Determination of Parameters for an Entropy-Based Atrial Fibrillation Detector

Entropy algorithm is an important nonlinear method for cardiovascular disease detection due to its power in analyzing short-term time series. In previous a study, we proposed a new entropy-based atrial fibrillation (AF) detector, i.e., EntropyAF, which showed a high classification accuracy in identifying AF and non-AF rhythms. As a variation of entropy measures, EntropyAF has two parameters that need to be initialized before the calculation: (1) tolerance threshold r and (2) similarity weight n. In this study, a comprehensive analysis for the two parameters determination was presented, aiming to achieve a high detection accuracy for AF events. Data were from the MIT-BIH AF database. RR interval recordings were segmented using a 30-beat time window. The parameters r and n were initialized from a relatively small value, then gradually increased, and finally the best parameter combination was determined using grid searching. AUC (area under curve) values from the receiver operator characteristic curve (ROC) were compared under different parameter combinations of parameters r and n, and the results demonstrated that the selection of these two parameters plays an important role in AF/non-AF classification. Small values of parameters r and n can lead to a better detection accuracy than other selections. The best AUC value for AF detection was 98.15%, and the corresponding parameter combinations for EntropyAF were as follows: r = 0.01, n = 0.0625, 0.125, 0.25, or 0.5; r = 0.05 and n = 0.0625, 0.125, or 0.25; and r = 0.10 and n = 0.0625 or 0.125.

Download Full-text

The Effects of Compression on the Detection of Atrial Fibrillation in ECG Signals

Applied Sciences ◽

10.3390/app11135908 ◽

2021 ◽

Vol 11 (13) ◽

pp. 5908

Author(s):

Raquel Cervigón ◽

Brian McGinley ◽

Darren Craven ◽

Martin Glavin ◽

Edward Jones

Keyword(s):

Atrial Fibrillation ◽

Characteristic Curve ◽

Set Partitioning ◽

Constrained Systems ◽

Battery Life ◽

Detection Accuracy ◽

Ecg Signal ◽

Signal Compression ◽

Ecg Signals ◽

Cardiac Devices

Although Atrial Fibrillation (AF) is the most frequent cause of cardioembolic stroke, the arrhythmia remains underdiagnosed, as it is often asymptomatic or intermittent. Automated detection of AF in ECG signals is important for patients with implantable cardiac devices, pacemakers or Holter systems. Such resource-constrained systems often operate by transmitting signals to a central server where diagnostic decisions are made. In this context, ECG signal compression is being increasingly investigated and employed to increase battery life, and hence the storage and transmission efficiency of these devices. At the same time, the diagnostic accuracy of AF detection must be preserved. This paper investigates the effects of ECG signal compression on an entropy-based AF detection algorithm that monitors R-R interval regularity. The compression and AF detection algorithms were applied to signals from the MIT-BIH AF database. The accuracy of AF detection on reconstructed signals is evaluated under varying degrees of compression using the state-of-the-art Set Partitioning In Hierarchical Trees (SPIHT) compression algorithm. Results demonstrate that compression ratios (CR) of up to 90 can be obtained while maintaining a detection accuracy, expressed in terms of the area under the receiver operating characteristic curve, of at least 0.9. This highlights the potential for significant energy savings on devices that transmit/store ECG signals for AF detection applications, while preserving the diagnostic integrity of the signals, and hence the detection performance.

Download Full-text

0588 Ring Pulse Oximeter for Screening of Moderate to Severe OSA: A Pilot Study

SLEEP ◽

10.1093/sleep/zsaa056.585 ◽

2020 ◽

Vol 43 (Supplement_1) ◽

pp. A225-A225

Author(s):

J Xue ◽

R Zhao ◽

J Li ◽

L Zhao ◽

B Zhou ◽

...

Keyword(s):

Pilot Study ◽

Pulse Oximeter ◽

Characteristic Curve ◽

Diagnostic Value ◽

Receiver Operator Characteristic Curve ◽

Oxygen Desaturation ◽

Significant Difference ◽

Acceptance Range ◽

The Difference ◽

Two Parameters

Abstract Introduction To evaluate the utility of the ring pulse oximeter for screening of OSA in adults. Methods 87 adults were monitored by a ring pulse oximeter and PSG simultaneously during a nocturnal in-lab sleep testing. 3% oxygen desaturation index (ODI3); Mean oxygen saturation(MSpO2), Saturation impair time below 90% (SIT90) derived from an automated algorithm of the ring pulse oximeter. Meanwhile, the parameters of PSG were scored manually according to the AASM Manual. Correlation and receiver operator characteristic curve analysis were used to measure the accuracy of ring pulse oximeter and its diagnostic value for moderate to severe OSA (AHI≥15). Results Among the 87 participants, 18 cases were AHI<5, 17 cases were diagnosed with mild OSA (AHI:5-14.9), 25 cases were diagnosed with moderate OSA (AHI:15-29.9) and 27 cases were diagnosed with severe OSA (AHI≥30). There was no significant difference between PSG and ring pulse oximeter in regard to ODI3 (23.4±23.5 vs 24.7 ± 21.7), and SIT90 (1.54%, range 0.14%-8.99% vs. 3.20%, range 0.60%, 12.30%) (P>0.05], Further analysis indicated that two parameters from the oximeter correlated well with that derived from PSG (r=0.889, 0.567, respectively, both p<0.05). Although MSpO2 correlated significantly (r=0.448, P<0.05), the difference was remarkable [95.9%, range 94.0% to 97.0% vs. 94.5%, range 93.3% to 95.7%, p<0.05]. Bland-Altman plots showed that the agreement of these three parameters was within the clinical acceptance range. The ROC curve showed that the sensitivity and specificity of the ring pulse oximeter when the oximeter derived ODI3 ≥12.5 in the diagnosis of moderate to severe OSA were 82.7% and 74.3%, respectively. Conclusion The pilot study indicated that ring pulse oximeter can detect oxygen desaturation events accurately, therefore to be used as a screening tool for moderate to severe OSA. Support The study was supported by the National Natural Science Foundation of China (No. 81420108002 and NO. 81570083).

Download Full-text

Predictors of Spontaneous Echocardiographic Contrast Within the Left Atrial Appendage in Cardiac Computed Tomography of Patients with Atrial Fibrillation

10.21203/rs.3.rs-979857/v1 ◽

2021 ◽

Author(s):

Kotaro Ouchi ◽

Toru Sakuma ◽

Takahiro Higuchi ◽

Jun Yoshida ◽

Ryosuke Narui ◽

...

Keyword(s):

Computed Tomography ◽

Atrial Fibrillation ◽

Left Atrial ◽

Cardiac Ct ◽

Left Atrial Appendage ◽

Cardiac Computed Tomography ◽

Characteristic Curve ◽

Receiver Operator Characteristic Curve ◽

Atrial Appendage ◽

Receiver Operator Characteristic

Abstract PurposeCardiac computed tomography (CT) depiction of the relationship between spontaneous echocardiographic contrast (SEC) and findings of the left atrial appendage (LAA) has not been reported. We evaluated predictors of SEC within the LAA using findings of cardiac CT in patients with atrial fibrillation (AF).MethodsWe retrospectively analyzed cardiac CT findings of the LAA, including morphology, volume, and filling defects, of 641 patients who underwent Transesophageal echocardiography (TEE) prior to pulmonary vein isolation (PVI) from January 6, 2013 through December 16, 2019 at our institution. We investigated potential associated factors that might be predictors of SEC and computed a receiver operator characteristic,choosing a threshold value at which the likelihood of SEC could be predicted based on the LAA volume indexed for body size.ResultsSEC correlated significantly with history of persistent AF (P<0.001; odds ratio [OR], 3.74; 95% confidence interval [CI], 1.91–7.29), LAA early filling defects (P =0.003; OR, 2.83; 95% CI, 1.43–5.62), LAAFV (P<0.001; OR, 0.97; 95% CI, 0.96–0.99), and indexed LAA volume (P = 0.001; OR, 1.18; 95% CI, 1.07–1.30) of 8.04 cm3/m2 or greater (sensitivity, 75.0%; specificity, 48.7%).The addition of LAAFV to indexed LAA volume increased the area under the receiver operator characteristic curve from 0.642 to 0.724 (P< 0.001).ConclusionFindings of LAA in cardiac CT might allow the noninvasive estimation of SEC and additional information for risk stratification and management of thromboembolic events in patients with AF.

Download Full-text

Wrist Band Photoplethysmography Autocorrelation Analysis Enables Detection of Atrial Fibrillation Without Pulse Detection

Frontiers in Physiology ◽

10.3389/fphys.2021.654555 ◽

2021 ◽

Vol 12 ◽

Author(s):

Eemu-Samuli Väliaho ◽

Pekka Kuoppa ◽

Jukka A. Lipponen ◽

Juha E. K. Hartikainen ◽

Helena Jäntti ◽

...

Keyword(s):

Atrial Fibrillation ◽

Characteristic Curve ◽

Pulse Interval ◽

Detection Accuracy ◽

Monitoring Method ◽

Pulse Detection ◽

Detection Algorithms ◽

Pulse Waves ◽

Predictor Model ◽

Atrial Fibrillation Detection

Atrial fibrillation is often asymptomatic and intermittent making its detection challenging. A photoplethysmography (PPG) provides a promising option for atrial fibrillation detection. However, the shapes of pulse waves vary in atrial fibrillation decreasing pulse and atrial fibrillation detection accuracy. This study evaluated ten robust photoplethysmography features for detection of atrial fibrillation. The study was a national multi-center clinical study in Finland and the data were combined from two broader research projects (NCT03721601, URL: https://clinicaltrials.gov/ct2/show/NCT03721601 and NCT03753139, URL: https://clinicaltrials.gov/ct2/show/NCT03753139). A photoplethysmography signal was recorded with a wrist band. Five pulse interval variability, four amplitude features and a novel autocorrelation-based morphology feature were calculated and evaluated independently as predictors of atrial fibrillation. A multivariate predictor model including only the most significant features was established. The models were 10-fold cross-validated. 359 patients were included in the study (atrial fibrillation n = 169, sinus rhythm n = 190). The autocorrelation univariate predictor model detected atrial fibrillation with the highest area under receiver operating characteristic curve (AUC) value of 0.982 (sensitivity 95.1%, specificity 93.7%). Autocorrelation was also the most significant individual feature (p < 0.00001) in the multivariate predictor model, detecting atrial fibrillation with AUC of 0.993 (sensitivity 96.4%, specificity 96.3%). Our results demonstrated that the autocorrelation independently detects atrial fibrillation reliably without the need of pulse detection. Combining pulse wave morphology-based features such as autocorrelation with information from pulse-interval variability it is possible to detect atrial fibrillation with high accuracy with a commercial wrist band. Photoplethysmography wrist bands accompanied with atrial fibrillation detection algorithms utilizing autocorrelation could provide a computationally very effective and reliable wearable monitoring method in screening of atrial fibrillation.

Download Full-text

Abstract 15890: Spatiotemporal Analysis of Phase and Frequency Dynamics in Human Persistent Atrial Fibrillation

Circulation ◽

10.1161/circ.132.suppl_3.15890 ◽

2015 ◽

Vol 132 (suppl_3) ◽

Author(s):

Nawshin Dastagir ◽

Frederique J Vanheusden ◽

Gavin S Chu ◽

João L Salinet ◽

Xin Li ◽

...

Keyword(s):

Atrial Fibrillation ◽

Time Window ◽

Persistent Atrial Fibrillation ◽

Spatiotemporal Analysis ◽

Detection Algorithm ◽

Dominant Frequency ◽

Jude Medical ◽

The Hilbert Transform ◽

Two Parameters ◽

Opposite Chirality

There is increasing focus on understanding the substrates that maintain persistent atrial fibrillation (persAF) based on dominant frequency (DF) sources and phase singularity points (PS). In this study we aimed to combine these two parameters and study the relationship between them to depict the complex spatiotemporal patterns of fibrillation. For 9 patients with longstanding persAF (duration: 34 ± 25 months) undergoing left atrial (LA) ablation, noncontact array catheter (EnSite Array, St. Jude Medical) was used to collect virtual unipolar electrograms (EGMs) simultaneously from 2048 nodes on the LA. After QRST subtraction, 3D DF maps were obtained through the fast Fourier Transform applied simultaneously to each individual EGM. DF was defined within the range of 4-10Hz (4s time window; 87.5% overlap; 30s/patient). Highest DF (HDF) regions for each individual window were defined as any LA geometry nodes where the calculated DF was within 0.25 Hz of the maximum DF value registered in the window. In order to correlate these HDF locations with PS, phase maps were constructed using the Hilbert transform approach and the locations of PS and its respective chirality (+ clockwise; - anticlockwise) were identified applying an automatic PS detection algorithm. A statistical majority of PSs (92.5%, p<0.001) were distributed outside the HDF regions. There was a relationship between PSs and the HDF regions such that PSs of opposite chirality influence the propagation of HDF. This was observed for all patients and in 72.1 (± 10.5) % of the total windows. The influence of direction of HDF movement by PSs of opposite chirality was observed 12 (±9) times for each window. A case illustration is presented on Figure 1. Our analysis suggests an organised behaviour of PS of opposite chirality and HDF regions travelling between them. Once an electrophysiological relationship is established, the spatiotemporal behaviour of PS and HDF could provide alternative ablation strategies for AF.

Download Full-text

A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings

Entropy ◽

10.3390/e20120904 ◽

2018 ◽

Vol 20 (12) ◽

pp. 904 ◽

Cited By ~ 9

Author(s):

Lina Zhao ◽

Chengyu Liu ◽

Shoushui Wei ◽

Qin Shen ◽

Fan Zhou ◽

...

Keyword(s):

Atrial Fibrillation ◽

Time Window ◽

Characteristic Curve ◽

Sample Entropy ◽

Youden Index ◽

Entropy Measure ◽

Discrimination Ability ◽

Fuzzy Function ◽

Electrocardiogram Ecg

Entropy-based atrial fibrillation (AF) detectors have been applied for short-term electrocardiogram (ECG) analysis. However, existing methods suffer from several limitations. To enhance the performance of entropy-based AF detectors, we have developed a new entropy measure, named EntropyAF, which includes the following improvements: (1) use of a ranged function rather than the Chebyshev function to define vector distance, (2) use of a fuzzy function to determine vector similarity, (3) replacement of the probability estimation with density estimation for entropy calculation, (4) use of a flexible distance threshold parameter, and (5) use of adjusted entropy results for the heart rate effect. EntropyAF was trained using the MIT-BIH Atrial Fibrillation (AF) database, and tested on the clinical wearable long-term AF recordings. Three previous entropy-based AF detectors were used for comparison: sample entropy (SampEn), fuzzy measure entropy (FuzzyMEn) and coefficient of sample entropy (COSEn). For classifying AF and non-AF rhythms in the MIT-BIH AF database, EntropyAF achieved the highest area under receiver operating characteristic curve (AUC) values of 98.15% when using a 30-beat time window, which was higher than COSEn with AUC of 91.86%. SampEn and FuzzyMEn resulted in much lower AUCs of 74.68% and 79.24% respectively. For classifying AF and non-AF rhythms in the clinical wearable AF database, EntropyAF also generated the largest values of Youden index (77.94%), sensitivity (92.77%), specificity (85.17%), accuracy (87.10%), positive predictivity (68.09%) and negative predictivity (97.18%). COSEn had the second-best accuracy of 78.63%, followed by an accuracy of 65.08% in FuzzyMEn and an accuracy of 59.91% in SampEn. The new proposed EntropyAF also generated highest classification accuracy when using a 12-beat time window. In addition, the results from time cost analysis verified the efficiency of the new EntropyAF. This study showed the better discrimination ability for identifying AF when using EntropyAF method, indicating that it would be useful for the practical clinical wearable AF scanning.

Download Full-text

CHA2DS2-VASc Score for Major Adverse Cardiovascular Events Stratification in Patients with Pneumonia with and without Atrial Fibrillation

Journal of Clinical Medicine ◽

10.3390/jcm10184093 ◽

2021 ◽

Vol 10 (18) ◽

pp. 4093

Author(s):

Bo-Yuan Wang ◽

Fei-Yi Lin ◽

Min-Sho Ku ◽

Yu-Hsun Wang ◽

Kun-Yu Lee ◽

...

Keyword(s):

Atrial Fibrillation ◽

Sensitivity And Specificity ◽

Cardiovascular Events ◽

Cox Regression ◽

Characteristic Curve ◽

Population Based ◽

Receiver Operator Characteristic Curve ◽

Incidence Density ◽

Major Adverse Cardiovascular Events ◽

Ischemic Attack

Background: Recent studies have shown an association between CHA2DS2-VASc (congestive heart failure, hypertension, age ≥ 75 years, diabetes mellitus, stroke or transient ischemic attack (TIA), vascular disease, age 65 to 74 years, sex category) score and outcome of acute myocardial infarction, stroke, and chest pain. As pneumonia can affect the cardiovascular system, this study aimed to investigate the performance of the CHA2DS2-VASc score for major adverse cardiovascular events (MACEs) risk stratification in patients with pneumonia. Methods: A retrospective population-based cohort study including 61,843 patients with pneumonia. These patients were divided into two cohorts that were stratified based on the presence or absence of underlying atrial fibrillation (AF). We calculated the CHA2DS2-VASc score and incidence density rates of MACEs in each cohort. Cox regression was conducted to calculate hazard ratio of MACEs in pneumonia patients. The diagnostic performance of CHA2DS2-VASc with regard to MACEs was tested using the receiver operator characteristic curve. Results: Pneumonia patients with higher CHA2DS2-VASc score were more likely develop MACEs in both the AF and non-AF groups. In the AF group, the areas under the curve (AUC), sensitivity, and specificity were 0.824 (0.7773–0.8708), 0.7, and 0.84 respectively. In the non-AF group, the AUC, sensitivity, and specificity were 0.8185 (0.8152–0.8217), 0.75, and 0.83 respectively. Conclusions: The CHA2DS2-VASc score showed good performance in the prediction of MACE in patients with pneumonia.

Download Full-text

AVALIAÇÃO DE UM INSTRUMENTO DE MENSURAÇÃO DE MORBIDADE PSÍQUICA: ESTUDO DE VALIDAÇÃO DO SELF-REPORTING QUESTIONNAIRE (SRQ-20)

Revista Baiana Saúde Pública ◽

10.22278/2318-2660.2010.v34.n3.a54 ◽

1970 ◽

Vol 34 (3) ◽

pp. 544 ◽

Cited By ~ 25

Author(s):

Kionna Oliveira Bernardes Santos ◽

Tânia Maria de Araújo ◽

Paloma de Sousa Pinho ◽

Ana Cláudia Conceição Silva

Keyword(s):

Characteristic Curve ◽

Receiver Operator Characteristic Curve ◽

Clinical Interview ◽

Receiver Operator Characteristic ◽

Interview Schedule ◽

Para Determinar ◽

Self Reporting Questionnaire

O Self-Reporting Questionnaire (SRQ-20), desenvolvido pela Organização Mundial de Saúde, tem sido utilizado para mensuração de nível de suspeição de transtornos mentais em estudos brasileiros, especialmente em grupos de trabalhadores. O objetivo deste estudo foi avaliar o desempenho do SRQ-20, com base em indicadores de validade (sensibilidade, especificidade, taxa de classificação incorreta e valores preditivos), e determinar o melhor ponto de corte para classificação dos transtornos mentais comuns na população estudada. O estudo incluiu 91 indivíduos selecionados aleatoriamente de um estudo de corte transversal realizado com população residente em áreas urbanas de Feira de Santana (BA). Entrevistas clínicas, realizadas por psicólogas, utilizando o Revised Clinical Interview Schedule (CIS-R), foi adotada como padrão-ouro. Na avaliação do desempenho do SRQ-20 foram estimados indicadores de validade (sensibilidade e especificidade). A curva Receiver Operator Characteristic Curve (ROC) foi utilizada para determinar o melhor ponto de corte para classificação de suspeitos/não suspeitos. O ponto de corte de melhor desempenho foi de 6/7 para a população investigada, revelando desempenho razoável com área sob a curva de 0,789. Os resultados indicam que o SRQ-20 possui característica discriminante regular.

Download Full-text

Haemoconcentration as a predictor of severity in acute pancreatitis

Journal of Kathmandu Medical College ◽

10.3126/jkmc.v4i1.15020 ◽

2016 ◽

Vol 4 (1) ◽

pp. 3-7

Author(s):

Tanka Prasad Bohara ◽

Dimindra Karki ◽

Anuj Parajuli ◽

Shail Rupakheti ◽

Mukund Raj Joshi

Keyword(s):

Acute Pancreatitis ◽

Pearson Correlation ◽

Characteristic Curve ◽

Scoring Systems ◽

Cost Effective ◽

Receiver Operator Characteristic Curve ◽

First Episode ◽

P Value ◽

Receiver Operator Characteristic ◽

Chi Square

Background: Acute pancreatitis is usually a mild and self-limiting disease. About 25 % of patients have severe episode with mortality up to 30%. Early identification of these patients has potential advantages of aggressive treatment at intensive care unit or transfer to higher centre. Several scoring systems are available to predict severity of acute pancreatitis but are cumbersome, take 24 to 48 hours and are dependent on tests that are not universally available. Haematocrit has been used as a predictor of severity of acute pancreatitis but some have doubted its role.Objectives: To study the significance of haematocrit in prediction of severity of acute pancreatitis.Methods: Patients admitted with first episode of acute pancreatitis from February 2014 to July 2014 were included. Haematocrit at admission and 24 hours of admission were compared with severity of acute pancreatitis. Mean, analysis of variance, chi square, pearson correlation and receiver operator characteristic curve were used for statistical analysis.Results: Thirty one patients were included in the study with 16 (51.61%) male and 15 (48.4%) female. Haematocrit at 24 hours of admission was higher in severe acute pancreatitis (P value 0.003). Both haematocrit at admission and at 24 hours had positive correlation with severity of acute pancreatitis (r: 0.387; P value 0.031 and r: 0.584; P value 0.001) respectively.Area under receiver operator characteristic curve for haematocrit at admission and 24 hours were 0.713 (P value 0.175, 95% CI 0.536 - 0.889) and 0.917 (P value 0.008, 95% CI 0.813 – 1.00) respectively.Conclusion: Haematocrit is a simple, cost effective and widely available test and can predict severity of acute pancreatitis.Journal of Kathmandu Medical College, Vol. 4(1) 2015, 3-7

Download Full-text

Identification of candidate biomarkers of liver hydatid disease via microarray profiling, bioinformatics analysis, and machine learning

Journal of International Medical Research ◽

10.1177/0300060521993980 ◽

2021 ◽

Vol 49 (3) ◽

pp. 030006052199398

Author(s):

Jinwu Peng ◽

Zhili Duan ◽

Yamin Guo ◽

Xiaona Li ◽

Xiaoqin Luo ◽

...

Keyword(s):

Random Forest ◽

Hydatid Disease ◽

Characteristic Curve ◽

Receiver Operator Characteristic Curve ◽

Random Forest Model ◽

Hepatic Hydatid Disease ◽

Forest Model ◽

Protein Protein Interaction ◽

Ppi Networks ◽

Microarray Profiling

Objectives Liver echinococcosis is a severe zoonotic disease caused by Echinococcus (tapeworm) infection, which is epidemic in the Qinghai region of China. Here, we aimed to explore biomarkers and establish a predictive model for the diagnosis of liver echinococcosis. Methods Microarray profiling followed by Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analysis was performed in liver tissue from patients with liver hydatid disease and from healthy controls from the Qinghai region of China. A protein–protein interaction (PPI) network and random forest model were established to identify potential biomarkers and predict the occurrence of liver echinococcosis, respectively. Results Microarray profiling identified 1152 differentially expressed genes (DEGs), including 936 upregulated genes and 216 downregulated genes. Several previously unreported biological processes and signaling pathways were identified. The FCGR2B and CTLA4 proteins were identified by the PPI networks and random forest model. The random forest model based on FCGR2B and CTLA4 reliably predicted the occurrence of liver hydatid disease, with an area under the receiver operator characteristic curve of 0.921. Conclusion Our findings give new insight into gene expression in patients with liver echinococcosis from the Qinghai region of China, improving our understanding of hepatic hydatid disease.

Download Full-text