AUTHOR=Qu Yimin , Zhuo Yuanyuan , Lee Jack , Huang Xingxian , Yang Zhuoxin , Yu Haibo , Zhang Jinwen , Yuan Weiqu , Wu Jiaman , Owens David , Zee Benny 

TITLE=Ischemic and haemorrhagic stroke risk estimation using a machine-learning-based retinal image analysis

JOURNAL=Frontiers in Neurology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.916966

DOI=10.3389/fneur.2022.916966

ISSN=1664-2295

ABSTRACT=Background: Stroke is the second leading cause of death worldwide, causing a considerable disease burden. Ischemic stroke is more frequent, but hemorrhagic stroke is responsible for more deaths. The clinical management and treatment are different, and it is advantageous to classify their risk as early as possible for disease prevention. Furthermore, retinal characteristics have been associated with stroke and can be used for stroke risk estimation. This study investigated machine learning approaches to retinal images for risk estimation and classification of ischemic stroke and hemorrhagic stroke. 

Study design: A case-control study was conducted in the Shenzhen Traditional Chinese Medicine Hospital. According to the computerised tomography scan (CT) or magnetic resonance imaging (MRI) results, stroke patients were classified into either ischemic stroke or haemorrhage stroke. In addition, a control group was formed using non-stroke patients from the hospital and healthy individuals from the community. Baseline demographic and medical information was collected from participants’ hospital medical records. Retinal images of both eyes of each participant were taken within two weeks of admission. Classification models using a machine-learning approach were developed. A ten-fold cross-validation method was used to validate the results.

Results: 711 patients were included, with 145 ischemic stroke patients, 86 hemorrhagic stroke patients, and 480 controls. Based on ten-fold cross-validation, the ischemic stroke risk estimation has a sensitivity and a specificity of 91.0% and 94.8%, respectively. The area under the ROC curve for ischemic stroke is 0.929 (95% CI 0.900 to 0.958). The hemorrhagic stroke risk estimation has a sensitivity and a specificity of 93.0% and 97.1%, respectively. The area under the ROC curve is 0.951 (95% CI 0.918 to 0.983). 

Conclusion: A fast and fully automatic method can be used for stroke subtype estimation and classification based on fundus photographs alone.