Related Experiment Video
Updated: Jun 8, 2026

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
Analysis of Stroke Detection during the COVID-19 Pandemic Using Natural Language Processing of Radiology Reports
1From the Departments of Radiology (M.D.L., M.L., F.D., K.C., K.B., S.R., W.A.M., J.K.-C.) mdli@mgh.harvard.edu.
Insights
The COVID-19 pandemic saw a 24% decrease in detected acute ischemic strokes via neuroimaging. However, a higher percentage of stroke-ordered imaging studies were positive, indicating a shift in stroke detection during the pandemic.
Area of Science:
- Neurology
- Radiology
- Data Science
Background:
- The COVID-19 pandemic has impacted healthcare, including neuroimaging volumes.
- Quantifying changes in acute or subacute ischemic strokes during the pandemic is crucial.
Purpose of the Study:
- To quantify the change in acute or subacute ischemic strokes detected by CT or MR imaging during the COVID-19 pandemic.
- To utilize natural language processing (NLP) of radiology reports for this quantification.
Main Methods:
- Retrospective analysis of 32,555 brain CT and MRI radiology reports from 2017-2020.
- Development and validation of a random forest NLP classifier to detect acute or subacute ischemic stroke in free-text reports.
- Evaluation of classifier performance using cross-validation and an external dataset.
Main Results:
- An estimated 24% decrease in acute or subacute ischemic strokes detected via neuroimaging from March-April 2020 compared to 2017-2019 averages.
- A significant increase in the proportion of stroke-ordered neuroimaging studies that detected acute or subacute ischemic strokes (16% to 21%, P=.01) in 2020.
- NLP classifier achieved high accuracy (0.97) and F1 score (0.74) in cross-validation but performed worse on external data.
Conclusions:
- Neuroimaging-detected acute or subacute ischemic stroke cases decreased during the COVID-19 pandemic.
- A higher proportion of stroke-ordered studies were positive, suggesting a potential change in stroke diagnosis patterns.
- NLP offers a valuable tool for tracking stroke numbers in epidemiologic studies, emphasizing the need for local classifier training.
Background And Purpose:
The coronavirus disease 2019 (COVID-19) pandemic has led to decreases in neuroimaging volume. Our aim was to quantify the change in acute or subacute ischemic strokes detected on CT or MR imaging during the pandemic using natural language processing of radiology reports.
Materials And Methods:
We retrospectively analyzed 32,555 radiology reports from brain CTs and MRIs from a comprehensive stroke center, performed from March 1 to April 30 each year from 2017 to 2020, involving 20,414 unique patients. To detect acute or subacute ischemic stroke in free-text reports, we trained a random forest natural language processing classifier using 1987 randomly sampled radiology reports with manual annotation. Natural language processing classifier generalizability was evaluated using 1974 imaging reports from an external dataset.
Results:
The natural language processing classifier achieved a 5-fold cross-validation classification accuracy of 0.97 and an F1 score of 0.74, with a slight underestimation (-5%) of actual numbers of acute or subacute ischemic strokes in cross-validation. Importantly, cross-validation performance stratified by year was similar. Applying the classifier to the complete study cohort, we found an estimated 24% decrease in patients with acute or subacute ischemic strokes reported on CT or MR imaging from March to April 2020 compared with the average from those months in 2017-2019. Among patients with stroke-related order indications, the estimated proportion who underwent neuroimaging with acute or subacute ischemic stroke detection significantly increased from 16% during 2017-2019 to 21% in 2020 (P = .01). The natural language processing classifier performed worse on external data.
Conclusions:
Acute or subacute ischemic stroke cases detected by neuroimaging decreased during the COVID-19 pandemic, though a higher proportion of studies ordered for stroke were positive for acute or subacute ischemic strokes. Natural language processing approaches can help automatically track acute or subacute ischemic stroke numbers for epidemiologic studies, though local classifier training is important due to radiologist reporting style differences.
More Related Videos
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
06:45Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
Published on: June 2, 2023
Related Concept Videos
Stroke: Introduction and Types
Ischemic Stroke l: Introduction
Hemorrhagic Stroke l: Introduction