患者报告与理赔数据健康指标联合建模预测前列腺癌男性预期寿命
基于SEER-CAHPS数据库纳入2004至2013年诊断的65岁以上前列腺癌男性3240例,比较5种嵌套竞争风险回归模型预测其他原因死亡的表现。将患者报告与理赔数据健康指标联合纳入模型时区分度最高(10年AUC 0.820),优于单独使用任一指标。
要点
- 患者报告与理赔数据健康指标联合建模优于单独使用任一指标(10年AUC 0.820)。
- 仅人口学模型10年AUC为0.721,加入肿瘤信息后升至0.755。
- 加入理赔数据健康指标AUC为0.777,加入患者报告健康指标为0.812。
核心结论
- 联合患者报告与理赔数据健康指标的预期寿命预测模型优于单独纳入这些指标的模型。
- 鉴于改善程度有限,实施预期寿命工具应平衡模型性能与数据可及性和保真度。
研究设计与样本
- 利用SEER-CAHPS数据库识别2004至2013年诊断的65岁以上前列腺癌男性。
- 共纳入3240例,提取人口学、肿瘤信息、理赔数据健康指标和患者报告健康指标4类数据。
- 比较5种嵌套竞争风险回归模型预测其他原因死亡的表现。
- 评估将新健康指标加入已有预测模型是否改善区分度。
主要发现
- 3240例中246例(7.6%)死于前列腺癌,631例(19.5%)死于其他原因。
- NCI合并症指数评分与患者报告总体健康相关但相关性弱(p<0.001,r=0.21)。
- 预测其他原因死亡的10年AUC从仅人口学的0.721升至加入肿瘤信息的0.755。
- 加入理赔数据健康指标后10年AUC为0.777,加入患者报告健康指标后为0.812。
- 全模型10年AUC最高为0.820,基于现有工具的模型加入新数据后性能亦改善(p<0.001)。
临床怎么用
- 临床决策中可考虑联合患者报告与理赔数据健康指标构建预期寿命预测模型。
- 实施预期寿命工具时需权衡模型性能提升幅度与数据可及性和保真度。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: Life expectancy has become a core consideration in prostate cancer care. While multiple prediction tools exist to support decision making, their discriminative ability remains modest, which hampers usage and utility. We examined whether combining patient reported and claims based health measures into prediction models improves performance. MATERIALS AND METHODS: Using SEER (Surveillance, Epidemiology, and End Results)-CAHPS (Consumer Assessment of Healthcare Providers and Systems) we identified men 65 years old or older diagnosed with prostate cancer from 2004 to 2013 and extracted 4 types of data, including demographics, cancer information, claims based health measures and patient reported health measures. Next, we compared the performance of 5 nested competing risk regression models for other cause mortality. Additionally, we assessed whether adding new health measures to established prediction models improved discriminative ability. RESULTS: Among 3,240 cases 246 (7.6%) died of prostate cancer while 631 (19.5%) died of other causes. The National Cancer Institute Comorbidity Index score was associated but weakly correlated with patient reported overall health (p <0.001, r=0.21). For predicting other cause mortality the 10-year area under the receiver operating characteristic curve improved from 0.721 (demographics only) to 0.755 with cancer information and to 0.777 and 0.812 when adding claims based and patient reported health measures, respectively. The full model generated the highest value of 0.820. Models based on existing tools also improved in their performance with the incorporation of new data types as predictor variables (p <0.001). CONCLUSIONS: Prediction models for life expectancy that combine patient reported and claims based health measures outperform models that incorporate these measures separately. However, given the modest degree of improvement, the implementation of life expectancy tools should balance model performance with data availability and fidelity.
引用
- Tan HJ, Zhou X, Spratte BN, et al. Patient Reported vs Claims Based Measures of Health for Modeling Life Expectancy in Men with Prostate Cancer. J Urol. 2020. PMID: 32909877. doi:10.1097/JU.0000000000001355
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。