PubMed Health⌕ Search

Biomedical subjects

S Barro

Publications and source records attributed to S Barro.

16 recordsLinked to original sources
PubMed2001

Detection of abnormality in the electrocardiogram without prior knowledge by using the quantisation error of a self-organising map, tested on the European ischaemia database.

Most systems for the automatic detection of abnormalities in the ECG require prior knowledge of normal and abnormal ECG morphology from pre-existing databases. An automated system for abnormality detection has been developed based on learning normal ECG morphology directly from the patient. The quantisation error from a self-organising map 'learns' the form of the patient's ECG and detects any change in its morphology. The system does not require prior knowledge of normal and abnormal morphologies. It was tested on 76 records from the European Society of Cardiology database and detected 90.5% of those first abnormalities declared by the database to be ischaemic. The system also responded to abnormalities arising from ECG axis changes and slow baseline drifts and revealed that ischaemic episodes are often followed by long-term changes in ECG morphology.

Electrocardiography↗
PubMed2001

Characterization of Galician (N.W. Spain) quality brand potatoes: a comparison study of several pattern recognition techniques.

Authenticity is an important food quality criterion and rapid methods to guarantee it are widely demanded by food producers, processors, consumers and regulatory bodies. The objective of this work was to develop a classification system in order to confirm the authenticity of Galician potatoes with a Certified Brand of Origin and Quality (CBOQ) 'Denominación Específica: Patata de Galicia' and to differentiate them from other potatoes that did not have this CBOQ. Ten selected metals were determined by atomic spectroscopy in 102 potato samples which were divided into two categories: CBOQ and non-CBOQ potatoes. Multivariate chemometric techniques, such as cluster analysis and principal component analysis, were applied to perform a preliminary study of the data structure. Four supervised pattern recognition procedures [including linear discriminant analysis (LDA), K-nearest neighbours (KNN), soft independent modelling of class analogy (SIMCA) and multilayer feed-forward neural networks (MLF-ANN)] were used to classify samples into the two categories considered on the basis of the chemical data. Results for LDA, KNN and MLF-ANN are acceptable for the non-CBOQ class, whereas SIMCA showed better recognition and prediction abilities for the CBOQ class. A more sophisticated neural network approach performed by the combination of the self-organizing with adaptive neighbourhood network (SOAN) and MLF network was employed to optimize the classification. Using this combined method, excellent performance in terms of classification and prediction abilities was obtained for the two categories with a success rate ranging from 98 to 100%. The metal profiles provided sufficient information to enable classification rules to be developed for identifying potatoes according to their origin brand based on SOAN-MLF neural networks.

Food Analysis↗
PubMed2001

Authentication of Galician (N.W. Spain) quality brand potatoes using metal analysis. Classical pattern recognition techniques versus a new vector quantization-based classification procedure.

The objective of this work was to develop a classification system in order to confirm the authenticity of Galician potatoes with a Certified Brand of Origin and Quality (CBOQ) and to differentiate them from other potatoes that did not have this quality brand. Elemental analysis (K, Na, Rb, Li, Zn, Fe, Mn, Cu, Mg and Ca) of potatoes was performed by atomic spectroscopy in 307 samples belonging to two categories, CBOQ and Non-CBOQ potatoes. The 307 x 10 data set was evaluated employing multivariate chemometric techniques, such as cluster analysis and principal component analysis in order to perform a preliminary study of the data structure. Different classification systems for the two categories on the basis of the chemical data were obtained applying several commonly supervised pattern recognition procedures [such as linear discriminant analysis, K-nearest neighbours (KNN), soft independent modelling of class analogy and multilayer feed-forward neural networks]. In spite of the fact that some of these classification methods produced satisfactory results, the particular data distribution in the 10-dimensional space led to the proposal of a new vector quantization-based classification procedure (VQBCP). The results achieved with this new approach (percentages of recognition and prediction abilities > 97%) were better than those attained by KNN and can be compared advantageously with those provided by LDA (linear discriminant analysis), SIMCA (soft independent modelling of class analogy) and MLF-ANN (multilayer feed-forward neural networks). The new VQBCP demonstrated good performance by carrying out adequate classifications in a data set in which the classes are subgrouped. The metal profiles of potatoes provided sufficient information to enable classification criteria to be developed for classifying samples on the basis of their origin and brand.

Journal Article↗
PubMed2000

A new approach for TU complex characterization.

In this paper, we present a new TU complex detection and characterization algorithm that consists of two stages; the first is a mathematical modeling of the electrocardiographic segment after QRS complex; the second uses classic threshold comparison techniques, over the signal and its first and second derivatives, to determine the significant points of each wave. Later, both T and U waves are morphologically classified. Amongst the principal innovations of this algorithm is the inclusion of U-wave characterization and a mathematical modeling stage, that avoids many of the problems of classic techniques when there is a low signal-to-noise ratio or when wave morphology is atypical. The results of the algorithm validation with the recently appeared QT database are also shown. For T waves these results are better when compared to other existing algorithms. U-wave results cannot be contrasted with other algorithms as, to our knowledge, none are available. Examples showing the causes of principal discrepancies between our algorithm and the QT database annotations are also given, and some ways of attempting to improve and benefit from the proposed algorithm are suggested.

Algorithms↗
PubMed1999

A problem-solving method for 'unprotocolised' therapy administration task in medicine.

This paper describes a problem-solving method for modelling the 'unprotocolised' treatment administration task in medicine. We argue that there are medical domains in which no well-established standard treatment protocols exist, and the physician has to decide on the therapy that is to be applied to each patient, in function of a set of therapeutic objectives to be fulfilled. For this reason, we propose the modelling of this type of task adapting the generic class of problem resolution methods for design task, labelled as Propose-Critique-Modify (PCM). In this paper, we are presenting a model of expertise which has been developed using the basic modelling components of the CommonKADS methodology.

Artificial Intelligence↗
PubMed1997

SUTIL: intelligent ischemia monitoring system.

SUTIL is an intelligent monitoring system for intensive and exhaustive follow up of patients in coronary care units. This system processes electrocardiographic and hemodynamic signals in real time, with the main objective of detecting ischemic episodes. In this paper, we describe the tasks included in SUTIL. In addition to basic tasks, those at higher levels will also be presented. Some of these latter tasks attempt to mimic, to some extent, the way in which the human expert operates.

Algorithms↗
PubMed1991

Fuzzy K-nearest neighbor classifiers for ventricular arrhythmia detection.

We report a study of the efficiency of 4 classifiers (the K-nearest-neighbor and single-nearest-prototype algorithms, each as parametrized by both Fuzzy C-Means and Fuzzy Covariance clustering) in the detection of ventricular arrhythmias in ECG traces characterized by 4 features derived from 7 spectral parameters. Principal components analysis was used in conjunction with a cardiologist's deterministic classification of 90 ECG traces to fix the number of trace classes to 5 (ventricular fibrillation/flutter, sinus rhythm, ventricular rhythms with aberrant complexes and 2 classes of artefact). Forty of the 90 traces were then defined as a test set; 5 different learning sets (numbering 25, 30, 35, 40 and 45 traces) were randomly selected from the remaining 50 traces; each learning set was used to parametrize both the classification algorithms using both fuzzy clustering algorithms and the parametrized classification algorithms were then applied to the test set. Optimal K for K-nearest-neighbor algorithms and optimal cluster volumes for Fuzzy Covariance algorithms were sought by trial and error to minimize classification differences with respect to the cardiologist's classification. Fuzzy Covariance clustering afforded significantly better perception of cluster structure than the Fuzzy C-Means algorithm, and the classifiers performed correspondingly with an overall empirical error ratio of just 0.10 for the K-nearest-neighbor algorithm parametrized by Fuzzy Covariance.

Algorithms↗
PubMed1990

Multimicroprocessor system for online monitoring in a CCU.

A real-time monitoring system for physiological signals, developed for patients in coronary care units (CCUs), is described. This system monitors the signals that have the greatest clinical value in a CCU environment (ECG and cardiovascular pressures), taking charge of detecting dangerous situations and of extracting information significant to the correct monitoring of the patient. The information it extracts, mainly from the ECG, is presented to the user in an ergonomic way using written reports and graphs which collect and compile the information, facilitating its interpretation. Some utilities have been developed to allow the user to modify certain monitoring conditions as well as to correct results derived from them, thereby improving the reliability of the monitoring process. The system uses a multimicroprocessor architecture (imposed by the need to perform a large number of tasks in real time) with a block based on the VME bus, charged with acquiring and processing the monitored signals, and an IBM-compatible PC/XT which is used as a system user interface and a massive storage device in which the information resulting from the monitoring of signals is stored.

Coronary Care Units↗
PubMed1990

Fuzzy beat labeling for intelligent arrhythmia monitoring.

The performance in automatic diagnosis of cardiac rhythm based on the analysis of the electrocardiographic signal (ECG) is strongly conditioned by the correct classification of each beat detected. In this work we present a fuzzy classifier of beats that applies empiric criteria and that permits it to ignore the frequent lack of clarity in the information coming from previous stages within ECG processing. The classification of each beat is performed applying diffuse conditional statements which represent the knowledge of the cardiologist expert and that use a set of descriptions of the temporal and morphological attributes of the analyzed beat. The process of classification is completed with information derived from the consideration of "families," which group beats that have QRSs of similar morphology, and with information brought in by the user himself in the monitoring process. The modularity of the classifier that has been developed facilitates the incorporation of new descriptions and classification criteria in order to increase its reliability. The design process proposed has a structure that is transferable to other analysis and event classification processes.

Arrhythmias, Cardiac↗
PubMed1989

Algorithmic sequential decision-making in the frequency domain for life threatening ventricular arrhythmias and imitative artefacts: a diagnostic system.

A preliminary study to approach the problem of reliably detecting life threatening ventricular arrhythmias in real time is described. An algorithm (DIAGNOSIS) has been developed in order to classify ECG signal records on the basis of the computation of four simple parameters calculated from a representation in the frequency domain. This algorithm uses a set of rules constituting an operative classification scheme based on the comparison of the parameters with a set of pre-established thresholds. This allows us to differentiate four general categories: ventricular fibrillation-flutter, ventricular rhythms, imitative artefacts and predominant sinus rhythm.

Algorithms↗
PubMedDate not supplied

Grammatic representation of beat sequences for fuzzy arrhythmia diagnosis.

The final stage of a system for automatic monitoring of cardiac arrhythmias is the diagnosis of the rhythm or arrhythmia present in the patient during the monitoring process. In this paper we approach the detection process by means of the analysis of the electrocardiographic signal (ECG) on a surface lead produced by those arrhythmias which can be recognized by identifying specific beat sequences and taking into account contextual information, mainly rhythm information. We have developed a diagnosis process for arrhythmias which uses a fuzzy classification of beats according to their etiology or focus of origin. The process we describe permits a more adequate consideration by the user of the arrhythmias diagnosed by the system, mainly in those cases in which the information derived from ECG analysis is not determinant.

Arrhythmias, Cardiac↗
PubMedDate not supplied

Fuzzy logic in a patient supervision system.

A patient supervision system in progress for intensive and coronary care units, focused on patients with acute myocardial infarct is briefly described particularly regarding the role that fuzzy logic is playing in its design, and why this is so.

Artificial Intelligence↗