Predicting healthcare expenditure by multimorbidity groups

Objectives

This article has two main purposes. Firstly, to model the integrated healthcare expenditure for the entire population of a health district in Spain, according to multimorbidity, using Clinical Risk Groups (CRG). Secondly, to show how the predictive model is applied to the allocation of health budgets.

Age and case mix-standardised survival for all cancer patients in Europe 1999–2007: Results of EUROCARE-5, a population-based study

BackgroundOverall survival after cancer is frequently used when assessing a health care service’s performance as a whole. It is mainly used by the public, politicians and the media, and is often dismissed by clinicians because of the heterogeneous mix of different cancers, risk factors and treatment modalities. Here we give survival details for all cancers combined in Europe, correlating it with economic variables to suggest reasons for differences.MethodsWe computed age and cancer site case-mix standardised relative survival for all cancers combined (ACRS) for 29 countries participating in the EUROCARE-5 project with data on more than 7.5 million cancer cases from 87 population-based cancer registries, using complete and period approach.ResultsDenmark, United Kingdom (UK) and Eastern European countries had lower survival than neighbouring countries. Five-year ACRS has been increasing throughout Europe, and substantial increases, between 1999–2001 and 2005–2007, have been achieved in countries where survival was lower in the past. Five-year ACRS for men and women are positively correlated with macro-economic variables like the Gross Domestic Product (GDP) and Total National Expenditure on Health (TNEH) (R² about 70%). Countries with recent larger increases in GDP and TNEH had greater increases in cancer survival.ConclusionsACRS serves to compare all cancer survival in Europe taking account of the geographical variability in case-mixes. The EUROCARE-5 data on ACRS confirm previous EUROCARE findings. Survival appears to correlate with macro-economic determinants, particularly with investments in the health care system.     

数据挖掘在疾病诊断相关组项目中的应用

病例分组被广泛认为是一种直接、合理、有效的医疗产出测量单位,疾病诊断相关组（DRGS）是以医疗资源消耗为分组轴心发展起来的一种病例分组模型。本DRGS病例分组研究以样本量较大的胆石病为例,将数据挖掘中的决策树的方法应用于构建DRGS病例组合的过程中。     

儿童热液烫伤病例 DRGs 分组方法的研究简

目的探索儿童热液烫伤病例的疾病诊断相关组合（DRGs）分组方法。方法以某军队三级医院烧伤中心热液烧伤儿童病例为研究对象,采用卡方自动交互监测（CHAID）构建决策树,找出有统计学意义的分类变量,对1290例病例进行分组。结果以烧伤面积、治疗结果、是否输血、是否休克作为分类节点将病例分为6个DRGs组合。结论CHAID决策树分类方法能够充分反映疾病严重程度、病情复杂性对医疗资源消耗的影响,使DRGs分组更加合理。     

Laboratory data predicts survival post hospitalization

From a database of 93,077 in-patient admissions, patients assigned to catastrophic, very severe, moderately severe, and average 30-day mortality risk categories (as defined in Medicare Hospital Mortality Information, 1989 release, from the Health Care Financing Administration (HCFA)) were selected for study. These admissions account for 30% of all admissions, but 70% of. all deaths up to 1 year post admission. To determine whether laboratory information adds to the predictive power of the information used by HCFA, we compare the performance of 1 year survival predictors (Cox model) that use only diagnostic, demographic, and comorbidity information, with the performance of predictors that also include laboratory information. Using a separate set of patients not used for model definition, we find that laboratory data contain significant prognostic information independent of that already available in non-laboratory data. In HCFA's catastrophic disorders for example, non-laboratory information reduces the average risk of predicting a wrong outcome by 17% relative to considering only catastrophic group membership, and adding,laboratory data reduces this risk by a further 21%. These improvements result primarily from considering the outcomes of a small set of routine laboratory tests (maximum BUN, AST, and WBC, and minimum CO₂, hematocrit, and sodium).     

The nature,content and interpractice variation of general practice: A regional study in Italy

The activity of 34 general practitioners (GP) working in solo practices in six Local Health Units were assessed, as a preliminary step of a main study, to evaluate and possibly improve the quality of GP professional performance using peer review and feed-back information. A wide interpractice variation was observed in patient visit and patient visiting rates, drug and test prescribing, in- and out-patient referrals, as well as in the composition of the practice case-mix. The extent of interpractice variation for relevant actions in the process of care was unchanged after adjusting for case-mix, suggesting that case-mix differences have little effect in explaining differences among physicians' overall pattern of care and health care resource consumptions.     

临床路径下病例组合方法研究

目的：探讨临床路径下病例组合方法和人工神经网络在病例组合中的应用。方法：利用某综合性医院的一个临床路径流程（腰椎间盘突出行椎板切除术或髓核摘除术）下的523份出院病历资料，采用K-MEANS聚类方法进行组合，用神经网络对预测病例的病例组合进行判断。结果：523份病历聚为4组，各组间费用95％可信区间互不重合；神经网络的训练误差为0．0029，病例组合预测和判断符合率为98．91％。结论：以临床路径下产生的病例为单元样本进行病例组合，结果更科学、客观。神经网络用于病例组合判断，不用确定单个节点变量的分割值，更符合病例组合由多变量共同作用的实情。     

Assessing population health care need using a claims-based ACG morbidity measure: a validation analysis in the Province of Manitoba

OBJECTIVES: To assess the ability of an Adjusted Clinical Group (ACG)-based morbidity measure to assess the overall health service needs of populations. Data Sources/Study Setting. Three population-based secondary data sources: registration and health service utilization data from fiscal year 1995-1996; mortality data from vital statistics reports from 1996-1999; and Canadian census data. The study included all continuously enrolled residents in the universal health care plan in Manitoba. STUDY DESIGN: Using 60 small geographic areas as the units of analysis, we compared a population-based "ACG morbidity index," derived from individual ACG assignments in fiscal year 1995-1996, with the standardized mortality ratio (ages < 75 years) for 1996-1999. Key variables included a population-based socioeconomic status measure and age- and sex-standardized physician utilization ratios. DATA EXTRACTION METHODS: The ACGs were assigned based on the complement of diagnoses assigned to persons on physician claims and hospital separation abstracts. The ACG index was created by weighting the ACGs using average health care expenditures. PRINCIPAL FINDINGS: The ACG morbidity index had a strong positive linear relationship with the subsequent rate of premature death in the small areas of Manitoba. The ACG index was able to explain the majority of the relationships between mortality and both socioeconomic status and physician utilization. CONCLUSIONS: In Manitoba, ACGs are closely related to premature mortality, commonly accepted as the best single indicator for health service need in populations. Issues in applying ACGs in settings where needs adjustment is a primary objective are discussed.