李秀惠臺灣大學:資訊工程學研究所陳伯豪Chen, Po-HauPo-HauChen2010-05-172018-07-052010-05-172018-07-052008U0001-1107200800202800http://ntur.lib.ntu.edu.tw//handle/246246/183410本篇論文主要描述國立台灣大學醫學院附設醫院目前新生兒資訊系統開發的架構與狀況，使得樣本蒐集、檢驗、診斷、評估、治療、追蹤病例服務、篩檢數據資料庫管理、臨床研究、院際通訊的工作更為健全。最後以資料探勘的技術來建立一輔助協助診斷系統提升篩檢正確率。以此基於支持向量機的罕見疾病輔助診斷系統，甲基丙二酸血症為例，來分析此目前疑陽性極高的疾病。The thesis aims to discuss about architecture and status of Newborn Screening Healthcare Information System of National Newborn Screening Center in National Taiwan University Hospital for further integrity and enhancements of sample collections, testing, diagnoses, evaluations, treatments or follow-up services, screening database management, as well as collaboration, communication among hospitals. Finally, we use data mining technology to build the diagnosis decision support system to improve the screening system accuracy. Then we examine the screening result of MMA which is high false-positive rate by the diagnosis decision support system based on support vector machine.Chapter 1 Introduction 1.1 Introduction 1.2 Background 2.3 Motivation and Objective 4.4 Thesis Organization 5hapter 2 Newborn Screening Healthcare Information System 6.1 NTUH HIS Architecture overview 6.2 Subsystem functionality. 7.3 Basic work sequence 10.4 Questionnaire 11hapter 3 Decision Support System Architecture and Data mining 12.1 SVM Web-Base Architecture 12.2 General Class Prediction with Supervised Method 17.3 The system progress and the detail of the design 18.4 Snapshot 31hapter 4 Experiment and Result 32.1 Material 32.2 Goal 34.3 Experiment progress 35.4 Experiment Result 36.4.1 Statistic components 36.4.2 Data set 37.4.3 Weight ratio 37.4.4 Grid Search with Features 38.4.5 Model parameters and model weight 42.4.6 Voting 43.4.7 Vote result compared with current method of NTUH 47hapter 5 Conclusion 48eference 49135 bytestext/htmlen-US新生兒篩檢資訊系統資料探勘支持向量機網路服務甲基丙二酸血症Newborn ScreeningInformation SystemData MiningSupport Vector MachineWeb ServicesMMAthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/183410/1/index.html