RESUMEN
BACKGROUND: Low back pain is a common musculoskeletal disorder that can incur high financial burden. A significant proportion of this burden may be incurred from referrals to health services and subsequent healthcare usages. Patients' overall experience of pain and its related life interferences may also have some relevance to this usage. OBJECTIVE: This study aimed to examine the referral practices and subsequent health service utilization of patients with LBP within a tertiary specialist clinic setting. A secondary objective was to explore potential associations between primary independent variables of pain and life interferences with health service utilization. METHODS: Participants were patients with low back pain, who completed a set of self-reported low back pain measures. These included measures for pain intensity, pain interference, disability and quality of life. The participants' back pain-related referral and health service utilization in the subsequent 12 months were recorded. RESULTS: A total of 282 patients completed the full measures. Of these, 59.9% were referred for physiotherapy, 26.3% for diagnostic imaging and 9.2% for interventional procedures. Compared to patients who were referred from tertiary care, those from primary care had lower pain intensity ( p = 0 . 001 ), pain interference ( p = 0 . 002 ), disability ( p = 0 . 001 ), but better physical and mental quality of life ( p < 0 . 001 , p = 0 . 017 ). High pain interference was a common factor among patients who were referred on to other services after first consultation. Levels of medical utilization and physiotherapy utilization were both associated with pain intensity ( F = 2 . 39 , p = 0 . 027 vs F = 3 . 87 , p = 0 . 001 ), pain interference ( F = 5 . 56 , p = 0 . 007 vs F = 4 . 12 , 0.01) and disability ( F = 5 . 89 , p = 0 . 001 vs F = 3 . 40 , p = 0 . 016 ). Regression analysis showed that the source of referral contributed to 6% of the variance in medical utilization and 3% of the variance in physiotherapy utilization. After controlling the demographic variables and referral sources, none of the independent variables added any significant variance to medical utilization. Only pain intensity contributed an additional 2% variance to physiotherapy utilization. CONCLUSION: Referral patterns and practices appear similar to those reported in other studies. Higher levels of pain intensity, interference, disability and quality of life appear to influence the referral to different health services and subsequent treatment utilization.
RESUMEN
Pain is an integrative phenomenon coupled with dynamic interactions between sensory and contextual processes in the brain, often associated with detectable neurophysiological changes. Recent advances in brain activity recording tools and machine learning technologies have intrigued research and development of neurocomputing techniques for objective and neurophysiology-based pain detection. This paper proposes a pain detection framework based on Electroencephalogram (EEG) and deep convolutional neural networks (CNN). The feasibility of CNN is investigated for distinguishing induced pain state from resting state in the recruitment of 10 chronic back pain patients. The experimental study recorded EEG signals in two phases: 1. movement stimulation (MS), where induces back pain by executing predefined movement tasks; 2. video stimulation (VS), where induces back pain perception by watching a set of video clips. A multi-layer CNN classifies the EEG segments during the resting state and the pain state. The novel approach offers high and robust performance and hence is significant in building a powerful pain detection algorithm. The area under the receiver operating characteristic curve (AUC) of our approach is 0.83 ± 0.09 and 0.81 ± 0.15, in MS and VS, respectively, higher than the state-of-the-art approaches. The sub-brain-areas are also analyzed, to examine distinct brain topographies relevant for pain detection. The results indicate that MS-induced pain tends to evoke a generalized brain area, while the evoked area is relatively partial under VS-induced pain. This work may provide a new solution for researchers and clinical practitioners on pain detection.