| abstract |
The invention relates to the field of medical science and technology, and provides a hypertension risk prediction method, a device, equipment and a medium, wherein the method comprises the steps of obtaining personal information and an eyeground image of a target to be detected; respectively inputting the fundus image into a preset arteriovenous segmentation model, a optic disc segmentation model and a lesion identification model, and respectively extracting arteriovenous vessels, optic disc regions and fundus lesion characteristics in the fundus image; quantizing the calibers of arteriovenous vessels in the video area to obtain vessel diameter quantized values corresponding to the arteriovenous vessels; constructing a risk prediction model for predicting the hypertension of the target to be detected based on the blood vessel diameter quantized value, the fundus lesion characteristics and the personal information by using a machine learning regression method; and inputting the fundus image corresponding to the target to be detected into the risk prediction model for detection to obtain a hypertension prediction result of the target to be detected. Because the risk prediction model is trained by adopting a plurality of variable factors, the accuracy of the hypertension risk prediction is greatly improved. |