Error-correction learning for artificial neural networks using the Bayesian paradigm. Application to automated medical diagnosis

被引:23
作者
Belciug, Smaranda [1 ]
Gorunescu, Florin [2 ]
机构
[1] Univ Craiova, Dept Comp Sci, Craiova 200585, Romania
[2] Univ Med & Pharm Craiova, Dept Biostat & Informat, Craiova 200349, Romania
关键词
Automated medical diagnosis; Bayesian-trained neural networks; Breast cancer; Lung cancer; Heart attack; Diabetes; BREAST-CANCER DETECTION; PREDICTION; ADMISSION; SYSTEM;
D O I
10.1016/j.jbi.2014.07.013
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Automated medical diagnosis models are now ubiquitous, and research for developing new ones is constantly growing. They play an important role in medical decision-making, helping physicians to provide a fast and accurate diagnosis. Due to their adaptive learning and nonlinear mapping properties, the artificial neural networks are widely used to support the human decision capabilities, avoiding variability in practice and errors based on lack of experience. Among the most common learning approaches, one can mention either the classical back-propagation algorithm based on the partial derivatives of the error function with respect to the weights, or the Bayesian learning method based on posterior probability distribution of weights, given training data. This paper proposes a novel training technique gathering together the error-correction learning, the posterior probability distribution of weights given the error function, and the Goodman-Kruskal Gamma rank correlation to assembly them in a Bayesian learning strategy. This study had two main purposes: firstly, to develop a novel learning technique based on both the Bayesian paradigm and the error back-propagation, and secondly, to assess its effectiveness. The proposed model performance is compared with those obtained by traditional machine learning algorithms using real-life breast and lung cancer, diabetes, and heart attack medical databases. Overall, the statistical comparison results indicate that the novel learning approach outperforms the conventional techniques in almost all respects. (C) 2014 Elsevier Inc. All rights reserved.
引用
收藏
页码:329 / 337
页数:9
相关论文
共 38 条
  • [1] Aeberhard S, 1994, IEEE SIGN PROC WORKS, V4, P14
  • [2] Artificial neural networks in medical diagnosis
    Amato, Filippo
    Lopez, Alberto
    Pena-Mendez, Eladia Maria
    Vanhara, Petr
    Hampl, Ales
    Havel, Josef
    [J]. JOURNAL OF APPLIED BIOMEDICINE, 2013, 11 (02) : 47 - 58
  • [3] Prediction of Severe Acute Pancreatitis at Admission to Hospital Using Artificial Neural Networks
    Andersson, Bodil
    Andersson, Roland
    Ohlsson, Mattias
    Nilsson, Johan
    [J]. PANCREATOLOGY, 2011, 11 (03) : 328 - 335
  • [4] [Anonymous], 2008, Bayesian evaluation of informative hypotheses, DOI [10.1007/978-0-387-09612-4_9, DOI 10.1007/978-0-387-09612-49]
  • [5] [Anonymous], 1992, 9202 J COOK U N QUEE
  • [6] A hybrid neural network/genetic algorithm applied to breast cancer detection and recurrence
    Belciug, Smaranda
    Gorunescu, Florin
    [J]. EXPERT SYSTEMS, 2013, 30 (03) : 243 - 254
  • [7] Belciug Smaranda., 2010, 2010 5th IEEE International Conference Intelligent Systems, P191, DOI DOI 10.1109/IS.2010.5548358
  • [8] Bishop CM., 1995, NEURAL NETWORKS PATT
  • [9] A novel artificial neural network method for biomedical prediction based on matrix pseudo-inversion
    Cai, Binghuang
    Jiang, Xia
    [J]. JOURNAL OF BIOMEDICAL INFORMATICS, 2014, 48 : 114 - 121
  • [10] ARTMAP-IC and medical diagnosis: Instance counting and inconsistent cases
    Carpenter, GA
    Markuzon, N
    [J]. NEURAL NETWORKS, 1998, 11 (02) : 323 - 336