Investigating the effects of movement speed on the lumbopelvic coordination during trunk flexion

Exploring how metronome pacing at varying movement speeds influences local dynamic stability and coordination variability of lumbar spine motion during repetitive lifting

Auditory metronomes have been used to preserve movement consistency when examining local dynamic stability (LDS) and coordination variability (CV) of lumbar spine motion during repetitive movements. However, the potential influence of the metronome itself on these outcome measures has rarely been considered. Therefore, this study investigated the influence of different metronome paces (i.e., lifting speeds) on measures of lumbar spine LDS and thorax-pelvis CV during a repetitive lifting/lowering task in comparison to self-paced movements. Ten participants completed 5 repetitive lift/lower trials, where participants completed 35 consecutive repetitions (analysis on last 30 repetitions) at a self-selected pace for the first and last trial, and were paced by a 10 lift/min, 15 lift/min, and 20 lift/min metronome, in randomized order, for the remaining three trials. The average self-paced lift/lower speed before and after experiencing the three different metronome paced speeds was 16.2 (±1.02) and 17.2 (±0.73) lifts/min, respectively, and the most-preferred metronome pace trial was 15 lifts/min. Thorax-pelvis CV during the self-paced trials were similar (p > 0.05) to the 15 lift/min metronome paced trials, while greater thorax-pelvis CV was observed for the 10 lift/min compared to the 15 lift/min and 20 lift/min and second self-paced trial (all p < 0.026). This movement speed effect was not observed for lumbar spine LDS; however, more-dynamically stable movements were observed during all metronome paced trials in comparison to the self-paced trials. This study highlights that careful consideration is required when employing a metronome to control/manipulate movement characteristics while examining neuromuscular control using non-linear dynamical systems measures.

Using a deep learning network to recognise low back pain in static standing

Low back pain (LBP) remains one of the most prevalent musculoskeletal disorders, while algorithms that able to recognise LBP patients from healthy population using balance performance data are rarely seen. In this study, human balance and body sway performance during standing trials were utilised to recognise chronic LBP populations using deep neural networks. To be specific, 44 chronic LBP and healthy individuals performed static standing tasks, while their spine kinematics and centre of pressure were recorded. A deep learning network with long short-term memory units was used for training, prediction and implementation. The performance of the model was evaluated by: (a) overall accuracy, (b) precision, (c) recall, (d) F1 measure, (e) receiver-operating characteristic and (f) area under the curve. Results indicated that deep neural networks could recognise LBP populations with precision up to 97.2% and recall up to 97.2%. Meanwhile, the results showed that the model with the C7 sensor output performed the best. Practitioner summary: Low back pain (LBP) remains the most common musculoskeletal disorder. In this study, we investigated the feasibility of applying artificial intelligent deep neural network in detecting LBP population from healthy controls with their kinematics data. Results showed a deep learning network can solve the above classification problem with both promising precision and recall performance.