Retrieval and adaptation in CBR through Bayesian Network for diagnosis of hepatic pathologies

Djebbar, Akila; Merouani, Hayet Farida

doi:10.3233/his-2012-0151

Cited by 8 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors apply feature selection algorithms to reduce the BN complexity. Still focusing on application domains, in [2] the authors describe a modeling of knowledge for a Case Based Reasoning system (CBR) applied to the diagnosis of the hepatic pathologies (both the cases and the knowledge of the domain are expressed by a Bayesian network (BN)).…”

Section: A View Into Work Related To Evolutionary Algorithms and Baymentioning

confidence: 99%

“…This is the case of the work described in [43] where a traditional GA is used to learn the structure of a BN for specifically representing the yeast cell-cycle gene network reconstruction. Another gene expression domain application of a collaborative EA-Bayes system is proposed in [2] where a structure learning method is proposed, aiming to simplify an induced BN for detecting splice junction site in gene sequences. Authors apply feature selection algorithms to reduce the BN complexity.…”

Section: A View Into Work Related To Evolutionary Algorithms and Baymentioning

confidence: 99%

See 1 more Smart Citation

The influences of canonical evolutionary algorithm operators and variable orderings in learning Bayesian classifiers from data

Santos

Hruschka

Nicoletti

et al. 2014

HIS

View full text Add to dashboard Cite

Variable Ordering (VO) plays an important role when inducing Bayesian Networks (BNs) and Bayesian Classifiers (BCs). Previous works in the literature suggest that it is worth pursuing the use of genetic/evolutionary algorithms for identifying a suitable VO, when learning a BN structure from data. This paper proposes a collaborative Evolutionary-Bayes algorithm named VOEA (Variable Ordering Evolutionary Algorithm) aimed at inducing BCs from data. The two VOEA versions presented in the paper refine a previously proposed algorithm named VOGA by employing only a single evolutionary operator (either crossover or mutation) as well as by using information about the class variable when defining the most suitable variable ordering for learning a BC. Experiments performed in a number of datasets revealed that the VOEA approach is promising and tends to generate suitable and representative BCs, particularly in its version VOEA_M, which only implements the mutation operator.

show abstract

Section: A View Into Work Related To Evolutionary Algorithms and Baymentioning

confidence: 99%

Section: A View Into Work Related To Evolutionary Algorithms and Baymentioning

confidence: 99%

The influences of canonical evolutionary algorithm operators and variable orderings in learning Bayesian classifiers from data

Santos

Hruschka

Nicoletti

et al. 2014

HIS

View full text Add to dashboard Cite

show abstract

“…Especially, with its ability to capture and reason with uncertainty, it has established a long history in medicine [1,8,12,13,19], leading to the development of various clinical decision support systems (CDSS). Some successful CDSS include MYCIN -diagnose and recommend treatment for blood infectious diseases [9], MUMIN -an expert assistant for electromyography analysis [22], ON-COCIN -assist physicians in diagnosis of cancer [10], QMR-DT network -microcomputer based decisionsupport tool for diagnosis in internal medicine [16], Heart Disease Program -to anticipate the effects of therapy in the domain of cardiovascular disorder [24] etc.…”

Section: Introductionmentioning

confidence: 99%

Self-adaptive Bayesian fuzzy inference nets to diagnose cardiovascular diseases

Sekar

Dong

2014

KES

View full text Add to dashboard Cite

A generalized Bayesian inference nets model (GBINM) to aid developers to construct self-adaptive Bayesian inference nets for various applications and a new approach of defining and assigning statistical parameters to Bayesian inference nodes needed to calculate propagation of probabilities and address uncertainties are proposed. GBINM and the proposed approach are applied to design an intelligent medical system to diagnose cardiovascular diseases. Thousands of site-sampled clinical data are used for designing and testing such a constructed system. The preliminary diagnostic results show that the proposed methodology has salient validity and effectiveness

show abstract

“…Literature review shows that among various AI technologies, expert system (ES), in particular Bayesian inference nets (BIN), has emerged as one of the most successful intelligent tools in various applications [ 12 – 14 ]. Especially, BIN with its ability to execute staged decision process and provide reasoned conclusions has established a long track record in medical informatics [ 15 – 19 ], leading to the development of various clinical decision support systems (CDSS) [ 20 – 24 ]. To support a doctor's approach of diagnosis with staged decision process, a BIN is adopted in this paper in order to design an intelligent CVD diagnosis system based on HDPs.…”

Section: Introductionmentioning

confidence: 99%

Function Formula Oriented Construction of Bayesian Inference Nets for Diagnosis of Cardiovascular Disease

Sekar

Dong

2014

BioMed Research International

View full text Add to dashboard Cite

An intelligent cardiovascular disease (CVD) diagnosis system using hemodynamic parameters (HDPs) derived from sphygmogram (SPG) signal is presented to support the emerging patient-centric healthcare models. To replicate clinical approach of diagnosis through a staged decision process, the Bayesian inference nets (BIN) are adapted. New approaches to construct a hierarchical multistage BIN using defined function formulas and a method employing fuzzy logic (FL) technology to quantify inference nodes with dynamic values of statistical parameters are proposed. The suggested methodology is validated by constructing hierarchical Bayesian fuzzy inference nets (HBFIN) to diagnose various heart pathologies from the deduced HDPs. The preliminary diagnostic results show that the proposed methodology has salient validity and effectiveness in the diagnosis of cardiovascular disease.

show abstract

Retrieval and adaptation in CBR through Bayesian Network for diagnosis of hepatic pathologies

Cited by 8 publications

References 12 publications

The influences of canonical evolutionary algorithm operators and variable orderings in learning Bayesian classifiers from data

The influences of canonical evolutionary algorithm operators and variable orderings in learning Bayesian classifiers from data

Self-adaptive Bayesian fuzzy inference nets to diagnose cardiovascular diseases

Function Formula Oriented Construction of Bayesian Inference Nets for Diagnosis of Cardiovascular Disease

Contact Info

Product

Resources

About