Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 4 de 4
Filter
Add more filters











Publication year range
1.
Rev. ing. bioméd ; 8(15): 51-58, ene.-jun. 2014. graf
Article in Spanish | LILACS | ID: lil-769151

ABSTRACT

Las enfermedades cardiovasculares son la principal causa de mortalidad en el mundo, por lo que el desarrollo de algoritmos que detecten arritmias cardíacas en tiempo real se ha convertido en un campo de investigación importante. El desarrollo de estos algoritmos ha conllevado a la mejora de dispositivos cardiacos portátiles. Este artículo presenta el desempeño de dos algoritmos basados en aprendizaje de máquina no supervisado para la detección de latidos de contracción ventricular prematura en la señal ECG. Los latidos se extraen de las bases de datos del MIT-BIH, los cuales fueron pre-procesados y segmentados por el grupo de investigación de Dinámica Cardiovascular de la UPB. La Transformada Wavelet Discreta, el Análisis de Componentes Principales y un método híbrido propuesto son implementados para la extracción de características y reducción de dimensiones, a partir de los cuales se generan 8 espacios de características para la evaluación de los algoritmos. Kmeans y Mapas auto-organizados son desarrollados y comparados en términos de precisión y costo computacional. Se logró una especificidad del 96.22 % y una sensibilidad del 95.04 % con un tiempo de ejecución de 79.41µs por latido. Los resultados permiten concluir que estos métodos pueden implementarse en aplicaciones de detección de arritmias en tiempo real debido a su bajo costo computacional.


Cardiovascular diseases are the principal cause of mortality in the world, so that the development of algorithms that detect cardiac arrhythmias in real time has become an important field of research. The development of these algorithms has led to the improvement of wearable cardiac devices. This paper presents the performance of two algorithms based in unsupervised learning methods for the detection of Premature Ventricular Contraction in the ECG signal. The beats are extracted from MIT-BIH databases, which were preprocessed and segmented by the UPB’s Dynamic Cardiovascular research group. The Discrete Wavelet Transform (DWT), Principal Component Analysis (PCA) and a proposed hybrid method are implemented for the feature extraction and dimension reduction, from which 8 feature spaces are generated and tested. Kmeans and Self Organizing Maps are developed and compared in terms of accuracy and computational cost. Specificity of 96.22 % and sensitivity of 95.94% with 79.41µs per beat are accomplished. The results show that these methods can be implemented in applications of real time arrhythmia detection because of their low computational cost.


A doença cardiovascular é a principal causa de morte em todo o mundo, de modo que o desenvolvimento de algoritmos para detectar arritmias cardíacas, em tempo real, tornou-se um importante campo de pesquisa. O desenvolvimento desses algoritmos tem levado a melhores dispositivos cardíacos portáteis. Este artigo apresenta o desempenho dos dois com base na aprendizagem de máquina sem supervisão para detecção de batidas de contração ventriculares prematuras nos algoritmos de sinais de ECG. As batidas são extraídos das bases de dados do MIT-BIH, que foram pré-processados e segmentado pelo grupo da UPB Cardiovasculares Dynamics pesquisa. A Transformada Wavelet Discreta, Análise de Componentes Principais e uma abordagem híbrida proposta são implementadas para extração de características e redução de dimensão, a partir do qual 8 espaços de recursos para a avaliação dos algoritmos são gerados. Kmeans e mapas de auto-organização são desenvolvidos e comparados em termos de precisão e custo computacional. A especificidade de 96,22% e uma sensibilidade de 95,04% com um tempo de execução de 79.41µs por batida foi alcançado. Os resultados mostram que estes métodos podem ser implementados em aplicações de detecção de arritmia em tempo real, devido ao seu baixo custo computacional.

2.
Arq. Inst. Biol. ; 77(2)2010.
Article in Portuguese | VETINDEX | ID: vti-760001

ABSTRACT

ABSTRACT Tuberculosis is an infectious chronic disease that affects mammals and birds and constitutes a serious problem for public and animal health. Pulmonary and mediastinic lymph node lesions of 43 animals slaughtered in 3 slaughterhouses in the metropolitan region of the city of Salvador, Bahia, Brazil, were analyzed with the objective of obtaining a molecular survey of the disease in bovines slaughtered in slaughterhouses in the state. Seven isolates ofMycobacterium bovis were identified through the spoligotyping technique and classified into 3 different spoligotypes (SB1055, SB0120, SB0268), described in Brazil and in many areas worldwide. The results indicate that the diagnostic method utilized may contribute to the creation of a database for the epidemiologic study of bovine tuberculosis in the state of Bahia.


RESUMO A tuberculose é uma enfermidade infecciosa crônica, que afeta mamíferos e aves e constitui um sério problema de saúde pública e animal. Objetivando realizar um levantamento molecular da enfermidade em bovinos abatidos em matadouros frigoríficos no Estado da Bahia, Brasil, foram analisadas as lesões pulmonares e de linfonodos mediastínicos de 43 carcaças de animais abatidos em três matadouros-frigoríficos localizados na Região Metropolitana de Salvador, Bahia. Sete isolados de Mycobacterium bovis foram identificados, através da técnica do spolygotyping, e discriminados em três diferentes espoligotipos (SB1055, SB0120 e SB0268) descritos no Brasil e em diversas áreas do mundo. Os resultados indicam que o método de diagnóstico utilizado pode contribuir para a criação de uma base de dados para o estudo epidemiológico da tuberculose bovina no Estado da Bahia.

3.
Arq. Inst. Biol ; 73(4)2006.
Article in Portuguese | LILACS-Express | VETINDEX | ID: biblio-1461829

ABSTRACT

ABSTRACT The present work studied, by mathematical modeling, the Mycobacterium avium infection dynamics in a swine population. In order to describe M. avium transmission dynamics, a compartmental model was elaborated. Since the model was aimed to estimate the relationship between infection rate and the rate of swine that presented lesions resulting from M. avium infection, detected at slaughter of 150-day-old animals, it was considered that the disease dynamics could be described by two compartments of animals: susceptible to the infection, and infected that could present lesions. The simulations results showed that for a certain force of infection, the proportion of infected animals at the end of the nursery stage (those that would present lesions at the slaughter) remains constant over time, not being subject to seasonal changes. The mathematical simulation of the disease, considering horizontal transmission as the major means of condemnation at slaughter due to granulomatous lymphadenitis, is inconsistent with what is observed within the population. Therefore, the environmental component plays a major/preponderant role in the mycobacterial infection dynamics of swine raised on farms in Brazil.


RESUMO O presente trabalho estudou, através de modelagem matemática, a dinâmica da infecção por Mycobacterium avium em uma população suína. Para descrever a dinâmica de transmissão de M. avium em granjas de suínos, foi elaborado um modelo de compartimentos. Como esse modelo visava estimar a relação entre taxa de infecção e proporção de suínos que apresentam lesões, detectadas no abate aos 150 dias de idade, resultantes de infecção por M. avium, considerou-se que a dinâmica da doença poderia ser descrita por dois compartimentos de animais: suscetíveis à infecção, e infectados que poderiam vir a apresentar lesões. Através dos resultados obtidos nas simulações realizadas, observou-se que para uma dada força de infecção, a proporção de infectados no final da fase de creche (aqueles que apresentariam lesões no abate) se mantém constante ao longo do tempo, não estando sujeita a variações de caráter sazonal. A simulação matemática da doença, considerando a transmissão horizontal como mecanismo principal da ocorrência de condenações em matadouro por linfadenite granulomatosa é inconsistente com o que se observa na população. Portanto, o componente ambiental tem papel preponderante na dinâmica das infecções micobacterianas dos suínos produzidos no Brasil.

4.
West Indian med. j ; West Indian med. j;49(suppl.4): 22-3, Nov. 9, 2000.
Article in English | MedCarib | ID: med-377

ABSTRACT

INTRODUCTION: In a previous study of patients with non-insulin-dependent diabetes mellitus (NIDDM) of less than 5 years' duration at the HCQ "Hermanos Ameijeiras", Cuba, we found abnormal values of T3 at iniitial evaluation. It was proved that the cause was an increase in the activity of the enzyme catalysing the process of peripheral deiodination of T4 to T3. OBJECTIVE: To examine these variables in a larger sample. SUBJECTS AND METHODS: One hundred and forty patients with NIDDM of 1-25 years' duration being treated by diet, and/or oral hypoglycaemic agents, were studied T3, T4, and insulin were measured by radio-immunoassay; glucose, by glucose-oxidase; cholesterol, triglycerides and HDL-cholestrol by the Trinder method; LDL and VLDL by the Ellefson formula; glycosylated haemoglobin by ion exchange chromatography, and microalbuminuria by an immuno-colorimetric semiquantitative method. The sample was divided into 5 groups: 1-2 years, 3-4 years, 5-6 years, 7-15 years, and more than 15 years' duration of diabetes mellitus. RESULTS: The results confirmed the previous findings that there was a marked increase in T3 (4.87, 4.49, 3.1, 2.8, 2.9 mmol/l, respectively) in the time of evolution but diminishing progressively as the time of evolution increases and normalizing in the 5-6 year group. There were no notable differences in T4 in the 5 groups of healthy controls (102, 113, 96, 94, 99 mmol/l). The blood glucose levels were higher than in the healthy population but a point of inflection was noted in the 5th -6th year of evolution (8.6, 8.2. 7.02, 8.4, 8.3 mmol/l). The insulin values were noted to have a greater variation between 1-2 years and 3-4 years, supposedly a treatment effect as in the 1-2 year group. There were patients who had not started treatment but the insulin in the 3-4 year group decreased with the introduction of treatment (48.7, 17.9, 32.1, 36.6, 39.5 mU/ml). Glycosylated haemoglobin showed a point of inflection in the 5th-6th year (7.2, 6.3, 8.2, 7.9, 8.5 percent). Lipid metabolism indicators, cholesterol (4.7, 5.2, 5.6, 5.74, 5.5 mmol/l), triglyceride (1.34, 2.01, 1.33, 1.95, 1.65 mmol/l) and low density lipoprotein (2.99, 3.14, 3.97, 3.95, 3.63 mmol/l) progressively increased with time of evolution. Microalbuminuria behaved the same (25, 12.4, 14.5, 33.4, 27.3 mg/l), showing a higher value at 1-2 years and diminishing between 3 and 6 years but increasing thereafter.(Au)


Subject(s)
Humans , Thyroid Hormones/analysis , Diabetes Mellitus, Type 2/complications , Cuba , Diabetes Mellitus, Type 2/diet therapy , Cohort Studies
SELECTION OF CITATIONS
SEARCH DETAIL