Parkinson disease prediction using machine learning

With more than 10 million cases globally, Parkinson disease is the second most common neurological disorder. Parkinson’s disease is generally distinguished by a decline in motor and cognitive function. There isn’t a single test that can be used to make a diagnosis. Instead, medical professionals must do a careful clinical investigation of the patient’s medical background. But this diagnostic approach is incredibly incorrect. According to National Institute of Neurological Disorders research, the accuracy of an early diagnosis—defined as five years or less of symptoms—is only 53%. Although this isn’t much better than winging it, prompt diagnosis is essential for successful treatment, Parkinson’s disease has no known cure, but early diagnosis and treatment can help manage symptoms and halt the illness’s development. Medication, deep brain stimulation, and physical therapy are possible forms of treatment. In recent years, research has focused on developing new technologies and methods for early detection and diagnosis of Parkinson’s disease, including the use of machine learning algorithms to analyze data from wearable devices and other sources. The hope is that by detecting the disease earlier, interventions can be implemented earlier and potentially improve outcomes for patients. To determine whether a person is affected with Parkinson disease or not, classification regarding machine learning methods is utilized. These algorithms include Random Forest, Decision trees, XGB classifier 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 approaches Random Forest classification algorithm achieved the high-test accuracy rate of 97.0%.