The Life Style Patterns and the Development Trend of Chronic Diseases in Healthy and Sub-healthy Groups Were Analyzed by Using Data-mining Techniques

Far Eastern Memorial Hospital

Status

Active, not recruiting

Conditions

Chronic Disease

Chronic Kidney Disease Stage 3

Chronic Kidney Disease Stage 2

Chronic Kidney Disease Stage 4

Chronic Kidney Disease Stage 1

Chronic Kidney Disease Stage 5

Metabolic Syndrome

Study type

Observational

Funder types

Other

Identifiers

NCT05225454

110027-E

Details and patient eligibility

About

Used multi-year health examination member profile by multi-algorithms technology, to find comprehensive key hazard factors or important high-risk group components for metabolic syndrome and chronic kidney disease or more common chronic diseases.

Full description

The proportion of the population over the age of 65 in Taiwan reached 7.10% in 1993. After Taiwan became an 「aging country」, the originally slow growth of the elderly population (9.9% in 2006) started to increase, and it reached 14.05% in 2018, which was almost 2 times that in 1993. In addition, Taiwan formally became an 「aged country」as defined globally. According to the statistical data from the Ministry of the Interior and the data from the National Development Council, it is estimated that the population over the age of 65 is rapidly growing. It is expected that 6 years later (by 2026), the elderly population in Taiwan will exceed 20%. Taiwan will formally become the「super-aged country」as defined globally, with a population structure similar to that in Japan, South Korea, Singapore, and some European countries (Department of Statistics, 2018; National Development Council, 2019). In order to effectively prevent and treat chronic diseases of sub-health populations and develop health management prediction systems that have unlimited market opportunities and potentials, the author intends to extend the achievements of individual projects sponsored by the Ministry of Science and Technology in recent years. By multi-year complete health examination member profile, this project used multiple algorithms, such as Logistic regression (LR); Classification And Regression Trees (CART); Hierarchical Linear Modeling (HLM); Random forests (RF); Support-Vector Machines (SVM); eXtreme Gradient Boosting (xGBoost); Light Gradient Boosting Machine (LightGBM) and multiple analysis tools to explore the common potential health hazard variables of the sub-health population to establish a comprehensive assessment health management system that can detect chronic diseases early, the research results will be provided for reference in related fields.

Enrollment

81,108 estimated patients

Sex

All

Volunteers

No Healthy Volunteers

Inclusion criteria