Objective: Parkinson’s disease is a chronic
neurodegenerative impairment which causes movement
impairment. Dopaminergic deficiency resulted from the loss
of dopaminergic neurons in the substantia nigracauses the
disease. UPDRS (Unified Park-inson’s disease rating scale)
is an important scale for evaluation of clinical severity of
Parkinson’s disease. Recent computational studies using in
silico prediction methods show promising results in terms
of their potential diagnostic relevance. This study aims to
evaluate the diagnostic potential of in silico methods using
vocal cord vibrations and the UPDR scale of Parkinson’s
Disease for obtaining more precise diagnosis model.
Material-Method: In this study an in silico prediction model
using telemonitoring measures, clinical motor and total
UPDRS for diagnosis of Parkinson’s disease was developed
by using regression analysis with neural network model. In
addition, we investigated the importance of different attributes
in our regression algorithm provided from telemonitoring and
UPDRS for evaluation of their predictive relevance.
Results: The correlation between predicted motor UPDRS
score and clinical motor UPDRS score was found as 97%.
Exclusion of Jitter values did not directly affect the predictive
power of the model.
Conclusions: Clinical UPDRS scoring proved its importance
to achieve to generate more predictive models.
Parkinson’s Disease Artificial Neural Network Regression Analysis
Konular | Sağlık Kurumları Yönetimi |
---|---|
Bölüm | Araştırma Makaleleri |
Yazarlar | |
Yayımlanma Tarihi | 14 Nisan 2017 |
Gönderilme Tarihi | 14 Nisan 2017 |
Yayımlandığı Sayı | Yıl 2017 |