Use protein and peptide data measurements from Parkinson's Disease patients to predict progression of the disease. https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/code
The goal of this competition is to predict the course of Parkinson's disease (PD) using protein abundance data. Evaluate each patient over a time series of 6 months, 12 months, and 24 months. My approach uses Linear Regression, Tree Regression, and Neural Networking to assess a Parkinson's 'updrs' numbers. These numbers, 1-4, are risk levels of a patient developing Parkinsons and the higher the number, the higher the risk. I use SMAPE (Symmetric Mean Absolute % Error) to determine the accuracy of these models as well.
The Data is split into 3 files, the Peptides, Proteins, and Clinical data.