Cross-platform clinical big data analysis and display system

Abstract

The invention discloses a cross-platform clinical big data analysis and display system. The system comprises a servo, an academic-edition website, a trade-edition website, an academic-edition embedded application and a trade-edition embedded application. The servo comprises a clinical medical data collection subsystem, an expert verification subsystem, an automatic acceleration subsystem, an automatic regressive diagnosis subsystem and an automatic statistics subsystem. Through the system, efficient and precise statistical analysis of clinical disease big data can be realized, medical big data can be utilized to perform longitudinal and transverse research quickly, data results can be recombined objectively, multiple models can be utilized for statistical analysis and display of the relation between different gendersand comorbidity, the relation between different age groups and comorbidity, the relation between diseases, the relation between drugs and diseases and the relation between drugs and operations, past theories can be verified, new theories can be proposed, and the system can be applied to the fields of medical treatment, insurance, medical research, pharmaceuticals, etc.

Description

technical field [0001] The invention relates to a system for analyzing and displaying big data of clinical diseases, which belongs to the technical fields of medical treatment and computer Internet. Background technique [0002] Comorbidity refers to two or more diseases that exist simultaneously or not at the same time, and the correlation between comorbidities is very important in the nosology of clinical medicine. Comorbidities show temporal relationships between co-existing diseases, and the age-emergent chronology often affects the establishment of disease classification and clinical decision-making. Complex chronic disease history is closely related to the prognosis of patients (Bmj 334, 1016-1017(2007) and Annals of family medicine 4, 417-422(2006)), especially in geriatric medicine and cancer (Jama 291, 2441-2447(2004) )aspect. As the aging population increases year by year, the research topic of comorbidities should be adapted, but there is not enough empirical me...

AI Technical Summary

Problems solved by technology

[0005] Although the above-mentioned innovative research has made academic contributions, there are still many obstacles to be solved in the experimental clinical application of the results. Here are the following reasons: 1. The database used is low in representativeness and does not record citizens General medical treatment habits; 2. The analysis methods used are cross-sectional research and self-created methods similar to generational tracking, and their evidence strength, causal derivation, and internal validity are lower than traditional generational tracking research; 3. Cross-sectional research is used It cannot calculate the complete disease cycle of the disease, mortality and other important clinical data; 4. Its automatic analysis lacks verification with high reliability, and neither internal verification in the database nor external verification outside the database is sufficient; 5. Lack of a collection of diagnostic codes that rationally count diseases; 6. Lack of excluding complications caused by drugs and surgery, etc.

[0006] In the past, some scholars in Taiwan used the data provided by the National Health Insurance Administration Ministry of Health and Welfare (National Health Insurance Administration Ministry of Health and Welfare) to refer to foreign pilot studies to establish big data for automatic analysis (cross-sectional), but cross-sectional (cross sectional) study) and a time-sensitive longitudinal study (longitudinal study), the difference in efficiency can reach dozens of times, and there are also obstacles in computational efficiency

Images