Download PDF
Methods Inf Med 1996; 35(03): 265-271
DOI: 10.1055/s-0038-1634655
Original Article
Schattauer GmbH

Abductive Machine Learning for Modeling and Predicting the Educational Score in School Health Surveys

R. E. Abdel-Aal
1   Energy Research Laboratory, Research Institute, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia
,
A. M. Mangoud
2   Department of Family and Community Medicine, Faculty of Medicine, King Faisal University, Dammam, Saudi Arabia
› Author Affiliations
Further Information

Publication History

Publication Date:
20 February 2018 (online)

    Permissions and Reprints

Abstract:

The use of modern abductive machine learning techniques is described for modeling and predicting outcome parameters in terms of input parameters in medical survey data. The AIM® (Abductory Induction Mechanism) abductive network machine-learning tool is used to model the educational score in a health survey of 2,720 Albanian primary school children. Data included the child’s age, gender, vision, nourishment, parasite infection, family size, parents’ education, and educational score. Models synthesized by training on just 100 cases predict the educational score output for the remaining 2,620 cases with 100% accuracy. Simple models represented as analytical functions highlight global relationships and trends in the survey population. Models generated are quite robust, with no change in the basic model structure for a 10-fold increase in the size of the training set. Compared to other statistical and neural network approaches, AIM provides faster and highly automated model synthesis, requiring little or no user intervention.

Keywords:

Machine Learning - Abductive Networks - Modeling - Prediction - Educational Performance - School Health Surveys
 

  • References

  • 1 Weiss SM, Kulikowski CA. Computer Systems That Learn. San Mateo, CA: Morgan Kaufmann Publishers; 1991
    Google Scholar
  • 2 Duda R, Hart P. Pattern Recognition and Scene Analysis. New York: Wiley; 1973
    Google Scholar
  • 3 Rumelhart D, Hinton G, Williams W. Learning internal representations by error propagation. In: Rumelhart D, McClelland J. eds. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Boston: MA: MIT Press; 1986
    Google Scholar
  • 4 Breiman L, Friedman J, Olshen R, Stone C. Classification and Regression Trees. Monterey, CA: Wadsworth; 1984
    Google Scholar
  • 5 Montgomery GJ, Drake KC. Abductive networks. In: Proceedings of the SPIE Applica tions of Artificial Neural Networks Conf.. Orlando: Florida; 1990: 56-64.
    Google Scholar
  • 6 Abdel-Aal RE, Elhadidy MA. A machinelearning approach to modelling and forecasting the minimum temperature at Dhahran, Saudi Arabia. Energy – The International Journal 1994; 19: 739-49.
    PubMedGoogle Scholar
  • 7 Abdel-Aal RE, Elhadidy MA. Modelling and forecasting the daily maximum temperature using abductive machine learning. Weather and Forecasting 1995; 10: 310-25.
    CrossrefPubMedGoogle Scholar
  • 8 Lancaster HO. An Introduction to Medical Statistics. New York: Wiley; 1974
    Google Scholar
  • 9 Szolovits P, Pauker S. Categorical and probabilistic reasoning in medical diagnosis. Artif Intell 1978; 11: 115-44.
    CrossrefPubMedGoogle Scholar
  • 10 Quinlan J. Simplifying decision trees. Intern J Man-Machine Stud 1987; 27: 221-34.
    PubMedGoogle Scholar
  • 11 Marshal SJ, Harrison RF, Kennedy R. Neural classification of chest pain symptoms: A comparison study. In: Proceedings of the 2nd International Conference on Artificial Neutral Networks. Bournemouth, UK: 1991: 200-4.
    Google Scholar
  • 12 Zhu K, Noakes PD, Green ADP. ECG monitoring with artificial neural networks. In: Proceedings of the 2nd International Conference on Artificial Neural Networks. Bournemouth, UK: 1991: 205-9.
    Google Scholar
  • 13 AIM User’s Manual. AbTech Corporation; Charlottesville VA: 1990
    Google Scholar
  • 14 Farlow SJ. The GMDH algorithm. In: Farlow SJ. ed. Self-Organizing Methods in Modeling: GMDH Type Algorithms. New York: Marcel-Dekker; 1984: 1-24.
    Google Scholar
  • 15 Barron AR. Predicted squared error – a criterion for automatic model selection. In: Farlow SJ. ed. Self Organizing Methods in Modeling: GMDH Type Algorithms. New York: Marcel-Dekker; 1984: 87-103.
    Google Scholar
  • 16 Diagnostic Techniques for Intestinal Parasitic Infections (IPI) Applicable to Primary Health Care (PHC) Services. WHO/PDP/ 85.2 Geneva: World Health Organisation; 1985
    Google Scholar
  • 17 Nokes C, Bundy DA. Compliance and absenteeism in school children: Implications for helminth control. Trans R Soc Trop Med Hyg 1993; 87.
    PubMedGoogle Scholar
  • 18 Peckham CS, Gardiner PA, Goldstein H. Acquired myopia in 11 year old children. BMJ 1977; 1: 542-4.
    CrossrefPubMedGoogle Scholar
  • 19 Peckham CS. Vision in childhood. Br Med Bull 1986; 42: 150-4.
    CrossrefPubMedGoogle Scholar
  • 20 Grisham JD, Simons HD. Refractive error and the reading process: A literature analysis. J Am Optom Assoc 1986; 57: 44-55.
    PubMedGoogle Scholar
  • 21 Prescience Corporation. Theorist® for the Macintosh™: Reference manual, Version 1.11. 1990
    PubMedGoogle Scholar
  • 22 SPSS inc. SPSS® for Windows™: SPSS Professional Statistics™, Release 5. 1992
    PubMedGoogle Scholar