Headache Interference as a Function of Affect and Coping: An Artificial Neural Network Analysis

Authors

  • Stuart Cathcart BA Hons,

    Corresponding author
    1. From the Department of Psychology, The University of Adelaide, South Australia.
    Search for more papers by this author
  • Felicity Materazzo MPsych

    1. From the Department of Psychology, The University of Adelaide, South Australia.
    2. Ms. Materazzo is also affiliated with the Pain Management Unit, Flinders Medical Centre, Bedford Park, South Australia.
    Search for more papers by this author

Address all correspondence to Mr. Stuart Cathcart, PO Box 167, Mawson A.C.T 2607, Canberra, Australia.

Abstract

Artificial neural networks present a technique for modeling relationships between variables in complex systems. The negative effects of headache are determined by many “biopsychosocial” elements that represent a complex system. Artificial neural networks may therefore be useful for examining psychological factors in headache. To test this hypothesis, we trained an artificial neural network to predict life-style interference attributed to headache from psychological measures of anger, depression, and coping appraisal and strategies. The artificial neural network demonstrated a better fit of the data than that obtained by multiple regression, and predicted interference levels to within 10% error for 80% of novel cases. Artificial neural networks may be a useful technique for examining psychological correlates of headache.

Ancillary