Routine blood tests tracked over time may help predict injury severity and survival chances after spinal cord damage, according to a University of Waterloo study.
The research team used advanced analytics and machine learning – a form of artificial intelligence that can detect patterns in large datasets – to assess whether daily hospital blood samples could provide early warning signs for spinal cord injury outcomes.
More than 20m people worldwide were affected by spinal cord injury in 2019, with 930,000 new cases each year, according to the World Health Organization.
Traumatic spinal cord injury often requires intensive care and presents with variable symptoms and recovery, making diagnosis and prognosis difficult in emergency and intensive care settings.
Dr Abel Torres Espín is professor in Waterloo’s school of public health sciences.
The researcher said: “Routine blood tests could offer doctors important and affordable information to help predict risk of death, the presence of an injury and how severe it might be.”
The researchers analysed hospital data from more than 2,600 patients in the US, assessing millions of data points from routine blood measurements such as electrolytes and immune cells taken during the first three weeks after injury.
They found that these patterns could forecast recovery and injury severity even without early neurological exams, which are not always reliable as they depend on patient responsiveness.
Dr Marzieh Mussavi Rizi is a postdoctoral scholar in Torres Espín’s laboratory at Waterloo.
Rizi said: “While a single biomarker measured at a single time point can have predictive power, the broader story lies in multiple biomarkers and the changes they show over time.”
The models, which do not rely on early neurological assessment, predicted mortality and injury severity as early as one to three days after hospital admission, compared with standard non-specific severity measures typically performed on arrival at intensive care.
Accuracy improved as more test results became available.
While MRI scans and fluid omics-based biomarkers – molecular signatures in body fluids – can also provide objective data, they are not always accessible across all medical settings. Routine blood tests, however, are cheap, easy to obtain and available in every hospital.
Torres Espín said: “Prediction of injury severity in the first days is clinically relevant for decision-making, yet it is a challenging task through neurological assessment alone.
“We show the potential to predict whether an injury is motor complete or incomplete with routine blood data early after injury, and an increase in prediction performance as time progresses.
“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.”
