• A S Salma Banu

Parkinson's disease is a progressive condition characterized by muscle weakness and arm and leg tremors resulting from a central nervous system disorder affecting movement. One approach for detecting Parkinson's disease is through voice analysis, as changes in voice patterns can indicate the presence of symptoms. In this project, a model was developed to detect Parkinson's disease using voice data, achieving an efficiency of 73.8%. The model was trained using a large dataset that included recordings from individuals without Parkinson's disease and those previously diagnosed with the condition. Machine learning algorithms were employed to analyze the data. Sixty per cent of the dataset was used for training, while the remaining 40% was used for testing. By inputting voice data into the model, it could determine whether the person showed symptoms of Parkinson's disease or not. The dataset consisted of 24 columns, each representing symptom values for a patient, except for the "status" column. The "status" column contained values of 0 and 1, where 1 indicated the presence of Parkinson's disease, and 0 indicated normal conditions. The main objectives of this article were to provide an understanding of Parkinson's disease and to detect its early onset. Various machine learning algorithms, such as XG Boost, KNN Algorithm, Support Vector Machines (SVMs), and Random Forest Algorithm, were utilized to achieve these goals. The focus was on evaluating the motor function ability of patients with Parkinson's disease. This project's scope was to demonstrate the high accuracy of detecting Parkinson's disease in its early stages, highlighting the potential for early diagnosis and intervention.

Parkinson's disease is a progressive condition characterized by muscle weakness and arm and leg tremors resulting from a central nervous system disorder affecting movement. One approach for detecting Parkinson's disease is through voice analysis, as changes in voice patterns can indicate the presence of symptoms. In this project, a model was developed to detect Parkinson's disease using voice data, achieving an efficiency of 73.8%. The model was trained using a large dataset that included recordings from individuals without Parkinson's disease and those previously diagnosed with the condition. Machine learning algorithms were employed to analyze the data. Sixty per cent of the dataset was used for training, while the remaining 40% was used for testing. By inputting voice data into the model, it could determine whether the person showed symptoms of Parkinson's disease or not. The dataset consisted of 24 columns, each representing symptom values for a patient, except for the "status" column. The "status" column contained values of 0 and 1, where 1 indicated the presence of Parkinson's disease, and 0 indicated normal conditions. The main objectives of this article were to provide an understanding of Parkinson's disease and to detect its early onset. Various machine learning algorithms, such as XG Boost, KNN Algorithm, Support Vector Machines (SVMs), and Random Forest Algorithm, were utilized to achieve these goals. The focus was on evaluating the motor function ability of patients with Parkinson's disease. This project's scope was to demonstrate the high accuracy of detecting Parkinson's disease in its early stages, highlighting the potential for early diagnosis and intervention.

"Earlier Identification of Parkinson’s Disease Using Deep Learning Algorithm - An Evolutionary Approach in Biomedical Application ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.134-137, April-2019, Available :http://www.jetir.org/papers/JETIR1904W18.pdf

"Earlier Identification of Parkinson’s Disease Using Deep Learning Algorithm - An Evolutionary Approach in Biomedical Application ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp134-137, April-2019, Available at : http://www.jetir.org/papers/JETIR1904W18.pdf