Optimal electrocardiographic lead systems: practical scenarios in smart clothing and wearable health systems.

Advances in wearable health systems, from a smart textile, signal processing, and wireless communications perspective, have resulted in the recent deployment of such systems in real clinical and healthcare settings. Nevertheless, the problem of identifying the most appropriate sites from which biological parameters can be recorded still remains unsolved. This paper aims to asses the effects of various practical constraints that may be encountered when choosing electrocardiographic recording sites for wearable health systems falling within the category of smart shirts for cardiac monitoring and analysis. We apply a lead selection algorithm to a set of 192 lead body surface potential maps (BSPM) and simulate a number of practical constraints by only allowing selection of recording sites from specific regions available in the 192 lead array. Of the various scenarios that were investigated, we achieved the best results when the selection process to identify the recording sites was constrained to an area around the precordial region. The top ten recording sites chosen in this region exhibited an rms voltage error of 25.8 mu V when they were used to estimate total ECG information. The poorest performing scenario was that which constrained the selection to two vertical strips on the posterior surface. The top ten recording sites chosen in this scenario exhibited an rms voltage error of 41.1 muV. In general, it was observed that out of all the scenarios investigated, those which constrained available regions to the posterior and lateral surfaces performed less favorably than those where electrodes could also be chosen on the anterior surface. The overall results from our approach have validated the proposed algorithm and its ability to select optimal recording sites taking into consideration the practical constraints that may exist with smart shirts.

Lead selection: old and new methods for locating the most electrocardiogram information.

The present article summarizes the work presented in several key studies over the past 3 decades in the area of limited lead selection. Specifically, we summarize the pioneering research of those investigators searching for the most "signal" information and those searching for the most "diagnostic" information. Initially, we present the work conducted by Barr et al and, later, Lux et al who investigated body surface potential maps to locate those recording sites containing the most signal information that subsequently facilitated the estimation of the electrical potentials at all other areas of the thoracic surface. Subsequently, the discussion focuses on the early work conducted by Kornreich et al, who used statistical methods to identify those recording sites containing optimal measurement features to improve upon the identification of different disease types. In addition to the aforementioned work, an overview of more recent complementary work is summarized.

Selection of optimal recording sites for limited lead body surface potential mapping in myocardial infarction and left ventricular hypertrophy.

A lead selection algorithm was applied to find optimal recording sites for limited lead body surface potential maps. The studied population consisted of a set of 117 lead body surface potential maps recorded from 744 subjects (229, normal; 278, with myocardial infraction [MI]; and 237, with left ventricular hypertrophy [LVH]). One generic lead set derived from all disease groups was found. Also found were 3 disease-specific lead sets (normal, MI, and LVH) and one specific to abnormal subjects (MI and LVH combined). The performance of each lead set in estimating data from other disease groups was largely similar. This was with the exception of leads specific to LVH in the estimation of normal data and normal leads in the estimation of LVH data. Here, the difference was found to be significant (P < .001). The top 6 recording sites in each lead set did not occupy the same positions as the 6 precordial leads. Although disease-specific lead sets are of limited practical use, this study has illustrated that, largely, there is little difference between the performance of different lead sets. The suboptimality of the 6 precordial leads has also been illustrated.

Personalisation and configuration of assistive technologies.

In this paper we present a multimedia tool that allows personalisation and configuration of an assistive technology. We have developed a tool called HomePUI that allows configuration of three disease domains; cognitive, physical and chronic. In this paper we present the rationale for our work, details of the developed tool and also present two case studies in which the tool has been used within cognitive and chronic disease management domains.

Synthesising the 12-lead electrocardiogram: Trends and challenges.

An area of electrocardiography which has received much interest of late is that of synthesising the 12-lead ECG from a reduced number of leads. The main advantage of this approach is obvious, as fewer recording sites are required to capture the same information. This, in turn, streamlines the ECG acquisition process with little detriment to the integrity of information used for interpretation. In the current article, we provide an overview of ECG synthesis along with a description of various 'limited lead' systems that have been reported in the literature. Based on this, several suggestions as to what the ECG of the future may entail have been made.

Optimizing the 12-lead electrocardiogram: a data driven approach to locating alternative recording sites.

BACKGROUND: Despite its widespread use, the limitations of the 12-lead electrocardiogram (ECG) are undisputed. The main deficiency is that just a small area of the precordium is interrogated and for some abnormalities information may be transmitted to a region of the body surface where information is not recorded. In this study, we attempted to optimize the 12-lead ECG by using a data-driven approach to suggest alternate recording sites. METHODS: A sequential lead selection algorithm was applied to a set of 744 body surface potential maps (BSPMs), consisting of recordings from subjects with myocardial infarction, left ventricular hypertrophy, and no apparent disease. A number of scenarios were investigated in which pairs of precordial leads were repositioned; these pairs were V3 and V5, V4 and V5, and V4 and V6. The algorithm was also used to find optimal positions for all 6 precordial leads. RESULT: Through estimation of entire surface potential distributions it was found that each of the scenarios, with 2 leads repositioned, captured more information than the standard 12-lead ECG. The scenario with V4 and V6 repositioned performed best with a root mean square error of 22.3 microvolts and a correlation coefficient of 0.967. This configuration also fared favorably when compared to the scenario where all 6 precordial leads were repositioned as optimizing all 6 leads offered no significant improvement. CONCLUSION: This study demonstrated the use of a lead selection algorithm in enhancing the 12-lead ECG. The results also indicated that repositioning just 2 precordial leads can provide the same level of information capture as that observed when all precordial leads are optimally placed.

Diagnosing old MI by searching for a linear boundary in the space of principal components.

Body surface potential mapping (BSPM) is a technique employing multiple electrodes to capture, via noninvasive means, an indication of the heart's condition. An inherent problem with this technique is the resulting high-dimensional recordings and the subsequent problems for diagnostic classifiers. A data set, recorded from a 192-lead BSPM system, containing 74 records is investigated. QRS isointegral maps, offering a summary of the information obtained during ventricular depolarization, were derived from 30 old inferior myocardial infarction and 44 normal recordings. Principal component analysis was applied to reduce the dimensionality of the recordings and a linear classifier was employed for classification. This perceptron-based classifier has been adapted so that the final weight and bias values are estimated prior to the learning process. This estimation process, referred to as the linear hyperplane approach (LHA), derives the estimated weights from a bisector hyperplane, placed orthogonal to the means of two class distributions in an n-dimensional Euclidean space. Estimating weights encourages a network to exhibit better generalization ability. Utilizing a number of different principal components as input features, the LHA achieved an average sensitivity and specificity of 79.58% and 76.45%, respectively, across all experiments. The average accuracy of 76.73% achieved with this approach was significantly better than the other benchmark classifiers evaluated against it.

Selection of optimal recording sites for limited lead body surface potential mapping: a sequential selection based approach.

BACKGROUND: In this study we propose the development of a new algorithm for selecting optimal recording sites for limited lead body surface potential mapping. The proposed algorithm differs from previously reported methods in that it is based upon a simple and intuitive data driven technique that does not make any presumptions about deterministic characteristics of the data. It uses a forward selection based search technique to find the best combination of electrocardiographic leads. METHODS: The study was conducted using a dataset consisting of body surface potential maps (BSPM) recorded from 116 subjects which included 59 normals and 57 subjects exhibiting evidence of old Myocardial Infarction (MI). The performance of the algorithm was evaluated using spatial RMS voltage error and correlation coefficient to compare original and reconstructed map frames. RESULTS: In all, three configurations of the algorithm were evaluated and it was concluded that there was little difference in the performance of the various configurations. In addition to observing the performance of the selection algorithm, several lead subsets of 32 electrodes as chosen by the various configurations of the algorithm were evaluated. The rationale for choosing this number of recording sites was to allow comparison with a previous study that used a different algorithm, where 32 leads were deemed to provide an acceptable level of reconstruction performance. CONCLUSION: It was observed that although the lead configurations suggested in this study were not identical to that suggested in the previous work, the systems did bear similar characteristics in that recording sites were chosen with greatest density in the precordial region.

A computational approach for peptidomic analysis in taxonomic study of amphibian species.

Peptides in the skin secretion of frogs have been studied for some time now because they frequently possess important biological activity such as antibiotic, antimicrobial, or anticancer properties. In this paper, we present a computational approach for measuring the degree of similarity between the entire peptide complement of the skin secretion of specimens from the same or different species. The first step in the analysis is the generation of a mass spectral profile from an experimental high-performance liquid chromatography/electrosparay ionization analysis of the sample. An "overlap" between the mass spectral profiles of different specimens is then proposed as a measure of their similarity. Analysis of specimens from three species of the genus Litoria, viz., L. Aurea, L. Caerulea, and L. Infrafrenata, and Rana Capito of genus Rana shows that the degree of similarity is highest between specimens from the same species, lower for specimens from different species of the same genus, and lowest between specimens from different genera. This indicates that comparison of skin peptide profiles (i.e., mass spectral profiles of skin secretion) is potentially a useful aid in the taxonomic study of amphibian species.

Mining for diagnostic information in body surface potential maps: a comparison of feature selection techniques.

BACKGROUND: In body surface potential mapping, increased spatial sampling is used to allow more accurate detection of a cardiac abnormality. Although diagnostically superior to more conventional electrocardiographic techniques, the perceived complexity of the Body Surface Potential Map (BSPM) acquisition process has prohibited its acceptance in clinical practice. For this reason there is an interest in striking a compromise between the minimum number of electrocardiographic recording sites required to sample the maximum electrocardiographic information. METHODS: In the current study, several techniques widely used in the domains of data mining and knowledge discovery have been employed to mine for diagnostic information in 192 lead BSPMs. In particular, the Single Variable Classifier (SVC) based filter and Sequential Forward Selection (SFS) based wrapper approaches to feature selection have been implemented and evaluated. Using a set of recordings from 116 subjects, the diagnostic ability of subsets of 3, 6, 9, 12, 24 and 32 electrocardiographic recording sites have been evaluated based on their ability to correctly asses the presence or absence of Myocardial Infarction (MI). RESULTS: It was observed that the wrapper approach, using sequential forward selection and a 5 nearest neighbour classifier, was capable of choosing a set of 24 recording sites that could correctly classify 82.8% of BSPMs. Although the filter method performed slightly less favourably, the performance was comparable with a classification accuracy of 79.3%. In addition, experiments were conducted to show how (a) features chosen using the wrapper approach were specific to the classifier used in the selection model, and (b) lead subsets chosen were not necessarily unique. CONCLUSION: It was concluded that both the filter and wrapper approaches adopted were suitable for guiding the choice of recording sites useful for determining the presence of MI. It should be noted however that in this study recording sites have been suggested on their ability to detect disease and such sites may not be optimal for estimating body surface potential distributions.

Heuristic charge assignment for deconvolution of electrospray ionization mass spectra.

We propose a new algorithm for deconvolution of electrospray ionization mass spectra based on direct assignment of charge to the measured signal at each mass-to-charge ratio (m/z). We investigate two heuristics for charge assignment: the entropy-based heuristic is adapted from a deconvolution algorithm by Reinhold and Reinhold;10 the multiplicative-correlation heuristic is adapted from the multiplicative-correlation deconvolution algorithm of Hagen and Monnig.6 The entropy-based heuristic is insensitive to overestimates of z(max), the maximum ion charge. We test the deconvolution algorithm on two single-component samples: the measured spectrum of human beta-endorphin has two prominent and one very weak line whereas myoglobin has a well-developed quasi-gaussian envelope of 17 peaks. In both cases, the deconvolution algorithm gives a clean deconvoluted spectrum with one dominant peak and very few artefacts. The relative heights of the peaks due to the parent molecules in the deconvoluted spectrum of a mixture of two peptides, which are expected to ionize with equal efficiency, give an accurate measure of their relative concentration in the sample.

Prediction models in the design of neural network based ECG classifiers: a neural network and genetic programming approach.

BACKGROUND: Classification of the electrocardiogram using Neural Networks has become a widely used method in recent years. The efficiency of these classifiers depends upon a number of factors including network training. Unfortunately, there is a shortage of evidence available to enable specific design choices to be made and as a consequence, many designs are made on the basis of trial and error. In this study we develop prediction models to indicate the point at which training should stop for Neural Network based Electrocardiogram classifiers in order to ensure maximum generalisation. METHODS: Two prediction models have been presented; one based on Neural Networks and the other on Genetic Programming. The inputs to the models were 5 variable training parameters and the output indicated the point at which training should stop. Training and testing of the models was based on the results from 44 previously developed bi-group Neural Network classifiers, discriminating between Anterior Myocardial Infarction and normal patients. RESULTS: Our results show that both approaches provide close fits to the training data; p = 0.627 and p = 0.304 for the Neural Network and Genetic Programming methods respectively. For unseen data, the Neural Network exhibited no significant differences between actual and predicted outputs (p = 0.306) while the Genetic Programming method showed a marginally significant difference (p = 0.047). CONCLUSIONS: The approaches provide reverse engineering solutions to the development of Neural Network based Electrocardiogram classifiers. That is given the network design and architecture, an indication can be given as to when training should stop to obtain maximum network generalisation.