A Hybrid Data Mining Approach for Generalizing Characteristics of Emergency Department Visits Causing Overcrowding

Hospital emergency department (ED) crowding has led to an increase in patient waiting times; solving this problem requires a better understanding of the patient behavior. In this work, we adopt decision tree analysis which facilitate the interpretation and understanding of ED visits at Mackay Memorial Hospital, a representative ED in our country. Accordingly, a hybrid data mining approach is proposed to predict patients' length of stay (LOS) and explain their associated characteristics under various LOSs, especially for frequent and non-urgent groups with shorter stays in the ED. With two datasets from the first half-years of 2009 and 2010 containing 40,849 and 43,708 records respectively, we verify the stability and robustness of the proposed approach. We confirm the qualified rules based on patient characteristics and treatment information extracted by the decision tree induction method for the patient population that primarily causes ED overcrowding-patients with non-urgent conditions and short ED stays-in terms of accuracy, medical clinical value and relatedness. We identify that patients with short LOSs demonstrated similar characteristics in visiting ED. We also identify that attributes such as treatment frequencies of laboratory testing, age, and mode of arrival are good indicators for predicting patients' LOSs. The results clarify ED crowding in Taiwan and can guide investigations of ED overcrowding from the perspective of generalizing characteristics of visits. The results serve as a reference model for related ED research in a similar context for clinical decision support.

關鍵字

Clinical Decision Support ； ED Overcrowding ； Hybrid Data Mining ； Length of Stay ； Patient Characteristics

並列摘要

醫院急診室壅塞將增加病患等待時間，因此若能了解病患就診行為將可減緩急診室壅塞問題。本研究試圖以決策數歸納分析方式瞭解與解釋病患就診行為，故提出混合式資料探勘方法以預測病患的滯留時間（length of stay, LOS）與解釋不同LOS下病患的相關就診行為，其中就診頻繁的非緊急且LOS短暫的病患為本研究重要分析目標。本研究取得合作醫院「臺北馬偕紀念醫院」2009與2010年急診室病歷，分別為40,849與43,708筆資料以進行實證研究，兩組獨立的資料有助於研究驗證所提方法之穩定性與強健性。研究基於病患個人特徵與診治行為，以決策數歸納並確認非緊急且LOS短暫的病患為造成急診室壅塞之重要族群，研究並分別透過實驗正確率、臨床價值性與相關性，萃取出高參考價值的病患行為規則。研究發現LOS短暫的病患具有相似的行為；此外，研究歸納抽血（Lab）次數、年紀與入院方式為預測病患滯留時間重要指標。研究主要由病患特徵以歸納與釐清造成臺灣急診室壅塞之原因，並提供具備相似背景之急診研究進行臨床支援決策的參考模型。

並列關鍵字

臨床醫療決策；急診室壅塞；混合式資料探勘；滯留時間；病患特徵

參考文獻

Ashour, O. M., & Okudan Kremer, G. E. (2016). Dynamic patient grouping and prioritization: A new approach to emergency department flow improvement. Health Care Management Science; 19(2), 192-205. doi: 10.1007/s10729-014-9311-1.

Azari, A., Janeja, V. P., & Mohseni, A. (2012). Predicting hospital length of stay (PHLOS): A multi-tiered data mining approach. In Jilles Vreeken (Ed), IEEE 12th International Conference on Data Mining Workshops (pp.17-24). doi: 10.1109/ICDMW.2012.69

Bellazzi, R., Diomidous, M., Sarkar, I. N., Takabayashi, K., Ziegler, A., & McCray, A.T. (2011). Data analysis and data mining: Current issues in biomedical informatics. Methods of Information in Medicine, 50(6), 536–544. doi: 10.3414/ME11-06-0002

Cao, L., Zhang, C., Yang, Q., Bell, D., Vlachos, M., Taneri, B.,…Graco, W. (2007). Domain-driven actionable knowledge discovery. IEEE Intelligent Systems, 22(4),78-88. doi: 10.1109/MIS.2007.67

Cao, L. (2010). Domain-driven data mining: Challenges and prospects. IEEE Transactions on Knowledge and Data Engineering, 22(6), 755-769. doi: 10.1109/TKDE.2010.32

國際替代計量

A Hybrid Data Mining Approach for Generalizing Characteristics of Emergency Department Visits Causing Overcrowding

全文下載

主題瀏覽