1
|
Ebrahimzadeh E, Kalantari M, Joulani M, Shahraki RS, Fayaz F, Ahmadi F. Prediction of paroxysmal Atrial Fibrillation: A machine learning based approach using combined feature vector and mixture of expert classification on HRV signal. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2018; 165:53-67. [PMID: 30337081 DOI: 10.1016/j.cmpb.2018.07.014] [Citation(s) in RCA: 46] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/07/2018] [Revised: 06/17/2018] [Accepted: 07/25/2018] [Indexed: 02/01/2023]
Abstract
BACKGROUND AND OBJECTIVE Paroxysmal Atrial Fibrillation (PAF) is one of the most common major cardiac arrhythmia. Unless treated timely, PAF might transform into permanent Atrial Fibrillation leading to a high rate of morbidity and mortality. Therefore, increasing attention has been directed towards prediction of PAF, to enable early detection and prevent further progression of the disease. Notwithstanding the pharmacological and electrical treatments, a validated method to predict the onset of PAF is yet to be developed. We aim to address this issue through integrating classical and modern methods. METHODS To increase the predictivity, we have made use of a combination of features extracted through linear, time-frequency, and nonlinear analyses performed on heart rate variability. We then apply a novel approach to local feature selection using meticulous methodologies, developed in our previous works, to reduce the dimensionality of the feature space. Subsequently, the Mixture of Experts classification is employed to ensure a precise decision-making on the output of different processes. In the current study, we analyzed 106 signals from 53 pairs of ECG recordings obtained from the standard database called Atrial Fibrillation Prediction Database (AFPDB). Each pair of data contains one 30-min ECG segment that ends just before the onset of PAF event and another 30-min ECG segment at least 45 min distant from the onset. RESULTS Combining the features that are extracted using both classical and modern analyses was found to be significantly more effective in predicting the onset of PAF, compared to using either analyses independently. Also, the Mixture of Experts classification yielded more precise class discrimination than other well-known classifiers. The performance of the proposed method was evaluated using the Atrial Fibrillation Prediction Database (AFPDB) which led to sensitivity, specificity, and accuracy of 100%, 95.55%, and 98.21% respectively. CONCLUSION Prediction of PAF has been a matter of clinical and theoretical importance. We demonstrated that utilising an optimized combination of - as opposed to being restricted to - linear, time-frequency, and nonlinear features, along with applying the Mixture of Experts, contribute greatly to an early detection of PAF, thus, the proposed method is shown to be superior to those mentioned in similar studies in the literature.
Collapse
Affiliation(s)
- Elias Ebrahimzadeh
- School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran; Biomedical Engineering Department, School of Electrical Engineering, Payame Noor University of North Tehran, Tehran, Iran; Seaman Family MR Research Center, Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.
| | - Maede Kalantari
- Department of Biomedical Engineering, Faculty of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
| | - Mohammadamin Joulani
- Student Research Committee, Faculty of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | | | - Farahnaz Fayaz
- Biomedical Engineering Department, School of Electrical Engineering, Payame Noor University of North Tehran, Tehran, Iran
| | - Fereshteh Ahmadi
- Biomedical Engineering Department, School of Electrical Engineering, Payame Noor University of North Tehran, Tehran, Iran
| |
Collapse
|
2
|
Bartholomay E, Polli I, Borges AP, Kalil C, Arroque A, Kohler I, Danzmann LC. Prevalence of oral anticoagulation in atrial fibrillation. Clinics (Sao Paulo) 2014; 69:615-20. [PMID: 25318093 PMCID: PMC4192404 DOI: 10.6061/clinics/2014(09)07] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/04/2014] [Accepted: 05/27/2014] [Indexed: 01/07/2023] Open
Abstract
OBJECTIVES Atrial fibrillation is the most common sustained arrhythmia and is associated with poor outcomes, including stroke. The ability of anticoagulation therapy to reduce the risk of stroke has been well established; however, the prevalence of anticoagulation therapy use in the Public Health System is unknown. The aim of this study is to evaluate both the prevalence of anticoagulation therapy among patients with atrial fibrillation and the indications for the treatment. METHODS In this cross-sectional study, we included consecutive patients who had atrial fibrillation documented by an electrocardiogram performed between September 2011 and March 2012 at a university hospital of the Public Health System. The variables analyzed included the risk of a thromboembolic event and/or bleeding, the use of antiplatelet or anticoagulation therapy, the location where the electrocardiogram report was initially reviewed and the specialty of the physician who initially reviewed it. RESULTS We included 162 patients (mean age 68.9 years, 56% men). Hypertension (90.1%), heart failure (53.4%) and stroke (38.9%) were the most prevalent diseases found. Only 50.6% of the patients knew that they had atrial fibrillation. Regarding the use of therapy, only 37.6% of patients classified as high risk according to the CHADS2 scores and 35.5% according to the CHA2DS2VASc used oral anticoagulation. A presumptive diagnosis of heart failure and the fact that the electrocardiogram was evaluated by a cardiologist were the only independent predictors of the use of anticoagulants. CONCLUSIONS Our study found a low prevalence of oral anticoagulation therapy among patients with atrial fibrillation and an indication for stroke prophylaxis for the use of this therapy, including among those with high CHADS2 and CHA2DS2VASc scores.
Collapse
Affiliation(s)
| | - Ismael Polli
- Universidade Luterana do Brasil, Cardiology, Porto Alegre, RS, Brazil
| | - Anibal Pires Borges
- Hospital São Lucas da Pontifícia Universidade Católica do Rio Grande do Sul, Cardiology, Porto Alegre, RS, Brazil
| | - Carlos Kalil
- Hospital São Lucas da Pontifícia Universidade Católica do Rio Grande do Sul, Cardiology, Porto Alegre, RS, Brazil
| | - André Arroque
- Universidade Luterana do Brasil, Cardiology, Porto Alegre, RS, Brazil
| | - Ilmar Kohler
- Universidade Luterana do Brasil, Cardiology, Porto Alegre, RS, Brazil
| | | |
Collapse
|
3
|
Molteni M, Cimminiello C. Warfarin and atrial fibrillation: from ideal to real the warfarin affaire. Thromb J 2014; 12:5. [PMID: 24548437 PMCID: PMC3937065 DOI: 10.1186/1477-9560-12-5] [Citation(s) in RCA: 27] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2013] [Accepted: 11/05/2013] [Indexed: 02/08/2023] Open
Abstract
Vitamin K Antagonists (VKAs) are widely used in clinical practice and nearly 1% of the entire population receives oral anticoagulation at least once in life. However, the rate of prescription of anticoagulation is low, compared to what it should be. No more than 50-60% of patients affected by atrial fibrillation (AF) receive anticoagulation. In the setting of AF, VKAs are safe and effective when properly managed, reducing stroke and systemic embolism by more than 60%. VKAs safety and effectiveness are closely related to the quality of anticoagulation (e.g. time in therapeutic range), and anticoagulation clinics offer the best management of anticoagulant therapy. However, a sizeable proportion of patients are managed elsewhere. In clinical practice, in the setting of AF, a low prescription rate of VKAs is frequently observed and this is due also to difficulties in managing laboratory monitoring and drug dose adjustment. The suboptimal management of therapy with VKAs leads to a lesser efficacy than that reported in clinical trials, and to an increase in adverse reactions. VKAs still remain the first and only available therapy for a number of diseases (e.g. valvular atrial fibrillation and mechanical prosthetic heart valves). Now, since approval of the new oral anticoagulants (NOAs), the choice of anticoagulant therapy in definite settings, such as stroke prevention in non-valvular atrial fibrillation (SPAF) or treatment of venous thromboembolism, has surely become more intriguing but also more problematic. In light of these new therapeutic options, we reviewed VKAs therapy, in the setting of atrial fibrillation, focusing on VKAs impact in real life. We analyzed the data about efficacy and safety of warfarin at three levels: clinical trial and real life, outside and inside anticoagulation clinics.
Collapse
Affiliation(s)
- Mauro Molteni
- Internal Medicine, Vimercate Hospital, Azienda Ospedaliera di Desio e Vimercate, Italy
| | - Claudio Cimminiello
- Internal Medicine, Vimercate Hospital, Azienda Ospedaliera di Desio e Vimercate, Italy
| |
Collapse
|
4
|
Davis RC, Hobbs FDR, Kenkre JE, Roalfe AK, Iles R, Lip GYH, Davies MK. Prevalence of atrial fibrillation in the general population and in high-risk groups: the ECHOES study. Europace 2012; 14:1553-9. [DOI: 10.1093/europace/eus087] [Citation(s) in RCA: 131] [Impact Index Per Article: 10.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
|
5
|
Characterization of the proportion of untreated and antiplatelet therapy treated patients with atrial fibrillation. Am J Cardiol 2011; 108:151-61. [PMID: 21545990 DOI: 10.1016/j.amjcard.2011.02.353] [Citation(s) in RCA: 29] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/16/2010] [Revised: 02/18/2011] [Accepted: 02/18/2011] [Indexed: 11/22/2022]
Abstract
Despite the efficacy of oral anticoagulants for stroke prevention in atrial fibrillation (AF), evidence suggests that many patients with AF who should be treated with vitamin K antagonists (VKAs) are treated with antiplatelet therapy or remain untreated. The aims of this study were to determine the proportion of patients with AF in each treatment category in clinical practice and to ascertain whether treatment is appropriate for stroke risk. An extensive search of the biomedical research published since 1994 was performed. Studies delineating the treatment of patients with AF were captured. Seventy-eight studies pertaining to the treatment of patients with AF were identified; 56 studies, containing data from 1980 to 2007, met the inclusion criteria. Over time, the use of VKA therapy for stroke prevention increased, while the proportion of untreated patients decreased; antiplatelet use remained static. Looking at the more recent data, (collected from 2000 onward), the proportion of patients receiving no therapy ranged from 4% to 48% (median 18%), antiplatelet therapy from 10% to 56% (median 30%), and VKA therapy from 9% to 86% (median 52%). Although most studies showed a decrease in the proportion of antiplatelet-treated and untreated patients with increasing stroke risk (12 of 14 studies), many patients at moderate or high risk for stroke were not treated according to guidelines. In conclusion, this review shows that up to 56% of patients with AF are treated with antiplatelet therapy, and up to 48% receive no therapy regardless of stroke risk level. This may reflect the inconvenience associated with VKA use, inadequate assessment of stroke risk, or poor adherence to treatment guidelines.
Collapse
|
6
|
Ogilvie IM, Newton N, Welner SA, Cowell W, Lip GYH. Underuse of oral anticoagulants in atrial fibrillation: a systematic review. Am J Med 2010; 123:638-645.e4. [PMID: 20609686 DOI: 10.1016/j.amjmed.2009.11.025] [Citation(s) in RCA: 695] [Impact Index Per Article: 49.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/03/2009] [Revised: 11/04/2009] [Accepted: 11/05/2009] [Indexed: 12/13/2022]
Abstract
BACKGROUND Atrial fibrillation is associated with substantial mortality and morbidity from stroke and thromboembolism. Despite an efficacious oral anticoagulation therapy (warfarin), atrial fibrillation patients at high risk for stroke are often under-treated. This systematic review compares current treatment practices for stroke prevention in atrial fibrillation with published guidelines. METHODS Literature searches (1997-2008) identified 98 studies concerning current treatment practices for stroke prevention in atrial fibrillation. The percentage of patients eligible for oral anticoagulation due to elevated stroke risk was compared with the percentage treated. Under-treatment was defined as treatment of <70% of high-risk patients. RESULTS Of 54 studies that reported stroke risk levels and the percentage of patients treated, most showed underuse of oral anticoagulants for high-risk patients. From 29 studies of patients with prior stroke/transient ischemic attack who should all receive oral anticoagulation according to published guidelines, 25 studies reported under-treatment, with 21 of 29 studies reporting oral anticoagulation treatment levels below 60% (range 19%-81.3%). Subjects with a CHADS(2) (congestive heart failure, hypertension, age >75 years, diabetes mellitus, and prior stroke or transient ischemic attack) score >or=2 also were suboptimally treated, with 7 of 9 studies reporting treatment levels below 70% (range 39%-92.3%). Studies (21 of 54) using other stroke risk stratification schemes differ in the criteria they use to designate patients as "high risk," such that direct comparison is not possible. CONCLUSIONS This systematic review demonstrates the underuse of oral anticoagulation therapy for real-world atrial fibrillation patients with an elevated risk of stroke, highlighting the need for improved therapies for stroke prevention in atrial fibrillation.
Collapse
|
7
|
Stroke due to atrial fibrillation and the attitude to prescribing anticoagulant prevention in Italy. J Neurol 2008; 255:796-802. [DOI: 10.1007/s00415-008-0615-2] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2007] [Revised: 03/19/2007] [Accepted: 03/28/2007] [Indexed: 10/21/2022]
|
8
|
Ruiz-Ortiz M, Romo-Peñas E, Franco-Zapata M, Mesa-Rubio D, Anguita-Sánchez M, Delgado-Ortega M, Castillo-Domínguez JC, López-Granados A, Arizón Del Prado JM. Anticoagulación oral en la fibrilación auricular no valvular: ¿son efectivas y seguras las recomendaciones científicas en la práctica clínica diaria? Rev Esp Cardiol 2006; 59:688-95. [PMID: 16938211 DOI: 10.1157/13091370] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
INTRODUCTION AND OBJECTIVES To study the efficacy and safety of an oral anticoagulation protocol for the treatment of nonvalvular atrial fibrillation, based on scientific associations' recommendations, in unselected patients seen in daily clinical practice. METHODS The study included all consecutive patients with permanent nonvalvular atrial fibrillation who attended two outpatient cardiology clinics between February 1, 2000 and February 1, 2002. They were treated according to an anticoagulation protocol based on Spanish Society of Cardiology and American College of Cardiology/American Heart Association/European Society of Cardiology guidelines. Patients were followed up prospectively for major events, such as death, stroke, transient ischemic attack, peripheral embolism and severe hemorrhage, which were recorded by treatment group. RESULTS A total of 624 patients were included in the study. Those receiving anticoagulation therapy (n=425; 68%) more frequently had hypertension, diabetes and previous embolism as well as a greater number of cardioembolic risk factors (P< .001). Overall, 93% of non-anticoagulated patients received platelet aggregation inhibitors (92% received aspirin). After a median follow-up of 21 months, the probability of an embolic event was lower in anticoagulated patients (0.81% vs 14.04%; P< .001), as was all-cause mortality (3.27% vs 6.42%; P=.003). However, there was no significant difference in the probability of severe bleeding (2.75% vs 2.93%; P=.96). Results were unchanged after adjustment for age, sex, and previous embolic events. CONCLUSIONS Oral anticoagulation therapy for nonvalvular atrial fibrillation implemented according to scientific associations' recommendations is effective and safe in daily clinical practice.
Collapse
|
9
|
Scalvini S, Piepoli M, Zanelli E, Volterrani M, Giordano A, Glisenti F. Incidence of atrial fibrillation in an Italian population followed by their GPs through a telecardiology service. Int J Cardiol 2005; 98:215-20. [PMID: 15686770 DOI: 10.1016/j.ijcard.2003.12.005] [Citation(s) in RCA: 15] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/12/2003] [Revised: 12/16/2003] [Accepted: 12/24/2003] [Indexed: 11/28/2022]
Abstract
BACKGROUND Atrial fibrillation (AF) is the most common sustained cardiac tachyarrhythmia and is often an occasional diagnosis in the absence of known cardiac disease. The aim of this study is to describe an Italian patient population with AF followed by their General Practitioners (GPs) using a telecardiology service. METHODS A total of 655 Italian GPs were equipped with a portable electrocardiographer. The ECG tracing of all consecutive patients (7516) received between January and September 2001 was included into the study. RESULTS AF was detected in 719 patients (9.%) (77+/-12 years). In 448 patients, it was a known chronic condition, while in 271 patients, it was a new diagnosis. In the chronic AF, the principal reason for the teleconsultation was a routine control by the GPs, but an uncontrolled cardiac rate was present in 29% of the cases, while an antiplatelet or anticoagulation therapy was administered in only 46.2% cases. The teleconsultation alone provided a solution to the GPs' requests in 348 patients (77.6%) (154 cases (34.5%) required no further action while 194 patients (43.5%) needed therapy adjustments only), while 47 patients (10.5%) required hospitalization and 51 patients needed further diagnostic tests. In 271 cases, a first evidence of atrial fibrillation was recorded: in 259 patients, GPs requested a teleconsultation in the presence of symptoms (mainly palpitation, dyspnoea and fatigue) and in 12 for routine control; in this case, 121 patients (46.9%) needed Emergency Department (ED) admission, 113 patients (39.1%) needed therapy adjustments and, for 19 patients (7.5%), further diagnostic tests were prescribed. CONCLUSION In Italy, many patients, in particular the elderly, with AF are followed by their GPs on a routine basis; a telecardiology service may provide a useful tool in the home management of chronic AF and in the first detection of new cases of AF.
Collapse
Affiliation(s)
- Simonetta Scalvini
- Department of Cardiology, Fondazione S. Maugeri, IRCCS, Via Pinidolo 23, 25124 Gussago Brescia, Italy.
| | | | | | | | | | | |
Collapse
|
10
|
Nilsson GH, Björholt I. Occurrence and quality of anticoagulant treatment of chronic atrial fibrillation in primary health care in Sweden: a retrospective study on electronic patient records. BMC CLINICAL PHARMACOLOGY 2004; 4:1. [PMID: 15028124 PMCID: PMC368440 DOI: 10.1186/1472-6904-4-1] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 10/20/2003] [Accepted: 02/09/2004] [Indexed: 11/10/2022]
Abstract
BACKGROUND Chronic atrial fibrillation is a prevalent cardiac disorder. The literature indicates varying proportions of those treated with anticoagulants, and varying intensity of anticoagulation. Electronic patient records are providing us with clinical data concerning management of anticoagulant treatment in real-life practice that is useful for audits. We aimed to assess warfarin treatment for chronic atrial fibrillation in primary health care with regard to prevalence, incidence, the proportion treated and the quality of anticoagulation control. METHODS Five primary health care centres in Stockholm with a registered population of 75146 participated in a one-year retrospective study of electronic patient records up until May 2000. All patients over 18 years of age with an encounter labelled 'Atrial fibrillation' were identified, and all records of patients on warfarin treatment were manually reviewed. Main outcome measures were number of patients with chronic atrial fibrillation, number of patients on wafarin treatment, and time within the therapeutic prothrombin range. RESULTS In total, 419 patients had chronic atrial fibrillation, giving a prevalence of 0.60% (age-adjusted 0.62%), the age group 65 years or older accounted for 91.6%, and 50.1% were women. Out of these, 50.4% (211 patients) were established on warfarin treatment for chronic atrial fibrillation (0.28% of the population), and there was a predominance of men (p = 0.02). Fifty-four patients started treatment with warfarin for chronic atrial fibrillation (0.07% of the population). Among 25 randomly selected patients on established treatment, the proportion of time within the therapeutic range was 70.2%. Among 24 randomly selected patients starting treatment, the proportion of time with therapeutic values was 54.2% and 66.9% the first and second months of treatment, respectively. CONCLUSIONS Chronic atrial fibrillation is common among the elderly in primary health care, and about half of these patients are treated with warfarin. It appears to be under-diagnosed, and may also be under-treated. About two thirds of treatment time is spent within the therapeutic range, and further improvement of the quality of anticoagulation control with warfarin may therefore be hard to achieve.
Collapse
Affiliation(s)
- Gunnar H Nilsson
- Department of Medicine, Research Unit of General Practice, Karolinska Institutet, Stockholm, Sweden
| | - Ingela Björholt
- Institute of Surgical Sciences, Göteborg University, Sahlgrenska University Hospital, Göteborg, Sweden
| |
Collapse
|
11
|
Ruiz Ortiz M, Romo Peñas E, Franco Zapata M, Mesa Rubio D, Anguita Sánchez M, López Granados A, Arizón del Prado JM, Vallés Belsué F. Un protocolo prospectivo permite incrementar la utilización de anticoagulación oral en pacientes con fibrilación auricular crónica no valvular. Rev Esp Cardiol 2003; 56:971-7. [PMID: 14563291 DOI: 10.1016/s0300-8932(03)76994-2] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
Abstract
INTRODUCTION AND OBJECTIVES Observational studies have shown that oral anticoagulants (OAC) prescription is suboptimal in patients with nonvalvular atrial fibrillation (NVAF). Our objective was to evaluate the usefulness of a prospective protocol for increasing OAC usage in these patients. PATIENTS AND METHOD From 1 February 2000 until 31 October 2002 we enrolled all patients with chronic NVAF seen in two outpatient cardiology clinics, excluding candidates for cardioversion. Each patient was studied to identify cardioembolic risk factors (CERF) and contraindications for OAC. Anticoagulation was suggested to all patients with > or =2 CERF and without contraindications for OAC. The decision to prescribe OAC was made by the physician in charge when there was only one CERF. RESULTS 721 patients fulfilled the inclusion criteria. Mean age was 73 +/- 8 years; 44% were men. In most cases NVAF was related with hypertension (57%), followed by no structural heart disease (25%) or ischemic heart disease (9%). The most frequent CERFs were hypertension (66%), age > or =75 years (45%) and diabetes (24%). A total of 663 patients had > or =1 CERF (92%), and 125 (19%) of these presented at least one contraindication for OAC. Of the 538 remaining patients (90%), 485 (67% of the whole series) were treated with anticoagulation. Of the patients with > or =2 CERF and without contraindications for OAC, 95% were treated. CONCLUSIONS A prospective protocol for use in the outpatient cardiology clinic allows to prescribe OAC in a large percentage of patients with NVAF.
Collapse
|