Congenital heart disease postoperative risk visual evaluation method based on patient similarity

Abstract

The invention discloses a patient similarity-based congenital heart disease postoperative risk visual evaluation method. The method comprises the following steps: constructing a congenital heart disease ontology according to multi-source heterogeneous disease knowledge; performing multi-dimensional feature extraction on the ultrasonic report text of the historical congenital heart disease patient to obtain standard ultrasonic text features; based on the standard ultrasonic text features, calculating the similarity distance of the ultrasonic text features of the congenital heart disease patient; on the basis of the similarity distance of the ultrasonic text features, fusing preoperative and intraoperative information of the congenital heart disease patients, calculating a similarity distance matrix among the congenital heart disease patients, and generating a congenital heart disease patient map; according to the map of the congenital heart disease patient, a similar patient group is recommended for the target patient through a similarity algorithm, and clinical personnel are assisted in conducting postoperative risk assessment on the target patient through the postoperative risk factors of the similar patient group. The assessment method can assist doctors in assessing the physiological and pathological conditions of the patient and enhance monitoring and management in the perioperative period.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for visually evaluating risk after congenital heart disease surgery based on patient similarity. Background technique [0002] Congenital heart disease (congenital heart disease for short) is a major birth deformity in China, and it is also a common disease that seriously endangers children's health. According to the "2020 China Cardiovascular Health and Disease Report", there are regional differences in the detection rate of congenital heart disease in my country, which is about 2.41‰-10.36‰. According to the "China Health Statistical Yearbook 2019", the mortality rate of congenital heart disease in urban residents in China in 2018 was 0.84 / 100,000, and that of rural residents was 1.02 / 100,000. The mortality rate of congenital heart disease in men is higher than that in women. Although with the development of cardiac surgery techniques and life monitoring metho...

AI Technical Summary

Problems solved by technology

Some machine learning-based prediction methods for postoperative complications of congenital heart disease have been proposed, but the lack of clear clinical interpretation in the actual application process has affected the clinical transformation of related technologies

Images