Interpretable disease risk analysis system based on pathological mode and attention mechanism

Abstract

The invention discloses a disease risk analysis system based on a pathological mode and an attention mechanism, wherein the system comprises an information collection device and a server; the information collection device is in communication connection with the server; the information collection device transmits the acquired demographic characteristic data information of a plurality of patients and the acquired electronic medical record data information of a target disease to the server; a portrait construction module, a graph embedding algorithm module, a medical record information extractionmodule, a training set construction module, a decision tree integration model module, a vectorization module, an attention mechanism module, a representation vector calculation module, a splicing module and a logistic regression analysis module are arranged in the server, and the server obtains a result required by health early warning based on the modules. According to the invention, big data service support is provided for health early warning, and the system has the advantage of accurate analysis result.

Description

technical field [0001] The invention relates to the field of smart medical care, in particular to a disease risk analysis information system based on pathological pattern mining and attention mechanism. Background technique [0002] In recent years, with the accumulation of big data in electronic medical records and the development of artificial intelligence technology, data-driven disease risk prediction methods have emerged as the times require, that is, by analyzing and mining big data in electronic medical records, a disease risk prediction model is established to realize the potential prediction of diseases. Early prediction of risks and trends. Disease risk prediction can give early warning of the future risk of certain diseases to assist doctors to formulate more effective treatment plans to prevent and control diseases. [0003] According to the trend of technology development, data-driven disease risk prediction methods can be roughly divided into two categories: s...

AI Technical Summary

Problems solved by technology

The advantage of shallow learning methods (such as logistic regression and decision tree models) is that they have better interpretability, but the disadvantage is that the performance of the model is too dependent on domain knowledge (that is, manually defined features), and the generalization ability is not strong; The advantage of the deep learning method is that it can automatically learn complex and hidden features with high accuracy, but the disadvantage is that the model is a black box system and lacks interpretability

If a model is difficult to interpret, its practical value is greatly limited

Images