A cmkmc-based human-machine collaborative intelligent medical assistant decision-making system

Abstract

The present invention relates to a CMKMC-based human-computer collaborative intelligent medical assistant decision-making system, including: a disease initial diagnosis module, which matches clinical data to the disease node attributes of the dynamic medical cognitive attribute knowledge base to determine the range of suspected clinical diseases and provide clinical inspection guidance, Obtain the results of the initial diagnosis; the precise diagnosis module, the clinical data that cannot be diagnosed in the initial diagnosis module of the disease will be clustered through the machine learning diagnosis network to carry out the quantitative risk probability analysis of suspected diseases, and obtain the results of the precise diagnosis; The accurate diagnosis results of the machine learning network cluster are verified with the first-diagnosed node information in the knowledge base of medical cognitive attributes, and the diagnosis conclusion is obtained through comprehensive evaluation; the self-evolution module analyzes and relearns the misdiagnosed cases of the system, and updates the knowledge base of medical cognitive attributes Inference paths and node attributes, and adjust the internal parameters of the machine learning diagnosis network cluster. The invention has the characteristics of high diagnostic accuracy and self-evolution.

Description

technical field [0001] The invention belongs to the field of artificial intelligence technology and smart medical technology, and specifically relates to a CMKMC-based human-machine collaborative intelligent medical assistant decision-making system, which integrates dynamic medical cognitive attribute knowledge base and machine learning diagnosis network cluster, and is based on a human-machine collaborative consultation mechanism , to assist clinical decision-making. Background technique [0002] At present, clinical medical decisions are mainly determined by medical practitioners in combination with their own experience and relevant examination reports of patients, and the results usually have a lot to do with the level of medical practitioners themselves. With the continuous improvement of modern society's requirements for the quality of medical services, the requirements for the quality and quantity of medical practitioners are also continuously improved. However, the t...

AI Technical Summary

Problems solved by technology

[0006] However, the current smart medical aided clinical decision-making system still has the following problems: ①Due to the black box characteristics of the AI ​​network, most of the current systems can only make a binary conclusion of "yes or no" of the disease, and cannot provide a specific diagnosis process

It makes it impossible for doctors to judge whether the system's auxiliary diagnosis basis is reasonable, which reduces the clinical practical value.

②The system is not closely integrated with clinical medical cognition, so it cannot automatically verify whether the diagnosis conclusion of the machine learning network is correct

③The system relies too much on the auxiliary diagnosis function of the machine learning network, and does not establish a hierarchical diagnosis mechanism for clinical diseases, which limits the scope of the system's diagnosable diseases in the actual clinical process

Images