Patient state prediction apparatus, patient state prediction method, and prediction program

Abstract

A prediction method of the present invention is able to generate fused feature quantities that can reflect the characteristics of a variety of data to predict the patient's state with high accuracy, even if inputting a different number of types of biological information and medical information from the learning data to a prediction model generated using learning data using a variety of biological information and medical information. The method includes an analysis step of extracting feature quantities by analyzing biometric information of a patient and medical care information of the patient other than the biometric information, a fusing step of generating a fused feature quantity by fusing the biometric information feature quantity and the medical care information feature quantity, a learning step of learning a relationship between the biometric information feature quantity and the medical care information feature quantity, a feature quantity mutation learning step of predicting the fused feature quantity by the feature quantity relationship learning from the input of only the biometric information, and a prediction step of predicting a patient state by using the predicted fused feature quantity obtained by the feature quantity mutation learning.

Description

technical field [0001] The present invention relates to a technique for predicting changes and abnormalities in a patient's condition. Background technique [0002] In the ICU (Intensive Care Unit), vital data (biological information) related to the patient's breathing, circulation, central nervous system, immunity, kidney function, blood, etc. are monitored and patients are triaged, but the number of patients is increasing , There is a shortage of doctors and nurses specializing in the ICU, and reducing the load on the scene is an urgent problem. [0003] In order to solve this problem, in recent years, the research and development of using the patient's biological information and diagnosis and treatment information to predict the sign of the patient's condition change and aggravation, and to apply it to the doctor's diagnosis support is being carried out. Patent Document 1 discloses a prediction technique using machine learning. Specifically, a technique is described in ...

AI Technical Summary

Problems solved by technology

[0002] In the ICU (Intensive Care Unit), vital data (biological information) related to the patient's breathing, circulation, central nervous system, immunity, kidney function, blood, etc. are monitored and patients are triaged, but the number of patients is increasing , Insufficient manpower of doctors and nurses specializing in ICU, reducing the load on the site is an urgent problem

Images