Predictive medicine: initial symptoms may determine outcome in clinically treated depressions

Nonlinear mathematical modeling methods were compared in the study of therapeutic outcome prediction for clinically depressed patients. The performance of backpropagation, a nonlinear regression technique, was compared to multiple linear and quadratic regression. The results demonstrated nonlinear methods were useful in studying depression. To look for nonlinear predictive relationships among pre-treatment symptoms, treatment, and outcome, several studies were performed on data from 99 patients. This study investigated whether linear and nonlinear methodologies could reliably predict percent improvement of clinically depressed individuals exposed to fluoxetine, desipramine, or cognitive behavioral therapy. The linear model performed at chance levels with no factor statistically significant. However, both nonlinear models, backpropagation and quadratic regression, predicted outcome at statistically significant levels (p<0.05)