This project was done as EEE-5286 BioSignal Processing course project in Fall 2017. This project implements the paper titled "Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis". Dataset used in this project can be found in the following link: https://www.physionet.org/physiobank/database/gaitndd/

The article presents the analysis of signals measured from patients with Amyotrophic Lateral Sclerosis (ALS) in order to discover some dynamic biomarkers. ALS, also known as Lou Gehrig's disease, is a neurodegenerative disease where the neurons controlling muscles that perform voluntary actions (motor neurons) are destroyed slowly with time. The cause of the disease is not known but there is evidence that it can be inherited genetically. The authors of the reference article introduced a hypothesis i.e. subjects with ALS would have an altered gait rhythm from the normal rhythm and performed analysis to prove the hypothesis. These variations would increase in the magnitude of the stride-to-stride fluctuation and perturbations in the fluctuation dynamics. In order to prove the hypothesis, the authors followed signal processing approaches such as the Detrended Fluctuation Analysis (DFA), autocorrelation of the stride time series, normalized nonstationarity index for stride intervals and the fluctuation dynamics. They compared the results of these analysis for patients with ALS with that of healthy patients and also with that of Parkinsons Disease (PD) and Huntington Disease (HD) patients. The authors found their results to be supportive of their hypothesis. This could hence be potentially used to characterize the biomarkers for motor control in ALS.

Reference:

Hausdorff, J. M., Lertratanakul, A., Cudkowicz, M. E., Peterson, A. L., Kaliton, D., & Goldberger, A. L. (2000). Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis. Journal of applied physiology, 88(6), 2045-2053.