## Routine Blood Tests Show Promise in Predicting Spinal Cord Injury Severity
Routine blood samples, readily available in hospitals and tracked over time, could significantly improve the prediction of spinal cord injury severity and even offer insights into patient mortality, according to a new University of Waterloo study.
Researchers utilized advanced analytics and machine learning – a form of artificial intelligence – to determine if standard blood tests could act as early indicators of outcomes for spinal cord injury patients.
With over 20 million people worldwide living with spinal cord injury and approximately 930,000 new cases occurring annually (according to the World Health Organization), accurate and timely diagnosis and prognosis are crucial, particularly in busy emergency departments and intensive care units.
“Routine blood tests offer doctors an affordable and accessible way to gain crucial details for predicting the risk of death, the presence of an injury, and its potential severity,” explained dr. Abel Torres Espín, a professor at Waterloo’s School of Public Health Sciences.
The study analyzed data from over 2,600 patients in the U.S., leveraging machine learning to identify patterns within common blood measurements – like electrolyte levels and immune cell counts – taken during the first three weeks post-injury. These patterns proved capable of forecasting recovery and injury severity, even *without* relying on early neurological exams, which can be unreliable due to patient responsiveness.
“The power isn’t in a single measurement, but in tracking how multiple biomarkers change over time,” noted Dr. Marzieh Mussavi Rizi, a postdoctoral scholar in Dr. Torres Espín’s lab.
The resulting models accurately predicted mortality and injury severity within one to three days of hospital admission, outperforming standard initial assessments. importantly, predictive accuracy increased as more blood test data became available.
While advanced techniques like MRI and fluid omics offer detailed data, they aren’t always readily accessible. Routine blood tests, though, are economical, easily obtained, and universally available in hospital settings.
“Predicting injury severity early on is vital for clinical decision-making, but challenging with neurological assessments alone,” Dr. Torres Espín stated. “Our research demonstrates the potential of routine blood data to predict whether an injury is complete or incomplete, with accuracy improving over time.”
This research lays the groundwork for improved clinical practice, enabling more informed decisions regarding treatment priorities and resource allocation in critical care for a wide range of physical injuries.
The study, “Modeling trajectories of routine blood tests as dynamic biomarkers for outcome in spinal cord injury,” was published in NPJ Digital medicine.
