As part of an integrated team, Kitware will contribute data management and machine learning expertise for ML2 project
In an effort to improve medical training for military personnel, Kitware has been selected by The University of North Carolina to aid in the development of the ML2 (Medical Learning through Machine Learning) system. ML2 aims to create a powerful analytical tool that will evaluate real-world patient data to predict the skills, training and patient care guidelines that military health care workers need to provide proper treatment on the battlefield. The two-year project is funded through a $1.6 million grant awarded to the UNC Eshelman School of Pharmacy by the Department of Defense.
An integrated technical team that includes UNC, SAS, PiTech, and Kitware will use AI and machine learning tools to achieve the objectives of the ML2 project. Specifically, the team will identify relationships that link incomplete treatment or treatment that is not in line with accepted procedures with provider skill and deviations from established treatment guidelines. They will focus on four leading causes of preventable death on the battlefield: blocked airways and breathing support, bleeding, collapsed lungs and burns. Trauma care records from one military (DoD-Joint Trauma System) and two civilian databases (Carolina Data Warehouse and North Carolina Trauma Registry) will be used for this project.
“This program is exciting for us as it is the first time we are applying our long-standing expertise in machine learning to the study of electronic medical records,” said Dr. Andinet Enquobahrie, director of medical computing at Kitware. “The ML2 project requires a deep understanding of data exploration and data management tools, and our team excels in these areas. We are combining the power of our proven open source tools with our team’s capabilities to quickly explore each hypothesis. We are looking forward to collaborating with the teams at UNC, SAS and PiTech to deliver a solution to the Department of Defense that will ultimately help save lives on the battlefield.”
To learn more about Kitware’s medical computing expertise and how it can be leveraged to benefit your research, please visit kitware.com/medical-computing
This work is supported by the US Army Medical Research and Materiel Command under Contract No. WSIXWH-18-C-0371. The views, opinions and/or findings contained in this report are those of the author(s) and should not be construed as an official Department of the Army position, policy or decision unless so designated by other documentation.