Development and feasibility of a smartphone, ECG and GPS based system for remotely monitoring exercise in cardiac rehabilitation

Background Despite its efficacy and cost-effectiveness, exercise-based cardiac rehabilitation is undertaken by less than one-third of clinically eligible cardiac patients in every country for which data is available. Reasons for non-participation include the unavailability of hospital-based rehabilitation programs, or excessive travel time and distance. For this reason, there have been calls for the development of more flexible alternatives. Methodology and Principal Findings We developed a system to enable walking-based cardiac rehabilitation in which the patient's single-lead ECG, heart rate, GPS-based speed and location are transmitted by a programmed smartphone to a secure server for real-time monitoring by a qualified exercise scientist. The feasibility of this approach was evaluated in 134 remotely-monitored exercise assessment and exercise sessions in cardiac patients unable to undertake hospital-based rehabilitation. Completion rates, rates of technical problems, detection of ECG changes, pre- and post-intervention six minute walk test (6 MWT), cardiac depression and Quality of Life (QOL) were key measures. The system was rated as easy and quick to use. It allowed participants to complete six weeks of exercise-based rehabilitation near their homes, worksites, or when travelling. The majority of sessions were completed without any technical problems, although periodic signal loss in areas of poor coverage was an occasional limitation. Several exercise and post-exercise ECG changes were detected. Participants showed improvements comparable to those reported for hospital-based programs, walking significantly further on the post-intervention 6 MWT, 637 m (95% CI: 565–726), than on the pre-test, 524 m (95% CI: 420–655), and reporting significantly reduced levels of cardiac depression and significantly improved physical health-related QOL. Conclusions and Significance The system provided a feasible and very flexible alternative form of supervised cardiac rehabilitation for those unable to access hospital-based programs, with the potential to address a well-recognised deficiency in health care provision in many countries. Future research should assess its longer-term efficacy, cost-effectiveness and safety in larger samples representing the spectrum of cardiac morbidity and severity.

Cardiac parasympathetic reactivation following exercise : implications for training prescription

The objective of exercise training is to initiate desirable physiological adaptations that ultimately enhance physical work capacity. Optimal training prescription requires an individualized approach, with an appropriate balance of training stimulus and recovery and optimal periodization. Recovery from exercise involves integrated physiological responses. The cardiovascular system plays a fundamental role in facilitating many of these responses, including thermoregulation and delivery/removal of nutrients and waste products. As a marker of cardiovascular recovery, cardiac parasympathetic reactivation following a training session is highly individualized. It appears to parallel the acute/intermediate recovery of the thermoregulatory and vascular systems, as described by the supercompensation theory. The physiological mechanisms underlying cardiac parasympathetic reactivation are not completely understood. However, changes in cardiac autonomic activity may provide a proxy measure of the changes in autonomic input into organs and (by default) the blood flow requirements to restore homeostasis. Metaboreflex stimulation (e.g. muscle and blood acidosis) is likely a key determinant of parasympathetic reactivation in the short term (0–90 min post-exercise), whereas baroreflex stimulation (e.g. exercise-induced changes in plasma volume) probably mediates parasympathetic reactivation in the intermediate term (1–48 h post-exercise). Cardiac parasympathetic reactivation does not appear to coincide with the recovery of all physiological systems (e.g. energy stores or the neuromuscular system). However, this may reflect the limited data currently available on parasympathetic reactivation following strength/resistance-based exercise of variable intensity. In this review, we quantitatively analyse post-exercise cardiac parasympathetic reactivation in athletes and healthy individuals following aerobic exercise, with respect to exercise intensity and duration, and fitness/training status. Our results demonstrate that the time required for complete cardiac autonomic recovery after a single aerobic-based training session is up to 24 h following low-intensity exercise, 24–48 h following threshold-intensity exercise and at least 48 h following high-intensity exercise. Based on limited data, exercise duration is unlikely to be the greatest determinant of cardiac parasympathetic reactivation. Cardiac autonomic recovery occurs more rapidly in individuals with greater aerobic fitness. Our data lend support to the concept that in conjunction with daily training logs, data on cardiac parasympathetic activity are useful for individualizing training programmes. In the final sections of this review, we provide recommendations for structuring training microcycles with reference to cardiac parasympathetic recovery kinetics. Ultimately, coaches should structure training programmes tailored to the unique recovery kinetics of each individual.

Mixed venous oxygen saturation monitoring revisited : thoughts for critical care nursing practice

Background Less invasive methods of determining cardiac output are now readily available. Using indicator dilution technique, for example has made it easier to continuously measure cardiac output because it uses the existing intra-arterial line. Therefore gone is the need for a pulmonary artery floatation catheter and with it the ability to measure left atrial and left ventricular work indices as well the ability to monitor and measure a mixed venous saturation (SvO2). Purpose The aim of this paper is to put forward the notion that SvO2 provides valuable information about oxygen consumption and venous reserve; important measures in the critically ill to ensure oxygen supply meets cellular demand. In an attempt to portray this, a simplified example of the septic patient is offered to highlight the changing pathophysiological sequelae of the inflammatory process and its importance for monitoring SvO2. Relevance to clinical practice SvO2 monitoring, it could be argued, provides the gold standard for assessing arterial and venous oxygen indices in the critically ill. For the bedside ICU nurse the plethora of information inherent in SvO2 monitoring could provide them with important data that will assist in averting potential problems with oxygen delivery and consumption. However, it has been suggested that central venous saturation (ScvO2) might be an attractive alternative to SvO2 because of its less invasiveness and ease of obtaining a sample for analysis. There are problems with this approach and these are to do with where the catheter tip is sited and the nature of the venous admixture at this site. Studies have shown that ScvO2 is less accurate than SvO2 and should not be used as a sole guiding variable for decision-making. These studies have demonstrated that there is an unacceptably wide range in variance between ScvO2 and SvO2 and this is dependent on the presenting disease, in some cases SvO2 will be significantly lower than ScvO2. Conclusion Whilst newer technologies have been developed to continuously measure cardiac output, SvO2 monitoring is still an important adjunct to clinical decision-making in the ICU. Given the information that it provides, seeking alternatives such as ScvO2 or blood samples obtained from femorally placed central venous lines, can unnecessarily lead to inappropriate treatment being given or withheld. Instead when using ScvO2, trending of this variable should provide clinical determinates that are useable for the bedside ICU nurse, remembering that in most conditions SvO2 will be approximately 16% lower.

Design of a Wearable Remote Neonatal Health Monitoring Device

In this text we present the design of a wearable health monitoring device capable of remotely monitoring health parameters of neonates for the first few weeks after birth. The device is primarily aimed at continuously tracking the skin temperature to indicate the onset of hypothermia in newborns. A medical grade thermistor is responsible for temperature measurement and is directly interfaced to a microcontroller with an integrated bluetooth low energy radio. An inertial sensor is also present in the device to facilitate breathing rate measurement which has been discussed briefly. Sensed data is transferred securely over bluetooth low energy radio to a nearby gateway, which relays the information to a central database for real time monitoring. Low power optimizations at both the circuit and software levels ensure a prolonged battery life. The device is packaged in a baby friendly, water proof housing and is easily sterilizable and reusable.

The effect of a perceptual cognitive task on exercise performance: the dual-task condition after brain injury

Objective: To examine the effect of additional cognitive demand on cycling performance in individuals with acquired brain injury (ABI). Design: Prospective observational study. Setting: Rivermead Rehabilitation Centre. Participants: Ten individuals with ABI ( 7 men, 3 women) ( traumatic brain injury 7, tumour 1, stroke 2) and 10 healthy controls ( 6 men, 4 women). Intervention: Individuals were asked to maintain a set cadence during a three-stage incremental cycling test in both single-task ( no additional task) and dual-task ( whilst performing an additional cognitive task) conditions. Results: The ABI group showed a slight slowing in cadence in stages 1 and 3 of the graded exercise test from the single-to the dual-task condition, although this was not significant ( p less than or equal to 0.05). The control group showed no slowing of cadence at any incremental stage. When directly comparing the ABI with the control group, the change in cadence observed in dual-task conditions was only significantly different in stage 3 ( p less than or equal to 0.05). Conclusions: Clinicians should be aware of the possibility that giving additional cognitive tasks ( such as monitoring exercise intensity) while individuals with acquired brain injury are performing exercises may detrimentally affect performance. The effect may be more marked when the individuals are performing exercise at higher intensities.

Effects of Cold Water Immersion and Active Recovery on Post-Exercise Heart Rate Variability

The aim of the present study was to investigate the potential benefits of cold water immersion (CWI) and active recovery (AR) on blood lactate concentration ([Lac]) and heart rate variability (HRV) indices following high-intensity exercise. 20 male subjects were recruited. on the first visit, an incremental test was performed to determine maximal oxygen consumption and the associated speed (MAS). The remaining 3 visits for the performance of constant velocity exhaustive tests at MAS and different recovery methods (6 min) were separated by 7-day intervals [randomized: CWI, AR or passive recovery (PR)]. The CWI and AR lowered [Lac] (p < 0.05) at 11, 13 and 15 min after exercise cessation in comparison to PR. There was a 'time' and 'recovery mode' interaction for 2 HRV indices: standard deviation of normal R-R intervals (SDNN) (partial eta squared = 0.114) and natural log of low-frequency power density (lnLF) (partial eta squared = 0.090). CWI presented significantly higher SDNN compared to PR at 15 min of recovery (p < 0.05). In addition, greater SDNN values were found in CWI vs. AR during the application of recovery interventions, and at 30 and 75 min post-exercise (p < 0.05 for all differences). The lnLF during the recovery interventions and at 75 min post-exercise was greater using CWI compared with AR (p < 0.05). For square root of the mean of the sum of the squares of differences between adjacent R-R intervals (RMSSD) and natural log of high-frequency power density (lnHF), a moderate effect size was found between CWI and PR during the recovery interventions and at 15 min post-exercise. Our findings show that AR and CWI offer benefits regarding the removal of [Lac] following high-intensity exercise. While limited, CWI results in some improvement in post-exercise cardiac autonomic regulation compared to AR and PR. Further, AR is not recommended if the aim is to accelerate the parasympathetic reactivation.

Prescribing and regulating exercise with RPE after heart transplant: a pilot study

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Hemodynamic response in one session of strength exercise with and without electrostimulation in heart failure patients: a randomized controlled trial

Background: Studies have investigated the influence of neuromuscular electrostimulation on the exercise/muscle capacity of patients with heart failure (HF), but the hemodynamic overload has never been investigated. The aim of our study was to evaluate the heart rate (HR), systolic and diastolic blood pressures in one session of strength exercises with and without neuromuscular electrostimulation (quadriceps) in HF patients and in healthy subjects. Methods: Ten (50% male) HF patients and healthy subjects performed three sets of eight repetitions with and without neuromuscular electrostimulation randomly, with one week between sessions. Throughout, electromyography was performed to guarantee the electrostimulation was effective. The hemodynamic variables were measured at rest, again immediately after the end of each set of exercises, and during the recovery period. Results: Systolic and diastolic blood pressures did not change during each set of exercises among either the HF patients or the controls. Without electrostimulation: among the controls, the HR corresponding to the first (85 ± 13 bpm, p = 0.002), second (84 ± 10 bpm, p < 0.001), third (89 ± 17, p < 0.001) sets and recuperation (83 ± 16 bpm, p = 0.012) were different compared to the resting HR (77 bpm). Moreover, the recuperation was different to the third set (0.018). Among HF patients, the HR corresponding to the first (84 ± 9 bpm, p = 0.041) and third (84 ± 10 bpm, p = 0.036) sets were different compared to the resting HR (80 ± 7 bpm), but this increase of 4 bpm is clinically irrelevant to HF. With electrostimulation: among the controls, the HR corresponding to the third set (84 ± 9 bpm) was different compared to the resting HR (80 ± 7 bmp, p = 0.016). Among HF patients, there were no statistical differences between the sets. The procedure was well tolerated and no subjects reported muscle pain after 24 hours. Conclusions: One session of strength exercises with and without neuromuscular electrostimulation does not promote a hemodynamic overload in HF patients. (Cardiol J 2011; 18, 1: 39-46)

Maximal muscular vascular conductances during whole body upright exercise in humans

[EN] That muscular blood flow may reach 2.5 l kg(-1) min(-1) in the quadriceps muscle has led to the suggestion that muscular vascular conductance must be restrained during whole body exercise to avoid hypotension. The main aim of this study was to determine the maximal arm and leg muscle vascular conductances (VC) during leg and arm exercise, to find out if the maximal muscular vasodilatory response is restrained during maximal combined arm and leg exercise. Six Swedish elite cross-country skiers, age (mean +/-s.e.m.) 24 +/- 2 years, height 180 +/- 2 cm, weight 74 +/- 2 kg, and maximal oxygen uptake (VO(2,max)) 5.1 +/- 0.1 l min(-1) participated in the study. Femoral and subclavian vein blood flows, intra-arterial blood pressure, cardiac output, as well as blood gases in the femoral and subclavian vein, right atrium and femoral artery were determined during skiing (roller skis) at approximately 76% of VO(2,max) and at VO(2,max) with different techniques: diagonal stride (combined arm and leg exercise), double poling (predominantly arm exercise) and leg skiing (predominantly leg exercise). During submaximal exercise cardiac output (26-27 l min(-1)), mean blood pressure (MAP) (approximately 87 mmHg), systemic VC, systemic oxygen delivery and pulmonary VO2(approximately 4 l min(-1)) attained similar values regardless of exercise mode. The distribution of cardiac output was modified depending on the musculature engaged in the exercise. There was a close relationship between VC and VO2 in arms (r= 0.99, P < 0.001) and legs (r= 0.98, P < 0.05). Peak arm VC (63.7 +/- 5.6 ml min(-1) mmHg(-1)) was attained during double poling, while peak leg VC was reached at maximal exercise with the diagonal technique (109.8 +/- 11.5 ml min(-1) mmHg(-1)) when arm VC was 38.8 +/- 5.7 ml min(-1) mmHg(-1). If during maximal exercise arms and legs had been vasodilated to the observed maximal levels then mean arterial pressure would have dropped at least to 75-77 mmHg in our experimental conditions. It is concluded that skeletal muscle vascular conductance is restrained during whole body exercise in the upright position to avoid hypotension.

Parameters and algorithms to evaluate cardiac mechanics by conductance catheter

This work is structured as follows: In Section 1 we discuss the clinical problem of heart failure. In particular, we present the phenomenon known as ventricular mechanical dyssynchrony: its impact on cardiac function, the therapy for its treatment and the methods for its quantification. Specifically, we describe the conductance catheter and its use for the measurement of dyssynchrony. At the end of the Section 1, we propose a new set of indexes to quantify the dyssynchrony that are studied and validated thereafter. In Section 2 we describe the studies carried out in this work: we report the experimental protocols, we present and discuss the results obtained. Finally, we report the overall conclusions drawn from this work and we try to envisage future works and possible clinical applications of our results. Ancillary studies that were carried out during this work mainly to investigate several aspects of cardiac resynchronization therapy (CRT) are mentioned in Appendix. -------- Ventricular mechanical dyssynchrony plays a regulating role already in normal physiology but is especially important in pathological conditions, such as hypertrophy, ischemia, infarction, or heart failure (Chapter 1,2.). Several prospective randomized controlled trials supported the clinical efficacy and safety of cardiac resynchronization therapy (CRT) in patients with moderate or severe heart failure and ventricular dyssynchrony. CRT resynchronizes ventricular contraction by simultaneous pacing of both left and right ventricle (biventricular pacing) (Chapter 1.). Currently, the conductance catheter method has been used extensively to assess global systolic and diastolic ventricular function and, more recently, the ability of this instrument to pick-up multiple segmental volume signals has been used to quantify mechanical ventricular dyssynchrony. Specifically, novel indexes based on volume signals acquired with the conductance catheter were introduced to quantify dyssynchrony (Chapter 3,4.). Present work was aimed to describe the characteristics of the conductancevolume signals, to investigate the performance of the indexes of ventricular dyssynchrony described in literature and to introduce and validate improved dyssynchrony indexes. Morevoer, using the conductance catheter method and the new indexes, the clinical problem of the ventricular pacing site optimization was addressed and the measurement protocol to adopt for hemodynamic tests on cardiac pacing was investigated. In accordance to the aims of the work, in addition to the classical time-domain parameters, a new set of indexes has been extracted, based on coherent averaging procedure and on spectral and cross-spectral analysis (Chapter 4.). Our analyses were carried out on patients with indications for electrophysiologic study or device implantation (Chapter 5.). For the first time, besides patients with heart failure, indexes of mechanical dyssynchrony based on conductance catheter were extracted and studied in a population of patients with preserved ventricular function, providing information on the normal range of such a kind of values. By performing a frequency domain analysis and by applying an optimized coherent averaging procedure (Chapter 6.a.), we were able to describe some characteristics of the conductance-volume signals (Chapter 6.b.). We unmasked the presence of considerable beat-to-beat variations in dyssynchrony that seemed more frequent in patients with ventricular dysfunction and to play a role in discriminating patients. These non-recurrent mechanical ventricular non-uniformities are probably the expression of the substantial beat-to-beat hemodynamic variations, often associated with heart failure and due to cardiopulmonary interaction and conduction disturbances. We investigated how the coherent averaging procedure may affect or refine the conductance based indexes; in addition, we proposed and tested a new set of indexes which quantify the non-periodic components of the volume signals. Using the new set of indexes we studied the acute effects of the CRT and the right ventricular pacing, in patients with heart failure and patients with preserved ventricular function. In the overall population we observed a correlation between the hemodynamic changes induced by the pacing and the indexes of dyssynchrony, and this may have practical implications for hemodynamic-guided device implantation. The optimal ventricular pacing site for patients with conventional indications for pacing remains controversial. The majority of them do not meet current clinical indications for CRT pacing. Thus, we carried out an analysis to compare the impact of several ventricular pacing sites on global and regional ventricular function and dyssynchrony (Chapter 6.c.). We observed that right ventricular pacing worsens cardiac function in patients with and without ventricular dysfunction unless the pacing site is optimized. CRT preserves left ventricular function in patients with normal ejection fraction and improves function in patients with poor ejection fraction despite no clinical indication for CRT. Moreover, the analysis of the results obtained using new indexes of regional dyssynchrony, suggests that pacing site may influence overall global ventricular function depending on its relative effects on regional function and synchrony. Another clinical problem that has been investigated in this work is the optimal right ventricular lead location for CRT (Chapter 6.d.). Similarly to the previous analysis, using novel parameters describing local synchrony and efficiency, we tested the hypothesis and we demonstrated that biventricular pacing with alternative right ventricular pacing sites produces acute improvement of ventricular systolic function and improves mechanical synchrony when compared to standard right ventricular pacing. Although no specific right ventricular location was shown to be superior during CRT, the right ventricular pacing site that produced the optimal acute hemodynamic response varied between patients. Acute hemodynamic effects of cardiac pacing are conventionally evaluated after stabilization episodes. The applied duration of stabilization periods in most cardiac pacing studies varied considerably. With an ad hoc protocol (Chapter 6.e.) and indexes of mechanical dyssynchrony derived by conductance catheter we demonstrated that the usage of stabilization periods during evaluation of cardiac pacing may mask early changes in systolic and diastolic intra-ventricular dyssynchrony. In fact, at the onset of ventricular pacing, the main dyssynchrony and ventricular performance changes occur within a 10s time span, initiated by the changes in ventricular mechanical dyssynchrony induced by aberrant conduction and followed by a partial or even complete recovery. It was already demonstrated in normal animals that ventricular mechanical dyssynchrony may act as a physiologic modulator of cardiac performance together with heart rate, contractile state, preload and afterload. The present observation, which shows the compensatory mechanism of mechanical dyssynchrony, suggests that ventricular dyssynchrony may be regarded as an intrinsic cardiac property, with baseline dyssynchrony at increased level in heart failure patients. To make available an independent system for cardiac output estimation, in order to confirm the results obtained with conductance volume method, we developed and validated a novel technique to apply the Modelflow method (a method that derives an aortic flow waveform from arterial pressure by simulation of a non-linear three-element aortic input impedance model, Wesseling et al. 1993) to the left ventricular pressure signal, instead of the arterial pressure used in the classical approach (Chapter 7.). The results confirmed that in patients without valve abnormalities, undergoing conductance catheter evaluations, the continuous monitoring of cardiac output using the intra-ventricular pressure signal is reliable. Thus, cardiac output can be monitored quantitatively and continuously with a simple and low-cost method. During this work, additional studies were carried out to investigate several areas of uncertainty of CRT. The results of these studies are briefly presented in Appendix: the long-term survival in patients treated with CRT in clinical practice, the effects of CRT in patients with mild symptoms of heart failure and in very old patients, the limited thoracotomy as a second choice alternative to transvenous implant for CRT delivery, the evolution and prognostic significance of diastolic filling pattern in CRT, the selection of candidates to CRT with echocardiographic criteria and the prediction of response to the therapy.

An initiative for participatory monitoring of large scale acquisitions: Opportunities and results thus far

Increasing commercial pressures on land are provoking fundamental and far-reaching changes in the relationships between people and land. Much knowledge on land-oriented investments projects currently comes from the media. Although this provides a good starting point, lack of transparency and rapidly changing contexts mean that this is often unreliable. The International Land Coalition, in partnership with Oxfam Novib, Centre de coopération internationale en recherche agronomique pour le développement (CIRAD), University of Pretoria, Centre for Development and Environment of the University of Bern (CDE), and GIZ, started to compile an inventory of land-related investments. This project aims to better understand the extent, trends and impacts of land-related investments by supporting an ongoing and systematic stocktaking exercise of the various investment projects currently taking place worldwide. It involves a large number of organizations and individuals working in areas where land transactions are being made, and able to provide details of such investments. The project monitors land transactions in rural areas that imply a transformation of land use rights from communities and smallholders to commercial use, and are made both by domestic and foreign investors (private actors, governments, government-back private investors). The focus is on investments for food or agrofuel production, timber extraction, carbon trading, mineral extraction, conservation and tourism. A novel way of using ITC to document land acquisitions in a spatially explicit way and by using an approach called “crowdsourcing” is being developed. This approach will allow actors to share information and knowledge directly and at any time on a public platform, where it will be scrutinized in terms of reliability and cross checked with other sources. Up to now, over 1200 deals have been recorded across 96 countries. Details of such transactions have been classified in a matrix and distributed to over 350 contacts worldwide for verification. The verified information has been geo-referenced and represented in two global maps. This is an open database enabling a continued monitoring exercise and the improvement of data accuracy. More information will be released over time. The opportunities arise from overcoming constraints by incomplete information by proposing a new way of collecting, enhancing and sharing information and knowledge in a more democratic and transparent manner. The intention is to develop interactive knowledge platform where any interested person can share and access information on land deals, their link to involved stakeholders, and their embedding into a geographical context. By making use of new ICT technologies that are more and more in the reach of local stakeholders, as well as open access and web-based spatial information systems, it will become possible to create a dynamic database containing spatial explicit data. Feeding in data by a large number of stakeholders, increasingly also by means of new mobile ITC technologies, will open up new opportunities to analyse, monitor and assess highly dynamic trends of land acquisition and rural transformation.

Evidence of cardiac injury and arrhythmias in dogs with acute kidney injury

OBJECTIVES Cardiac involvement in the course of acute kidney injury is described in humans as cardiorenal syndrome type 3 but has received only limited attention in dogs. This study was designed to evaluate cardiac injury and dysfunction in acute kidney injury in dogs and its association with outcome. METHODS This prospective cohort study enrolled 24 client-owned dogs with acute kidney injury. Cardiac disorders were evaluated with thoracic radiographs, echocardiography, 24-hour Holter monitoring and cardiac troponin I concentrations within 2 days of admission and 7 to 10 days later. RESULTS Most dogs were diagnosed with leptospirosis (n=18, 75%) and presented with moderate-to-severe acute kidney injury, International Renal Interest Society grades III to V. Dogs with ê100 ventricular premature complexes per 24 hour in the first examination (n=8) had significantly higher initial cTnI concentrations (P=0·007) compared to dogs with fewer than 100. In receiver operating characteristic curve analysis, the number of ventricular premature complexes was predictive of outcome (AUC 0·83, P<0·001). CLINICAL SIGNIFICANCE Acute kidney injury seems to be associated with cardiac injury and arrhythmias in dogs. The data do not indicate a cardiac cause of poor outcome in dogs with increased number of ventricular premature complexes but the association may reflect the severity of disease.

New Concepts for PVC Detection

A new scheme is proposed for the detection of premature ventricular beats, which is a vital function in rhythm monitoring of cardiac patients. A transformation based on the first difference of the digitized electrocardiogram (ECG) signal is developed for the detection and delineation of QRS complexes. The method for classifying the abnormal complexes from the normal ones is based on the concepts of minimum phase and signal length. The parameters of a linear discriminant function obtained from a training feature vector set are used to classify the complexes. Results of application of the scheme to ECG of two arrhythmia patients are presented.