PCCI data science and clinical experts, along with team leaders at Parkland Health and Hospital System, have published a new paper about the Parkland Trauma Index of Mortality* on arXiv. arVix is an open archive for scholarly articles maintained and operated by Cornell University. The paper Parkland Trauma Index of Mortality (PTIM): Real-time Predictive Model for PolyTrauma Patients explores how a machine learning algorithm that uses electronic medical record data to predict 48hour mortality during the first 72 hours of hospitalization.
This project is an outstanding collaboration between PCCI and Parkland and probably first of its kind dynamic and real-time predictive model for polytrauma patients, said Manjula Julka, MD, MBA, Vice President, Clinical Innovation at PCCI. Dr. Adam Starr, distinguished ortho trauma surgeon at Parkland, is a key leader in this project. Parklands trauma center is committed to providing state-of-the-art innovative, high quality care for best health outcomes. This paper outlines how we were able to leverage machine learning to help predict mortality for trauma patients in a way where surgery and critical care teams are able to use this, along with other clinical decision support tools, as a way to help save lives.
To view and download the paper, click on the image below:
*The Parkland Trauma Index of Mortality model is a free software and is distributed under the terms of the GNU Lesser General Public License (LGPL).