Pain Relief Using Artificial Neural Network
Pain is the sensation by which humans body alarms about tissue lesion. Due to complexity of the nature of pain and mechanism(s) involved, the utilization of computational models in the field of pain has been very limited. Artificial neural networks (ANNs) are appearing as useful alternatives to traditional statistical modeling techniques in many scientific disciplines. ANN is the mathematical model of the neurons which are the main biological components of the brain. The aim of this study was to design of an ANN for pain control on the basis of experimental data. Thermal and electrical stimulation were used for induction and inhibition of the pain respectively in healthy adult volunteers. Pain intensity was measured with visual analog scale (VAS) from 0 to 10. We used multilayer perceptron to clustering our data and pain modeling. In this model, the VAS scores and different doses of electrical stimulation were considered as inputs for the ANN, and the network was asked to release electrical stimulation at appropriate dose and time for inhibition of pain signals as an output We had pain model network by test error=.085 and train error=6.58 * 10(Λ)-5. It seems this model would be useful in clinical situations for pain relief.
thermal pain modeling VAS Electrical stimulation
Farzaneh Samiee Mercedeh Jahanseir Siamak Haghipour
Biomedical Engineering Faculty, Science and Research Branch, Islamic Azad University,Tehran, Iran.
国际会议
成都
英文
980-984
2010-12-17（万方平台首次上网日期，不代表论文的发表时间）