Suche
Mein Konto
Novel AI algorithm predicts mortality risk for patients who suffer a serious injury
Scientists from the Department of Traumatology and Acute Critical Medicine at Osaka University Graduate School of Medicine have developed an AI algorithm to predict mortality risk for patients with severe injuries. Using the Japan Trauma Data Bank for 2013 to 2017, they were able to obtain records of over 70,000 patients who had suffered blunt force trauma, allowing researchers to identify critical factors that could more accurately guide treatment strategies. Accident doctors in emergency rooms have to make decisions about life and death quickly and often with very limited information. Part of the challenge is that the factors affecting the...
Novel AI algorithm predicts mortality risk for patients who suffer a serious injury
Scientists from the Department of Traumatology and Acute Critical Medicine at Osaka University Graduate School of Medicine have developed an AI algorithm to predict mortality risk for patients with severe injuries. Using the Japan Trauma Data Bank for 2013 to 2017, they were able to obtain records of over 70,000 patients who had suffered blunt force trauma, allowing researchers to identify critical factors that could more accurately guide treatment strategies.
Accident doctors in emergency rooms have to make decisions about life and death quickly and often with very limited information. Part of the challenge is that the factors that predict the likelihood of adverse clinical outcomes are not fully understood, and sometimes the body's own inflammatory and blood clotting changes in response to serious injury cause more harm than good. A more rigorous and comprehensive approach to trauma care is clearly needed.
Now a team of researchers from Osaka University Graduate School of Medicine has analyzed a database of all trauma cases recorded in Japan using machine learning algorithms. This included patient information such as age and type of injury. In addition, mass spectrometry and proteomic analyzes were performed on serum from trauma patients at Osaka Hospital. This provided more specific information about blood markers that could indicate an increase or decrease in certain proteins.
Our study has important clinical implications. It can help identify the highest-risk patients who could benefit most from early intervention.”
Jotaro Tachino, lead author of the study, Graduate School of Medicine, Osaka University
The team used hierarchical cluster analysis of the data and found that 11 variables were most strongly correlated with increased mortality rates, including type and severity of injury. Additionally, they saw that patients at highest risk often had excessive inflammation or even an acute inflammatory response. They also found protein markers that signaled downregulated clotting, which was strongly associated with negative outcomes.
“The methodology we used for this project can also be extended to the development of new treatment strategies and therapeutics for other diseases for which large data sets are available,” says senior author Hiroshi Ogura. This work can significantly optimize the allocation of scarce ER healthcare resources to save more people. The team also hopes this research can help reveal ways to calm inflammatory pathways that can spiral out of control after traumatic injuries.
Source:
Reference:
Tachino, J., et al. (2022) Development of clinical phenotypes and biological profiles through proteomic analysis of trauma patients. Intensive care. doi.org/10.1186/s13054-022-04103-z.
.