Skip to content

Research Pipelines Informatics Laboratory

 

The Research Pipelines Laboratory provide online interfaces for distributed computing and storage systems. The compute cluster uses the Hortonworks platform and is compatible with R, Python, Java, Scala, and Spark. Additionally, it can be used to interface with the Hive distributed data warehouse, or UTHSC PostgreSQL, MySQL or Oracle databases. The  Apache c-takes server can process free text and extract clinical concepts.  Her lab can manage projects from data extraction and transformation to modeling and visualization for small-scale and big data projects. 

Current Research

  • Data-Driven Identification of Costly Multi-Morbidity Groupings and Their Progression (funded by NIH R15 AG067232-01 grant)
  • Machine Learning lung cancer prediction and Social Determinants of Health (SDoH)
  • Machine learning opioid addiction and SDoH

Contact

If you would like more information, please contact Charisse Madlock-Brown, PhD

 

Last Published: Mar 15, 2021