The authors declare no conflict of interest (AKA dual commitments, competing interests, and competing loyalties).
ORIGINAL RESEARCH ARTICLE
An Artificial Neural Network Approach for Predicting Functional Outcome in Fibromyalgia Syndrome after Multidisciplinary Pain Program
Article first published online: 5 AUG 2013
Wiley Periodicals, Inc.
Volume 14, Issue 10, pages 1450–1460, October 2013
How to Cite
Salgueiro, M., Basogain, X., Collado, A., Torres, X., Bilbao, J., Doñate, F., Aguilera, L. and Azkue, J. J. (2013), An Artificial Neural Network Approach for Predicting Functional Outcome in Fibromyalgia Syndrome after Multidisciplinary Pain Program. Pain Medicine, 14: 1450–1460. doi: 10.1111/pme.12185
- Issue published online: 16 OCT 2013
- Article first published online: 5 AUG 2013
- Fundación FF y Ciencia SER
- Government of the Basque Country under program SAIOTEK. Grant Number: SA-2010/00110
- Ayudas a Grupos de Investigación del Sistema Universitario Vasco
- Government of the Basque Country
- Treatment Outcome
The objective of this study was to evaluate the ability of artificial neural networks (ANNs) to predict, on the basis of clinical variables, the response of persons with fibromyalgia syndrome (FMS) to a standard, 4-week interdisciplinary pain program.
The design of this study is retrospective longitudinal.
Fibromyalgia outpatient clinic in a tertiary-care general hospital.
The subjects of this study include outpatients with FMS.
Multidisciplinary pain program including pain pharmacotherapy, cognitive-behavioral therapy, physical therapy, and occupational therapy.
Reliable change (RC) of scores on the Stanford Health Assessment Questionnaire (HAQ), and accuracy of ANNs in predicting RC at discharge or at 6-month follow-up as compared to Logistic Regression.
ANN-based models using the sensory-discriminative and affective-motivational subscales of the McGill Pain Questionnaire, the HAQ disability index, and the anxiety subscale of Hospital Anxiety and Depression Scale at baseline as input variables correctly classified 81.81% of responders at discharge and 83.33% of responders at 6-month follow-up, as well as 100% of nonresponders at either evaluation time-point. Logistic regression analysis, which was used for comparison, could predict treatment outcome with accuracies of 86.11% and 61.11% at discharge and follow-up, respectively, based on baseline scores on the HAQ and the mental summary component of the Medical Outcomes Study—Short Form 36.
Properly trained ANNs can be a useful tool for optimal treatment selection at an early stage after diagnosis, thus contributing to minimize the lag until symptom amelioration and improving tertiary prevention in patients with FMS.