of Figure 3 — Figure 3: Performance comparison for all experiments (E11, E12, E21, E22).

Ref.	Optimizer	Model	Method	Split	Acc	Sen	PPV	F1	AUC
[ 14 ]	Optuna	XGB	mixed	70/30	-	-	-	99.00	-
[ 15 ]	Optuna	AlexNet	mixed	80/20	-	-	-	-	97.23
[ 16 ]	GA	CNN	mixed	-	99.95	100	-	-	-
[ 29 ]	GS	SVM	mixed	60/40	96.50	-	-	-	-
[ 17 ]	BOHB	CNN/LSTM	mixed	80/20	72.80	-	-	59.31	-
[ 18 ]	Hyperband	DMNN	intra	dataset	-	-	-	-	83.40

Table 6: Comparison with state-of-the-art approaches

Atrial Fibrillation Detection

See all 12 papers

A New AFIB Detection Method with Deep Neural Networks
Oct 29, 2026Sara Gjorgjieva, Ana Angjelevska, Dimitar Trajanov +1Atrial Fibrillation Detection Electrocardiogram Classification
Innovation Dooel, Skopje, North Macedonia · Ss. Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering, North Macedonia
FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection
Aug 4, 2026Amirhossein Taleshinosrati, Yangyang Wang, Atitaya Phoemsuk +5Atrial Fibrillation Detection Electrocardiogram Foundation Models
SDU Health Informatics and Technology University of Southern Denmark Odense, 5230, Denmark · Department of Computer Science University of Helsinki Helsinki, 00100, Finland · School of Computer Science and Electronic Engineering University of Essex Colchester, CO4 3SQ, UK +1
A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients
Dec 19, 2025Sarah Nassar, Nooshin Maghsoodi, Sophia Mannina +7Atrial Fibrillation Detection Electrocardiogram Foundation Models
Department of Electrical and Computer Engineering at Queen’s University, Kingston, ON, Canada · School of Computing at Queen’s University, Kingston, ON, Canada · Smith School of Business at Queen’s University, Kingston, ON, Canada +5

Oct 29, 2026J/K move · Enter open · S save

A New AFIB Detection Method with Deep Neural Networks

Sara Gjorgjieva, Ana Angjelevska, Dimitar Trajanov, Marjan Gusev

Innovation Dooel, Skopje, North Macedonia · Ss. Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering, North Macedonia

Atrial Fibrillation Detection Electrocardiogram Classification Electrocardiography

Open paper AskPDF arXiv

Early detection of atrial fibrillation (AFIB), characterized by irregular heart rhythms, can potentially save thousands of lives annually [20]. Numerous studies have attempted to address this challenge using various algorithms and methodologies. This paper introduces a novel and robust method that enhances the precision of AFIB detection. Neural Networks (NN) are widely recognized for their ability to identify complex electrocardiogram (ECG) patterns, facilitating the accurate detection of irregular heart rhythms. This study explores multiple conventional machine learning algorithms alongside neural network approaches to develop a robust AFIB detection system. To evaluate the effective- ness and robustness of the proposed method, the MIT BIH arrhythmia database (MITDB) and the Long-term Atrial Fibrillation Database (LTAFDB), both available on the Physionet site. Our approach presents a novel feature engineering technique, employing specific features such as a time series of the differences in successive heart rates (dBPM) rather than traditional inter-beat intervals. The model analyzes inputs labeled into five distinct classes, using only clean intervals identified through a new labeling method for training while treating others as outliers. This strategy ensures a more accurate and reliable AFIB detection process. The best-performing model, a Deep Neural Network (DNN), achieved an F1 score of 95.18% for binary atrial fibrillation classification on a benchmark dataset distinct from the training set. Models trained using our approach have demonstrated superior performance than previously published models.

Abstract

Atrial Fibrillation Detection

Explore similar work

A New AFIB Detection Method with Deep Neural Networks

FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection

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