建立類神經網路模型預測住院跌倒之發生

Establishing an Artificial Neural Network Model for Predicting Inpatient Falls

謝森松(Sen-Song Shieh)

指導教授 ： 李友專

臺北醫學大學/醫學院/醫學資訊研究所/碩士(2004年)

摘要

近年來，世界各國愈來愈重視病人安全（Patient Safety）之相關議題，因此如何建立「病人安全管理體系」，儼已成為全球性醫療管理之新趨勢，在過去因不當醫療管理所衍生之問題如：藥物不良事件（Adverse Drug Event）、手術相關（Procedure Related）、院內感染（Nosocomial Infection）、以及住院跌倒（Inpatient Falls）等意外事件曾引發社會各界不同程度之關切，因此未來有關現代醫療管理等重要課題之研究將逐漸成為各大醫院謀求服務品質提昇之重要目標。 據相關研究資料顯示，住院跌倒約佔醫院意外事件之80％，而許多住院跌倒之案例更將導致病人病情惡化、產生併發症及延長其住院日數，嚴重耗用醫療成本。為解決長存於各醫療院所之此一困擾問題，本研究將以回溯性之方式收集台北市某醫學中心住院病患電子病歷（Electronic Medical Records）資料（含三年跌倒組及非跌倒組計3496筆），希望藉由本研究所建立之類神經網路（Artificial Neural Network）模型，進一步地準確預測住院跌倒之發生，以確保病人安全，降低醫療成本。 有關於住院跌倒之研究，O''connell等人以「Morse Fall Scale 跌倒評分表」應用在澳洲某醫院兩個老人急性病房，結果顯示其敏感性為83%，特異性為29%，陽性預測值為18%。Hendrich A.L.等人曾以「Hendrich II 模組跌倒危險評估表」執行相關之研究課題，而其所得之敏感性及特異性分別為74.9%及73.9%。此外，Oliver, D.等人亦曾針對老人住院病患，應用「STRATIFY跌倒危險評估表」執行住院跌倒之研究，並得出93%之敏感性及88%之特異性。而透過本論文之研究方法，電子病歷經由本研究所採之類神經網路模型所得之敏感性與特異性則分別為87.19 %及87.64%。研究者得到的結論是電子病歷在預測住院病人跌倒之發生上，可以做為預測因子很好的資料來源。

關鍵字

病人安全 ； 跌倒 ； 跌倒危險因子 ； 類神經網路 ； 電子病歷

並列摘要

Most of the countries have paid much attention to the issues of patient safety in recent years. The construction of a patient safety system has gradually turned into a global brand-new trend in the medical management. In the past, the medical accidents such as adverse drug event, procedure related, nosocomial infection, and inpatient falls etc., which normally resulted from the improper medical management, have caused different degrees of commotions in our society. Therefore, the study of a new management criterion for the medical issues will become the useful implement to enhance the service quality in a modern hospital. Some research data have shown that the chance of inpatient falls covers nearly 80% of the hospital’s contingency. Moreover, in many cases inpatient falls along with serious injury will aggravate patients'' condition, produce complications and increase patient’s length of stay. Such situations always consume much amount of medical cost. In order to solve these afflictive problems, the retrospective patients’ medical history data to the amount of 3496 from one medical center hospital in Taipei were employed in this research. These data include both faller and non-faller’s Electronic Medical Records（EMR）. The objective of this research is to establish an Artificial Neural Network（ANN）model combined with EMR for the prediction of inpatient falls. Such method could be further used to provide a safe care for the patients and reduce the medical cost. Regarding the research of inpatient falls, O''connell used the Morse Fall Scale as part of a fall prevention programme on two aged care wards in an acute care hospital setting in Australia. Findings revealed that the Morse Scale had a sensitivity of 83%, a specificity of 29% and a positive predictive value of 18%. Hendrich A.L. used the Hendrich II fall risk model in large concurrent case/control study of hospitalized patients, and herein obtained the significant values of sensitivity and specificity, which were 74.9% and 73.9% respectively. Meanwhile, applying the STRATIFY fall risk assessment tool, Oliver, D. got the 93% sensitivity and 88% specificity for the elderly inpatients study case. In this paper, an ANN model according with EMR have been used as an analysis tool; the sensitivity and specificity from the model analysis are 87.19% and 87.64% respectively. The conclusion is that EMR can be employed as a useful source to accurately predict the occurrence of fall risk factor.

並列關鍵字

patient safety ； falls ； fall risk factor ； Artificial Neural Network ； Electronic Medical Records

參考文獻

中文文獻 【1】溫明寰、胡麗霞、劉君華，腸胃科住院病患預防跌倒之改善方案，新台北護理期刊，第四卷第一期，2002年2月，第101-109

【25】Haumschild, Mark J, Karfonta, Terry L, Haumschild, Mary S, Phillips, Sharon E. Clinical and economic outcomes of a fall-focused pharmaceutical intervention program. American Journal of Health-System Pharmacy, 2003; 60: 1029-1032.

Canberra: Australian Institute of Health and Welfare, Report No., Health and Welfare Series No 6, 1999. 【9】Sattin RW. Falls among older persons: a public health perspective. Annu Rev Public Health, 1992; 13: 489-508.

【15】Barbieri E. Patient falls are not patient accidents. Journal of Gerontological Nursing 9, 1983; (3):165-173.

【16】Cape R. Falls in the elderly. Australian Family Physician, 1988; 17: 523-527.