距離加權平均法在醫療衛材使用量預測之應用

The Applications of Distance Weight Average Method in Inventory Forecast of Medical Materials

楊淑文(Shu-Wen Yang)

指導教授 ： 黃怡詔

國立屏東科技大學/管理學院/工業管理系所/碩士(2013年)

https://doi.org/10.6346/NPUST.2013.00192

摘要

在醫院的內部成本中，資材成本約占總成本的25%至45%，因此資材成本管控成為醫院永續經營的重要目標之一。本研究以台灣某區域教學醫院的住院衛材資料庫做為樣本，應用距離與權重之概念提出一個距離加權平均法(Distance Weight Average Method, DWAM)，並結合溫氏指數平滑法(Winter's Exponential Smoothing)進行各疾病內每項衛材之需求預測。經研究發現，有70%的疾病可先利用距離加權平均法求得衛材用量之修正平均值，再乘上溫氏指數平滑法之預測病患數量，其所得到的預測結果較佳。此研究成果可提供未來預測之參考，並減少庫存過多或短缺的情形。

關鍵字

小樣本 ； 醫療衛材 ； 需求預測 ； 距離加權平均法 ； 離群值

並列摘要

Among the internal costs of a hospital, the material costs account for 25% to 45% of total costs. Therefore, the control of material costs has become one of important goals in respect of sustainable operation of the hospital.

　　The study adopted the database of medical materials used by hospitalized patient in certain regional education hospital as example. We proposed a Distance Weight Average Method (DWAM), DWAM based on the idea of distance and weight to reduce the effect of outlier to the average, followed by using the Winter's Exponential Smoothing to get demand forecast for each medical material of various diseases.

　　With research findings, we can use the DWAM to acquire the corrected average of medical material consumption and then multiplied by the forecast number of patients from Winter's Exponential Smoothing. This kind of forecast method is applicable to 70% of diseases. The research results area available for the references of forecast in the future and reduce the conditions of excess or short inventory.

並列關鍵字

Small Data Set ； Medical Materials ； Demand Forecasting ； Distance Weight Average Method ； Outlier

參考文獻

1.Abdel, A.R.E. and A.M. Mangoud (1998), “Modeling and Forecasting Monthly Patient Volume at a Primary Health Care Clinic using Univariate Time-Series Analysis,” Computer Methods and Programs in Biomedicine, vol. 56, no. 3, pp. 235–247.

2.Abraham, G., G.B. Byrnes and C.A. Bain (2009), “Short-Term Forecasting of Emergency Inpatient Flow,” IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 3, pp. 380–388.

3.Ahmed S. (2005), “Seasonal Models of Peak Electric Load Demand,” Technological Forecasting and Social Change, vol. 72, no. 5, pp. 609–622.

5.Billah, B., M.L. King, R.D. Snyder and A.B. Koehler (2006), “Exponential Smoothing Model Selection for Forecasting,” International Journal of Forecasting, vol. 22, no. 2, pp. 239–247.

6.Broyles, J.R., J.K. Cochran and D.C. Montgomery (2010), “A Statistical Markov Chain Approximation of Transient Hospital Inpatient Inventory,” European Journal of Operational Research, vol. 207, no. 3, pp. 1645–1657.