Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May 26;37(1):165.
doi: 10.1007/s40520-025-03063-y.

Heterogeneity in mortality risk prediction: a study of vulnerable adults in the Canadian longitudinal study on aging

Mame Fana Ndiaye  1   2 , Mark R Keezer  1   2   3   4 , Quoc Dinh Nguyen  5   6   7
Affiliations

Heterogeneity in mortality risk prediction: a study of vulnerable adults in the Canadian longitudinal study on aging

Mame Fana Ndiaye et al. Aging Clin Exp Res. .

Abstract

Background: 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.

Methods: 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).

Results: 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.

Conclusion: 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.

Keywords: Aging population; CLSA; Health outcomes; Mortality prediction; Personalized medicine.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval: This study was approved by the Research Ethics Board of the Centre hospitalier de l’Université de Montréal (2024–12123, 23.309– LM). The procedures used in this study adhere to the tenets of the Declaration of Helsinki. Competing interests: The authors declare no competing interests. Disclaimer: The opinions expressed in this manuscript are the author’s own and do not reflect the views of the Canadian Longitudinal Study on Aging.

Figures

Fig. 1
Fig. 1
Analysis workflow
Fig. 2
Fig. 2
C-index (A) and Brier (B) forest plots for the different subgroups. C-index and Brier values for model A across different subgroup categories. Each point represents the c-index value (A) or the Brier value (B) for the corresponding subgroup, with error bars indicating the 95% confidence intervals
Fig. 3
Fig. 3
Calibration plots for model A. Predicted probability of survival represented on the x-axis. Actual outcome represented on the y-axis.(A) Age under 65.(B) Age 65 to 74. (C) Age over 75. (D) < 2 chronic conditions. (E) 2 chronic conditions. (F) ≥ 3 chronic conditions. (G) Non frail.(H) Pre-frail. (I) Frail. (J) No deficiency. (K) 1–2 deficiencies.(L)  ≥ 3 deficiencies.(M) No cognitive impairment.(N) Cognitive impairment
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Yourman LC, Lee SJ, Schonberg MA, Widera EW, Smith AK (2012) Prognostic indices for older adults: A systematic review. JAMA 307(2):182 - PMC - PubMed
    1. Shipe ME, Deppen SA, Farjah F, Grogan EL (2019) Developing prediction models for clinical use using logistic regression: an overview. J Thorac Dis 11(S4):S574–S584 - PMC - PubMed
    1. Piovani D, Sokou R, Tsantes AG, Vitello AS, Bonovas S (2023) Optimizing clinical decision making with decision curve analysis: insights for clinical investigators. Healthcare 11(16):2244 - PMC - PubMed
    1. Barbazzeni B, Friebe M, Prevention (2022) Prediction, Personalization, and Participation as Key Components in Future Health. In: Friebe M, editor. Novel Innovation Design for the Future of Health [Internet]. Cham: Springer International Publishing; [cited 2024 Feb 17]. pp. 147–52. Available from: https://link.springer.com/10.1007/978-3-031-08191-0_14
    1. Nong P, Raj M, Platt J (2022) Integrating predictive models into care: facilitating informed decision-making and communicating equity issues. Am J Manag Care 28(1):18–24 - PubMed

LinkOut - more resources