檢傷分類制度的執行有助於急診部門進行病患分流,使病況眞正危急的患者獲得即時的治療。而檢傷護理人員與醫師診療的檢傷分類決策是否一致,則關係到醫院的醫療品質、病患滿意度與生命安全。因此在急診人次持續攀升的今天,如何有效的提升檢傷分類的一致性與穩健性,是本研究所關切的重要議題。本研究與台灣某醫學中心急診醫學部進行合作,從流程建構、參數選取到抽取樣本,架構出一個檢傷分類的預測模型,並且由模型中隨機產出2,000筆所需的病患資料。經過資料探勘後,本研究發現多群判別分析能夠有效的區辨出病患的危急程度達90.6%,並且透過資料導出一種規則,利用產出的判別函數來預測,一個新的病患應該歸屬檢傷分類的哪一等級,進而提高檢傷分類的一致性與穩健性。
The implementation of triage system helps the distribution of patients in emergency departments so that patients in imminent danger in emergencie departments can get timely treatment. However, the consistency between the decisions of the Emergency Nurses and the Physicians will have influence on the quality of medical care, patient’s satisfaction, life safety and the payment of the National Health Insurance. As a result, in the time when the person-time for emergency medical service is continuously increasing, how to effectively enhance the Consistency and Robustness of the triage system is a very important task. The Emergency Department of a medical center in Taiwan cooperated to conduct the research. A predictive model of triage system is contracted from the contract procedure, selection of parameters to sample screening. 2,000 pieces of data needed for the patients is chosen randomly by the computer. Categorizations of data mining were used to classify public as triage scales: Multi-group Discriminant Analysis (MDA). With emergency department database parameters used as input, automated classifiers show promise for discriminating between triage scales. The ability under the histogram was 90.6% (MDA).