Prediction of Parkinson’s disease using XGBoost

OUR PROPOSED TITLE:

Parkinson’s disease Classification using Machine Learning

IEEE BASE PAPER ABSTRACT:

Parkinson’s Disease (PD) is one of the world’s most serious public health issues. It is a well-known fact that approximately one million people in the United States suffer from Parkinson’s disease, while the global number of persons suffering from Parkinson’s disease is estimated to be around 5 million. It is a long term neurological condition that affects the dopamine producing nerve cells in the brain. Tremor, poor posture, and poor balance are common symptoms. It mostly affects people in their 60s and slows down their speech, causing them to talk softly and slurredly. Inappropriate silences between words and extended pauses before starting to speak characterize the patient’s vocal pattern. In this paper we extend a work which used the motor symptoms and aims to predict Parkinson illness at an early stage using machine learning techniques based on speech samples obtained from the UCI ML collection of Parkinson’s patients. In this research, we evaluate the performance of classifiers that outperformed with high accuracy, such as decision trees with ensemble classifier models like XGBoost and Random Forest, utilizing with different machine learning models.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Random Forest Classifier.

OUR PROPOSED ABSTRACT:

Parkinson’s disease is a progressive neurological disorder that affects movement, characterized by symptoms such as tremors, stiffness, and difficulty with coordination and balance. It is caused by the loss of dopamine-producing cells in the brain. Currently, there is no cure for Parkinson’s disease, and treatment options are limited to managing symptoms. The prediction of Parkinson’s disease using machine learning techniques can help diagnose the disease at an early stage, which can lead to more effective treatment and management of symptoms.

Machine learning models can analyze large amounts of clinical data and identify patterns and relationships that may not be immediately apparent to human clinicians. By training these models on datasets containing relevant clinical information, they can predict the likelihood of developing Parkinson’s disease or the progression of the disease. Such predictions can assist in developing personalized treatment plans and monitoring the effectiveness of the treatment over time. Therefore, the use of machine learning for the prediction of Parkinson’s disease can have significant implications for the early diagnosis and management of the disease.

The objective of this project is to predict Parkinson’s disease using machine learning techniques, specifically the Random Forest Classifier. The dataset used in this project contains clinical data acquired from electronic medical records at the UCI ML repository. Our approach involved preprocessing the data, selecting the relevant features, and training the Random Forest Classifier on the structured dataset. Our results showed that the model achieved a Train Accuracy of 100% and a Test Accuracy of 97%. These results demonstrate the potential of using machine learning techniques in the diagnosis and prediction of Parkinson’s disease.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.8.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

Ezhilin Freeda S, Ezhil Selvan T C, Vishnu Durai R S, “Prediction of Parkinson’s disease using XGBoost”, 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), IEEE CONFERENCE, 2022.

Python IEEE Projects

Prediction of Parkinson’s disease using XGBoost