Major
Health Informatics
Research Abstract
Many diseases such as diabetes and cardiovascular diseases are actionable, i.e. they are preventable by early intervention. One to two years of early warning would represent a huge advance in dealing with these conditions and could help prevent further complications such as heart disease, stroke, kidney failure, blindness, and amputation. In this project, we are developing an extensible condition forecasting model to assess the risk of diabetes and heart problems in patients in advance. Using TensorFlow, Elastic MapReduce (EMR), and AWS Sagemaker, we are training a Wide and Deep Neural Network on a dataset of more than 170 million electronic health records (EHR). By identifying patients at higher risk of disease, we also help Healthgrades build better and more efficient targeted campaigns.
Faculty Mentor/Advisor
Professor Patricia A. Francis-Lyon
Course
Bio-Informatics
Forecasting Model for Disease Propensity Using EHR Data
Many diseases such as diabetes and cardiovascular diseases are actionable, i.e. they are preventable by early intervention. One to two years of early warning would represent a huge advance in dealing with these conditions and could help prevent further complications such as heart disease, stroke, kidney failure, blindness, and amputation. In this project, we are developing an extensible condition forecasting model to assess the risk of diabetes and heart problems in patients in advance. Using TensorFlow, Elastic MapReduce (EMR), and AWS Sagemaker, we are training a Wide and Deep Neural Network on a dataset of more than 170 million electronic health records (EHR). By identifying patients at higher risk of disease, we also help Healthgrades build better and more efficient targeted campaigns.
