Analysis of Stroke Detection during the COVID-19 Pandemic Using Natural Language Processing of Radiology Reports

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.