Hartz A J, Guse C, Sigmann P, Krakauer H, Goldman R S, Hagen T C
Medical College of Wisconsin, Department of Family and Community Medicine, Milwaukee 53226.
Med Care. 1994 Sep;32(9):881-901. doi: 10.1097/00005650-199409000-00001.
The Health Care Financing Administration (HCFA) plans to use the Uniform Clinical Data Set System (UCDSS) to collect data on hospitalized Medicare patients. This study examined the value of UCDSS data for creating severity of illness measures. UCDSS data were obtained from a study hospital and from a national data set for patients with pneumonia (n = 528) and stroke (n = 565). Models to predict length of stay or an adverse event were derived for each condition using HCFA claims data alone, UCDSS data alone, and UCDSS data supplemented with additional information also abstracted from charts. The models were derived from one set of patients and validated on another. The R2 for predicting length of stay in the validation data for the UCDSS model was 0.29 for pneumonia and 0.19 for stroke compared to R2 values from the claims model of 0.09 for stroke and 0.06 for pneumonia. UCDSS models also were better than claims models for predicting adverse events. The best UCDSS models included International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes and other information requiring clinical judgment, and were improved by adding more information on patient functional status. Some findings were more strongly associated with outcome for the study hospital than for the national data. These results suggest that UCDSS models will predict outcome much better than the claims based models currently used by HCFA for the analysis of hospitalization-related mortality; more functional status information should be added to UCDSS; and despite an extensive objective database, the most predictive UCDSS models require clinician-assigned diagnostic codes.
医疗保健财务管理局（HCFA）计划使用统一临床数据集系统（UCDSS）来收集医疗保险住院患者的数据。本研究探讨了UCDSS数据在创建疾病严重程度衡量指标方面的价值。UCDSS数据取自一家研究医院以及一个针对肺炎患者（n = 528）和中风患者（n = 565）的全国数据集。分别使用单独的HCFA理赔数据、单独的UCDSS数据以及补充了从病历中提取的其他信息的UCDSS数据，为每种病症推导预测住院时长或不良事件的模型。这些模型基于一组患者推导得出，并在另一组患者中进行验证。在验证数据中，UCDSS模型预测肺炎住院时长的R2为0.29，预测中风住院时长的R2为0.19，而理赔模型预测中风的R2值为0.09，预测肺炎的R2值为0.06。UCDSS模型在预测不良事件方面也优于理赔模型。最佳的UCDSS模型包括国际疾病分类第九版临床修订本（ICD - 9 - CM）编码以及其他需要临床判断的信息，并且通过添加更多关于患者功能状态的信息而得到改进。对于研究医院而言，一些研究结果与结局的关联比全国数据更为紧密。这些结果表明，UCDSS模型在预测结局方面将比HCFA目前用于分析住院相关死亡率的基于理赔的模型要好得多；应向UCDSS添加更多功能状态信息；并且尽管有一个广泛的客观数据库，但最具预测性的UCDSS模型仍需要临床医生指定的诊断编码。
