dc.description.abstract | In recent years, big data research has gradually become a prominent study. Using data mining, we can find the correlation between different factors, and use data to support the guess. In the medical field, we can observe the relationship between disease and possible factors. Based on these results, it can provide us with strategies to improve medical care and enhance the progress in the field of biomedicine in the future.
Our laboratory cooperates with Landseed Hospital to obtain their outpatient data over the years. The information includes the patient′s age, gender, education level and place of residence. With these large amounts of outpatient data, we can use machine learning methods for patient group and filter useful rules.
We focus on the prevalence of Taoyuan in different places of residence. We divided the Taoyuan area into coastal and inland areas according to the administrative area classification, and used decision trees to discuss the differences in the prevalence of residents in the two areas. Judging the significance of the study method, and finally screening out the demographic groups with significant differences in disease in the two regions.
The main reasons for the difference in the prevalence between coastal and inland areas around the world are environmental pollution, eating habits, urban-rural gaps, natural disasters, personal habits, etc. We compared the results of the Taoyuan area with the results of other parts of the world, and cross-examined the reasons for the difference in the prevalence of coastal and inland areas in the Taoyuan area.
Give the results to the regional hospitals for reference, so that the regional hospitals can provide corresponding medical care and programs for these special demographic groups in the future. | en_US |