Scalp EEG-Based Pain Detection Using Convolutional Neural Network.

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.

Health professionals' referral practice and related healthcare utilization for people with low back pain in Singapore: A retrospective study.

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.

Cost-effectiveness of hydrotherapy versus land-based therapy in patients with musculoskeletal disorders in Singapore.

BACKGROUND: The study evaluated the cost-effectiveness of hydrotherapy versus land-based therapy in patients with musculoskeletal disorders (MSDs) in Singapore. METHODS: A decision-analytic model was constructed to compare the cost-effectiveness of hydrotherapy to land-based therapy over 3 months from societal perspective. Target population comprised patients with low back pain (LBP), osteoarthritis (OA), rheumatoid arthritis (RA), total hip replacement (THR) and total knee replacement (TKR). Subgroup analyses were carried out to determine the cost-effectiveness of hydrotherapy in individual MSDs. Relative treatment effects were obtained through a systematic review of published data. RESULTS: Compared to land-based therapy, hydrotherapy was associated with an incremental cost-effectiveness ratio (ICER) of SGD 27 471 per quality-adjusted life-year (QALY) gained, which was below the willingness-to-pay threshold of SGD 70 000 per QALY (one gross domestic product per capita in Singapore in 2015). For the respective MSDs, hydrotherapy were dominant (more effective and less costly) in THR and TKR, cost-effective for LBP and RA, and not cost-effective for OA. Treatment adherence and cost of hydrotherapy were key drivers to the ICER values. CONCLUSIONS: Hydrotherapy was a cost-effective rehabilitation compared to land-based therapy for a population with MSDs in Singapore. However, the benefit of hydrotherapy was not observed in patients with OA.

Efficacy of a Virtual Reality Commercial Gaming Device in Upper Limb Recovery after Stroke: A Randomized, Controlled Study.

OBJECTIVE: To compare the efficacy of a virtual reality commercial gaming device, Nintendo wii (NW) with conventional therapy and customary care in facilitating upper limb recovery after stroke. DESIGN: Randomized, controlled, single-blinded study. SETTING: Tertiary rehabilitation center. PARTICIPANTS: 105 subjects admitted to in inpatient rehabilitation program within 6 weeks of stroke onset. INTERVENTIONS: Subjects were randomly assigned to one of three groups of upper limb exercises: (1) NW gaming; (2) conventional therapy; (3) control. NW gaming and conventional therapy were provided fourtimes a week for 3 weeks. MAIN OUTCOME MEASURE(S): The main outcome measure was Fugl-Meyer assessment (FMA) of upper limb function. Secondary outcome measures included Action Research Arm Test, Functional Independence Measure, and Stroke Impact Scale. These measures were assessed at baseline, completion of intervention (week 3) and at 4 weeks and 8 weeks after completion of intervention. The primary outcome measure was the change in FMA scores at completion of intervention. RESULTS: The mean age was 57.5±9.8 years, and subjects were enrolled at a mean of 13.7±8.9 days after stroke. The mean baseline FMA score was 16.4±14.2. There was no difference in FMA scores between all 3 groups at the end of intervention, and at 4 and 8 weeks after completion of intervention. Similar findings were also noted for the secondary outcome measures. CONCLUSION(S): Twelve sessions of augmented upper limb exercises via NW gaming or conventional therapy over a 3-week period was not effective in enhancing upper limb motor recovery compared to control.