Summary: | 碩士 === 國立成功大學 === 醫學資訊研究所 === 102 === There are diseases with unknown risk patterns. Some of them may not cause obvious symptoms at the initiation stage such that they are hard to detect or predict. To achieve effective early treatment and prevention, we need to understand better the risk patterns and factors of diseases. Traditional methods for finding disease risk patterns primarily examine the clinical observations with statistical approaches one by one. However, there tend to be limited clinical observations which are manually validated through clinical experiences.
In this work, we proposed a novel framework for disease risk pattern mining and assessment by adopting data mining techniques. To evaluate the proposed framework, we utilize the National Health Insurance Research Database of Taiwan and take the Chronic Kidney Disease as an application target disease. Consequently, we found a number of risk patterns for CKD in form of association rules. Through evaluation by medical experts, some of the discoveries are found to be potentially new findings on CKD that may bring new insight for further medical studies.
|