Human vs. Machine Learning Based Detection of Facial Weakness Using Video Analysis

Frontiers in Neurology

Gustavo K. Rohde¹  Yan Zhuang²  Joseph F. Carrera³  Iris Lin⁴  Chad M. Aldridge⁵  Mattia Wruble⁵  Haydon Pitchford⁵  Sherita Chapman⁵  Mark M. McDonald⁵  Brett J. Schneider⁵  Omar Uribe⁵  William A. Dalrymple⁵  Bradford B. Worrall⁶  Andrew M. Southerland⁶  Timothy L. McMurry⁶ 

[1] Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, United States;Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, United States;Department of Neurology, University of Michigan, Ann Arbor, MI, United States;Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States;Department of Neurology, University of Virginia, Charlottesville, VA, United States;Department of Public Health Sciences, University of Virginia, Charlottesville, VA, United States;

关键词: cerebrovascular disease;    stroke;    infarction;    access to care;    diagnostic test;    computer vision;   

DOI  :  10.3389/fneur.2022.878282

来源: DOAJ

【 摘 要 】

BackgroundCurrent EMS stroke screening tools facilitate early detection and triage, but the tools' accuracy and reliability are limited and highly variable. An automated stroke screening tool could improve stroke outcomes by facilitating more accurate prehospital diagnosis and delivery. We hypothesize that a machine learning algorithm using video analysis can detect common signs of stroke. As a proof-of-concept study, we trained a computer algorithm to detect presence and laterality of facial weakness in publically available videos with comparable accuracy, sensitivity, and specificity to paramedics.Methods and ResultsWe curated videos of people with unilateral facial weakness (n = 93) and with a normal smile (n = 96) from publicly available web-based sources. Three board certified vascular neurologists categorized the videos according to the presence or absence of weakness and laterality. Three paramedics independently analyzed each video with a mean accuracy, sensitivity and specificity of 92.6% [95% CI 90.1–94.7%], 87.8% [95% CI 83.9–91.7%] and 99.3% [95% CI 98.2–100%]. Using a 5-fold cross validation scheme, we trained a computer vision algorithm to analyze the same videos producing an accuracy, sensitivity and specificity of 88.9% [95% CI 83.5–93%], 90.3% [95% CI 82.4–95.5%] and 87.5 [95% CI 79.2–93.4%].ConclusionsThese preliminary results suggest that a machine learning algorithm using computer vision analysis can detect unilateral facial weakness in pre-recorded videos with an accuracy and sensitivity comparable to trained paramedics. Further research is warranted to pursue the concept of augmented facial weakness detection and external validation of this algorithm in independent data sets and prospective patient encounters.

【 授权许可】

Unknown