An expert system for diagnosis of acute myocardial infarction with ECG analysis

Rabelo, Álvaro; Rocha, Ângela Machado; Oliveira, Káthia Marçal de; Souza, Agnaldo D. de; Ximenes, Antonio A.; Andrade, Carlos Jefferson do Nascimento; Onnis, Daniela; Olivaes, Ivan; Lobo, Nelson; Ferreira, Nivea; Werneck, Vera

doi:10.1016/s0933-3657(97)00385-0

Cited by 11 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This method starts with a graph and repetitively adds nodes/edges to maximize the following model-selection criterion (5) where • i, j and k are the indexes of the child node, of the parents of the child node, and of the possible values of the child node, respectively,…”

Section: K2 Algorithmmentioning

confidence: 99%

“…Trained physicians are able to recognize patterns in a patient's ECG signal and use them as the basis for diagnosis [1], for instance to diagnose heart ailments such as arrhythmia [2], ischemia [3,4], or prediction of an impending heart attack [5]. Researchers have tried since the inception of computers to develop techniques and algorithms for automated processing of ECG signals for various medical applications [6,7], whether as standalone applications or as a decision aid to physicians.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evolving a Bayesian classifier for ECG-based age classification in medical applications

Wiggins

Saad

Litt

et al. 2008

Applied Soft Computing

View full text Add to dashboard Cite

Objective-To classify patients by age based upon information extracted from their electrocardiograms (ECGs). To develop and compare the performance of Bayesian classifiers.Methods and Material-We present a methodology for classifying patients according to statistical features extracted from their ECG signals using a genetically evolved Bayesian network classifier. Continuous signal feature variables are converted to a discrete symbolic form by thresholding, to lower the dimensionality of the signal. This simplifies calculation of conditional probability tables for the classifier, and makes the tables smaller. Two methods of network discovery from data were developed and compared: the first using a greedy hill-climb search and the second employed evolutionary computing using a genetic algorithm (GA).Results and Conclusions-The evolved Bayesian network performed better (86.25% AUC) than both the one developed using the greedy algorithm (65% AUC) and the naïve Bayesian classifier (84.75% AUC). The methodology for evolving the Bayesian classifier can be used to evolve Bayesian networks in general thereby identifying the dependencies among the variables of interest. Those dependencies are assumed to be non-existent by naïve Bayesian classifiers. Such a classifier can then be used for medical applications for diagnosis and prediction purposes.

show abstract

Section: K2 Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evolving a Bayesian classifier for ECG-based age classification in medical applications

Wiggins

Saad

Litt

et al. 2008

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…A primeira definição de um processo de software na FBC foi feita em 1994, com o início de um projeto para o desenvolvimento de um sistema especialista para apoio ao diagnóstico de enfarto agudo do miocárdio (SEC) [13]. A primeira atividade, neste projeto, foi elaborar um documento que descrevesse um processo de software baseado na norma ISO 9000-3 [6], nas características de sistemas especialistas e nos aspectos específicos do projeto.…”

Section: Um Processo De Software Para Sistemas Baseados Em Conhecimentounclassified

Melhoria de Processos de Software e Evolução de Ambientes de Desenvolvimento de Software com base no Conhecimento do Domínio e na Cultura Organizacional

Villela¹,

Santos²,

Travassos³

et al. 2002

Anais Do I Simpósio Brasileiro De Qualidade De Software (SBQS 2002)

Self Cite

View full text Add to dashboard Cite

Em busca da melhoria da qualidade de seus produtos e do aumento da produtividade de suas equipes, organizações têm prestado mais atenção em seus processos de software. Este esforço tem envolvido a definição de um processo para a organização e o estabelecimento de metas de melhoria, levando em consideração boas práticas de engenharia de software. No entanto, nossa experiência em definir processos de software para várias organizações tem mostrado que o conhecimento sobre o domínio e a cultura organizacional são aspectos importantes para a melhoria dos processos de software. Desta forma, descrevemos como nossa abordagem para a definição de processos de software e para suporte automatizado ao desenvolvimento de software evoluiu para tratar estes aspectos. O resultado foi o surgimento de duas novas famílias de ambientes de desenvolvimento de software: Ambientes de Desenvolvimento de Software Orientados a Domínio (ADSOD) e Ambientes de Desenvolvimento de Software Orientados a Organização (ADSOrg). Este artigo apresenta, ainda, um resumo das lições que temos aprendido na definição e melhoria de processos de software.

show abstract

“…Computer-aided diagnosis has become an inevitable technique in most hospitals and medical centers. Several frameworks and systems such as expert system [1], medical diagnostic system [2], integrated healthcare systems [3], emergency medical decision support system (MDSS), clinical decision support system [4], clinical recommender system [5], prediction system, and various other machine learning models [6][7][8][9], are used for efficient diagnosis and prognosis. These systems are preferred more than human experts due to factors such as efficient response, consistency, targetspecificity, permanence, and sometimes even multi-domain functionality.…”

Section: Introductionmentioning

confidence: 99%

Knowledge-based Systems and Interestingness Measures: Analysis with Clinical datasets

Christopher

Nehemiah

Kannan

2016

Journal of Computing and Information Technology

View full text Add to dashboard Cite

Knowledge mined from clinical data can be used for medical diagnosis and prognosis. By improving the quality of knowledge base, the efficiency of prediction of a knowledge-based system can be enhanced. Designing accurate and precise clinical decision support systems, which use the mined knowledge, is still a broad area of research. This work analyses the variation in classification accuracy for such knowledge-based systems using different rule lists. The purpose of this work is not to improve the prediction accuracy of a decision support system, but analyze the factors that influence the efficiency and design of the knowledge base in a rule-based decision support system. Three benchmark medical datasets are used. Rules are extracted using a supervised machine learning algorithm (PART). Each rule in the ruleset is validated using nine frequently used rule interestingness measures. After calculating the measure values, the rule lists are used for performance evaluation. Experimental results show variation in classification accuracy for different rule lists. Confidence and Laplace measures yield relatively superior accuracy: 81.188% for heart disease dataset and 78.255% for diabetes dataset. The accuracy of the knowledge-based prediction system is predominantly dependent on the organization of the ruleset. Rule length needs to be considered when deciding the rule ordering. Subset of a rule, or combination of rule elements, may form new rules and sometimes be a member of the rule list. Redundant rules should be eliminated. Prior knowledge about the domain will enable knowledge engineers to design a better knowledge base.ACM CCS (2012) Classification: Information systems → Information systems applications → Decision support systems → Expert systems

show abstract

An expert system for diagnosis of acute myocardial infarction with ECG analysis

Cited by 11 publications

References 20 publications

Evolving a Bayesian classifier for ECG-based age classification in medical applications

Evolving a Bayesian classifier for ECG-based age classification in medical applications

Melhoria de Processos de Software e Evolução de Ambientes de Desenvolvimento de Software com base no Conhecimento do Domínio e na Cultura Organizacional

Knowledge-based Systems and Interestingness Measures: Analysis with Clinical datasets

Contact Info

Product

Resources

About