An AI-powered analysis of routine blood tests reveals hidden patterns that predict recovery and survival after spinal cord injuries. This University of Waterloo breakthrough could make life-saving predictions affordable and accessible in hospitals worldwide.
More than 20 million people worldwide were affected by spinal cord injury in 2019 (the most recently reported data), with 930,000 new cases each year, according to the World Health Organisation.
Traumatic spinal cord injury often requires intensive care and is characterized by variable clinical presentations and recovery trajectories, complicating diagnosis and prognosis, especially in emergency departments and intensive care units.
The scientists utilised advanced analytics and machine learning to assess whether routine blood tests could serve as early warning signs for spinal cord injury patient outcomes.
AI breakthrough
The researchers sampled hospital data from more than 2,600 patients in the U.S. Next, they deployed machine learning to analyse millions of data points and discover hidden patterns in common blood measurements, such as electrolytes and immune cells, taken during the first three weeks after a spinal cord injury.
The scientists found that these patterns could help forecast recovery and injury severity, even without early neurological exams, which are not always reliable as they depend on a patient’s responsiveness.
The models (which do not rely on early neurological assessment) were established to be accurate in predicting mortality and the severity of injury as early as one to three days after admission to the hospital. This was compared to standard non-specific severity measures that are often performed during the first day of arrival to intensive care.
The research also found that accuracy increased over time as more blood tests became available. Although other measures, such as MRI and fluid omics-based biomarkers, can also provide objective data, they are not always readily accessible across medical settings. Routine blood tests, on the other hand, are economical, easy to obtain, and available in every hospital.
Going forwards
This foundational work can open new possibilities in clinical practice, allowing for better-informed decisions about treatment priorities and resource allocation in critical care settings for many physical injuries.
The research is featured in the journal njp Digital Medicine, titled “Modeling trajectories of routine blood tests as dynamic biomarkers for outcome in spinal cord injury.”
