裴佳佳 劉媛華



摘 要:建立分級診療制度是我國醫改“十三五”規劃五大任務之首,而基層醫療衛生機構承擔著分級診療的基礎任務,是基本醫療衛生服務和公共衛生服務的雙重承載,如何提高基層醫療衛生機構服務水平具有重大研究意義。選取上海市2010 -2016年基層醫療機構診療數據,建立基于多因素影響的上海市基層醫療機構診療量預測組合模型。首先運用灰色關聯分析對各影響因素與診療量的相關性進行排序,篩選出主要影響因素變量;然后應用GM(1,N)模型對各年度診療量進行預測,并利用改進粒子群算法進行背景值優化,以提高預測準確性;最后運用該模型預測2017 -2020年診療量。仿真實驗結果表明,該模型較單一的GM(1,N)模型準確性更高,預測有效可行。
關鍵詞:醫療機構診療量預測;灰色關聯分析;GM(1,N)模型;PSO;背景值優化
DOI:10. 11907/rjdk. 182517
中圖分類號:TP319
文獻標識碼:A文章編號:1672-7800(2019)006-0130-05
Abstract: The establishment of a grading diagnosis and treatment system is the first of the five major tasks of the 13th Five-Year Plan for medical reform in China. The primary health care institutions are responsible for the basic tasks of grading diagnosis and treatment. They are the dual burdens of basic medical and public health services and how to improve the primary health care institutions. Service levels have significant research implications. This paper selects the data of primary and secondary medical institutions in Shanghai from 2010 to 2016, and establishes a combined model for the diagnosis and treatment of primary care institutions in Shanghai based on multi-factor effects. Firstly, the gray correlation analysis is used to sort the correlation between each influencing factor and the amount of diagnosis and treatment, and the main influencing factors are selected. Then the GM(1,N) model is used to predict the annual diagnosis and treatment, and the improved particle swarm optimization algorithm is used. The background value is optimized to improve the accuracy of the predicted value; finally, the model is used to predict the amount of medical treatment from 2017 to 2020. The simulation results show that the model has higher accuracy than the single GM(1,N) model, which indicates that the model is effective and feasible.
Key Words: forecast of diagnosis and treatment volume of medical institutions; grey relational analysis; GM(1,N) model; PSO; background value optimization
0 引言
基層醫療機構是整個醫療體系的根基,承擔著提供基本醫療衛生服務和基本公共衛生服務的責任,對保障和改善居民健康狀況具有重要作用,是國家實施分級診療、雙向轉診制度很重要的一環,對緩解“看病難、看病貴”問題具有重要意義[1]。2015年9月,國務院辦公廳出臺《關于推進分級診療制度建設的指導意見》(國發辦[2015]70號),強調以提高基層醫療服務能力為重點,以常見病、多發病、慢性病分級診療為突破口,引導優質醫療資源下沉,形成科學合理的就醫秩序,逐步建立符合國情的分級診療制度[2]。為此,上海加大了醫療資源投入,實施“5+3+1”工程,建成102個示范性社區衛生服務中心,基層醫療機構診療效率和服務水平有了很大提高。分析上海市基層醫療機構未來發展趨勢,對提高上海市醫療綜合服務水平,保障人民健康有著重要意義。
目前對于基層醫療機構的研究方法主要是實地調研和統計學分析[3],建立模型進行分析的甚少。本文應用灰色系統理論對總診療量進行預測研究。首先,總診療量可以反映醫療服務能力、患者就醫取向。從分級診療構建角度看,基層醫療機構的診療量可以反映患者就診的選擇變化,從而體現分級診療是否有效[4]。灰色系統理論是鄧聚龍教授[5]于1982年創立的,以部分信息已知、信息未知的小數據、貧信息不確定性問題為研究對象,通過提取已知信息,實現對未來變化的定量預測,其特點是少數據建模,模型構造簡單,計算方便。