Summary: A new study shows that routine hospital blood tests could help predict the severity of spinal cord injury and survival possibilities. The researchers used automatic learning to analyze the data of thousands of patients and found that patterns in blood markers, such as electrolytes and immune cells, predicted recovery results as soon as one or three days after admission.
Unlike neurological exams, which depend on the patient’s ability to respond, this method offers objective and reliable ideas. The findings could improve emergency care and the allocation of resources for spinal cord injuries worldwide.
Key facts
Predictive value: Blood markers patterns forecast gravity and mortality of the lesion.
Source: Waterloo University
Routine blood samples, such as those taken daily in any hospital and tracked over time, could help predict the seriousness of an injury and even provide information about mortality after the damage of the spinal cord, according to a recent study by the University of Waterloo.
The research team used advanced analysis and automatic learning, a type of artificial intelligence, to assess whether routine blood tests could serve as early warning signs for the results of patients with spinal cord injuries.
According to the World Health Organization, more than 20 million people worldwide were affected by spinal cord injury in 2019, with 930,000 new cases each year. Traumatic spinal cord lesion often requires intensive care and is characterized by variable clinical presentations and recovery trajectories, which complicates diagnosis and prognosis, especially in emergency departments and intensive care units.
“Routine blood tests could offer doctors important and affordable information to help predict the risk of death, the presence of an injury and how serious it could be,” said Dr. Abel Torres Espín, professor at the Faculty of Public Health Sciences of Waterloo.
The researchers took hospital data of more than 2,600 patients in the US. Uu. They used automatic learning to analyze 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.
They discovered that these patterns could help forecast the recovery and seriousness of the lesion, even without early neurological exams, which are not always reliable since they depend on a patient’s ability to respond.
“While a single biomarker measured in a single point of time can have a predictive power, the widest story lies in multiple biomarkers and the changes they show over time,” said Dr. Marzieh Mussavi Rizi, a postdoctoral scholar in the Laboratory of Torres Espín in Waterloo.
The models, which do not depend on the early neurological evaluation, were precise to predict the mortality and severity of the injury as soon as one or three days after the entrance to the hospital, compared to the non -specific standard measures of gravity that are often carried out during the first day of arrival at intensive care.
The investigation also found that precision increased over time as more blood tests were available. Although other measures, such as magnetic resonance and biomarkers based on fluid omic, can also provide objective data, are not always easily accessible in medical environments. Routine blood tests, on the other hand, are economical, easy to obtain and are available in each hospital.
“The prediction of the seriousness of the injury in the first days is clinically relevant to decision making, but it is a challenging task through neurological evaluation only,” said Torres Espín. “We show the potential to predict whether an injury is complete or incomplete with the blood data of routine early after the lesion, and an increase in prediction performance as time progresses.
“This fundamental work can open new possibilities in clinical practice, allowing better informed decisions on treatment priorities and the allocation of resources in critical care environments for many physical injuries.”
On this research news of the spinal cord injuries and neurology
Author: Ryon Jones
Source: Waterloo University
Contact: Ryon Jones – University of Waterloo
Image: The image is accredited to Neuroscience News
Original research: open access.
“Modeling of routine blood analysis trajectories such as dynamic biomarkers for the result in spinal cord injury” by Abel Torres Espín et al. NPJ digital medicine
Abstract
Routine blood analysis trajectory modeling such as dynamic biomarkers for the result in spinal cord lesion
Routinely collected blood tests may reflect underlying pathophysiopathological processes.
We demonstrate that the dynamics of the blood analysis collected routinely has validity of prediction in the acute spinal cord lesion (SCI). Using Mimic data (N = 2615) for modeling and follow -up SCI study data (n = 137) for validation, we identify multiple trajectories for common blood markers.
We develop automatic learning models for the dynamic prediction of hospital mortality, the occurrence of LME in patients with trauma in the spine and severity of SCI (full engine versus incomplete).
The hospital mortality model achieved a ROC-AUC out of the training of 0.79 (0.77–0.81) the first day after the injury, improving at 0.89 (0.88–0.89) by day 21. To detect the presence of SCI after the trauma of the column, the highest ROC-AUC was 0.71 (0.69–0.72) Severity of the LME was 0.81 (0.77-0.85).
Our complete models overcame the SAPS II gravity score after seven days of hospitalization.
