智慧型護理計畫決策支援系統之建置評估

Development of the Intelligence Nursing Care Plan Decision Support System

薛伊秀(Yi-Shiou Shiue)

指導教授 ： 吳帆

國立中正大學/管理學院/資訊管理學系/碩士(2013年)

摘要

護理人員是醫療產業中的主要照護人力，也是醫療團隊中執行醫師醫囑的關鍵成員，其工作效率直接影響病人安全及醫療照護品質，病人安全被視為是護理品質的指標，當今全世界許多國家皆面臨健康照護人員短缺的問題，而照護人力不足與病人安全確實存在著密切的相關性。

護理人員在第一線承擔極大的壓力，在繁忙的工作中，對於資料的紀錄謄寫等都是每天必備的工作要素。根據文獻指出，臨床照護工作的時間分配約略可分為四大區塊，如護理評估、護理活動、護理紀錄及其他，其中又以護理紀錄佔37％為最耗時。護理計畫是臨床護理人員執行醫療照護的重要依據，如能透過設計完善的資訊系統來輔助，尋求迅速又正確完整的撰寫護理計畫方法，將可以提高醫療照護的品質，縮短護理記錄書寫的時間，彌補護理人力吃緊，人員負荷量過大的窘境，並能加強處理問題的能力。

本研究的目的主要是以人工智慧的技術來協助護理計畫的擬定，以NANDA護理診斷為基礎，使用中央研究院之中文斷詞系統與未知詞擷取系統做為工具，經語句斷詞處理、字詞比對及護理診斷決策演算法，推演出適當的護理計畫建議，再由護理人員做出最後的檢視與判斷，確定或拒絕該診斷、護理計畫及相關的處置，整合護理評估資料即時運用，減少護理人員重複書寫的時間。

關鍵字

案例式推理 ； 決策支援系統 ； 自然語言處理 ； 護理計畫

並列摘要

Nurses are the majority of the workforce in the medical industry, and are key medical team members in carrying out physicians' orders. As a result, the efficiency of the nursing staff directly affects the quality of medical care and the well-being of the patients. Patient safety is regarded as an important indicator of nursing care quality. Many countries now face healthcare provider shortfalls, and recognize a close correlation between adequate manpower and patient safety.

Nurses have to bear extremely heavy stress. To record and transcript all kinds of medical data is a daily work during the busy hours. According to literature, time allocation of clinical nursing works could be divided into nursing evaluation, nursing activities, nursing records, and others. The one taking the most hours or 37% of total clinical nursing time is nursing records. The Nursing Care Plan is an important basis for nurses to carry out their nursing diagnosis, treatments and intervention. If we could development of nursing care plan systems to help to do this kind of job, it may provide good quality of care, decrease the time that nurses duplicate patient history, reduce nurses’ burden and enhance the abilities to solve problems.

The main purpose of this study is to use artificial intelligence technique to generate nursing care plan. In this study, we use the nursing care database as the core, and follow the standards of NANDA Nursing Diagnosis Handbook. This system functions including sentence segmentation, keyword matching and the decision algorithm of nursing diagnosis. Make clinical judgments about patients’ actual or potential problems and provide applicable nursing plans and interventions. The staffs review and make final decision to accept or reject these judgments, nursing plans and related interventions. Registered data were optimally reused upon summarization and readmission to reduce the nurses’workloads.

並列關鍵字

Case-based Reasoning ； Decision Support System ； Natural Language Processing ； Nursing Care Plan

參考文獻

2. 方亞芸、邱艷芬（2005）。國際護理作業分類系統之臨床適用性評估－台灣ICNP臨床測試計畫。實證護理，1(2)，77-89。doi：10.6225/JEBN.1.2.77

4. 李麗紅、楊政議（2001）。護理診斷書寫常見的錯誤。護理雜誌，48(6)，83-88。doi：10.6224/JN.48.6.83

6. 周幸生、林麗華、曾院美、尹祚芊、張博論、陳玉枝（2006）。護理計畫決策支援系統雛型之建立。榮總護理，23(2)，147-156。

7. 邱艷芬、蔡欣玲（2001）。國際護理作業分類系統在健康資訊、知識及系統的發展－參加「國際護理作業分類系統翻譯者與評估者研習會」紀事。護理雜誌，48(1)，15-18。doi：10.6224/JN.48.1.15

8. 常玉琴、黃惠姿、王襄華、張雅惠、樊君儀、高麗娟、戴千淑（2009）。提昇護理記錄書寫完整性之改善方案。榮總護理，26(3)，304-310。