Method for predicting critically ill death based on attention mechanism temporal convolution network algorithm

Abstract

The invention relates to a method for predicting critically ill death based on an attention mechanism temporal convolution network algorithm, and belongs to the field of artificial intelligence and medical treatment. The method comprises the following steps: 1, acquiring and analyzing intensive care and surgery multi-source monitoring data; 2, inputting the data into temporal convolution network (TCN) and extracting characteristics; 3, calculating attention weight of each characteristic through an attention mechanism based on the characteristics extracted from the temporal convolution network;and 4, calculating death risk coefficients through a linear layer to predict the critically ill death risk. The method disclosed by the invention has the advantages that the method is used as a critically ill death prediction tool, death of critically ill patients can be predicted so that the survival probability of the critically ill patients is increased and an effective method of a medical care plan is objectively worked out.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and medical application, and relates to a method for predicting critical illness death based on an attention mechanism time series convolution network algorithm. Background technique [0002] Globally, critical perioperative adverse events are responsible for millions of deaths each year. Therefore, it is of great significance to study the life and death prediction of critically ill patients. First of all, accurate prediction of life and death of critically ill patients can improve the survival rate of critically ill patients; secondly, early life and death prediction of critically ill patients, as a useful indicator to measure medical level, can help doctors evaluate patients' conditions, and objectively formulate and revise medical treatment. Nursing plan, determine the best discharge time, reduce overtreatment of patients, thereby reducing the cost of treatment for patients; thirdly, acc...

AI Technical Summary

Problems solved by technology

Due to the high-dimensional and complex physiological data of critically ill patients, the use of traditional scoring systems to deal with life and death prediction problems cannot be effectively dealt with, and the prediction effect for different diseases is also unstable, which cannot meet the clinical requirements

Images