Nothing Special   »   [go: up one dir, main page]
Skip to main content

Advertisement

Springer Nature Link
Log in

Maintenance of a Bayesian network: application using medical diagnosis

  • Original Paper
  • Published:
Evolving Systems Aims and scope Submit manuscript

Abstract

This study investigates a proposal of new Bayesian network model for the diagnosis of the most frequent breast pathologies and their implementation under a medical diagnostic system as part of maintenance. It consists in reproducing the process of doctor’s diagnosis that allows the identification of a disease through its symptoms. The proposed Bayesian network allows a representation of qualitative and quantitative knowledge expressing the uncertainty divided into four levels: clinical level, medical imaging level, biological level and diagnostic level. Bayesian networks are used to calculate the probabilities of the most likely a posteriori or causes, of an observed anomaly by using the clustering algorithm proposed by GeNIe tool and should be sufficient for our application. In order to improve the performances of the system and due to errors in the construction of the model which is supplied a priori by an expert, and the changes in the dynamics domains, we propose the maintenance of BN that implements the policies of updating a fixed structure and considers its reorganization by defining supplementary variables noted as maintenance actions that could be add them or deleted and their values can be edited.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Abbreviations

BN:

Bayesian network

CBR:

Case based reasoning

ADP:

Adenopathy

MCT:

Modification of the coloration of the teguments

CPD:

Conditional probability distribution

RSM:

Result of the screening of mammography

M:

Malignant

B:

Benign

S:

Speculated

O:

Oval

R:

Round

Ir:

Irregular

Re:

Regular

H:

Heterogenous

Ho:

Homogenous

References

  • Agnieszka O, Druzdzel JM, Wasyluk H (1998) A probabilistic causal model for diagnostic for diagnostic of liver disorders. Intell Inform Syst vii. In: Proceedings of the workshop held in Malbork, Poland, pp 379–387

  • Cooper GF (1990) The computational complexity of probabilistic inference using bayesian belief networks. Artif Intell 42(2):393–405

    Article  MathSciNet  MATH  Google Scholar 

  • Djebbar A (2013) Optimizing retrieval phase in CBR through pearl and JLO algorithms for medical diagnosis. J Adv Intell Paradig 5:161–181

    Article  Google Scholar 

  • Djebbar A, Merouani HF (2005) Mocabban: a modeling case base by a bayesian network applied to the diagnosis of hepatic pathologies. In: International conference on computational intelligence for modelling, control and automation, 2005 and international conference on intelligent agents, web technologies and internet commerce, vol 2, pp 678–685. IEEE

  • Yaneli A-AM, Nicandro C-R, Efrén M-M, Nancy P-C, Gabriel A-MH et al (2013) Assessment of bayesian network classifiers as tools for discriminating breast cancer pre-diagnosis based on three diagnostic methods. In: Batyrshin I, González Mendoza M (eds) Advances in Artificial Intelligence, Lecture Notes in Computer Science, vol 7629. Springer, Berlin, Heidelberg, pp 419–431

  • Franck C (2003) Aide à l’optimisation à la maintenance à partir de réseau bayesien et fiabilité dans un contexte doublement censuré. PhD thesis, the University of Joseph Fourier

  • Getoor L (2007) Introduction to statistical relational learning. MIT press

  • Hamdi-Cherif M, Bidoli E, Birri S, Mahnane A, Laouamri S, Zaidi Z, Boukharouba H, Cherka D, Rakeb M, Kara L et al (2014) Le cancer à sétif, algérie, 1986–2010. J Afr du Cancer Afr J Cancer 6(3):166–173

    Article  Google Scholar 

  • Horny M (2014) Bayesian networks

  • Lauritzen SL, Spiegelhalter DJ (1988) Local computations with probabilities on graphical structures and their application to expert systems. J Royal Stat Soc Ser B (Methodological) 50(2):157–224

    MathSciNet  MATH  Google Scholar 

  • Lucas P (2001) Expert knowledge and its role in learning bayesian networks in medicine: an appraisal. In: Artificial intelligence in medicine, pp 156–166. Springer

  • Memon A, Parveen S, Sangrarasi A, Malik AM, Laghari A, Talpur KAH (2007) Changing pattern of benign breast lumps in young females. World J Med Sci 2(1):21–24

    Google Scholar 

  • Naim P, Wuillemin P-H, Leray P, Pourret O, Becker A (1999) R éseaux bayésiens

  • Pearl J (1986) Fusion, propagation, and structuring in belief networks. Artif Intell 29(3):241–288

    Article  MathSciNet  MATH  Google Scholar 

  • Pearl J (1988) Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, USA

    MATH  Google Scholar 

  • Seixas FL, Zadrozny B, Laks J, Conci A, Saade DCM (2014) A bayesian network decision model for supporting the diagnosis of dementia, alzheimer s disease and mild cognitive impairment. Comput Biol Med 51:140–158

    Article  Google Scholar 

  • Vila-Francés J, Sanchis J, Soria-Olivas E, Serrano AJ, Martinez-Sober M, Bonanad C, Ventura S (2013) Expert system for predicting unstable angina based on bayesian networks. Expert Syst Appl 40(12):5004–5010

    Article  Google Scholar 

  • Zhou J, Wang D, Schlegel V, Zempleni J (2011) Development of an internet based system for modeling biotin metabolism using bayesian networks. Comput Methods Programs Biomed 104(2):254–259

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Science Department, LRI Laboratory, SRF Equip, Badji Mokhtar University, BP 12, 23000, Annaba, Algeria

    Ahlem Refai & H. F. Merouani

  2. Service Maternity CHU Ibn Rochd, Faculty Medicine, Badji Mokhtar University, Annaba, Algeria

    Hayet Aouras

Authors
  1. Ahlem Refai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. H. F. Merouani
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hayet Aouras
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ahlem Refai.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Refai, A., Merouani, H.F. & Aouras, H. Maintenance of a Bayesian network: application using medical diagnosis. Evolving Systems 7, 187–196 (2016). https://doi.org/10.1007/s12530-016-9146-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12530-016-9146-8

Keywords

Search

Navigation