| Summary: | 博士 === 國立交通大學 === 資訊管理研究所 === 106 === The World Health Organization identified depressive disorder as one of the three major diseases in the 21st century and it is one of the most common diseases encountered by psychiatry. Studies have shown that patients with depression are more likely than non-depression to have dementia in the future. There is an association between depression and dementia. Patients with depression may have dementia in the future and easier to face the disability caused by dementia. However, some studies have indicated that, compared to other people, patients with depressive disorder have a higher risk of suffering from dementia. From the above reasoning to infer the depressive disorder and dementia may exist a correlation. However, although there are many related studies that point out that depressive disorder is one of the important factor of dementia, many researchers are also anxious to explore the answer of "Will history of depressive disorder increase the risk of dementia in the future?", however, these findings are not consistent. In addition, there has been no study of evidence-based construction of dementia prediction model of depressive disorder patients for clinical practice. Therefore, this study will use machine-learning techniques to construct a follow-up dementia prediction model for depressive disorder patients to assist depressive disorder patients and their medical staffs to predict his/her possible risk of suffering from dementia, and then develop early intervention and prevention measures. The data source of this study is NHIRD LHID 2000. In NHIRD LHID 2000, it random select 1 million people who is insured in 2000, and collected all of their medical data. Moreover, these 1 million people is the population of this study. The study select samples from the NHIRD LHID 2000 database, whose order is diagnosis by psychiatrists in 2000 to 2004, and excluded those diagnosed depressive disorder in 1996 to 1999, in order to ensure research samples in this study are new depression cases. Then, to retrieve the demographic data and diagnostic related data from the database for follow-up analysis. Next, we used machine-learning techniques to analyze the prediction result of follow-up risk of dementia in patients with depression. In addition, this study also compared the follow-up dementia prediction results for depressive disorder patients from the viewpoint of disease severity and age differences. In addition, this study also added temporal considerations to identify the predictors of comorbidity. Based on the above results and findings to develop a depressive disorder patients’ dementia prediction clinical decision support system to assist physicians and patients in clinical decision-making.
|
|---|
