Application of patient-reported outcomes in clinical evaluation of acupuncture for cervical spondylosis with artificial neural network

Abstract

Cervical spondylosis (CS) is a disease caused by nonspecific degenerative disorders, therefore it requires high demands for diagnosis due to its diversity and complexity. Patient-reported outcomes (PRO) assessment techniques are on the foundation of psychometrics, which obtain patients' own feelings about daily life, health, subjective satisfaction with treatment and other aspects of personal experience through interviews, questionnaires and other forms of self-assessment. This paper explores the applicability of patient-reported outcomes for clinical evaluation of therapeutic effect of acupuncture for CS and attempts to establish a clinical outcome evaluation model consequently. We introduce SF-36 life quality questionnaire as the main index and visual analogue scale (VAS) as reference index, observe 162 cases as experimental data from a multi-center randomized controlled trial (RCT) on acupuncture for neck pain caused by cervical spondylosis, among others, 150 cases finished the whole course. During the initial phases of study, to verify whether PRO technique is suitable to evaluate the effect of acupuncture for CS, we apply some statistical methods in reliability analysis, validity analysis and responsiveness analysis at different measure times, that is, pre-treatment, post-treatment and during follow-up. The results of reliability analysis show that the Cronbach's statistic alpha of whole scale is 0.834 and that of the standardized items is 0.872. The results of validity analysis shows that 8 common factors selected from SF-36 have an accumulative variance contribution rate of 75.621%, which are represented as physical function (PF), role-physical (RP), general health (GH), mental health (MH), vitality (VT), role-emotion (RE), bodily pain (BP), and society function (SF) respectively. The results of the responsiveness analysis show that except mental health, SF-36 scores at the end of treatment, one month and 3 months after the follow-up differed from those before treatment (P<;0.05). In the further study, we employ three-layer, feed forward neural networks with a back propagation algorithm for the evaluation of acupuncture for CS on the basis of features that were extracted from SF-36. Consequently, the comprehensive assessment model for therapeutic effect of acupuncture for CS based on ANN has good performance with learning precision 96.88%. In general, the experimental results indicate that the PRO techniques have good applicability to the evaluation of therapeutic effect of acupuncture for CS and artificial neural network can offer a feasible approach to the comprehensive assessment as well.