GRYMTR: a traumatic brain injury decision support tool
Annually, 10 million deaths or hospitalizations are traumatic brain injury related, with a majority of cases in low- and middle-income countries. Many traumatic brain injury patients require surgery to prevent permanent disability or death. Unfortunately, the global neurosurgery capacity cannot meet the demand. Providers in these countries are forced to ration limited resources often without the support of diagnostic technologies. Thus, better understanding of traumatic brain injury in-hospital outcomes in a low-resource setting is needed to support prudent use of limited, life-saving resources.
Cyrus Elahi and colleagues have developed a machine learning-based decision support tool that could optimize care for traumatic brain injury patients. GRYMTR produces a patient risk for bad outcome. The tool helps providers predict survival for their patients based on potential treatment options using the vital signs and physical exam findings. The tool is supported by a machine learning based predictive model. The model is built from thousands of previous traumatic brain injury patient encounters in low resource settings.
This tool could support monitoring and evaluation by insurance companies and encourage a more prudent use of hospital resources
- This tool empowers lower- skilled providers and support physicians making life or death decisions
- Produces a patient risk for bad outcome using vital signs and physical exam findings
- The model equals or outperforms previous traumatic brain injury predictive models