This document summarizes research on using machine learning to predict chronic disease risk. It discusses how healthcare generates massive amounts of data that can be used for prediction. The paper proposes a new convolutional neural network (CNN) based model that uses both structured and unstructured data from hospitals to predict disease risk. It compares this multimodal approach to existing unimodal prediction models. The document also reviews several other studies applying machine learning to tasks like heart disease prediction using large healthcare datasets. The goal is to develop effective machine learning models for predicting disease outbreaks in communities using real hospital data.