查詢結果分析
來源資料
頁籤選單縮合
題 名 | 利用資料探勘技術輔助疾病診斷是否異常=Using Data Mining Techniques to Aid Careless Diagnoses for Diseases |
---|---|
作 者 | 陳垂呈; | 書刊名 | 資訊科學應用期刊 |
卷 期 | 2:2 民95.12 |
頁 次 | 頁155-172 |
分類號 | 419.21 |
關鍵詞 | 資料探勘; 關聯規則; 症狀; 疾病; 異常診斷; Data mining; Association rules; Symptoms; Diseases; Careless diagnosis; |
語 文 | 中文(Chinese) |
中文摘要 | 在醫學診斷資料中隱藏著許多有價值的資訊,如何從這些資料中利用有效的方法來找出有價值資訊,是資料管理者必須考量的問題。 在本篇論文中,我們以診斷資料為探勘的資料來源,並以某一病患為探勘的目標,利用關聯規則分別從以下兩方面來偵測疾病診斷是否異常: 一是考量此一病患被診斷罹患之疾病是否具有異常的傾向,我們設計一個探勘關聯規則的方法,且探勘出之關聯規則的前置項目組,必須被包含於 此一病患症狀中,根據關聯規則所顯示出的特徵,我們可判斷此一病患之疾病診斷是否具有異常的傾向;二是考量此一病患被問診顯示之症狀是否 具有異常的傾向,我們設計一個探勘關聯規則的方法,且探勘出之關聯規則的前置項目組,必須被包含於此一病患被診斷的疾病項目中,根據關聯 規則所顯示出的特徵,我們可判斷此一病患之症狀問診是否具有異常的傾向。此探勘結果,對臨床經驗不足之醫療人員可以對其避免診斷的疏忽, 可以提供非常有用的參考資訊。 |
英文摘要 | There is lots of valuable information that are hidden in medical diagnostic data. It is the important problem how to use effective methods to find the information for the manager of these data. In this paper, we use diagnostic data as the source of mining, and let one patient as the target of mining. We use association rules to detect careless diagnosis for diseases from two aspects, respectively. One is to consider the patient who is diagnosed to have those diseases whether carelessness or not. We propose a method to mine association rules whose antecedents are contained in the patient’s symptom items. According to the characteristics of the association rules, we can find can detect the patient who is diagnosed to have the diseases whether carelessness or not. The other is to consider the patient who is inquired to have those symptoms whether carelessness or not. We propose a method to mine association rules whose antecedents are contained in the diagnosed disease items for the patient. According to the characteristics of the association rules, we can detect the patient who is inquired to have the symptoms whether carelessness or not. The results of mining can provide very useful information to avoid careless diagnoses for inexperience hospital staffs. |
本系統中英文摘要資訊取自各篇刊載內容。