An Evolutionary Technique for Medical Diagnostic Risk Factors Selection

  • Dimitrios Mantzaris
  • George Anastassopoulos
  • Iliadis
  • Adam Adamopoulos
Conference paper
Part of the IFIP International Federation for Information Processing book series (IFIPAICT, volume 296)


This study proposes an Artificial Neural Network (ANN) and Genetic Algorithm model for diagnostic risk factors selection in medicine. A medical disease prediction may be viewed as a pattern classification problem based on a set of clinical and laboratory parameters. Probabilistic Neural Networks (PNNs) were used to face a medical disease prediction. Genetic Algorithm (GA) was used for pruning the PNN. The implemented GA searched for optimal subset of factors that fed the PNN to minimize the number of neurons in the ANN input layer and the Mean Square Error (MSE) of the trained ANN at the testing phase. Moreover, the available data was processed with Receiver Operating Characteristic (ROC) analysis to assess the contribution of each factor to medical diagnosis prediction. The obtained results of the proposed model are in accordance with the ROC analysis, so a number of diagnostic factors in patient's record can be omitted, without any loss in clinical assessment validity.


Artificial Neural Network Mean Square Error Receiver Operating Characteristic Analysis Area Under Curve Probabilistic Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Dayhoff J., and DeLeo J., “Artificial Neural Networks Opening the Black Box”, CANCER Supplement, 2001, Vol. 91, No. 8, pp. 1615–1635.CrossRefGoogle Scholar
  2. 2.
    Huang D., “A Constructive Approach for Finding Arbitrary Roots of Polynomials by Neural Networks”, IEEE Transactions on Neural Networks, 2004, Vol. 15, No. 2, pp. 477–491.CrossRefGoogle Scholar
  3. 3.
    Levano M., and Nowak H., “Application of New Algorithm, Iterative SOM, to the Detection of Gene Expressions”, Proceedings 10th International Conference on Engineering Applications of Neural Networks, 2007, Thessaloniki, Greece, pp. 141–147.Google Scholar
  4. 4.
    Zaknick A., “Introduction to the Modified Probabilistic Neural Network for General Signal Processing”, IEEE Transactions on Signal Processing, 1998, Vol. 46, No.7, pp. 1980–1990.CrossRefGoogle Scholar
  5. 5.
    Iliadis L., “An Intelligent Artificial Neural Network Evaluation System Using Fuzzy Set Hedges: Application in Wood Industry” Proceedings 19th IEEE Annual International Conference on Tools with Artificial Intelligence (ICTA), pp. 366–370.Google Scholar
  6. 6.
    Paschalidou A., Iliadis L., Kassomenos P., and Bezirtzoglou C., “Neural Modelling of the Tropospheric Ozone Concentrations in an Urban Site”, Proc. 10th International Conference on Engineering Applications of Neural Networks, 2007 Thessaloniki, Greece, pp. 436–445.Google Scholar
  7. 7.
    Keogan M., Lo J., Freed K., Raptopoulos V., Blake S., Kamel I., Weisinger K., Rosen M., and Nelson R., “Outcome Analysis of Patients with Acute Pancreatitis by Using an Artificial Neural Network”, Academic Radiology, 2002, Vol. 9, No. 4, pp. 410–419.CrossRefGoogle Scholar
  8. 8.
    Brause R., Hanisch E., Paetz J., and Arlt B., “Neural Networks for Sepsis Prediction — the MEDAN-Project1”, Journal für Anästhesie und Intensivbehandlung, 2004, Vol. 11, No. 1, pp. 40–43.Google Scholar
  9. 9.
    Gómez-Ruiz J., Jerez-Aragonés J., Muñoz-Pérez J., and Alba-Conejo E., “A Neural Network Based Model for Prognosis of Early Breast Cancer”, Applied Intelligence, 2004, Vol. 20, No. 3, pp. 231–238.CrossRefGoogle Scholar
  10. 10.
    Mantzaris D., Anastassopoulos G., Tsalkidis A., and Adamopoulos A., “Intelligent Prediction of Vesicoureteral Reflux Disease”, WSEAS Transactions on Systems, 2005, Vol. 4, Issue 9, pp. 1440–1449.Google Scholar
  11. 11.
    Anagnostou T., Remzi M., and Djavan B., “Artificial Neural Networks for Decision-Making in Urologic Oncology”, Reviews In Urology, 2003, Vol. 5, No. 1, pp.15–21.Google Scholar
  12. 12.
    Mantzaris D., Anastassopoulos G., Adamopoulos A., and Gardikis S., “A Non-Symbolic Implementation of Abdominal Pain Estimation in Childhood”, Information Science, 2008, Vol. 178, pp. 3860–3866.CrossRefGoogle Scholar
  13. 13.
    Economou G., Lymperopoulos D., Karavatselou E., and Chassomeris C., “A New Concept Toward Computer-Aided Medical Diagnosis — A Prototype Implementation Addressing Pulmonary Diseases” IEEE Transactions in Information Technology in Biomedicine, 2001 Vol. 5, Issue 1, pp. 55–66.CrossRefGoogle Scholar
  14. 14.
    Mantzaris D., Anastassopoulos C., and Lymperopoulos K., “Medical Disease Prediction Using Artificial Neural Networks”, Proceedings IEEE International Conference on BioInformat-ics and BioEngineering, 2008, Athens, GreeceGoogle Scholar
  15. 15.
    Georgopoulos E., Likothanassis S., and Adamopoulos A., “Evolving Artificial Neural Networks Using Genetic Algorithms”, Neural Network World, 2000, Vol. 4, pp.565–574MATHGoogle Scholar
  16. 16.
    Blazadonakis M., Moustakis V., and Charissis G., “Deep Assessment of Machine Learning Techniques Using Patient Treatment in Acute Abdominal Pain in Children”, Artificial Intelligence in Medicine, 1996, Vol. 8, pp. 527–542CrossRefGoogle Scholar
  17. 17.
    Branke J., “Evolutionary Algorithms for Neural Network Design and Training”, Proceedings 1st Nordic Workshop on Genetic Algorithms and its Applications, 1995, Vaasa, Finland.Google Scholar
  18. 18.
    Yao X., “Evolving Artificial Neural Networks”, Proceedings of the IEEE, 1999, Vol. 87, No. 9, pp. 1423–1447.CrossRefGoogle Scholar
  19. 19.
    Burgess N., “A Constructive Algorithm that Converges for Real-Valued Input Patterns”, International Journal on Neural Systems, 1994 Vol. 5, No. 1, pp. 59–66.CrossRefGoogle Scholar
  20. 20.
    Angeline P., Sauders G., and Pollack J., “An Evolutionary Algorithm that Constructs Recurrent Neural Networks”, IEEE Transaction on Neural Networks, 1994 Vol. 5, pp. 54–65.CrossRefGoogle Scholar
  21. 21.
    Adamopoulos A., Georgopoulos E., Manioudakis G., and Likothanassis S., “An Evolutionary Method for System Structure Identification Using Neural Networks”, Neural Computation '98, 1998Google Scholar
  22. 22.
    Billings S., and Zheng G., “Radial Basis Function Network Configuration Using Genetic Algorithms”, Neural Networks, 1995, Vol. 8, pp. 877–890.CrossRefGoogle Scholar
  23. 23.
    Swets J., “Signal Detection Theory and Roc Analysis in Psychology and Diagnostics: Collected Papers”, Lawrence Erlbaum Associates, 1996, Mahwah NJ.Google Scholar
  24. 24.
    Streiner D., and Cairney J., “What's Under the ROC? An Introduction to Receiver Operating Characteristics Curves”, The Canadian Journal of Psychiatry, 2007, Vol. 52, No. 2, pp. 121– 128.Google Scholar
  25. 25.
    Parzen E., “On Estimation of a Probability Density Function and Mode”, Annals of Mathematical Statistics, 1962, Vol. 33, No.3, pp. 1065–1076.MathSciNetCrossRefMATHGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2009

Authors and Affiliations

  • Dimitrios Mantzaris
    • 1
  • George Anastassopoulos
    • 1
    • 2
  • Iliadis
    • 2
    • 3
  • Adam Adamopoulos
    • 2
    • 4
  1. 1.Medical Informatics LaboratoryDemocritus University of ThraceAlexandroupolisHellas
  2. 2.Hellenic Open UniversityPatrasGreece
  3. 3.Department of Forestry &Management of the Environment and Natural ResourcesDemocritus University of ThraceOrestiadaHellas
  4. 4.Medical Physics LaboratoryDemocritus University of ThraceAlexandroupolisHellas

Personalised recommendations