Hypertension risk prediction method and device

Abstract

The invention discloses a hypertension risk prediction method and device. The method comprises the following steps: obtaining to-be-detected data, wherein the to-be-detected data comprises a blood oxygen signal image, a power spectrum characteristic image and clinical characteristics of an OSA patient; and inputting the to-be-detected data into a pre-trained hypertension risk prediction model, wherein the output result of the hypertension risk prediction model is the hypertension probability of the OSA patient. More hypertension associated information is provided for the hypertension risk prediction model through the blood oxygen signal image and the power spectrum characteristic image, so that the hypertension prediction accuracy is improved. On the other hand, the related characteristicsof the blood oxygen signal are automatically extracted from the blood oxygen signal image and the power spectrum characteristic image through the hypertension risk prediction model, and the hypertension prediction result can be obtained without manual extraction and characteristic processing, so that the manual error is greatly reduced, and the hypertension prediction precision and efficiency ofOSA patients are further improved.

Description

technical field [0001] The invention relates to a method for predicting the risk of hypertension and a corresponding device for predicting the risk of hypertension, belonging to the technical field of artificial intelligence-assisted diagnosis. Background technique [0002] Obstructive sleep apnea (OSA for short) is a sleep-breathing disease with sleep snoring accompanied by apnea and daytime sleepiness as the main clinical manifestations, with a prevalence rate of 4%. The disease can cause intermittent hypoxia, hypercapnia, and sleep disorder, and can lead to hypertension, coronary heart disease, arrhythmia, cerebrovascular disease, cognitive dysfunction, type 2 diabetes and other multi-organ multi-system damage. [0003] Hypertension is the leading cause of cardiovascular disease with a prevalence of 20%. However, due to its chronic onset characteristics, more than 50% of hypertensive people worldwide do not realize that they have hypertension. Due to frequent drops in b...

AI Technical Summary

Problems solved by technology

Usually, people are not aware enough of their own health conditions, and cannot immediately detect the disease at the early stage of the disease, and often treat it when the disease develops to a more serious condition, so it is easy to miss the best time for intervention and treatment

Images