Affordable Access

Non-specific Low back pain : Exploratory analysis and clustering for a new paradigm

  • Robinault, Lucien
Publication Date
Sep 19, 2023
External links


Non-specific low back pain (NSLBP) is a major public health issue and is a concern in most if not all contemporary societies. Despite NSLBP being so widespread, our understanding of its underlying causes, as well as our capacity to provide effective treatments, remains limited due to the high diversity in the population that does not respond to generic treatments. Clustering the NSLBP population based on shared characteristics offers a potential solution for developing personalized interventions. However, the complexity of NSLBP and the reliance on subjective categorical data in previous attempts present challenges in achieving reliable and clinically meaningful clusters. This work features to goals : 1. First objective : Provide an exploratory work to better understand the influence and importance of the selected variables in regards to NSLBP and our sample population, and gather information to prepare subgrouping2. Second objective : Provide an attempt at clustering our population sample in order to discriminate valuables subgroups Data were acquired from 46 subjects who performed six simple movement tasks (back extension, back flexion, lateral trunk flexion right, lateral trunk flexion left, trunk rotation right, and trunk rotation left) at two different s peeds (maximum and preferred). High-density electromyography (HD EMG) data from the lower back region were acquired, jointly with motion capture data, using passive reflective markers on the subject’s body and clusters of markers on the subject’s spine. An exploratory analysis was conducted using a deep neural network and factor analysis. Based on selected variables, various models were trained to classify individuals as healthy or having NSLBP in order to assess the importance of different variables. The models were trained using different set of data : full data set, anthropometric data set, biomechanical data set, neuromuscular data set, and balance and proprioception data set. The models achieved high accuracy in categorizing individuals as healthy or NSLBP. Factor analysis revealed that individuals with NSLBP exhibited different movement patterns to healthy individuals, characterized by slower and more rigid movements. Anthropometric variables (age, sex, and BMI) were significantly correlated with NSLBP components. Clustering was attempted on our full data set, and reduced data set, using PCA or the insights gather in the exploratory analysis part. The data set were either movement agnostic or movement specific. Results s howed v iable c lustering using spectral algorithm, with the RBF kernel and the discretize label assignment’s algorithm, expressing a spectrum of low back pain as did similar work before. The data set used was the full data set with spine cluster of marker data, after dimension reduction using principal component analysis. In conclusion, different data types, such as body measurements, movement patterns, and neuromuscular activity, can provide valuable information for identifying individuals with NSLBP. To gain a comprehensive understanding of NSLBP, it is crucial to investigate the main domains influencing its prognosis as a cohesive unit rather than studying them in isolation. Simplifying the conditions for acquiring dynamic data is recommended to reduce data complexity, and using back flexion and trunk rotation as effective options should be further explored. The importance and probable usefulness of meta data, such as anthropometric data for the biophysical domain, was also noted. In the light of those results, we formulated the following new paradigm hypothesis : low back pain yields adaptations common to every subject, but due to inter-subject differences in the 5 main domains known to have a major influence on low back pain prognosis (biophysical, comorbidities, social, psychological and genetic) those adaptations are expressed in very unique way for each subject.

Report this publication


Seen <100 times