Advanced ECG Research Articles

Predicting CRT Response Using Machine Learning Analysis of Pre-Implant ECG Data

Introduction: Despite the use of guideline based selection criteria between 10 to 20% of patients will be non-responders to CRT. We evaluated the predictors of response using pre-implant clinical, echocardiographic, 12L advanced ECG (A-ECG) and the application of machine learning. Methods: 61 consecutive patients referred for CRT were identified. Digital ECG files were processed using a novel algorithm, echocardiographic metadata, clinical factors and outcomes were sourced from electronic clinical records. Statistical analysis using Medcalc and Microsoft Azure Machine Learning (ML) was applied. Results: 15 (26%) patients were considered non-responders, based on clinical and echocardiographic criteria. Non-responders had lower stroke volume, LV mass, as well as larger LVESD and LVOT area. A-ECG univariate predictors of response included QTc (AUC 0.74, 95%CI 0.6 - 0.8, p = 0.0007), QRS area and vectorcardiographic markers of RV dysfunction. A neural network of 4 ECG features yielded an AUC 0.77 compared with an AUC of 0.56 using a control feature set of traditional CRT selection criteria (cardiomyopathy type, QRSd, LVEF, and AF presence). Conclusion: Numerous clinical features are associated with CRT nonresponse. Of these, QTc had the highest discriminatory ability, though this was enhanced with multivariate ML.

Expecting the Expected: Electrocardiographic Identification for Ablation Targets.

An invariable hallmark of an experienced invasive electrophysiologist is his or her ability to thoroughly examine preprocedural data so as to anticipate the likely site of successful ablation. Indeed, teaching rounds for electrophysiology at any institution is likely replete with examples of how careful analysis of the ECG and structural imaging data are used to anticipate not only where to ablate but also the specific anatomic hurdles that may be encountered, facilitating planning to avoid complications. Although advanced imaging has become increasingly useful to understand substrate abnormalities, the mainstay for preprocedural prediction of successful ablation remains the ECG. See Article by Namdar et al From the outset, the field of electrophysiology has relied heavily on the ECG for clinical and invasive diagnoses. Every student’s knowledge base includes ECG localization for accessory pathways and detailed ECG vector analysis to diagnose the origin of monomorphic ventricular tachycardia and atrial tachycardia.1 In this installment of Teaching Rounds in Cardiac Electrophysiology, Namdar et al2 add to this legacy instructing us on an advanced multielectrode surface ECG analysis system that allowed a surprisingly high degree of spatial resolution in identifying a coronary venous epicardial ventricular tachycardia focus. The authors elegantly instruct us on the use of the new system, but, more importantly, provide a …

Athlete's heart versus arrhythmogenic cardiomyopathy by advanced ECG criteria

A 27-year old male patient was admitted to the hospital because of non-exercise related chest pain. Until 2007 he accomplished competitive sports.

Analysis of ECG Measures of Cardiac Repolarization in Relation to Arrhythmic Events in an Implantable Cardioverter Defibrillator Population

ECG-derived measures of cardiac repolarization may have utility in risk prediction of future ventricular arrhythmia, and a range of different measures have been proposed. We compared time-based, vectorcardiographic, and singular value decomposition (SVD) derived measures of repolarization to determine which was most predictive of appropriate therapy in an ICD population. We examined the independent prognostic value of a range of repolarization measures derived from 60 second 12-lead ECG recordings in 150 patients receiving new ICD implants in relation to the occurrence of appropriate therapy during follow-up. Over an average follow-up of 2.15 ± 0.87 years, male gender, presence of premature ventricular complex (PVC), relative T wave residuum (TWR-rel, measures regional repolarization heterogeneity), and TCRT (the total cosine R-to-T, describes the global angle between repolarization and depolarization wavefronts) were the only independent predictors of appropriate therapy. With every 0.01% increase in TWR-rel, there was 2% increased risk of appropriate therapy (HR = 1.02, 95% CI 1.006-1.034, P < 0.001). With every 1° decrease in TCRT, there was an increase in arrhythmic risk of 0.9% (HR 1.009, 95% CI 1.003-1.015, P = 0.003). The use of advanced analytic ECG techniques to derive measures of repolarization abnormality might shave utility in risk stratification in an ICD population.

MYBPC3 hypertrophic cardiomyopathy can be detected by using advanced ECG in children and young adults

IntroductionThe conventional ECG is commonly used to screen for hypertrophic cardiomyopathy (HCM), but up to 25% of adults and possibly larger percentages of children with HCM have no distinctive abnormalities on the conventional ECG, whereas 5 to 15% of healthy young athletes do. Recently, a 5-min resting advanced 12-lead ECG test (“A-ECG score”) showed superiority to pooled criteria from the strictly conventional ECG in correctly identifying adult HCM. The purpose of this study was to evaluate whether in children and young adults, A-ECG scoring could detect echocardiographic HCM associated with the MYBPC3 genetic mutation with greater sensitivity than conventional ECG criteria and distinguish healthy young controls and athletes from persons with MYBPC3 HCM with greater specificity. MethodsFive-minute 12-lead ECGs were obtained from 15 young patients (mean age 13.2years, range 0–30years) with MYBPC3 mutation and phenotypic HCM. The conventional and A-ECG results of these patients were compared to those of 198 healthy children and young adults (mean age 13.2, range 1month-30years) with unremarkable echocardiograms, and to those of 36 young endurance-trained athletes, 20 of whom had athletic (physiologic) left ventricular hypertrophy. ResultsCompared with commonly used, age-specific pooled criteria from the conventional ECG, a retrospectively generated A-ECG score incorporating results from just 2 derived vectorcardiographic parameters (spatial QRS-T angle and the change in the vectorcardiographic QRS azimuth angle from the second to the third eighth of the QRS interval) increased the sensitivity of ECG for identifying MYBPC3 HCM from 46% to 87% (p<0.05). Use of the same score also demonstrated superior specificity in a set of 198 healthy controls (94% vs. 87% for conventional ECG criteria; p<0.01) including in a subset of 36 healthy, young endurance-trained athletes (100% vs. 69% for conventional ECG criteria, p<0.001). ConclusionsIn children and young adults, a 2-parameter 12-lead A-ECG score is retrospectively significantly more sensitive and specific than pooled, age-specific conventional ECG criteria for detecting MYBPC3-HCM and in distinguishing such patients from healthy controls, including endurance-trained athletes.

Differential diagnosis of arrhythmogenic right ventricular cardiomyopathy and granulomatous myocarditis by advanced ECG analysis

In nearly 12% of cases arrhythmogenic cardiomyopathy can be diagnosed without any typical ECG changes [1]. In the latest classification published by Frank Marcus in 2010 epsilon waves and T-wave inversions in right precordial leads are major ECG criteria that leads together with imaging techniques, formation of ventricular extrasystole and genetic information to the diagnosis of arrhythmogenic cardiomyopathy [2]. If typical ECG findings are missing atypical ECG changes like localized right precordial QRS prolongation, QRS fragmentation and typical changes in lead aVR (amplitude of Q wave 3 mm or more and R wave 2 mm or less and inverted T-waves) have been described [3]. We report a 50-year-old male patient whowas admitted to hospital because of chest pain and ventricular extrasystole. ECG revealed incomplete right bundle branchblock and no typical or atypical sign for arrhythmogenic cardiomyopathy (Fig. 1). Echocardiography showed normal contracting left ventricle and no signs of valvular dysfunction. The right ventricle had a sacculation in the right ventricular outflow tract without dilatation, a dilatation of the inferior region and sacculations of the apical area (Fig. 2). Coronary angiography showed normal coronary arteries and left ventricular angiography revealed normal contracting left ventricular without any segmental contraction impairment. But right ventricular angiography was abnormal with sacculation of the inferior region and a deep horizontal fissure of the apical segment.

Machine Learning Applied to Advanced ECG and Echocardiographic Metadata, in Patients with Left Ventricular Dysfunction

Patrick Gladding , Sarah Gleeson , Yi-Wen Liao , Clementina Dugo , Andrew Cave , Lifeng Zhou , Martin Orr , Kazuaki Negishi , Alan Borowski , Jagir Hussan , Peter Hunter , Mohammed Kassemi , David Martin , Benjamin Levine , Todd Schlegel , James Thomas 9 Waitemata DHB, Auckland, New Zealand Menzies Research Institute, University of Tasmania, Hobart, Tas, Australia Cleveland Clinic Foundation, Cleveland, Ohio, USA Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand NASA Glen Research Centre, Cleveland, Ohio, USA Wyle Science, Technology and Engineering Group, Houston, Texas, USA University of Texas Southwestern Medical Center, Dallas, Texas, USA Karolinska Institutet, and Nicollier-Schlegel Sarl, Stockholm, Trelex, Sweden, Switzerland Blumh Cardiovascular Institute, Northwestern University Feinberg School of Medicine, Chicago, Ill., USA, National Space Biomedical Research Foundation, Houston, Texas, USA Corresponding author.

Enhancement of electrocardiogram information value by identification of the ECG spectrum phases

The authors discuss feasibility to extract additional information about electrical activity of the heart from the ECG magnitude and phase spectrum. Fifty digitized ECG fragments from the MIT-BIH Arrhythmia Database and PhysioBank ECG repository data were analyzed. It was shown that ECG phase harmonics contains valuable information about the ECG signal that can be used eventually for the development of advanced ECG analysis tools.

Evaluating the Atrial Myopathy Underlying Atrial Fibrillation: Identifying the Arrhythmogenic and Thrombogenic Substrate.

Atrial disease or myopathy forms the substrate for atrial fibrillation (AF) and underlies the potential for atrial thrombus formation and subsequent stroke. Current diagnostic approaches in patients with AF focus on identifying clinical predictors with the evaluation of left atrial size by echocardiography serving as the sole measure specifically evaluating the atrium. Although the atrial substrate underlying AF is likely developing for years before the onset of AF, there is no current evaluation to identify the preclinical atrial myopathy. Atrial fibrosis is 1 component of the atrial substrate that has garnered recent attention based on newer MRI techniques that have been applied to visualize atrial fibrosis in humans with prognostic implications regarding the success of treatment. Advanced ECG signal processing, echocardiographic techniques, and MRI imaging of fibrosis and flow provide up-to-date approaches to evaluate the atrial myopathy underlying AF. Although thromboembolic risk is currently defined by clinical scores, their predictive value is mediocre. Evaluation of stasis via imaging and biomarkers associated with thrombogenesis may provide enhanced approaches to assess risk for stroke in patients with AF. Better delineation of the atrial myopathy that serves as the substrate for AF and thromboembolic complications might improve treatment outcomes. Furthermore, better delineation of the pathophysiologic mechanisms underlying the development of the atrial substrate for AF, particularly in its earlier stages, could help identify blood and imaging biomarkers that could be useful to assess risk for developing new-onset AF and suggest specific pathways that could be targeted for prevention.

High resolution ECG-aided early prognostic model for comatose survivors of out of hospital cardiac arrest

Out of hospital cardiac arrest (OHCA) has a high mortality despite modern treatment. Reliable early prognosis in OHCA could significantly improve clinical decision making. We explored prognostic utility of advanced ECG parameters, obtained from high-resolution ECG, in combination with clinical and OHCA-related parameters during treatment with mild induced hypothermia (MIH) and after rewarming in unconscious survivors of OHCA. Ninety-two patients during MIH and 66 after rewarming were included. During MIH, a score based on initial rhythm, QRS-upslope and systolic pressure resulted in an area under curve (AUC) of 0.82 and accuracy of 80% for survival. After rewarming, a score based on admission rhythm, sum of 12 lead QRS voltages, and mean lateral ST segment level in leads I and V6 resulted in an AUC of 0.88 and accuracy of 85% for survival. ECG can assist with early prognostication in unconscious survivors of OHCA during MIH and after rewarming.

Exhaled breath analysis using a carbon nanotube-based sensor array for metabolic and cardiovascular applications

Background: ETT has a sensitivity (68%) and specificity (77%) for angiographic coronary artery disease (CAD), leading to missed diagnoses as well as to false positive results. Advanced ECG (A-ECG) is a low-cost, software method for improving the diagnostic characteristics of traditional resting 12L-ECG. Methods: We retrospectively performed A-ECG analysis on the electronically stored, 10-sec resting 12L-ECG files of 58 patients with intermediate to high clinical suspicion of CAD who had positive ETT tests that prompted coronary angiography. A-ECG calls of ‘Disease’ versus ‘No Disease’ were made in a blinded and automated fashion on the stored data using a validated 6-parameter A-ECG score that combines results from certain conventional ECG parameters with those from T-wave complexity and derived 3-dimensional ECG. Results: Of the 58 patient 12L-ECGs, one was excluded due to noise and six due to other proven cardiac abnormalities found on echocardiography (e.g., LVH, systolic dysfunction). Resting A-ECG returned 42 ‘Disease’ and 9 ‘No Disease’ (e.g. Figure 1) calls with a sensitivity of 97.2% and specificity of 53% for the angiography results. By design in this retrospective study with known referral-bias, the positive ETT results were 71% sensitive and 0% specific for the same angiography results in the same patients. Conclusion: In this group of patients who underwent angiography prompted by positive ETT, the addition of A-ECG test to the ETT would have substantially increased overall specificity without statistically significantly compromising sensitivity. AECG would theoretically reduce unnecessary invasive coronary angiograms by 53%, with a cost savings of $528/A-ECG.

Wearable advanced single chip ECG telemonitoring system using SoPC

A lot of care must be taken to choose the processor for the biomedical application to meet out the real time constrains. Also the complexity of the programming increases with the multi processing environments. The real time Operating systems can support the problem up to a particular limit based on the processor architecture. When the hard real time parameters needs higher Multi processing environment, the processor struck to a limit. This paper deals with the wearable telemonitoring and Lab on chip feature for the 12 lead ECG interpretation and analysis with maintaining the patient history in case of arrhythmia like diseases. Instead of implementing the application on a single processor or FPGA solution, it is implemented using NIOS II (Altera IP core) based multi core architecture. The System on chip consists of GPS tracking, GSM base band work and the ECG processing elements and this proposes a most user friendly and wearable single medical chip. The idea of this paper is to improve the efficiency and speed of processing of the ECG interpretation and telemonitoring by separating tasks between the processors.

A usability evaluation of medical software at an expert conference setting

IntroductionA usability test was employed to evaluate two medical software applications at an expert conference setting. One software application is a medical diagnostic tool (electrocardiogram [ECG] viewer) and the other is a medical research tool (electrode misplacement simulator [EMS]). These novel applications have yet to be adopted by the healthcare domain, thus, (1) we wanted to determine the potential user acceptance of these applications and (2) we wanted to determine the feasibility of evaluating medical diagnostic and medical research software at a conference setting as opposed to the conventional laboratory setting. MethodsThe medical diagnostic tool (ECG viewer) was evaluated using seven delegates and the medical research tool (EMS) was evaluated using 17 delegates that were recruited at the 2010 International Conference on Computing in Cardiology. Each delegate/participant was required to use the software and undertake a set of predefined tasks during the session breaks at the conference. User interactions with the software were recorded using screen-recording software. The ‘think-aloud’ protocol was also used to elicit verbal feedback from the participants whilst they attempted the pre-defined tasks. Before and after each session, participants completed a pre-test and a post-test questionnaire respectively. ResultsThe average duration of a usability session at the conference was 34.69min (SD=10.28). However, taking into account that 10min was dedicated to the pre-test and post-test questionnaires, the average time dedication to user interaction of the medical software was 24.69min (SD=10.28). Given we have shown that usability data can be collected at conferences, this paper details the advantages of conference-based usability studies over the laboratory-based approach. For example, given delegates gather at one geographical location, a conference-based usability evaluation facilitates recruitment of a convenient sample of international subject experts. This would otherwise be very expensive to arrange. A conference-based approach also allows for data to be collected over a few days as opposed to months by avoiding administration duties normally involved in laboratory based approach, e.g. mailing invitation letters as part of a recruitment campaign.Following analysis of the user video recordings, 41 (previously unknown) use errors were identified in the advanced ECG viewer and 29 were identified in the EMS application. All use errors were given a consensus severity rating from two independent usability experts. Out of a rating scale of 4 (where 1=cosmetic and 4=critical), the average severity rating for the ECG viewer was 2.24 (SD=1.09) and the average severity rating for the EMS application was 2.34 (SD=0.97). We were also able to extract task completion rates and times from the video recordings to determine the effectiveness of the software applications. For example, six out of seven tasks were completed by all participants when using both applications. This statistic alone suggests both applications already have a high degree of usability. As well as extracting data from the video recordings, we were also able to extract data from the questionnaires. Using a semantic differential scale (where 1=poor and 5=excellent), delegates highly rated the ‘responsiveness’, ‘usefulness’, ‘learnability’ and the ‘look and feel’ of both applications. ConclusionThis study has shown the potential user acceptance and user-friendliness of the novel EMS and the ECG viewer applications within the healthcare domain. It has also shown that both medical diagnostic software and medical research software can be evaluated for their usability at an expert conference setting. The primary advantage of a conference-based usability evaluation over a laboratory-based evaluation is the high concentration of experts at one location, which is convenient, less time consuming and less expensive.

Impact of advanced exercise ECG analysis on cost of coronary artery disease management

Conventional analysis of exercise electrocardiogram (EX-ECG) has limited accuracy. This study aims to evaluate the potential impact of improving EX-ECG accuracy on costs of diagnosis and number of misdiagnoses of coronary artery disease (CAD). A decision-tree model was simulated including sequential application of diagnostic procedures for suspected CAD. The model was structured in two main branches (presence or absence of CAD). A probabilistic sensitivity analysis was then performed for several combinations of improvement in test sensitivity and specificity. A clear trend in cost reduction was observed at improving EX-ECG specificity (about 8-8.5 million dollars, corresponding to a 5.6-7.6% reduction according to the prevalence level). Wrong diagnoses counted for 9-13% of test. Improvements in test parameters lead to reductions in wrong diagnoses, especially when increasing specificity (8.8-12.5%). A proper improvement in EX-ECG sensitivity and specificity would have a relevant impact on the costs of CAD management, while reducing the number of misdiagnoses.

Accuracy of advanced versus strictly conventional 12-lead ECG for detection and screening of coronary artery disease, left ventricular hypertrophy and left ventricular systolic dysfunction

BackgroundResting conventional 12-lead ECG has low sensitivity for detection of coronary artery disease (CAD) and left ventricular hypertrophy (LVH) and low positive predictive value (PPV) for prediction of left ventricular systolic dysfunction (LVSD). We hypothesized that a ~5-min resting 12-lead advanced ECG test ("A-ECG") that combined results from both the advanced and conventional ECG could more accurately screen for these conditions than strictly conventional ECG.MethodsResults from nearly every conventional and advanced resting ECG parameter known from the literature to have diagnostic or predictive value were first retrospectively evaluated in 418 healthy controls and 290 patients with imaging-proven CAD, LVH and/or LVSD. Each ECG parameter was examined for potential inclusion within multi-parameter A-ECG scores derived from multivariate regression models that were designed to optimally screen for disease in general or LVSD in particular. The performance of the best retrospectively-validated A-ECG scores was then compared against that of optimized pooled criteria from the strictly conventional ECG in a test set of 315 additional individuals.ResultsCompared to optimized pooled criteria from the strictly conventional ECG, a 7-parameter A-ECG score validated in the training set increased the sensitivity of resting ECG for identifying disease in the test set from 78% (72-84%) to 92% (88-96%) (P < 0.0001) while also increasing specificity from 85% (77-91%) to 94% (88-98%) (P < 0.05). In diseased patients, another 5-parameter A-ECG score increased the PPV of ECG for LVSD from 53% (41-65%) to 92% (78-98%) (P < 0.0001) without compromising related negative predictive value.ConclusionResting 12-lead A-ECG scoring is more accurate than strictly conventional ECG in screening for CAD, LVH and LVSD.

Cardiac repolarization abnormalities and potential evidence for loss of cardiac sodium currents on electrocardiograms of patients with Chagas heart disease

Some individuals with Chagas disease develop right precordial lead ST segment elevation in response to an ajmaline challenge test, and the prevalence of right bundle branch block (RBBB) is also high in Chagas disease. Because these same electrocardiographic abnormalities occur in the Brugada syndrome, which involves genetically defective cardiac sodium channels, acquired damage to cardiac sodium channels may also occur in Chagas disease. We studied several conventional and advanced resting 12-lead/derived Frank-lead ECG parameters in 34 patients with Chagas -related heart disease (mean age 39 14 years) and in 34 age-/gender-matched healthy controls. All ECG recordings were of 5-10 min duration, obtained in the supine position using high fidelity hardware/software (CardioSoft, Houston, TX). Even after excluding those Chagas patients who had resting BBBs, tachycardia and/or pathologic arrhythmia (n=8), significant differences remained in multiple conventional and advanced ECG parameters between the Chagas and control groups (n=26/group), especially in their respective QT interval variability indices, maximal spatial QRS-T angles and low frequency HRV powers (p=0.0006, p=0.0015 and p=0.0314 respectively). In relation to the issue of potential damage to cardiac sodium channels, the Chagas patients had: 1) greater than or equal to twice the incidence of resting ST segment elevation in leads V1-V3 (n=10/26 vs. n=5/26) and of both leftward (n=5/26 versus n=0/26) and rightward (n=7/26 versus n=3/26) QRS axis deviation than controls; 2) significantly increased filtered (40-250 Hz) QRS interval durations (92.1 8.5 versus 85.3 plus or minus 9.0 ms, p=0.022) versus controls; and 3) significantly decreased QT and especially JT interval durations versus controls (QT interval: 387.5 plus or minus 26.4 versus 408.9 plus or minus 34.6 ms, p=0.013; JT interval: 290.5 plus or minus 26.3 versus 314.8 plus or minus 31.3 ms; p=0.0029). Heart rates and Bazett-corrected QTc/JTc intervals were not significantly different between groups. Patients with Chagas heart disease have increased cardiac repolarization abnormalities, especially by advanced ECG. Moreover, as a group, they have decreased uncorrected JT and QT interval durations and increased filtered QRS interval durations (versus age/gender-matched controls), all suggesting a potential loss of cardiac sodium channel function that might be mediated, in part, by cardiac autonomic damage. Overall findings support Brugada et al's recent hypothesis that the pathway leading to sudden death may often be similar in Chagas' disease and Brugada syndrome i.e., damage to the sodium channel (infectious/immunologic/autonomic in Chagas' genetic in Brugada) with consequent loss of sodium currents may facilitate a phase II-reentry based arrhythmic substrate for ventricular fibrillation in both conditions. In general, JT interval-related results have been underreported in the Chagas literature.

In vivo measurement of QT prolongation, dispersion and arrhythmogenesis: application to the preclinical cardiovascular safety pharmacology of a new chemical entity.

In addition to in silico and in vitro measurements, cardiac electrophysiology in experimental animals plays a decisive role in the selection of a potential 'cardio-safe' new chemical entity (NCE). The present synopsis critically reviews such in vivo techniques in experimental animals. In anaesthetized guinea-pigs, surface ECG recordings readily identify the typical effects of Class I to IV anti-arrhythmic compounds and of If blockers such as zatebradine on ECG intervals and morphology, but also of non-cardiovascular NCEs affecting cardiac electrical activity via ion channels or neurogenic mechanisms. QT/RR plots indicate that bradycardia is a dominant effect of IKr blockers (dual modulation by IKr of sinus node activity and ventricular repolarization). Nevertheless, correction of QT with Bazett's formula usually distinguishes between drug-induced heart rate reduction and real prolongation of ventricular repolarization (QTc). The anaesthetized guinea-pig model thus is a useful tool for first line in vivo testing of an NCE for effects on cardiac electrophysiology, in particular when combined with measurements of drug levels in plasma and heart tissues. In anaesthetized dogs, advanced ECG analyses identify drug-induced effects on atrial and ventricular intervals, on temporal and transmural dispersion of ventricular repolarization and on incidences of early after-depolarizations. This can be combined with complete haemodynamic, pulmonary and pharmacokinetic analyses in one preparation. However, compound doses/plasma levels needed for effects on ventricular repolarization in this model are substantially higher than those identified in guinea-pigs, at least for IKr blocking compounds. Therefore, we use this 'information-rich' canine model as a second line approach. In awake, trained and appropriately instrumented dogs, readings of surface ECG in combination with cardio-haemodynamic and behavioural assessments can be performed after the administration of an NCE via the expected therapeutic route, including oral medication. However, at higher doses the compound under scrutiny may induce overall behavioural side-effects, related to its primary pharmacological action, such as gastrokinetic repercussions or CNS-mediated sedation or excitation. Such primary pharmacological effects are bound to compromise the evaluation of real drug-induced changes on cardiac electrophysiology, readily identified by resource-friendly setups in smaller animals. Therefore, we use such paradigms as an imperative, final cardiovascular check-up, before a 'First in Man' administration of the NCE. In anaesthetized, methoxamine-challenged rabbits, arrhythmogenic effects of IKr blockers (torsades de pointes) and of dual channel INa/IKr blockers (conduction disturbances) are readily identified. Drug-induced QT dispersion rather than a 'simple' QTc prolongation determines the ventricular arrhythmogenic effect of IKr blockers. The latter effect also depends on the rate of drug delivery (plasma levels vs. heart level, equilibrium throughout the myocardium). Therefore, we use models sensitized for arrhythmogenesis to document further the profile of a comparatively 'cardio-safe' NCE. We conclude that the interpretation of an integrated profile of activity of an NCE on in vitro and in vivo cardiovascular parameters, in comparison with the characteristics of its primary pharmacology and target disease, determines its eventual selection via a scientific, rather than a 'checklist' or 'menu' approach to cardiovascular safety pharmacology. Appropriate tests in experimental animals play a key role in this process.

Signal processing and pattern recognition with soft computing

We describe the overall role of soft computing (SC) in signal processing and pattern recognition (SPPR) with specific applications to biomedical engineering, geoscience for mining and civil engineering human interfaces, and image processing. Detection of characteristic points in an electrocardiogram to implement an advanced ECG analyzer is presented which is carried out using both conventional SPPR techniques and self-organizing neural networks. Successful technologies for monitoring a geostructure by supervised and self-organizing neural networks are described. Identification of a freehand drawing by a combination of fuzzy logic and neural networks is also described. Moreover, application of fuzzy logic to image segmentation is presented. Finally, innovation of SPPR using SC technologies is discussed.

ECG interpretation for obstetric nurses

Obstetric nurses are not routinely called on to perform continuous cardiac monitoring or ECGs. However, obstetric nurses will be caring for most pregnant women with cardiac complications. Basic and advanced ECG courses and Advanced Cardiac Life Support (ACLS) courses are offered at most hospitals. Obstetric nurses are encouraged to take advantage of these courses, as even nurses in Level I institutions are caring for patients on continuous ECG monitors. A basic understanding of the ECG is expected of all nurses. Obstetric nurses are encouraged to participate in an ACLS program. Full reviews of the anatomy, physiology, and electrical pathways are available in numerous texts.

Effective extraction of diagnostic ECG waveform information using orthonormal basis functions derived from body surface potential maps

A common basis of orthogonal waveform functions was derived from 128 lead body surface potential maps of 405 subjects. Twelve such orthogonal functions or frames were adequate for reconstruction of original ECGs from the beginning of QRS to the end of T. A larger number of frames (18) was required when basis functions were derived separately for QRS (10) and ST-T segments (8). Diagnostic information content of the coefficients of the orthogonal basis functions was evaluated in comparison with Minnesota Code criteria for myocardial infarction and with a more advanced multivariate ECG analysis program (Pipberger Program). This was done by deriving a linear discriminant function for separating normals from ECGs of patients with myocardial infarction and testing the discriminant in a different test population of infarcts and normals. The diagnostic accuracy of orthogonal basis functions was as good as that of Pipberger's program and considerably better than that of the Minnesota Code. The classification method described is insensitive to noise and errors in detecting QRS and T wave onsets and offsets or in selecting proper baseline for amplitude measurements. The robustness and enhanced classification stability with respect to noise and minor wave detection errors is a potential advantage particularly in serial ECG comparison.