Predicting ischemic stroke risk from atrial fibrillation based on multi-spectral fundus images using deep learning

Abstract

BackgroundIschemic stroke (IS) is one of the most common serious secondary diseases of atrial fibrillation (AF) within 1 year after its occurrence, both of which have manifestations of ischemia and hypoxia of the small vessels in the early phase of the condition. The fundus is a collection of capillaries, while the retina responds differently to light of different wavelengths. Predicting the risk of IS occurring secondary to AF, based on subtle differences in fundus images of different wavelengths, is yet to be explored. This study was conducted to predict the risk of IS occurring secondary to AF based on multi-spectrum fundus images using deep learning.MethodsA total of 150 AF participants without suffering from IS within 1 year after discharge and 100 IS participants with persistent arrhythmia symptoms or a history of AF diagnosis in the last year (defined as patients who would develop IS within 1 year after AF, based on fundus pathological manifestations generally prior to symptoms of the brain) were recruited. Fundus images at 548, 605, and 810 nm wavelengths were collected. Three classical deep neural network (DNN) models (Inception V3, ResNet50, SE50) were trained. Sociodemographic and selected routine clinical data were obtained.ResultsThe accuracy of all DNNs with the single-spectral or multi-spectral combination images at the three wavelengths as input reached above 78%. The IS detection performance of DNNs with 605 nm spectral images as input was relatively more stable than with the other wavelengths. The multi-spectral combination models acquired a higher area under the curve (AUC) scores than the single-spectral models.ConclusionsThe probability of IS secondary to AF could be predicted based on multi-spectrum fundus images using deep learning, and combinations of multi-spectrum images improved the performance of DNNs. Acquiring different spectral fundus images is advantageous for the early prevention of cardiovascular and cerebrovascular diseases. The method in this study is a beneficial preliminary and initiative exploration for diseases that are difficult to predict the onset time such as IS.

Prediction of Cardiovascular Markers and Diseases Using Retinal Fundus Images and Deep Learning: A Systematic Scoping Review

“…Most studies were conducted in the general population or without the mention of specific patient groups (22 out of 24). Two studies had more specific study populations, one included people with atrial fibrillation, 19 and another included people with type 1 diabetes or type 2 diabetes. 20 We used the first authors' first affiliation as a proxy for the geographical location of the studies.…”

“…Cross-sectional studies systolic and diastolic blood pressure 20,32,34,42 left ventricular characteristics 43 brachial-ankle pulse-wave velocity 44 coronary artery calcium score [28][29][30][45][46][47] carotid intima-media thickness 33 hypertension 48,49 peripheral arterial disease 50 coronary heart disease 10,51 cerebrovascular disease 10 stroke 19,[52][53][54] diagnosis of CVD 55 Follow-up studies major adverse cardiovascular events 32 peripheral arterial disease 20 coronary heart disease 20,29 stroke 20,21,29,30 myocardial infarction 20,21,30,43 major heart failure 21,30 CVD mortality [28][29][30]33…”