Patient heart failure death risk prediction system based on characteristic rearrangement one-dimensional convolutional neural network

Abstract

The present invention discloses a patient heart failure death risk prediction system based on a characteristic rearrangement one-dimensional convolution neural network. The method comprises the following steps: acquiring an original data set of patients with heart failure from an electronic medical record system of a hospital; performing a characteristic engineering pretreatment on the acquired data set, wherein the characteristic engineering pretreatment comprises performing one-hot encoding mapping on the acquired original data set to obtain a disease-related information characteristic set and forming a corresponding heart failure death data set of the patients together with heart failure death labels of the patients in the original data set; performing characteristic rearrangement on the data set based on chi-square correlation analysis, arranging characteristics in a descending order from high to low according to correlation with heart failure death of the patients, and screening arearranged characteristic subset; and using the convolution neural network to conduct heart failure death prediction training of the patients. The patient heart failure death risk prediction system is beneficial to assisting diagnosis and treatment of heart failure diseases and improving clinical nursing conditions of the patients.

Description

technical field [0001] The invention relates to the field of artificial intelligence-assisted medical decision-making, in particular to a heart failure death risk prediction system for patients based on a feature-rearranged one-dimensional convolutional neural network. Background technique [0002] Heart failure is a serious heart disease with high morbidity and mortality. In recent years, heart failure symptoms have become one of the main reasons for the elderly to be hospitalized. Data show that the prevalence of heart failure in both sexes is about 2.5%, and 39.4% of them are elderly people over 60 years old. According to the results of the American Cardiovascular Disease Report, from 2012 to 2030, the prevalence of heart failure in the elderly is expected to increase by 46%, which will lead to an increase of about 8 million heart failure patients. In China, heart failure is also one of the common causes of hospitalization in cardiovascular diseases. Since the 1970s, the...

AI Technical Summary

Problems solved by technology

However, there are still some deficiencies in previous research: previous research often ignores the correlation between the characteristics of heart failure, and thus does not give enough structural information to machine learning modeling techniques. ;There is often an imbalance in heart failure disease data, which is due to the small number of cases of severe disease patients, which is the biggest obstacle to the prediction of heart failure death risk

Images