基于PNN-LSSVM模型的医院总收入预测

PNN-LSSVM Model is Established to Predict the Hospital Medical Income

目的:以云南省某医院总收入为研究对象,对该医院2013年收入数据进行建模、预测。方法:根据医院总收入特性,首先对医院总收入进行分类,分类后分别建立适合各类别的LSSVM模型。结果:相比单一预测模型预测精度高,对30个样本点预测平均相对误差为4.95%。结论:医院总收入直接反映了医院的业务情况、筹资结构和经济效益,与医院的可持续发展息息相关,且各因素之间的关系是模糊的,很难依据各影响因素进行预测。本文充分考虑到医院总收入的特性,利用建立的PNN-LSSVM模型对医院总收入进行预测,为医院制订中、长期发展规划提供依。

Objective:To take the total income of a hospital in Yunnan Province as the research object,to model and predict the 2013 income data of the hospital.Methods:According to the characteristics of the hospital's total income,the hospital's total income is first classified,and the LSSVM models suitable for each category are established after classification.Results:Compared with the single prediction model,the prediction accuracy is high,and the average relative error for the 30 sample points is 4.95%.Conclusion:The hospital's total income directly reflects the hospital's business situation,fund raising structure and economic benefits,and is closely related to the sustainable development of the hospital.The relationship among various factors is ambiguous and it is difficult to predict based on various factors.This paper fully considers the characteristics of the hospital's total income,uses the established PNN-LSSVM model to predict the total hospital revenue,to provide guidance for hospitals to formulate medium and long-term development plans.