Parkinson's Identification Research Articles

Feature Weighting for Parkinson's Identification using Single Hidden Layer Neural Network

The diagnosis of Parkinson has become easier with the existence of machine learning. It includes using existing features from the biometric dataset generated by the person to identify whether he has Parkinson or not. The features differ in their discrimination capability and they suffer from redundancy. Hence, researchers have recommended using feature selection for Parkinson's identification. The feature selection aims at finding the most important and relevant features to produce an efficient and effective model. In this article, we present entropy-based Parkinson classification. The goal is to select only 50% of the most relevant features for Parkinson prediction. Two variants of neural networks are used for evaluation, the first one is a feed-forward Extreme Learning Machine ELM and the second one is Fast Learning Machine FLN. Also, the K-Nearest Neighbor KNN algorithm is used for evaluation. The results show the superiority of ELM and FLN when the model of feature selection is used with an accuracy of 80% compared with only 78% when the model is not used.

An improved sex-specific and age-dependent classification model for Parkinson's diagnosis using handwriting measurement

Background and ObjectivesDiagnosis of Parkinson's with higher accuracy is always desirable to slow down the progression of the disease and improved quality of life. There are evidences of inherent neurological differences between male and females as well as between elderly and adults. However, the potential of such gender and age infomration have not been exploited yet for Parkinson's identification. MethodsIn this paper, we develop a sex-specific and age-dependent classification method to diagnose the Parkinson's disease using the online handwriting recorded from individuals with Parkinson's (n = 37; m/f-19/18;age-69.3 ± 10.9yrs) and healthy controls (n = 38; m/f-20/18;age-62.4 ± 11.3yrs). A support vector machine ranking method is used to present the features specific to their dominance in sex and age group for Parkinson's diagnosis. ResultsThe sex-specific and age-dependent classifier was observed significantly outperforming the generalized classifier. An improved accuracy of 83.75% (SD = 1.63) with the female-specific classifier, and 79.55% (SD = 1.58) with the old-age dependent classifier was observed in comparison to 75.76% (SD = 1.17) accuracy with the generalized classifier. ConclusionsCombining the age and sex information proved to be encouraging in classification. A distinct set of features were observed to be dominating for higher classification accuracy in a different category of classification.

The history of parkinsonism: Descriptions in ancient Indian medical literature

The clinical syndrome of parkinsonism was identified in ancient India even before the period of Christ and was treated methodically. The earliest reference to bradykinesia dates to 600 bc. Evidences prove that as early as 300 bc, Charaka proposed a coherent picture of parkinsonism by describing tremor, rigidity, bradykinesia, and gait disturbances as its components. The scenario was further developed by Madhava, Vagbhata, and Dalhana all through history. The 15th-century classic "Bhasava rajyam" introduced the term kampavata, which may be regarded as an ayurvedic analogue of parkinsonism. The pathogenesis of kampavata centered on the concept of imbalance in the vata factor, which controls psychomotor activities. The essential element in therapy was the administration of powdered seed of Mucuna pruriens, or atmagupta, which as per reports, contains 4%-6% of levodopa. In addition to proving the existence and identification of parkinsonism in ancient India, the study points to the significance of ancient Indian Sanskrit works in medical history.

Identification of parkinsonism and Parkinson's disease.

Parkinson's disease is a common movement disorder associated with considerable disability. The clinical syndrome of parkinsonism is based on the presence of core clinical features of rest tremor, bradykinesia, rigidity and impaired postural reflexes or gait. Parkinsonism is most often caused by Parkinson's disease, but can also be caused by other disorders, including cerebrovascular disease, multiple-system atrophy, progressive supranuclear palsy and other disorders. Parkinsonism can be identified by questionnaires and confirmed in person or by videotaped clinical examinations. The identification of presymptomatic cases remains problematic but is motivated by the hope for treatment before symptoms appear. Quantitative approaches to the diagnosis of parkinsonism based on the measurement of the cardinal features are available. Clinical approaches should include identification of features atypical for Parkinson's disease, which exclude the diagnosis, and documentation of a response to dopaminergic medications, which support a diagnosis of Parkinson's disease. Loss of smell and visual dysfunction are found in early patients and may be useful in screening protocols. In addition, behavioral changes, including depressive symptoms, may be detected in presymptomatic cases. Cognitive changes, such as impaired set shifting, have been observed in early Parkinson's disease, but can be seen with other causes of parkinsonism. Neuroimaging techniques, including positron emission tomography or single-photon emission computed tomography, are available to quantify dopaminergic neurons, while magnetic resonance imaging may be helpful in differentiating other forms of parkinsonism from Parkinson's disease. There are numerous approaches available to the identification of parkinsonism and Parkinson's disease. The gold standard remains a clinical diagnosis, confirmed by autopsy.