Energy entropy feature for the discrimination between the patients with amyotrophic lateral sclerosis and healthy subjects
by Chandrakar Kamath
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 20, No. 3, 2016

Abstract: Amyotrophic Lateral Sclerosis (ALS) is a type of neurological disease due to the degeneration of motor neurons. Hypothesising that ALS patient will experience an altered gait rhythm, with changes in the magnitude of the stride-to-stride fluctuations and perturbations in the fluctuation dynamics, the gait rhythm of ALS patients is compared with those of healthy subjects using energy entropy (EE) feature and approximate entropy (ApEn). It is found that EE (ApEn) was increased (decreased) in ALS patients compared to EE feature in healthy controls. It is found that in the diagnostic ability test ApEn performed well with AROC = 0.8222, accuracy = 83.3%, specificity = 66.7%, sensitivity = 93.3%, and precision = 85.7%, while EE feature outperformed with AROC = 0.9803, accuracy = 93.8%, specificity = 94.1%, sensitivity = 96.3%, and precision = 96.1%. Results also showed that the diagnostic performance of EE feature is much superior compared to that of ApEn in discriminating ALS from patients with Parkinson and Huntington diseases.

Online publication date: Tue, 22-Mar-2016

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com