Gait Analysis Using a Support Vector Machine for Lumbar Spinal Stenosis

Abstract

Lumbar spinal canal stenosis (LSS) is diagnosed based on physical examination and radiological documentation of lumbar spinal canal narrowing. Differential diagnosis of the level of lumbar radiculopathy is difficult in multilevel spinal stenosis. Therefore, the authors focused on gait analysis as a classification method to improve diagnostic accuracy. The goal of this study was to identify gait characteristics of L4 and L5 radiculopathy in patients with LSS and to classify L4 and L5 radiculopathy using a support vector machine (SVM). The study group comprised 13 healthy volunteers (control group), 11 patients with L4 radiculopathy (L4 group), and 22 patients with L5 radiculopathy (L5 group). Light-emitting diode markers were attached at 5 sites on the affected side, and walking motion was analyzed using video recordings and the authors' development program. Potential gait characteristics of each group were identified to use as SVM parameters. In the knee joint of the L4 group, the waveform was similar to that of normal gait, but knee extension at initial contact was slightly greater than that of the other groups. In the ankle joint of the L5 group, the one-peak waveform pattern with disappearance of the second peak was present in 10 (45.5%) of 22 cases. The total classification accuracy was 80.4% using the SVM. The highest and lowest classification accuracies were obtained in the control group (84.6%) and the L4 group (72.7%), respectively. The authors' walking motion analysis system identified several useful factors for differentiating between healthy individuals and patients with L4 and L5 radiculopathy, with a high accuracy rate.

Artificial intelligence and machine learning in spine research

“…However, only a few studies involving ML techniques to investigate spinal disorders have been presented so far; this lack of documentation reflects the technical difficulties in assessing position and motion of the vertebrae due to soft tissue artifacts . An example of a pioneering study in this field is offered by Hayashi et al, who trained an SVM to distinguish gait patterns associated to either L4 or L5 radiculopathy in patients suffering from lumbar canal stenosis, achieving an accuracy of 80.4%.…”

Analysis of Dynamic Plantar Pressure before and after the Occurrence of Neurogenic Intermittent Claudication in Patients with Lumbar Spinal Stenosis: An Observational Study

“…FPA referred to the angle between the longitudinal axis of one foot and the walking direction, and its outward rotation indicated that the patient had an "out-toe" gait when walking [24]. Previous studies confirmed that patients with LSS had a wide-based gait [17], which was mainly manifested by awkward and faltering walking patterns. These patterns could reflect the characteristics of patients with unstable trunk and limited dynamic balance [11].…”

An automatic non-invasive method for Parkinson's disease classification

“…SVM classifier is computationally very efficient and has been used extensively in gait identification [32,33].A leave-one-out-cross- statistically using the independent t-test in SPSS software [34].For each classification accuracy a symmetrical 95% confidence interval (CI) was calculated assuming binomial distribution. …”