查詢結果分析
來源資料
相關文獻
- 運用資料探勘技術建構植牙手術成敗之預測模型
- A Graph-Based Approach to Discovering Multiple-Level Association Rules from Large Databases
- 線上教材瀏覽模式之分析工具--資料探勘模式在網路學習課程之發展與應用實例
- 利用資料探勘語言挖掘感興趣的資訊
- 探勘中文新聞文件
- An Incremental Updating Technique for Discovering Sequential Patterns in Large Databases
- 一對一個人化服務機制
- 高效能多媒體文件分類法則之研究
- 利用決策樹分類法建置資料倉儲中檢核與整合大量企業資料之機制
- 挖掘企業資料的寶藏--淺談資料探勘技術
頁籤選單縮合
題 名 | 運用資料探勘技術建構植牙手術成敗之預測模型=Using Data Mining to Construct the Forecasting Models for Efficacy of Dental Implant |
---|---|
作 者 | 林承俊; 胡雅涵; | 書刊名 | 醫學與健康期刊 |
卷 期 | 6:2 2017.09[民106.09] |
頁 次 | 頁57-69 |
分類號 | 416.96 |
關鍵詞 | 人工植牙手術; 植體早期成敗; 植體晚期成敗; 資料探勘; Dental implant surgery; Efficacy; Dental implant; Data mining; |
語 文 | 中文(Chinese) |
中文摘要 | 目的:在過去文獻中探討植體成敗因素僅就患者系統性疾病、手術方式及贗復型式等單一因素進行統計學相關顯著分析,因此本研究將建立預警機制以減少失敗機會,進一步納入目前文獻缺乏的影響因子進行分析。方法:本研究收集嘉義市某區域教學醫院接受植牙治療患者臨床資料,包含:年齡、性別、缺牙原因、系統性疾病、抽煙、喝酒、嚼檳榔、醫師科別、醫師執業年數、植牙位置、骨頭硬度、骨脊增生術、上顎竇增高術、植體系統、植體長度、植體寬度、贗復物形式、支台體角度及義齒固定方式,總計八大類別 20個變項,再以決策樹、支援向量機及邏輯斯迴歸等資料探勘技術分成植體早期成敗及晚期成敗兩個面向進行分析。結果:以單一分類器比較預測率方面,不論植體早期成敗或是晚期成敗方面, C4.5(J48)決策樹預測效能最高,分別為62.6%及69.8%;從分析中發現植體系統不分植體早期成敗及晚期成敗皆有影響,另外以CART(Classification and Regression Tree)分類迴歸樹找出影響植體成敗的關聯規則。結論:本研究希望能藉由研究之結果建立植體早期及晚期成敗預測模型,幫助臨床醫師遇到臨床相關情形時,可以選用預測結果較佳之植體系統及贗復方式,以減少因治療失敗發生糾紛之目的。 |
英文摘要 | OBJECTIVES. According to past literature, most of the exploratory factors only were statistically significant for single diseases such as systemic disease, surgical procedure and prosthetic type. In this study, we sought to reduce failures in dental implants by establishing early warning mechanisms taking into account various patient and dentist factors and denture fixation. METHODS. We collected clinical data of patients undergoing dental implantation in a local hospital of Chiayi. These data included age, sex, causes of tooth loss, systemic diseases, smoking, drinking, chewing betel nuts, department of dental division, physician practice years, implant position, bone density, bony augmentation, maxillary sinus augmentation, implant systems, implant length, implant width, prosthetic form, and the angle of the abutment and fixation of denture. A total of eight categories were created for the 20 variables. A decision tree, support vector machine, and logistic regression were used to analyze the prediction of dental implant success and failure. RESULTS. C4.5 (J48) decision tree had the highest predictive efficiency of 62.6% and 69.8% respectively, regardless of the early or late successes and failures in a single classifier. In addition, the risk prediction models were established based on the classification regression tree (CART). The correlated rules were established to predict the early and late failure of dental implants. CONCLUSION. We hope to establish the prediction models of early and late success or failure of dental implants by using the results of this study. This should help clinicians to reduce failure by choosing the optimal implant systems and the prosthetic therapies for their patients. |
本系統中英文摘要資訊取自各篇刊載內容。