摘要
目的 用数据挖掘技术对患者病情危重度进行分类和评价。方法 用急性上呼吸道感染病例的病案首页数据和决策树分析法 ,确定分类标准、分类变量和决策树的生长及剪枝规则 ,建立病情危重度分类评价模型。结果 上呼吸道感染患者的病情划分为 4个等级 ,每个等级对应一个量化的危重度分值 ;医院收治患者的整体病情用危重度指数表示。经新样本考核 ,危重度等级和危重度指数对治疗结果、医疗资源消耗有一定预测能力 ,且随医院规模的增大而提高。结论 评价分析结果能够反映患者和医院收治病人的病情 ,可为医疗质量评价和医院费用补偿提供重要统计学依据。
Objective To classify and evaluate the severity of diseases with data mining techniques.Methods By application of decision tree model and abstract data of inpatients, determining the target and predict variables and rules of tree growing and pruning, established a model for assessment of severity of a patient with acute upper respiratory infections.Results The severity is presented in 4 degrees, with each one a numeric score. A severity index that presents the overall level of inpatient severity of a health provider is also developed. The result of applying the model to new data shows that the score and index can predict clinical outcome and resource consumption and distinguish hospitals of different scales to a certain extent.Conclusion The model can indicate the severity of patients and thus can be used as an adjustment factor in assessment of hospital performance and imbursement of healthcare organizations.
出处
《中国卫生统计》
CSCD
北大核心
2003年第1期16-19,共4页
Chinese Journal of Health Statistics
基金
国家自然科学基金资助项目( 79870 0 50 )
军队医药卫生"十五"重点课题 ( 0 1G0 0 6 - 1]