決策輔助系統推播圖文品質保證機制之實證研究

An Empirical Study on the Quality Assurance of Notification Mechanism in Decision Support System

目的：臺北市立聯合醫院於決策輔助系統之建置，主要係以使用者觀點需要時再登入頁面獲得資訊，為使病床資訊能主動且正確推播提供給使用者參考，研究目的是經由品質確保的驗證流程後，再供使用者取得最新的參考決策資訊。
方法與結果：決策輔助系統推播主要是依系統更新頻率，經由即時通訊軟體API開發自動化推播前端網頁製作的病床圖文資訊，推播機制建立在完成驗證程序後，方可推播給使用者。本研究驗證流程係應用圖片相似度比對方法，實證經此品質保證機制可有效減少自動化推播的異常發生，正常推播比例可達95%至98%。
結論：決策輔助系統的資訊在自動化推播機制的應用已漸趨成熟，後續自動化推播的開發亦能應用本研究的驗證機制以供醫院同仁獲取正確有效的資訊。

Objective: Taipei City Hospital has developed a Decision Support System (DSS) to integrate comprehensive hospital information. Traditionally, users have accessed the system only when specific information was required. To ensure that data on bed availability are delivered proactively and with a high degree of accuracy, this study aims to validate a quality assurance framework that verifies the integrity of decision-support information prior to its dissemination to end users.
Methods and Results: The DSS notification mechanism is designed in accordance with the system’s update frequency and integrates Messaging API to automate the generation and dissemination of bed availability information through a front-end web interface. A validation process is established to ensure the correctness and completeness of bed availability information. To verify data integrity, this study applies an image similarity comparison method, demonstrating that the proposed quality assurance mechanism effectively reduces anomalies in automated notifications and achieves a normal notification success rate between 95% and 98%.
Conclusion: The application of automated notifications within the DSS has reached a high level of operational maturity. Future developments can leverage the validation mechanism established in this study to further enhance the accuracy and reliability of information provided to hospital staff.