Skip to content. | Skip to navigation

Personal tools


You are here: Home / Research / Selected Research / Nguyen and colleagues to use Big Data to create health outcome models

Nguyen and colleagues to use Big Data to create health outcome models

Multi-year NIH R01

Faculty Associatre Quynh C. Nguyen, assistant professor of Epidemiology and Biostatistics, has been awarded an R01 grant from the National Institutes of Health (NIH) / National Library of Medicine for her project, "Neighborhood Looking Glass: 360 Degree Automated Characterization of the Built Environment for Neighborhood Effects Research." The multi-year award will enable Dr. Nguyen to use Google Street View images and computer vision algorithms to assess the relationship between neighborhood features and health outcomes. It also enables construction of a national data repository of built environment features that the team will make publicly available.

One of the goals of the grant is to devise new ways to characterize neighborhood environments. Researchers have traditionally depended on neighborhood surveys and on-site visits to assess neighborhood environments, but those methods are costly and time-consuming and limit the number of areas that can be examined. Big data presents new opportunities for costs savings and efficiencies, and it allows for investigations of national patterns.

A team led by Dr. Nguyen will work to develop informatics techniques to produce neighborhood quality indicators. They will measure the accuracy of data algorithms and construct an interactive geoportal for neighborhood data visualization and sharing. This is an interdisciplinary team including top-notch researchers in the field of computer vision (Tolga Tasdizen), data management (Feifei Li), and clinical outcomes research (Kim Brunisholz).

The project will benefit from Dr. Nguyen’s previous research and a large collection of medical records from Intermountain Healthcare to investigate neighborhood influences on the risk of obesity and substance abuse. A potential result may be health providers and advocates  being better able to predict potential health outcomes based on neighborhood characteristics and give individuals better information on how to improve the outcomes.