A Robust Detection Method of Atrial Fibrillation

Hu, Jing; Zhao, Wei; Xu, Yanwu; Jia, Dongya; Yan, Cong; Wang, Hongmei; You, Tianyuan

doi:10.22489/cinc.2018.268

Cited by 3 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultimately, this work proposes a comparison with other authors that in their work, tried to achieve the same goal, AFIB detection using non-invasive real time techniques. Through the comparison shown in Table 8, can be seen in the Recall metric that this work, using both DSP and the ML model, had slightly better performance than two authors, [9] and [10], while the approach proposed by Ross-Howe et al [7] achieved the best performance with 98.33% of recall.…”

Section: Discussionmentioning

confidence: 72%

“…Through the comparison shown in Table 8, can be seen in the Recall metric that this work, using both DSP and the ML model, had slightly better performance than two authors, [9] and [10], while the approach proposed by Ross-Howe et al [7] achieved the best performance with 98.33% of recall.…”

Section: Discussionmentioning

confidence: 74%

“…There are other authors who have tried to combine the advantages of deep neural networks with handcrafted features. Hu et al [10] have used the AF Classification from a Short Single Lead ECG Recording: The PhysioNet/Computing in Cardiology Challenge 2017 [11] dataset to extract multiple features. The handcrafted features represent HRV, morphological, frequency domain, and others.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Atrial Fibrillation Detection in short-term Photoplethysmography (PPG) signals using artificial intelligence

Talukdar

Deus

Sehgal

2023

Preprint

View full text Add to dashboard Cite

Atrial Fibrillation (AFIB) is a common atrial arrhythmia that affects millions of people worldwide. However, most of the time, AFIB is paroxysmal and can pass unnoticed in medical exams therefore regular screening is required. This paper proposes machine learning methods to detect AFIB from short-term ECG and PPG signals. Several experiments were conducted across five different databases with three of them containing ECG signals and the other two consisting of only PPG signals. A total of 269,842 signal segments were analyzed across all datasets (212,266 were of normal sinus rhythm (NSR) and 57,576 corresponded to AFIB segments). Experiments were conducted to investigate the hypothesis that a machine learning model trained to predict AFIB from ECG segments, could be used to predict AFIB from PPG segments. A random forest machine learning algorithm achieved the best accuracy and achieved a 90% accuracy rate on the UMMC dataset (216 samples) and a 97% accuracy rate on the MIMIC-III dataset (2,134 samples). The ability to detect AFIB with significant accuracy using machine learning algorithms from PPG signals, which can be acquired via non-invasive contact or contactless, is a promising step forward toward the goal of achieving large-scale screening for AFIB.

show abstract

Section: Discussionmentioning

confidence: 72%

Section: Discussionmentioning

confidence: 74%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Atrial Fibrillation Detection in short-term Photoplethysmography (PPG) signals using artificial intelligence

Talukdar

Deus

Sehgal

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This interval is a crucial part of diagnosing abnormal heart rhythms, which can help learners understand a variety of heart facts [17]. Heart rate variability can be estimated because this interval is one of the most critical significant durations [26]. In AF, ventricular rate increases and is frequently rapid, resulting in an irregular RR Interval [5].…”

Section: Rr Interval Detectionmentioning

confidence: 99%

The Sensitivity of The Heart Rate Detection for Atrial Electrograms Signal

Kong¹,

Ahmad²,

Hassan³

et al. 2021

Elektrika

View full text Add to dashboard Cite

Atrial Fibrillation (AF) is the most familiar example of arrhythmia that will occur health problems such as stroke, heart failure and other complications. Globally, the number of AF patients will more than triple by 2050 worldwide. Current methods involve performing large-area ablation without knowing the exact location of key parts. The reliability of the technology can be used as a target for atrial fibrillation’s catheter ablation. The factors that leading to the onset of atrial fibrillation include the triggering factors that induce arrhythmia and the substrate that maintains the arrhythmia. The project’s aim is to create a method for identifying AF that can be used as screening tool in medical practice. The primary goals for the detection method’s design are to develop a MATLAB software program that can compare the complexity of a normal ECG signal and an AF ECG signal. Currently, this can be achieved by the ECG Signal’s R peaks and RR Interval. For AF detection, there are more R peaks and RR Intervals and it is irregular. In this research, the detection of AF is based on the heart rate (RR Intervals). For the ECG preprocessing, Pan-Tompkins Algorithm and Discrete Wavelet Transform is used to detect the sensitivity on the R peaks and RR Intervals. As a result, Discrete Wavelet Transform algorithm gives 100% sensitivity for the dataset obtained from MIT-BIH Atrial Fibrillation and MIT-BIH Arrhythmia Database.

show abstract

“…There are other authors who have tried to combine the advantages of deep neural networks with handcrafted features. Hu et al [ 10 ] have used the Atrial Fibrillation Classification from a Short Single Lead ECG Recording: The PhysioNet/Computing in Cardiology Challenge 2017 [ 11 ] dataset to extract multiple features. The handcrafted features represent HRV, morphological, frequency domain, and others.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Atrial Fibrillation Detection in Short-Term Photoplethysmography (PPG) Signals Using Artificial Intelligence

Talukdar,

De Deus,

Sehgal

2023

Cureus

View full text Add to dashboard Cite

Background Atrial fibrillation (AFIB) is a common atrial arrhythmia that affects millions of people worldwide. However, most of the time, AFIB is paroxysmal and can pass unnoticed in medical exams; therefore, regular screening is required. This paper proposes machine learning (ML) methods to detect AFIB from short-term electrocardiogram (ECG) and photoplethysmography (PPG) signals. Aim Several experiments were conducted across five different databases, with three of them containing ECG signals and the other two consisting of only PPG signals. Experiments were conducted to investigate the hypothesis that an ML model trained to predict AFIB from ECG segments could be used to predict AFIB from PPG segments. Materials and methods A random forest (RF) ML algorithm achieved the best accuracy and achieved a 90% accuracy rate on the University of Mississippi Medical Center (UMMC) dataset (216 samples) and a 97% accuracy rate on the Medical Information Mart for Intensive Care (MIMIC)-III datasets (2,134 samples). Results A total of 269,842 signal segments were analyzed across all datasets (212,266 were of normal sinus rhythm (NSR) and 57,576 corresponded to AFIB segments). Conclusions The ability to detect AFIB with significant accuracy using ML algorithms from PPG signals, which can be acquired via non-invasive contact or contactless, is a promising step forward toward the goal of achieving large-scale screening for AFIB.

show abstract

A Robust Detection Method of Atrial Fibrillation

Cited by 3 publications

References 11 publications

Evaluation of Atrial Fibrillation Detection in short-term Photoplethysmography (PPG) signals using artificial intelligence

Evaluation of Atrial Fibrillation Detection in short-term Photoplethysmography (PPG) signals using artificial intelligence

The Sensitivity of The Heart Rate Detection for Atrial Electrograms Signal

Evaluation of Atrial Fibrillation Detection in Short-Term Photoplethysmography (PPG) Signals Using Artificial Intelligence

Contact Info

Product

Resources

About