journal · Frontiers in Stroke · 2023
Potential and limitations of computed tomography images as predictors of the outcome of ischemic stroke events: a review
See where this sits in the topic map →Summary AI-generated
- TL;DR
- This systematic review examines how well brain computed tomography (CT) scans and clinical data can predict the functional recovery of ischemic stroke patients.
- Problem
- Predicting functional outcomes for stroke patients remains an open and challenging problem.
- Method
- The paper provides a systematic review of existing approaches that predict ischemic stroke outcomes—measured by the modified Rankin scale—using clinical information and features extracted from admission CT scans.
- Results
- While studies generally agree that CT data contains useful information, incorporating this data into predictive models does not consistently yield statistically significant improvements in prediction quality.
- Contributions
- Not specified in the abstract.
- Limitations
- Not specified in the abstract.
- Takeaways
- CT scans hold valuable data for stroke prognosis, but current models face challenges in reliably translating this information into significantly better predictions.
- Applications
- Predictive modeling tools used in clinical settings to assess patient recovery following an ischemic stroke.
- Topics
- Healthcare, Clinical Decision Support, Medical Imaging, Stroke Prognosis
- For industry
- Healthcare
- Why it matters
- Provides a critical overview of the current potential and limitations of using medical imaging for stroke outcome prediction.
Abstract
The prediction of functional outcome after a stroke remains a relevant, open problem. In this article, we present a systematic review of approaches that have been proposed to predict the most likely functional outcome of ischemic stroke patients, as measured by the modified Rankin scale. Different methods use a variety of clinical information and features extracted from brain computed tomography (CT) scans, usually obtained at the time of hospital admission. Most studies have concluded that CT data contains useful information, but the use of this information by models does not always translate into statistically significant improvements in the quality of the predictions.