Ndiaye Mame Fana, Keezer Mark R, Nguyen Quoc Dinh
Research Centre of the Centre Hospitalier de l'Université de Montréal (CRCHUM), Montreal, Canada.
School of Public Health of the Université de Montréal, Department of Social and Preventive Medicine, Montreal, Canada.
Aging Clin Exp Res. 2025 May 26;37(1):165. doi: 10.1007/s40520-025-03063-y.
Mortality prediction models are essential for clinical decision-making, but their performance may vary across patient subgroups. This study aimed to evaluate how a general mortality prediction model performs across subgroups defined by vulnerability factors and to test whether model improvements could improve prediction accuracy.
We analyzed data from 49,266 participants in the Canadian Longitudinal Study on Aging. A general mortality prediction model (Model A) was developed using Cox proportional hazard regression with LASSO, incorporating variables spanning sociodemographic factors, lifestyle habits, comorbidities, and physical/cognitive function measures. Performance was evaluated across subgroups defined by age, frailty, multimorbidity, cognitive function, and functional impairment using discrimination (c-index), calibration, and Brier scores. We tested two additional strategies: incorporating subgroup-specific variables (Model B) and developing tailored models for different mortality risk categories (Models C1, C2, C3).
Over a median 6-year follow-up, 7.5% (3672) participants died. The general model performed well overall (c-index: 0.82, 95% CI 0.80-0.84; Brier: 0.036, 95% CI 0.032-0.040), but performance varied across subgroups. It was lower in frail individuals (c-index: 0.73, 95% CI 0.71-0.75; Brier: 0.12, 95% CI 0.11-0.13) and those with multiple chronic conditions (c-index: 0.76, 95% CI 0.75-0.78; Brier: 0.08, 95% CI 0.07-0.08), with risk underestimated in these groups. Neither incorporating subgroup variables nor developing risk-stratified models significantly improved performance.
Important variability in performance, particularly in vulnerable groups, highlights the limitations of a one-size-fits-all and underscores the need for more granular predictive models that account for subpopulation-specific characteristics to enhance mortality risk prediction.
死亡率预测模型对临床决策至关重要，但其性能在不同患者亚组中可能有所不同。本研究旨在评估一个通用的死亡率预测模型在由脆弱因素定义的亚组中的表现，并测试模型改进是否能提高预测准确性。
我们分析了加拿大老龄化纵向研究中49266名参与者的数据。使用带有LASSO的Cox比例风险回归开发了一个通用死亡率预测模型（模型A），纳入了社会人口学因素、生活习惯、合并症以及身体/认知功能测量等变量。使用区分度（c指数）、校准和Brier分数，对由年龄、虚弱、多种疾病、认知功能和功能障碍定义的亚组的性能进行了评估。我们测试了另外两种策略：纳入亚组特定变量（模型B）以及为不同死亡率风险类别开发定制模型（模型C1、C2、C3）。
在中位6年的随访期内，7.5%（3672名）参与者死亡。通用模型总体表现良好（c指数：0.82，95%置信区间0.80 - 0.84；Brier分数：0.036，95%置信区间0.032 - 0.040），但在各亚组中的表现有所不同。在虚弱个体（c指数：0.73，95%置信区间0.71 - 0.75；Brier分数：0.12，95%置信区间0.11 - 0.13）和患有多种慢性病的个体（c指数：0.76，95%置信区间0.75 - 0.78；Brier分数：0.08，95%置信区间0.07 - 0.08）中表现较低，这些组中的风险被低估。纳入亚组变量和开发风险分层模型均未显著提高性能。
性能的重要变异性，尤其是在弱势群体中，凸显了一刀切方法的局限性，并强调需要更精细的预测模型，该模型应考虑亚人群特定特征以增强死亡率风险预测。
