Department of Biosciences and Nutrition, Karolinska Institutet, Huddinge, Sweden.
Integrated Cardio Metabolic Centre (ICMC), Department of Medicine, Karolinska Institutet, Huddinge, Sweden.
J Gerontol A Biol Sci Med Sci. 2023 Jan 26;78(1):158-166. doi: 10.1093/gerona/glac186.
There is a growing interest in generating precise predictions of survival to improve the assessment of health and life-improving interventions. We aimed to (a) test if observable characteristics may provide a survival prediction independent of chronological age; (b) identify the most relevant predictors of survival; and (c) build a metric of multidimensional age.
Data from 3 095 individuals aged ≥60 from the Swedish National Study on Aging and Care in Kungsholmen. Eighty-three variables covering 5 domains (diseases, risk factors, sociodemographics, functional status, and blood tests) were tested in penalized Cox regressions to predict 18-year mortality.
The best prediction of mortality at different follow-ups (area under the receiver operating characteristic curves [AUROCs] 0.878-0.909) was obtained when 15 variables from all 5 domains were tested simultaneously in a penalized Cox regression. Significant prediction improvements were observed when chronological age was included as a covariate for 15- but not for 5- and 10-year survival. When comparing individual domains, we find that a combination of functional characteristics (ie, gait speed, cognition) gave the most accurate prediction, with estimates similar to chronological age for 5- (AUROC 0.836) and 10-year (AUROC 0.830) survival. Finally, we built a multidimensional measure of age by regressing the predicted mortality risk on chronological age, which displayed a stronger correlation with time to death (R = -0.760) than chronological age (R = -0.660) and predicted mortality better than widely used geriatric indices.
Combining easily accessible characteristics can help in building highly accurate survival models and multidimensional age metrics with potentially broad geriatric and biomedical applications.
人们越来越关注生成精确的生存预测，以改善对健康和改善生活干预措施的评估。我们旨在：（a）检验是否可观察的特征可以提供独立于实际年龄的生存预测；（b）确定与生存最相关的预测因素；（c）构建多维年龄指标。
使用来自瑞典 Kungsholmen 老龄化和护理国家研究的 3095 名年龄≥60 岁的个体的数据。在惩罚性 Cox 回归中，共测试了 83 个变量，涵盖 5 个领域（疾病、风险因素、社会人口统计学、功能状态和血液检查），以预测 18 年死亡率。
当在惩罚性 Cox 回归中同时测试来自所有 5 个领域的 15 个变量时，获得了不同随访时间（接收者操作特征曲线下面积 [AUROCs] 0.878-0.909）的最佳死亡率预测。当将实际年龄作为协变量包含在 15 年但不包括 5 年和 10 年生存预测中时，观察到了显著的预测改善。当比较各个领域时，我们发现功能特征（即步态速度、认知）的组合提供了最准确的预测，对于 5 年（AUROC 0.836）和 10 年（AUROC 0.830）生存，其估计值与实际年龄相似。最后，我们通过将预测的死亡率风险回归到实际年龄，构建了一个多维的年龄指标，与死亡时间的相关性更强（R =-0.760），比实际年龄（R =-0.660）更强，并且比广泛使用的老年指数更能预测死亡率。
结合易于获得的特征可以帮助构建高度准确的生存模型和多维年龄指标，这些模型和指标可能具有广泛的老年学和生物医学应用。
