Fast neural network learning algorithms for medical applications

被引:83
|
作者
Azar, Ahmad Taher [1 ]
机构
[1] MUST, Fac Engn, Comp & Software Engn Dept, 6th Of October City, Egypt
来源
NEURAL COMPUTING & APPLICATIONS | 2013年 / 23卷 / 3-4期
关键词
Multilayer perceptron (MLP); Optimum topology; Levenberg-Marquardt (LM); Conjugate gradient algorithms; Quasi-Newton algorithms; DIETARY-PROTEIN INTAKE; UREA KINETIC-MODEL; ARTIFICIAL-INTELLIGENCE; RENAL-TRANSPLANTATION; POST DIALYSIS; HEMODIALYSIS; KT/V; PREDICTION; REGRESSION; PATIENT;
D O I
10.1007/s00521-012-1026-y
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Measuring the blood urea nitrogen concentration is crucial to evaluate dialysis dose (Kt/V) in patients with renal failure. Although frequent measurement is needed to avoid inadequate dialysis efficiency, artificial intelligence can repeatedly perform the forecasting tasks and may be a satisfactory substitute for laboratory tests. Artificial neural networks represent a promising alternative to classical statistical and mathematical methods to solve multidimensional nonlinear problems. It also represents a promising forecasting application in nephrology. In this study, multilayer perceptron (MLP) neural network with fast learning algorithms is used for the accurate prediction of the post-dialysis blood urea concentration. The capabilities of eight different learning algorithms are studied, and their performances are compared. These algorithms are Levenberg-Marquardt, resilient backpropagation, scaled conjugate gradient, conjugate gradient with Powell-Beale restarts, Polak-Ribiere conjugate gradient and Fletcher-Reeves conjugate gradient algorithms, BFGS quasi-Newton, and one-step secant. The results indicated that BFGS quasi-Newton and Levenberg-Marquardt algorithm produced the best results. Levenberg-Marquardt algorithm outperformed clearly all the other algorithms in the verification phase and was a very robust algorithm in terms of mean absolute error (MAE), root mean square error (RMSE), Pearson's correlation coefficient () and concordance coefficient (R (C) ). The percentage of MAE and RMSE for Levenberg-Marquardt is 0.27 and 0.32 %, respectively, compared to 0.38 and 0.41 % for BFGS quasi-Newton and 0.44 and 0.48 % for resilient backpropagation. MLP-based systems can achieve satisfying results for predicting post-dialysis blood urea concentration and single-pool dialysis dose (sp) Kt/V without the need of a detailed description or formulation of the underlying process in contrast to most of the urea kinetic modeling techniques.
引用
收藏
页码:1019 / 1034
页数:16
相关论文
共 50 条
  • [41] NEURAL-NETWORK ALGORITHMS - APPLICATIONS IN THE ANALYSIS OF COMPLEX TRAITS
    LUCEK, P
    OTT, J
    AMERICAN JOURNAL OF HUMAN GENETICS, 1995, 57 (04) : 1132 - 1132
  • [42] Neural network structures and training algorithms for RF and microwave applications
    Wang, F
    Devabhaktuni, VK
    Xi, CG
    Zhang, QJ
    INTERNATIONAL JOURNAL OF RF AND MICROWAVE COMPUTER-AIDED ENGINEERING, 1999, 9 (03) : 216 - 240
  • [43] Neural network training algorithms on parallel architectures for finance applications
    Thulasiram, RK
    Rahman, RM
    Thulasiraman, P
    2003 INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING WORKSHOPS, PROCEEDINGS, 2003, : 236 - 243
  • [44] Analytical incremental learning: Fast constructive learning method for neural network
    Alfarozi, Syukron Abu Ishaq (syukron@outlook.com), 1600, Springer Verlag (9948 LNCS):
  • [45] A Fast Learning Algorithm of Self-Learning Spiking Neural Network
    Bodyanskiy, Yevgeniy
    Dolotov, Artem
    Pliss, Iryna
    Malyar, Mykola
    PROCEEDINGS OF THE 2016 IEEE FIRST INTERNATIONAL CONFERENCE ON DATA STREAM MINING & PROCESSING (DSMP), 2016, : 104 - 107
  • [46] Analytical Incremental Learning: Fast Constructive Learning Method for Neural Network
    Alfarozi, Syukron Abu Ishaq
    Setiawan, Noor Akhmad
    Adji, Teguh Bharata
    Woraratpanya, Kuntpong
    Pasupa, Kitsuchart
    Sugimoto, Masanori
    NEURAL INFORMATION PROCESSING, ICONIP 2016, PT II, 2016, 9948 : 259 - 268
  • [47] Research on network intrusion detection security based on improved extreme learning algorithms and neural network algorithms
    Dai, Zhenjun
    INTERNATIONAL JOURNAL OF BIOMETRICS, 2020, 12 (01) : 56 - 66
  • [48] Constructive neural-network learning algorithms for pattern classification
    Parekh, R
    Yang, JH
    Honavar, V
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02): : 436 - 451
  • [49] Distributed cooperative learning algorithms using wavelet neural network
    Xie, Jin
    Chen, Weisheng
    Dai, Hao
    NEURAL COMPUTING & APPLICATIONS, 2019, 31 (04): : 1007 - 1021
  • [50] NEURAL NETWORK CONSTRUCTIVE ALGORITHMS - TRADING GENERALIZATION FOR LEARNING EFFICIENCY
    SMIEJA, FJ
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 1993, 12 (02) : 331 - 374