Classification of psychosocial risk factors (yellow flags) for the development of chronic low back and leg pain using artificial neural network.

Due to international guidelines of treatment of acute low back pain (LBP), psychosocial risk factors like depressive mood and maladaptive pain-related coping strategies ('yellow flags') have to be assessed in the early phase of acute pain. Within this longitudinal study in patients with LBP and leg pain, we used an artificial neural network (ANN) to classify the pain intensity 6 months after the onset of treatment. Psychosocial risk factors were used as input neurons. The training of the three-layer ANN using the back-propagation algorithm yields to an accuracy of 83.1%. Further on, the complexity of this structure indicated the necessity of an early screening procedure that allows a differentiation between several high risk groups and a low risk profile in order to predict the long-term development of pain intensity.