Analysis of Parkinson’s and Alzheimer’s Disease Using Various Machine Learning Based Algorithm

Alzheimer’s disease is a progressive neurological condition that gradually deteriorates memory, cognitive function, and the ability to perform basic tasks. It leads to brain shrinkage (atrophy) and the loss of brain cells over time. Parkinson’s disease is the second most prevalent neurodegenerative disorder, with its incidence projected to double over the next three decades. Precise diagnosis of Alzheimer’s Parkinson’s disease remains difficult, and symptoms persist in the early stages of the disease. Recent developments over the past 5 years have led to an increase in the validation of clinical diagnostic criteria, the introduction of research criteria for prodromal Alzheimer’s and Parkinson’s disease and the discovery of genetic subtypes and the quantity of genetic variations linked to the risks of these disorders. When neurons are dead or not functioning properly, they produce less dopamine, which can cause Parkinson’s movement problems. On the other hand, the abnormal build-up of proteins in and around brain cells leads to Alzheimer. Although there is no cure for these two menacing diseases, early detection of these diseases can be very helpful. Medications exist that can temporarily alleviate symptoms. Support is also accessible to assist individuals with the condition and their families in managing daily life. Medications, surgical treatments, and other treatments can often relieve some of the symptoms. For example, prescribing drugs that increase dopamine levels in the brain. In this project, we aim to create a model using ML based algorithms to diagnose Alzheimer’s and Parkinson’s disease based on various parameters. In addition to XG Boost, the model has been compared to Decision Tree Classifiers, Random Forest, SVM and KNN.