Knowledge graph-based cross-department early-diagnosis and decision support system for chronic kidney diseases

Abstract

The invention discloses a knowledge graph-based cross-department early-diagnosis and decision support system for chronic kidney diseases. The system comprises a patient information model establishmentmodule, a patient information model library storage module, a knowledge graph association module, a knowledge graph reasoning module and a decision support feedback module. According to the invention, a patient information model is constructed, and an OMOP CDM standard term system is utilized to construct electronic medical record data of patients into the patient information model with unified concept codes and unified semantic structures; the advantages of a semantic technology in data interaction and expansion are given to play, so the system has better adaptability and expandability to heterogeneous data of different hospitals; and meanwhile, clinical suggestions obtained through knowledge reasoning based on the knowledge graph are originated from clinical guidelines and doctor experience conforming to evidence-based medicine, and reasoning process and suggestion reasons can be traced and acquired by constructing reasoning instances, so the reasoning process and the suggestion reason can be given while clinical suggestions are given, and the credibility of doctors to decision support suggestions is improved.

Description

technical field [0001] The present invention relates to a knowledge map technology and a decision support technology for early diagnosis of chronic diseases, in particular to a cross-department chronic kidney disease early diagnosis decision support system based on a knowledge map. Background technique [0002] Chronic kidney disease (CKD) is a major chronic disease that seriously endangers human health and can significantly increase the morbidity and mortality of cardiovascular diseases. Epidemiological surveys in my country show that the prevalence of CKD has reached 10.8%. Based on this, it is estimated that there are more than 100 million CKD patients in my country. However, the survey shows that the awareness and awareness rate of kidney disease manifestations in primary hospitals and non-nephrologists in my country is low: the awareness rate of chronic kidney disease in the general population is only 12.5%, and the treatment rate is as low as 7.5%. International studi...

AI Technical Summary

Problems solved by technology

[0004] The existing decision support technology for early diagnosis of chronic kidney disease has the following problems: (1) The current expert system based on electronic medical records is often deeply integrated with the hospital electronic medical record system, using a specific data structure and medical terminology system, which leads to its expansion and transplantation Poor compatibility, often cannot be applied to many different hospitals; at the same time, the established diagnostic rules are difficult to expand, and cannot be updated in time with changes in clinical guidelines for chronic kidney disease

(2) Auxiliary support based on machine learning needs to input a large number of patient clinical examination and diagnosis data as model training features, and patient electronic medical record data often lack sufficient examination results, resulting in poor applicability of machine learning models; in addition, machine learning models cannot Given a clear reason for the diagnosis, only the risk level can be provided, resulting in insufficient trust of clinicians in the system

Images