Patient-Specific Detection of Atrial Fibrillation in Segments of ECG Signals using Deep Neural Networks

Atrial Fibrillation (AF) is the most common cardiac arrhythmia worldwide. It is associated with reduced quality of life and increases the risk of stroke and myocardial infarction. Unfortunately, many cases of AF are asymptomatic and undiagnosed, which increases the risk for the patients. Due to its paroxysmal nature, the detection of AF requires the evaluation, by a cardiologist, of long-term ECG signals. In Colombia, it is difficult to have access to an early diagnosis of AF because of the associated costs to the detection and the geographical distribution of cardiologists. This work is part of a macro project that aims to develop a specific-patient portable device for the detection of AF. This device will be based on a Convolutional Neural Network (CNN). We aim to find a suitable CNN model, which later could be implemented in hardware. Diverse techniques were applied to improve the answer regarding accuracy, sensitivity, specificity, and precision. The final model achieves an accuracy of , a specificity of , a sensitivity of and a precision of . During the development of the model, the computational cost and memory resources were taking into account in order to obtain an efficient hardware model in a future implementation of the device.

Download Full-text

Long-Term Outcomes and Improvements in Quality of Life in Patients with Atrial Fibrillation Treated with Catheter Ablation vs. Antiarrhythmic Drugs

SSRN Electronic Journal ◽

10.2139/ssrn.3408053 ◽

2019 ◽

Author(s):

Zi-Heng Zheng ◽

Jun Fan ◽

Cheng-Cheng Ji ◽

Yun-Jiu Cheng ◽

Xu-Miao Chen ◽

...

Keyword(s):

Quality Of Life ◽

Atrial Fibrillation ◽

Catheter Ablation ◽

Antiarrhythmic Drugs ◽

Long Term Outcomes

Download Full-text

On-device Prior Knowledge Incorporated Learning for Personalized Atrial Fibrillation Detection

ACM Transactions on Embedded Computing Systems ◽

10.1145/3476987 ◽

2021 ◽

Vol 20 (5s) ◽

pp. 1-25

Author(s):

Zhenge Jia ◽

Yiyu Shi ◽

Samir Saba ◽

Jingtong Hu

Keyword(s):

Atrial Fibrillation ◽

Prior Knowledge ◽

Domain Knowledge ◽

Fine Tuning ◽

Cardiac Monitoring ◽

Patient Specific ◽

Detection Accuracy ◽

Specific Patient ◽

Deep Model ◽

Tuning Strategy

Atrial Fibrillation (AF), one of the most prevalent arrhythmias, is an irregular heart-rate rhythm causing serious health problems such as stroke and heart failure. Deep learning based methods have been exploited to provide an end-to-end AF detection by automatically extracting features from Electrocardiogram (ECG) signal and achieve state-of-the-art results. However, the pre-trained models cannot adapt to each patient’s rhythm due to the high variability of rhythm characteristics among different patients. Furthermore, the deep models are prone to overfitting when fine-tuned on the limited ECG of the specific patient for personalization. In this work, we propose a prior knowledge incorporated learning method to effectively personalize the model for patient-specific AF detection and alleviate the overfitting problems. To be more specific, a prior-incorporated portion importance mechanism is proposed to enforce the network to learn to focus on the targeted portion of the ECG, following the cardiologists’ domain knowledge in recognizing AF. A prior-incorporated regularization mechanism is further devised to alleviate model overfitting during personalization by regularizing the fine-tuning process with feature priors on typical AF rhythms of the general population. The proposed personalization method embeds the well-defined prior knowledge in diagnosing AF rhythm into the personalization procedure, which improves the personalized deep model and eliminates the workload of manually adjusting parameters in conventional AF detection method. The prior knowledge incorporated personalization is feasibly and semi-automatically conducted on the edge, device of the cardiac monitoring system. We report an average AF detection accuracy of 95.3% of three deep models over patients, surpassing the pre-trained model by a large margin of 11.5% and the fine-tuning strategy by 8.6%.

Download Full-text

Quality of life and patient-centered outcomes following atrial fibrillation ablation: short- and long-term perspectives to improving care

Expert Review of Cardiovascular Therapy ◽

10.1586/erc.12.62 ◽

2012 ◽

Vol 10 (7) ◽

pp. 889-900 ◽

Cited By ~ 4

Author(s):

Sanghamitra Mohanty ◽

Luigi Di Biase ◽

Rong Bai ◽

Pasquale Santangeli ◽

Agnes Pump ◽

...

Keyword(s):

Quality Of Life ◽

Atrial Fibrillation ◽

Atrial Fibrillation Ablation ◽

Patient Centered ◽

Short And Long Term

Download Full-text

Prospective Assessment of Short- and Long-Term Quality of Life After Ablation for Atrial Fibrillation

Journal of Cardiovascular Electrophysiology ◽

10.1111/j.1540-8167.2011.02165.x ◽

2011 ◽

Vol 23 (2) ◽

pp. 121-127 ◽

Cited By ~ 35

Author(s):

STEPHANIE FICHTNER ◽

ISABEL DEISENHOFER ◽

SIBYLLE KINDSMÜLLER ◽

MARIJANA DZIJAN-HORN ◽

STYLIANOS TZEIS ◽

...

Keyword(s):

Quality Of Life ◽

Atrial Fibrillation ◽

Prospective Assessment ◽

Short And Long Term

Download Full-text

Determinants of Cancer-specific Quality of Life in Veteran Lung Cancer Survivors Eligible for Long-Term Cure

10.1101/518910 ◽

2019 ◽

Author(s):

Duc Ha ◽

Andrew L. Ries ◽

Jeffrey J. Swigris

Keyword(s):

Quality Of Life ◽

Lung Cancer ◽

Cancer Survivors ◽

Summary Score ◽

European Organization ◽

Specific Patient ◽

Patient Reported ◽

Sleep Difficulties

AbstractRationale/ObjectiveQuality of life (QoL) is an important issue in lung cancer survivors. We aimed to identify determinants of QoL in lung cancer survivors eligible for long-term cure.MethodsWe performed an exploratory analysis of a cross-sectional study of consecutive lung cancer survivors who completed curative-intent treatment ≥1 month previously. Variables tested included demographic, clinical, physiologic, and symptom-specific patient-reported outcome measures. We defined the primary outcome as a previously-validated cancer-specific QoL measure – the European Organization for Research and Treatment of Cancer QoL Questionnaire Core 30 (C30) summary score. We also verified our findings with the C30 global health status/QoL subscale and a summated score of lung cancer-specific QoL from the EORTC-Lung Cancer Module 13.ResultsIn 75 enrolled participants, measures of fatigue, depression, sleep difficulties, and dyspnea were statistically significant determinants of the C30 summary score in multivariable linear regression analyses. Together, these four symptoms accounted for approximately 85% of the variance in cancer-specific QoL (p<0.001). When we verified our findings with global QoL and lung cancer-specific QoL, fatigue and dyspnea were consistent determinants of QoL.ConclusionsWe found four symptoms – dyspnea, fatigue, depression, and sleep difficulties – that are important determinants of and together accounted for almost all of the variance in cancer-specific QoL in lung cancer survivors eligible for long-term cure. These findings have implications to reduce symptom burden and improve function and QoL in these patients.

Download Full-text

Development of atrial fibrillation catheter ablation and ablation strategies

ESC CardioMed ◽

10.1093/med/9780198784906.003.0509 ◽

2018 ◽

pp. 2168-2173

Author(s):

Gerhard Hindricks ◽

Nikolaos Dagres ◽

Philipp Sommer ◽

Andreas Bollmann

Keyword(s):

Atrial Fibrillation ◽

Catheter Ablation ◽

Antiarrhythmic Drug ◽

Left Ventricular ◽

Left Ventricular Ejection ◽

First Line ◽

Ventricular Ejection Fraction ◽

First Line Therapy

Catheter ablation has evolved to an established therapy for patients with symptomatic atrial fibrillation (AF). Complete pulmonary vein isolation currently is the best endpoint for catheter ablation. This can be achieved with balloon-based cryoablation as well as by point-by-point radiofrequency ablation supported by non-fluoroscopic mapping technologies—both technologies seem equally effective. AF catheter ablation is indicated in patients with symptomatic AF usually after failure of antiarrhythmic drug therapy. Selected patients with AF and tachycardia-induced heart failure may benefit from ablation by a significant improvement of left ventricular ejection fraction. The success rate (i.e. freedom from AF and atrial tachycardia) after a single procedure is approximately 50–60% for patients with paroxysmal AF and 40% for patients with persistent AF. With multiple procedures, freedom from AF can be achieved in up to 80% of patients with paroxysmal AF and 60% of patients with persistent AF. When performed after failed rhythm control attempts with antiarrhythmic drugs, catheter ablation is superior to a further attempt with antiarrhythmic drug medication. When applied as first-line therapy, catheter ablation tends to be slightly superior to first-line antiarrhythmic drug treatment. The complication rate of AF catheter ablation is 5–7%; severe complications occur in 2–3% (cardiac tamponade, periprocedural stroke, atrio-oesophageal fistula). Catheter ablation significantly improves quality of life but has no proven effect on mortality and/or stroke. Thus, in general, oral anticoagulation should be continued long term even if ablation is considered successful.

Download Full-text

Long-term quality of VKA treatment and clinical outcome after extreme overanticoagulation in 14,777 AF and VTE patients

Thrombosis and Haemostasis ◽

10.1160/th14-06-0537 ◽

2015 ◽

Vol 113 (04) ◽

pp. 881-890 ◽

Cited By ~ 9

Author(s):

Nic J. G. M. Veeger ◽

Nakisa Khorsand ◽

Hanneke C. Kluin-Nelemans ◽

Hilde A. M. Kooistra ◽

Karina Meijer ◽

...

Keyword(s):

Atrial Fibrillation ◽

Venous Thromboembolism ◽

Clinical Outcome ◽

Vitamin K ◽

Vitamin K Antagonists ◽

P Value ◽

Risk Of Bleeding ◽

Increased Risk

SummaryVitamin K antagonists (VKA) are widely used in atrial fibrillation and venous thromboembolism (VTE). Their efficacy and safety depend on individual time in the therapeutic range (iTTR). Due to the variable dose-response relationship within patients, also patients with initially stable VKA treatment may develop extreme overanticoagulation (EO). EO is associated with an immediate bleeding risk, but it is unknown whether VKA treatment will subsequently restabilise. We evaluated long-term quality of VKA treatment and clinical outcome after EO. EO was defined as international normalized ratio (INR) ≥ 8.0 and/or unscheduled vitamin K supplementation. We included a consecutive cohort of initially stable atrial fibrillation and venous thromboembolism patients. In EO patients, the 90 days pre- and post-period were compared. In addition, patients with EO were compared with patients without EO using a matched 1:2 cohort. Of 14,777 initially stable patients, 800 patients developed EO. The pre-period was characterised by frequent overanticoagulation, and half of EO patients had an inadequate iTTR (< 65 %). After EO, underanticoagulation became more prevalent. Although the mean time between INR-measurements decreased from 18.6 to 13.2 days, after EO inadequate iTTR became more frequent (62 %), p-value < 0.001. A 2.3 times (95 % confidence interval [CI] 2.0–2.5) higher risk for iTTR< 65 % after EO, was accompanied by increased risk of bleeding (hazard ratio [HR] 2.1;CI 1.4–3.2), VKA-related death 17.0 (HR 17.0;CI 2.1–138) and thrombosis (HR 5.7;CI 1.5–22.2), compared to the 1600 controls. In conclusion, patients continuing VKA after EO have long-lasting inferior quality of VKA treatment despite intensified INR-monitoring, and an increased risk of bleeding, thrombosis and VKA-related death.Note: There have been no previous presentations, reports or publications of the complete data that appear in the article. Parts of the data in this article have been presented as a poster at the American Society of Hematology (ASH) congress 2013, New Orleans, United States.

Download Full-text

P3446Regional variation in quality of anticoagulation control among european patients with atrial fibrillation: the EORP-AF general long-term registry

European Heart Journal ◽

10.1093/eurheartj/ehy563.p3446 ◽

2018 ◽

Vol 39 (suppl_1) ◽

Author(s):

M Proietti ◽

C Laroche ◽

M I Popescu ◽

A Tello-Montoliu ◽

I Garcia-Bolao ◽

...

Keyword(s):

Atrial Fibrillation ◽

Anticoagulation Control

Download Full-text

A Wearable Electrocardiogram Telemonitoring System for Atrial Fibrillation Detection

Sensors ◽

10.3390/s20030606 ◽

2020 ◽

Vol 20 (3) ◽

pp. 606 ◽

Cited By ~ 3

Author(s):

Minggang Shao ◽

Zhuhuang Zhou ◽

Guangyu Bin ◽

Yanping Bai ◽

Shuicai Wu

Keyword(s):

Atrial Fibrillation ◽

Ecg Monitoring ◽

Web Browser ◽

Ecg Signals ◽

Cloud Server ◽

Android App ◽

Electrocardiogram Ecg ◽

The Web ◽

Ecg Data

In this paper we proposed a wearable electrocardiogram (ECG) telemonitoring system for atrial fibrillation (AF) detection based on a smartphone and cloud computing. A wearable ECG patch was designed to collect ECG signals and send the signals to an Android smartphone via Bluetooth. An Android APP was developed to display the ECG waveforms in real time and transmit every 30 s ECG data to a remote cloud server. A machine learning (CatBoost)-based ECG classification method was proposed to detect AF in the cloud server. In case of detected AF, the cloud server pushed the ECG data and classification results to the web browser of a doctor. Finally, the Android APP displayed the doctor’s diagnosis for the ECG signals. Experimental results showed the proposed CatBoost classifier trained with 17 selected features achieved an overall F1 score of 0.92 on the test set (n = 7270). The proposed wearable ECG monitoring system may potentially be useful for long-term ECG telemonitoring for AF detection.

Download Full-text