結合臺灣健保資料庫與生物醫學文獻偵測藥物不良反應

Detecting Drug Safety Signals by Combining National Taiwan Health Insurance Research Database and Biomedical Literature

劉睿蕓(Jui-Yun Liu)

指導教授 ： 魏志平

國立臺灣大學/管理學院/資訊管理學研究所/碩士(2016年)

https://doi.org/10.6342/NTU201603198

摘要

因受限於受試者人數與觀察期長度，在藥物上市前的臨床實驗中很難發現所有的藥物不良反應。因此，藥物主動監視（Pharmacovigilance）的目標在於提早偵測出藥物安全信號，並最大限度地減少對病人的傷害。一個信號（signal）指的是一個潛在的藥物不良反應，而這個藥物與不良反應（疾病）之間的關係是以前不曾被得知的或未正式被記錄下來的。藥物不良反應自發報告系統（Spontaneous Reporting System）和電子健康記錄（Electronic Health Record）是用於偵測藥物安全信號的兩個主要資料來源。由於SRS資料存在一些限制，有研究轉向使用電子健康紀錄進行藥物上市後監控。近年來，開始有人使用多個資料來源偵測藥物不良反應，如生物醫學文獻也可以用來輔助藥物上市後監控。
在本研究中，我們提出一個改良方法，藉由結合臺灣健保資料庫與MEDLINE資料庫，並利用排序學習法排序可疑的藥物安全信號，找出可能的藥物不良反應。除了傳統基於失衡分析法的變數外，我們也納入了基於主題模型考量藥物和疾病之間隱性關係的變數以及基於ABC模型的文獻變數。我們亦建立了三個額外的實驗情境以評估本研究所提出的方法效能。主要結果顯示，本研究所提出的使用多個變數和多種資料來源的方法能夠有效提升偵測藥物不良反應的準確度。

關鍵字

藥物主動監視 ； 資料探勘 ； 臺灣健保資料庫 ； 生物醫學文獻

並列摘要

It is difficult to identify all the adverse drug reactions (ADRs) during premarketing clinical trials. As the result, the aims of Pharmacovigilance (PhV) are detecting signals early and minimizing harm to patients. A signal means a potential adverse drug event which is previously unknown or incompletely recorded. Spontaneous reporting system (SRS) and electronic health record (EHR) are two major data sources used for drug safety signal detection. Due to inherent limitations of using SRSs for signal detection, some research has focused on the use of EHR databases for PhV. In recent years, some researchers start to use multiple data sources to detect adverse drug events. For example, biomedical literature has been used to assist the detection of potentials ADRs.
In this study, we propose an improved method incorporating both Taiwan’s national health insurance research database and MEDLINE database to rank and detect signals on the basis of a learning to rank approach. In addition to multiple traditional disproportional analysis measures and LDA-based measures considering the implicit relations between drugs and diseases, literature-based measures under the idea of ABC model are also added. We also design three additional experiments to evaluate our proposed method for drug safety signal detection. The major results show that our proposed method using multiple measures and multiple sources has better effectiveness for signal detection than using single measure and single source, except for one disease.

並列關鍵字

Pharmacovigilance ； Data mining ； NHIRD ； Biomedical literature

參考文獻

Almenoff, J. S., Pattishall, E. N., Gibbs, T. G., DuMouchel, W., Evans, S. J., Yuen, N. (2007). Novel statistical tools for monitoring the safety of marketed drugs. Clinical Pharmacology and Therapeutics, 82(2), 157-166.

Avillach, P., Dufour, J. C., Diallo, G., Salvo, F., Joubert, M., Thiessard, F., Mougin, F., Fourrier-Reglat, A., Pariente, A., Fieschi, M. (2013). Design and validation of an automated method to detect known adverse drug reactions in MEDLINE: A contribution from the EU-ADR project. Journal of the American Medical Informatics Association, 20(3), 446-452.

Bate, A., Evans, S. J. (2009). Quantitative signal detection using spontaneous ADR reporting. Pharmacoepidemiology and Drug Safety, 18(6), 427-436.

Chen, K.-A. (2013). Mining biomedical literature and ontologies for drug repositioning discovery. Unpublished Master Thesis, Department of Information Management, National Taiwan University, Taiwan, R.O.C.

Choi, N. K., Chang, Y., Kim, J. Y., Choi, Y. K., Park, B. J. (2011). Comparison and validation of data-mining indices for signal detection: Using the Korean National Health Insurance claims database. Pharmacoepidemiology and Drug Safety, 20(12), 1278-1286.