Ventricular Fibrillation Detection Research Articles

Prediction and Detection of Ventricular Fibrillation Using Complex Features and AI-Based Classification

We analyzed the possibility of detecting and predicting ventricular fibrillation (VF), a medical emergency that may put people’s lives at risk, as the medical prognosis depends on the time in which medical personnel intervene. Therefore, besides immediate detection of VF, the possibility of predicting VF 40 or even 50 min in advance was analyzed. For testing the proposed algorithm, we used ECG signals taken from the MIT-BIH database, namely, Malignant Ventricular Ectopy Database, Sudden Cardiac Death Holter Database and Normal Sinus Rhythm Database. The presented method is based on features extracted from the ECG signals in the time domain, frequency domain and complexity measures. For VF detection, the possibility of identifying the VF episode in the first 3 s after its occurrence was tested. For this, the first 3 s immediately after the appearance of VF were cut out and the features were computed on these sections. For VF prediction, 3 min of the ECG signal clipped 40 or 50 min before VF onset was used. Then, on these pieces of ECG signal, the specific features were calculated for 1 s segments. For the normal signal situation, 3 min was randomly selected from the database with normal ECGs. For the classification or detection stage, both an MLP-type neural network and the classifiers from the Machine Learning toolbox of the MATLAB® environment were used. The results obtained for both detection and classification are over 94% in both cases. The novelty of our results compared to those previously obtained is the time interval with which the possibility of prediction was analyzed, namely, 50 min in advance of the VF installation date. This means that the patient will be informed that it is possible to suffer a VF and has time to take the necessary measures to overcome a possible medical emergency.

Detection of Ventricular Fibrillation Using Ensemble Empirical Mode Decomposition of ECG Signals

Ventricular fibrillation (VF) is a critical ventricular arrhythmia with severe consequences. Due to the severity of VF, it urgently requires a rapid and accurate detection of abnormal patterns in ECG signals. Here, we present an efficient method to detect abnormal electrocardiogram (ECG) signals associated with VF by measuring orthogonality between intrinsic mode functions (IMFs) derived from a data-driven decomposition method, namely, ensemble empirical mode decomposition (EEMD). The proposed method incorporates the decomposition of the ECG signal into its IMFs using EEMD, followed by the computation of the angles between subsequent IMFs, especially low-order IMFs, as the features to discriminate normal and abnormal ECG patterns. The proposed method was validated through experiments using a public MIT-BIH ECG dataset for its effectiveness in detecting VF ECG signals compared to conventional methods. The proposed method achieves a sensitivity of 99.22%, a specificity of 99.37%, and an accuracy of 99.28% with a 3 s ECG window and a support vector machine (SVM) with a linear kernel, which performs better than existing VF detection methods. The capability of the proposed method can provide a perspective approach for the real-time and practical computer-aided diagnosis of VF.

The Rate of Success of CPR in Patients Suffering from Cardiac Arrest in Patients Admitted in CCU in Cardiology Department Ayub Medical Teaching Institute

Cardiopulmonary resuscitation (CPR) is an essential procedure used to treat patients who are in cardiac arrest, particularly in the Critical Care Unit (CCU). Objective: To assess the success rate of CPR admitted to the CCU, revealing insight on the effectiveness of current resuscitation techniques. Methods: This retrospective study was conducted at Department of Cardiology Ayub Medical Teaching Institute, Abbottabad, between 13th April 2023 to 30th November 2023, 110 patients had cardiac arrest while in the intensive care unit. Data were gathered and examined on patient demographics, pre-existing comorbidities, time to start CPR, duration of CPR, and results. CPR success was defined as a sustained restoration of spontaneous circulation (ROSC) for at least 20 minutes. Results: This study included 110 cardiac patients. Most patients (68.18%) were male. Hypertension was the most common comorbidity at 72.7%. CPR started on average 4.8 minutes late, with a 1.2-minute standard deviation. The average CPR time was 18.2 minutes, with a 5.6-minute SD. After cardiac arrest, 60 (54.5%) patients began CPR within 5 minutes. Another subgroup found 96.0% CPR success in 25 (22.7%) ventricular fibrillation patients. Then occurred ventricular tachycardia (80.0%), pulseless electrical activity (76.0%), and asystole (68.9%). These data suggest that CPR works better in ventricular fibrillation patients. Conclusions: This research sheds light on cardiac arrest CCU patients' demographics, care, and outcomes. The data show that early CPR and ventricular fibrillation detection and treatment improve outcomes for these individuals.

Dysfunction of CRT-D in acute myocardial infarction: is there a place for programing?

The article describes a clinical case of a patient with a previously implanted cardiac resynchronization therapy with defibrillator function (CRT-D). For a long time, the patient was observed in the implanting clinic and the data was also transmitted via remote monitoring. The developing acute myocardial infarction in the right coronary artery caused a change in the parameter of the amplitude of the spontaneous R-wave in the patient. Subsequent ventricular fibrillation (VF) due to stent thrombosis was undetected by the defibrillator and resulted in no detection and cessation of VF, despite the implanted CRT-D. Changing the programming parameters did not affect the possibility of detecting a recurrent VF. The VF that occurred twice was stopped by the first discharge of the external device. In view of the remaining low hyposensing, a decision was made to reimplant the detecting part of the right ventricular electrode, after which defibrillation test proved to be effective for termination induced VF. We believe that at critically low parameters of spontaneous R-wave hyposensing, for the device to detect low-amplitude ventricular arrhythmias, programming the parameters does not solve the problem of hyposensing. Current myocardial infarction as the cause of hyposensing may require active surgical tactics replacement of the pacing and sensing electrode, in cases where the device connector allows this.

Abstract 106: Assessing Out-of-Hospital Cardiac Arrest Management With a New Automated External Defibrillator Algorithm: A Prospective Before-After Study on Ventricular Fibrillation Detection During Chest Compressions With a Shortened CPR Cycle

Introduction: During out-of-hospital cardiac arrests (OHCA), AEDs analyze cardiac rhythm every 2 minutes with chest compressions (CC) having to be interrupted. Since 2021, the Paris Fire Brigade has used AEDs equipped with an "Analysis While Compressing" (AWC) module that enables an external electric shock (EES) to be delivered every minute if required. This new algorithm aligns AED analysis timing with potential VF recurrence but results in redistribution between CC time and analysis periods. We aimed to assess the CC fraction (CCF) in OHCA patients who received AWC and compared it with the CCF in 2017 patients who received a standard (STD) algorithm. Method: In this observational, prospective before-after study, we included adult non-traumatic OHCA patients with initial Ventricular Fibrillation (iVF) rescued by firefighters. Their AEDs provided STD algorithm in 2017 and AWC algorithm in 2022. All AED parameters were measured within 10 minutes of the initial shock. Primary outcome was the CCF, a criterion sensitive to algorithm modifications. Secondary outcomes were pre and post-shock pauses, and the percentage of time the cardiac rhythm was organized. We matched patients from both periods on four key covariates (sex, age, location, bystander status) using propensity score matching. The estimator for continuous variables was the median [interquartile range]. Results: We included 285 consecutive patients in each period. Most were men, 74% (212/285) in 2017 and 81% (231/285) in 2022; median ages were 58 [49-69] and 60 [51-72] years. After propensity score matching, CCF improved significantly with the AWC algorithm (77% [72%-80%]) vs. the STD algorithm (72% [67%-76%], p<0.01). Pre and post-shock pauses decreased from 19 [17-23] and 4.5 [3-6] to 11[9-16] and 3.8 [2-5] sec. in 2017 and 2022, respectively (p < 0.01). Delay from VF recurrence to the next shock decreased from 124 [92-135] sec. in 2017 to 60 [37-71] sec. in 2022 (p< 0.01). The time spent in an organized rhythm during the first ten min. of AED connection increased from 7 % [0-46] in 2017 to 14% [0-58] in 2022 (p< 0.01). Conclusion: AWC improved hands-on times, CCF, and time ratio spent in cardiac organized rhythm. Further analyses are underway to measure its impact on survival at hospital discharge.

Efficient Extraction of Deep Image Features Using a Convolutional Neural Network (CNN) for Detecting Ventricular Fibrillation and Tachycardia.

To safely select the proper therapy for ventricular fibrillation (VF), it is essential to distinguish it correctly from ventricular tachycardia (VT) and other rhythms. Provided that the required therapy is not the same, an erroneous detection might lead to serious injuries to the patient or even cause ventricular fibrillation (VF). The primary innovation of this study lies in employing a CNN to create new features. These features exhibit the capacity and precision to detect and classify cardiac arrhythmias, including VF and VT. The electrocardiographic (ECG) signals utilized for this assessment were sourced from the established MIT-BIH and AHA databases. The input data to be classified are time-frequency (tf) representation images, specifically, Pseudo Wigner-Ville (PWV). Previous to Pseudo Wigner-Ville (PWV) calculation, preprocessing for denoising, signal alignment, and segmentation is necessary. In order to check the validity of the method independently of the classifier, four different CNNs are used: InceptionV3, MobilNet, VGGNet and AlexNet. The classification results reveal the following values: for VF detection, there is a sensitivity (Sens) of 98.16%, a specificity (Spe) of 99.07%, and an accuracy (Acc) of 98.91%; for ventricular tachycardia (VT), the sensitivity is 90.45%, the specificity is 99.73%, and the accuracy is 99.09%; for normal sinus rhythms, sensitivity stands at 99.34%, specificity is 98.35%, and accuracy is 98.89%; finally, for other rhythms, the sensitivity is 96.98%, the specificity is 99.68%, and the accuracy is 99.11%. Furthermore, distinguishing between shockable (VF/VT) and non-shockable rhythms yielded a sensitivity of 99.23%, a specificity of 99.74%, and an accuracy of 99.61%. The results show that using tf representations as a form of image, combined in this case with a CNN classifier, raises the classification performance above the results in previous works. Considering that these results were achieved without the preselection of ECG episodes, it can be concluded that these features may be successfully introduced in Automated External Defibrillation (AED) and Implantable Cardioverter Defibrillation (ICD) therapies, also opening the door to their use in other ECG rhythm detection applications.

Low Risk of Inappropriate Shock Among Pediatric Patients With an Implantable Cardioverter Defibrillator: A Single Center Experience.

Implantable cardioverter-defibrillators (ICD) are increasingly being used among the pediatric population for indications of both primary and secondary prevention. There is limited long-term data on the outcomes of pediatric patients following ICD implantation. The aim of this study was to investigate the characteristics of this population, burden of appropriate and inappropriate shock and complication rate in a large tertiary pediatric medical center. Included were children under the age of 18years who underwent ICD implantation and had clinical follow up at our center. Data were retrospectively collected between study period 2005-2020. Primary outcome was the incidence of ICD shock appropriate and inappropriate. Secondary outcome was defining our patient population characteristics. Our cohort included 51 patients who underwent ICD implantation. Mean age at implantation was 10.9 ± 4.7years and average follow-up time was 67months. Diagnoses of implanted patients were: 28 (55%) patients with syndromes with risk for sudden death, cardiomyopathy in 14 patients (27%) and congenital heart disease (CHD) in 9 patients (18%). Forty-two (82%) patients had an ICD implanted for secondary prevention after experiencing a life-threatening arrhythmia and 9 (18%) for primary prevention. An endocardial system was implanted in 39 (76%) patients and an epicardial systems in 12 (24%) patients. A total of 20 (39%) patients received appropriate shocks for ventricular fibrillation(VF). 5 patients received inappropriate shocks, 4 due to sinus tachycardia and 1 due to rapidly conducted atrial fibrillation. Those who received an inappropriate shock had a significantly shorter ICD-programmed VF detection cycle length compared to those who did not receive an inappropriate shock (320ms versus 270ms, p = 0.062). This single center study demonstrates a high rate of appropriate ICD shocks (39%) and a low rate of inappropriate ICD shocks. Accurate programming of ICD devices in the pediatric population is paramount to avoid inappropriate ICD shocks.

Defibrillation testing during S-ICD implantation: How relevant? Results from a multicenter study

Abstract Funding Acknowledgements Type of funding sources: None. Introduction Defibrillation testing (DFT) is still recommended in patients with subcutaneous implantable cardioverter-defibrillator (S-ICD) to ensure proper detection of ventricular fibrillation and confirm effective defibrillation. Given the significant risk of complications, recent studies, are reconsidering the interest of the DFT in S-ICD. The purpose of this study was to assess the clinical "real-life" outcomes of DFT over a mid-term follow-up period after third-generation S-ICD implantation. Methods and Results 368 patients (pts) (47.9 ± 15.5 years old; male 72.8%) implanted with Generation 3 S-ICD system were included in this retrospective multicenter registry-based study. Mean left ventricular ejection fraction (LVEF) was 40.8% (primary prevention 56.1%). For 99.2% pts, S-ICD implantation was performed using the two-incision technique and intermuscular positioning of the generator was performed for all pts. 81% pts underwent ICD testing during implantation. Reasons for not performing DFT were: very low LVEF (3.5%), intracardiac thrombus (2.4%) and VF induction failure. In 2.2% (8 pts) DFT was unsuccessful, causes were: induction of ventricular tachycardias with rates falling below the shock zone for 3 pts while shocks were ineffective for 5 pts. One patient required revision for contralateral lead implantation, while sensing vector reprogramming and shock polarity modification were efficient for the others. The mean impedance was 68.4 (±14.7) Ω and time to shock therapy ranged from 10 to 33 s, with a mean of 16.7 (±4) s. A total of 36 appropriate shocks (10.1%) have been observed after a FU period of 11.02±8.8 months (1.8 shocks per patient, several shocks for 12pts, failure of the first shock for 5 patients). 17 patients (4.6%) underwent S-ICD system extraction. The reasons were pocket site complication (7 pts), pacing indication for cardiac resynchronization therapy or bradycardia (3 pts), and S-ICD lead dysfunction (4 pts). Extraction after heart transplant was needed in 3 pts. Among the 4 pts explanted for system dysfunction, only one patient had a DFT during implantation. After a mean follow-up of 19±12.1 months, the mortality rate was 3.8% (no S-ICD-related deaths were reported). There was no significant difference between the 2 groups of pts with and without DFT testing (p=0.629). Conclusion The DFT remains for the moment highly recommended during S-ICD implantations. Results from randomized studies are still needed to confirm the relevance of DFT during S-ICD implantation.

Defibrillation test in paediatric patients: should be done?

Abstract Funding Acknowledgements Type of funding sources: None. The defibrillation test (DFT) of an implantable cardioverter-defibrillator (ICD) is performed to evaluate ventricular fibrillation detection and termination. In adults, routine defibrillation testing for transvenous ICD is less usually done as some studies found no advantages but some potentially risks associated with. On the other hand, implantation of ICDs in paediatric patients has different characteristics than in adults. The position of the defibrillation coil will change with the body’s growth and could reflect changes in the defibrillation vector. Also, the reasons of implantation of an ICD are different (ventricular arrhythmias frequently associated with adult’s myocardial infarction vs channelopathies, non-ischemic myocardiopathies and congenital heart defects in children and young). There is still lack of information about the utility of the DFT in paediatric patients. Objective To describe the characteristics of paediatric patients who underwent implantation of an ICD , results of DFT and follow-up. Methodology Retrospective cohort study of patients less than 21 years old who underwent implantation of an ICD in the lasts 10 years at a reference paediatric hospital. In DFT, VF was induced by T wave shock, fast burst pacing or continuous direct current. Response of ICD to VF was evaluated. Patients with failure to terminate VF by ICD were defibrillated with external defibrillator. Results 68 patients with 73 ICD implantations (five replacements). Median age was 13 years old. The youngest patient was 2 years old and the oldest 21 years old. 72.6% (53/73) of patients underwent DFT. In 90.6% (48/53) of them, a VF was induced. In two patients (4%, 2/48) the ICD did not terminate the VF. One of these patients had Danon syndrome and the VF did not terminate despite of maximum energy discharged and changes in the vector of defibrillation; the problem was fixed with replacement of the single coil lead by a dual coil system. The other patient had arrhythmogenic cardiomyopathy and the ICD did not detect the VF. During the follow up, there were 20 shocks in 13 patients. 13 shocks were appropriate (and successful). One patient died because of non-arrhythmic illness. Conclusions In paediatric patients, the defibrillation test is useful to ensure both adequate detection of malignant ventricular arrhythmias, as well as their ability to reverse them. Its lack of performance could affect 4% of the implants. Therefore, its performance in paediatric patients is recommended. There could be greater utility in patients with hypertrophic cardiomyopathy.

PO-05-078 SHOCK REDUCTION THROUGH EARLY DELIVERY OF ANTITACHYCARDIA PACING FOR FAST VENTRICULAR TACHYCARDIAS

Antitachycardia pacing (ATP) is a programmable therapy in implantable cardiac defibrillator (ICD) devices that has been demonstrated to effectively reduce the need for shocks. Limited data, however, exists on the potential benefits of early ATP delivery in the ventricular fibrillation (VF) zone. While ATP is programmed to be delivered as a first line of therapy for ventricular tachycardia (VT) events, it does so only once the episode meets detection criteria by the ICD. Newer generations of BIOTRONIK ICDs have the ability for earlier delivery of ATP, called Early ATP OneShot, to be programmed in the VF therapy zone. Early ATP is delivered when 12 out of 16 events, plus stability criteria, are met to target fast VTs detected in the programmed VF therapy zone. This option is available for patients with longer detection times (VF detection counters of 16 out of 20 or higher) and allows the device to deliver ATP before episode detection counter criteria is met, thus providing therapy earlier than traditional ATP. To compare the success rates of Early ATP OneShot (eATP) for episodes in the VF zone against traditional ATP OneShot (tATP) programming. Using BIOTRONIK’s real-world research database, CERTITUDE, 696 patients with eATP capable ICD devices with VF episodes transmitted via remote monitoring were divided into groups based on tATP (n=584) or eATP (n=112) programming for the VF therapy zone. Each device detected episode was evaluated to determine the therapy (ATP and/or shocks) delivered, whether therapy was successful, or if the episode self-terminated. Patients with detection zone counters lower than 16 out of 20 were excluded. eATP was successful in 69.4% of cases in terminating episodes in the VF zone whereas tATP was successful in 49.1% of cases (p<0.0001). Extrapolation of the eATP success rate to the tATP cohort results in 30.0% less shocks (203 avoided shocks out of 676 total shocks). Cohorts did not differ statistically in mean R-R interval at episode detection, nor in device programming for detection limit zone or counters. Episode duration was shorter in the eATP cohort (p<0.0001). As compared to traditional programming, use of Early ATP OneShot provides increased success rates to terminate fast VTs detected in the VF zone, potentially reducing unnecessary shocks.Tabled 1Table: Comparison of ATP Therapy Groups for Device Detected VF Episodes (PO-05-078)OutcomeEarly ATP OneShotTraditional ATP OneShotp value (difference)Patients with VF Event112584-ATP Therapy Success Rate (Successes/Attempts)69.4% (161/232)49.1% (491/1001)<0.0001Median VF Episode Duration (sec)1217<0.0001Mean R-R interval at VF Episode Detection (ms)2572530.17Mean Programmed Rate of VF Detection Limit (ms)2882910.20Median Programmed Detection Counters for Programmed VF Zone (X/Y criteria)18/2418/240.94 Open table in a new tab

New atrial arrhythmia occurrence in single chamber implantable cardioverter defibrillator patients: A real-world investigation.

A current limitation of single chamber implantable cardioverter defibrillators (ICDs) is the lack of an atrial lead to reliably detect atrial fibrillation (AF) episodes. A novel ventricular based atrial fibrillation (VBAF) detection algorithm was created for single chamber ICDs to assess R-R variability for detection of AF. Patients implanted with Visia AF™ ICDs were prospectively enrolled in the Medtronic Product Surveillance Registry from December 15, 2015 to January 23, 2019 and followed with at least 30 days of monitoring with the algorithm. Time to device-detected daily burden of AF ≥ 6 min, ≥6 h, and ≥23 h were reported. Clinical actions after device-detected AF were recorded. A total of 291 patients were enrolled with a mean follow-up of 22.5 ± 7.9 months. Of these, 212 (73%) had no prior history of AF at device implant. However, 38% of these individuals had AF detected with the VBAF algorithm with daily burden of ≥6 min within two years of implant. In these 80 patients with newly detected AF by their ICD, 23 (29%) had a confirmed clinical diagnosis of AF by their provider. Of patients with a clinical diagnosis of AF, nine (39%) were newly placed on anticoagulation, including five of five (100%) patients having a burden >23 h. Continuous AF monitoring with the new VBAF algorithm permits early identification and actionable treatment for patients with undiagnosed AF that may improve patient outcomes.

Ventricular Fibrillation and Tachycardia Detection Using Features Derived from Topological Data Analysis

A rapid and accurate detection of ventricular arrhythmias is essential to take appropriate therapeutic actions when cardiac arrhythmias occur. Furthermore, the accurate discrimination between arrhythmias is also important, provided that the required shocking therapy would not be the same. In this work, the main novelty is the use of the mathematical method known as Topological Data Analysis (TDA) to generate new types of features which can contribute to the improvement of the detection and classification performance of cardiac arrhythmias such as Ventricular Fibrillation (VF) and Ventricular Tachycardia (VT). The electrocardiographic (ECG) signals used for this evaluation were obtained from the standard MIT-BIH and AHA databases. Two input data to the classify are evaluated: TDA features, and Persistence Diagram Image (PDI). Using the reduced TDA-obtained features, a high average accuracy near 99% was observed when discriminating four types of rhythms (98.68% to VF; 99.05% to VT; 98.76% to normal sinus; and 99.09% to Other rhythms) with specificity values higher than 97.16% in all cases. In addition, a higher accuracy of 99.51% was obtained when discriminating between shockable (VT/VF) and non-shockable rhythms (99.03% sensitivity and 99.67% specificity). These results show that the use of TDA-derived geometric features, combined in this case this the k-Nearest Neighbor (kNN) classifier, raises the classification performance above results in previous works. Considering that these results have been achieved without preselection of ECG episodes, it can be concluded that these features may be successfully introduced in Automated External Defibrillation (AED) and Implantable Cardioverter Defibrillation (ICD) therapies.

A method for continuous rhythm classification and early detection of ventricular fibrillation during CPR

AimWe developed a method which continuously classifies the ECG rhythm during CPR in order to guide clinical care. MethodsWe conducted a retrospective study of 432 patients treated following out-of-hospital cardiac arrest. Continuous ECG sequences from two-minute CPR cycles were extracted from defibrillator recordings and further divided into five-second clips. We developed an algorithm using wavelet analysis, hidden semi-Markov modeling, and random forest classification. The algorithm classifies individual clips as asystole, organized rhythm, ventricular fibrillation, or Inconclusive while integrating information from previous clips. Classifications were compared to manual annotations to estimate accuracy in an independent validation dataset. Continuous sequences were classified as shockable, non-shockable, or Inconclusive; classifications were used to compute shock sensitivity and specificity. ResultsOf 432 patient-cases, 290 were used for development and 142 for validation. In the 12,294 validation ECG clips during CPR, accuracies were 0.88 (95% CI 0.85–0.91) for asystole, 0.98 (95% CI 0.98–0.99) for organized rhythm, and 0.97 (95% CI 0.96–0.97) for ventricular fibrillation, with 43% classified as Inconclusive. Of 457 continuous sequences, shock sensitivity was 0.90 (95% CI 0.86–0.93), shock specificity was 0.98 (95% CI 0.93–0.99), and 7% were Inconclusive. Median delay to ventricular fibrillation recognition was 10 (IQR 5–32) seconds. ConclusionA novel algorithm continuously classified the primary resuscitation rhythms—asystole, organized rhythms, and ventricular fibrillation—with 88–98% accuracy, enabling accurate shock advisory guidance during most two-minute CPR cycles. Additional investigation is required to understand how algorithm implementation could affect rescuer actions and clinical outcomes.

Personalized subcutaneous implantable cardioverter-defibrillator sensing vectors generated by mathematical rotation increase device eligibility whilst preserving device performance

Approximately 5.7% of potential subcutaneous implantable cardioverter-defibrillator (S-ICD) recipients are ineligible by virtue of their vector morphology, with higher rates of ineligibility observed in some at-risk groups. Mathematical vector rotation is a novel technique that can generate a personalized sensing vector, one with maximal R:T ratio, using electrocardiogram (ECG) signal recorded from the present S-ICD location. A cohort of S-ICD ineligible patients were identified through ECG screening of ICD patients with no ventricular pacing requirement and their personalized vectors were generated using ECG signal from a Holter monitor. Subcutaneous ICD eligibility in this cohort was then recalculated. In a separate cohort, episodes of arrhythmia were recorded in patients undergoing arrhythmia induction, and arrhythmia detection in standard S-ICD vectors was compared to rotated vectors using an S-ICD simulator. Ninety-two participants (mean age 64.9 ± 2.7 years) underwent screening and 5.4% were found to be S-ICD ineligible. Personalized vector generation increased the R:T ratio in these vectors from 2.21 to 7.21 (4.54-9.88, P < 0.001) increasing the cohort eligibility from 94.6% to 100%. Rotated S-ICD vectors also showed high ventricular fibrillation (VF) detection sensitivity (97.8%), low time to VF detection (6.1 s), and excellent tachycardia discrimination (sensitivity 96%, specificity 88%), with no significant differences between rotated and standard vectors. In S-ICD ineligible patients, mathematical vector rotation can generate a personalized vector that is associated with a significant increase in R:T ratio, resulting in universal device eligibility in our cohort. Ventricular fibrillation detection efficacy, time to VF detection, and tachycardia discrimination were not affected by vector rotation.

Non-transvenous ICD therapy: current status and beyond.

Subcutaneous implantable cardioverter/defibrillators (S-ICDs) have been developed to offer ICD treatment to patients without venous access to the heart and to overcome complications associated with transvenous leads, particularly lead fracture/insulation defects and endocarditis. Several studies and registries have demonstrated the feasibility and safety of S‑ICD in different groups of patients. Further developments in S‑ICD technology involve the combination with devices that can provide anti-bradycardia and anti-tachycardia pacing if needed. The extravascular ICD (EV-ICD) is anew system that similarly offers ICD therapy without atransvenous lead but uses asubsternal instead of asubcutaneous lead to facilitate detection of ventricular fibrillation and to provide anti-tachycardia and also temporary anti-bradycardia pacing. The first animal but also clinical data on EV-ICDs have been published. This review discusses the current state, potential advantages and limitations, and future research of both S‑ICD and EV-ICD.

DETECTION OF VENTRICULAR FIBRILLATION USING WAVELET TRANSFORM AND PHASE SPACE RECONSTRUCTION FROM ECG SIGNALS

This study proposes the detection of ventricular fibrillation (VF) by wavelet transforms (WTs) and phase space reconstruction (PSR) from electrocardiogram (ECG) signals. A neural network with weighted fuzzy memberships (NEWFM) is used to detect VF as a classifier. In the first step, the WT was used to remove noise in ECG signals. In the second step, coordinates were mapped from the wavelet coefficients by the PSR. In the final step, NEWFM used the mapped coordinates-based features as inputs. The NEWFM has the bounded sum of weighted fuzzy memberships (BSWFM) that can easily appear the distinctness between the normal sinus rhythm (NSR) and VF in the graphical characteristics. The BSWFM can easily be set up in a portable automatic external defibrillator (AED) to detect VF in an emergency.

Real-time machine learning-based intensive care unit alarm classification without prior knowledge of the underlying rhythm.

AimsThis work attempts to develop a standalone heart rhythm alerting system for the intensive care unit (ICU), where life-threatening arrhythmias have to be identified/alerted more precisely and more instantaneously (i.e. with lower latency) than existing bedside monitors. Methods and resultsWe use the dataset from the PhysioNet 2015 Challenge, which contains records that led to true and false arrhythmic alarms in the ICU. These records have been re-annotated as one of eight classes, namely (i) asystole, (ii) extreme bradycardia, (iii) extreme tachycardia, (iv) ventricular fibrillation (VF), (v) ventricular tachycardia (VT), (vi) normal sinus rhythm, (vii) sinus tachycardia, and (viii) noise/artefacts. Arrhythmia-specific features and features that measure the signal quality were extracted from all the records. To improve VF detection, an improved, over an existing, single-lead R-wave detection was developed that takes into account the R-waves detected in all electrocardiographic (ECG) leads. To avoid false R-wave detection due to pacing spikes, ECG signals were filtered with a low pass filter prior to R-wave detection, while the raw signals were used for feature extraction. Random forest was used as the classifier, and 10-time five-fold cross-validation, resulted in a macro-average sensitivity of 81.54%.ConclusionsIn conclusion, comparing with the bedside monitors used in the PhysioNet 2015 competition, we find that our method achieves higher positive predictive values for asystole, extreme bradycardia, VT, and VF; furthermore, our method is able to alert the presence of arrhythmia instantaneously, i.e. up to 4 s earlier.

Cardiac arrhythmia spot light: Detection of ventricular fibrillation-Not all ICDs are created equal.

Intracardiac device electrograms demonstrating differing VF sensing performance between two manufacturer ICD generators.

Detection of Ventricular Fibrillation Based on Ballistocardiography by Constructing an Effective Feature Set.

Ventricular fibrillation (VF) is a type of fatal arrhythmia that can cause sudden death within minutes. The study of a VF detection algorithm has important clinical significance. This study aimed to develop an algorithm for the automatic detection of VF based on the acquisition of cardiac mechanical activity-related signals, namely ballistocardiography (BCG), by non-contact sensors. BCG signals, including VF, sinus rhythm, and motion artifacts, were collected through electric defibrillation experiments in pigs. Through autocorrelation and S transform, the time-frequency graph with obvious information of cardiac rhythmic activity was obtained, and a feature set of 13 elements was constructed for each 7 s segment after statistical analysis and hierarchical clustering. Then, the random forest classifier was used to classify VF and non-VF, and two paradigms of intra-patient and inter-patient were used to evaluate the performance. The results showed that the sensitivity and specificity were 0.965 and 0.958 under 10-fold cross-validation, and they were 0.947 and 0.946 under leave-one-subject-out cross-validation. In conclusion, the proposed algorithm combining feature extraction and machine learning can effectively detect VF in BCG, laying a foundation for the development of long-term self-cardiac monitoring at home and a VF real-time detection and alarm system.

Design and Preliminary Results of Sensing and Detection for an Extravascular Implantable Cardioverter-Defibrillator.

This study reports the sensing and arrhythmia detection performance of a novel extravascular (EV) implantable cardioverter-defibrillator (ICD) in a first-in-human pilot study. The EV ICD lead is implanted in the substernal space, resulting in novel sensing and detection challenges. It uses a programmable sensing profile with new or modified discrimination of oversensing and of ventricular tachycardia (VT) from supraventricular tachycardia (SVT). Electrograms were post-processed from induced ventricular fibrillation (VF) at implant to determine virtual detection times for each programmable sensitivity and the least-sensitive safe sensitivity setting. In ambulatory patients, programmed sensitivity provided at least a twofold safety margin for detecting induced VF. Noise discrimination was stress tested, and the effects of source, posture, and lead maturation were determined on electrogram amplitude. Telemetry Holter monitors were used to quantify undersensing and oversensing. In 20 patients at implant, the least-sensitive safe sensitivity for VF detection ranged from 0.1 to 0.6mV. Seventeen patients were followed up for a total of 16.6 patient-years. Electrogram amplitudes were stable over time, but there were significant differences among postures and sensing vectors. For the primary sensing vector, the weighted oversensing and undersensing rates were 1.03% and 0.40% respectively, on a beat-to-beat basis. Oversensing did not cause inappropriate therapy in patients with in situ leads. Oversensing discriminators withheld VF detection in 4 of 5 spontaneous, sustained oversensed episodes. SVT-VT discriminators correctly classified 93% of 128 sustained SVTs in monitor zones. In the EV ICD pilot study, oversensing did not cause inappropriate therapy during ambulatory follow-up of stable leads.