Idiopathic Parkinson using machine learning

Parkinson disease has more than 10 million cases worldwide, making it the second most prevalent neurological disorder overall. A decline in motor and cognitive function is the main characteristic of Parkinson’s disease. No one test can be utilized to establish a diagnosis. Instead, health care providers must do a thorough clinical inquiry of the patient’s medical history. But this diagnostic strategy is completely off. According to studies, only 53% of cases with early diagnosis—defined as five years or less of symptoms—are correct. Even if it’s not much better than winging it, therapeutic success depends on early diagnosis. Although research is ongoing and medications or surgery can assist, as of right now, there is no known cure for Parkinson disease. Frequently result in notable improvements with motor symptoms. One of the deadliest illnesses is Parkinson’s disease. Therefore, detecting it earlier could assist avoid or lessen the impacts. A person’s Parkinson disease status can be determined by. A person’s Parkinson disease status can be determined by: classification regarding machine learning methods are utilized. These algorithms include decision tree, logistic regression and other "Ensemble" learning techniques, which aim to increase accuracy by merging many models. The implementation of the machine learning model can greatly enhance the Parkinson disease diagnosing process. This study shows that, in comparison to other classification algorithms, the ensemble methods The high test accuracy percentage of 95.5 percent was attained with the Random Forest classification algorithm. As this project is related to health, we made sure that we selected the correct algorithm that gave the low false positive and False Negative values by using confusion matrix.