Parkinson’s Disease Symptom Detection using Hybrid Feature Extraction and Classification Model

In recent years, there has been a significant demand for diagnosing and monitoring various neurological-based disease diseases such as Parkinson’s disease. This study aims to develop a web-based symptom detector that can predict Parkinson’s disease at an early stage. Users can either draw or upload a spiral image on the website for analysis. To achieve this, the study proposes a hybrid model that combines the Histogram of Oriented Gradients Descriptor and Random Forest Classifier. Features are being extracted from a series of spiral drawings, which serve as the dataset, and then classifies the extracted data using the proposed model. The achieved results show an average accuracy, sensitivity, and specificity of 83.33%, 73.33%, and 93.33% respectively. In conclusion, this approach demonstrates promising potential for early detection of Parkinson’s disease using the proposed web-based symptom detector.