Precision Health expands campus-wide data resources offered on Analytics Platform

Feature Stories

Precision Health expands campus-wide data resources offered on Analytics Platform

Precision Health at the University of Michigan has recently improved and expanded its offerings for campus researchers in genetics, pharmacogenomics, operations, AI, and a host of other precision health–related fields.

With this enhanced Analytics Platform, Precision Health has defined a clear pathway for researchers across campus to access de-identified clinical data: a milestone in its goal of accelerating research and collaboration in a secure environment. The Analytics Platform makes it easier for faculty across departments to collaborate on data-driven analyses for patient risk stratification, disease prevention, treatment, and more. A new Sharepoint documentation site (umich password required to access) guides researchers through the features, resources, and tools available to them.

Increased data privacy and security measures are required to support this increased access. All users—new and current—of Precision Health DataDirect are required to complete robust human subjects research training and appropriate data use agreements. To get started, please refer to the Analytics Platform User Guide [pdf] (umich password required) on the documentation site.

Following is a table listing new data and compute resources available through the Precision Health Analytics Platform, and how to get more information about them.

Resource Resource type Description More information
(umich password required)
De-identified electronic health record data through Precision Health DataDirect data
  • De-identified clinical data for ~4M Michigan Medicine patients
  • Complete through April 30, 2020, and updated quarterly
  • Laboratory results, ordered and administered medications, vital sign measurements, diagnoses and other structured elements collected during inpatient and outpatient visits
Analytics Platform User Guide
COVID starting population
(predefined and validated cohort)
data
  • Patients who have tested positive for SARS-CoV-2 at Michigan Medicine or who at any point carried a diagnosis of COVID-19
  • Complete through April 30, 2020, and updated quarterly
COVID-19 Data via DataDirect
Chest X-ray data data
  • More than 6,500 de-identified chest images performed on more than 2,100 patients who were tested for COVID-19 during hospitalizations
Accessing the COVID-19 chest X-ray Dataset on Turbo
High-performance compute platform infrastructure
  • Six compute nodes on Armis2, a high-performance computing environment administered by Advanced Research Computing Technology Services (ARC-TS) and dedicated to Precision Health
  • Each node contains eight RTX 2080 TI GPUs for researcher usage
Accessing Analytics Environments
Star allele calls service
  • Pharmacogenomics information for Michigan Genomics Initiative participants
  • Provides in-silico calls for star alleles and activity phenotypes
  • Translation of genetic data into star alleles allows research into genetic predictors of medication treatment outcomes
Michigan Genomics Initiative: Accessing Star Allele Calls

For information not covered above, please contact Precision Health’s Research Scientific Facilitators at PHDataHelp@umich.edu.

What’s in the pipeline

Precision Health’s Analytics Platform continues to evolve. These resources are coming soon:

  • Additional starting populations centered on heart failure, surgery, and other areas
  • Socioeconomic data
  • Patient-Reported Outcomes data: this will be the first-ever research survey data available in DataDirect. The data leverage NIH PROMIS (Patient-Reported Outcomes Measurement Information System) measures and include domains of pain severity, physical function, depression, and anxiety, as well as life stress scales
  • De-identified SQL server instance of the Precision Health DataDirect database that supports large-scale queries

Precision Health encourages collaboration between investigators from different schools and colleges to maximize available resources. Visit the Precision Health Member Database to search for potential collaborators or to become a member.

“We hope these resources will accelerate interdisciplinary collaborations across campus and lead to new findings that ultimately improve patient care,” says Precision Health Co-Director Jenna Wiens. “The Data Analytics &IT workgroup has spent many months working with units across campus to build a system that improves access to data, while promoting the responsible use of data. It’s exciting to see it realized!”