Overestimation of Cardiovascular Mortality Risk by Kaplan-Meier in Competing Risks Settings: A Web-Based Calculator and NHANES Analysis
DOI:
https://doi.org/10.6000/1929-6029.2025.14.31Keywords:
Competing risks, Cardiovascular mortality, Web-based health analytics, NHANES, Clinical decision supportAbstract
Background: Traditional Kaplan-Meier (KM) event rates are widely used for cardiovascular risk prediction and tend to overestimate absolute event risk for patients by censoring competing events, such as non-cardiovascular death. Competing risks analysis (CRA), which account for such terminal events, offers more accurate estimates. However, its application in a web-based health analytics remains limited.
Methods: Using a simulated cohort (n = 2,500; 100 repetitions) and the 1999–2000 NHANES cohort (n = 2,480) with 2019 National Death Index mortality linkage, the researcher compared KM estimates to CRA’s Cumulative Incidence Function (CIF), implemented via Aalen-Johansen estimators and Fine-Gray subdistribution hazard models. We assessed relative differences (bias) in 5-, 10-, 15-, and 20-year cardiovascular mortality predictions across risk strata. Findings informed a web-based calculator prototype that dynamically estimates age-specific KM and CIF probabilities while highlighting potential misclassification risks.
Results: KM consistently overestimated cardiovascular mortality risk compared to CIF. In the NHANES cohort, KM estimated the 5-year risk to be 5.85% higher than the actual rate (4.37% vs. 4.13%) and 20-year risk by 28.3% (20.02% vs. 15.60%). In the simulated data, KM overestimated the 5-year risk by 7.63% (5.84% vs. 5.42%) and the 20-year risk by 31.17% (21.37% vs. 16.25%). KM-based models tend to misclassify a substantial portion of patients into higher-risk groups compared to CIF-adjusted models.
Conclusion: This study demonstrates that Kaplan-Meier consistently overestimates cardiovascular mortality in comparison to competing risk methods across five time points, through using both simulated and nationally representative data. We quantify this overestimation and provide an online calculator that shows differences by age. Our tool improves the usability and interpretability of competing risks analysis for older adults in digital health settings, in contrast to tools like SCORE2.
References
Putter H, Fiocco M, Geskus RB. Tutorial in biostatistics: Competing risks and multi-state models. Stat Med 2007; 26(11): 2389-430. DOI: https://doi.org/10.1002/sim.2712
World Health Organization. Digital health strategies for cardiovascular disease prevention: a global perspective. Geneva: WHO; 2023 [cited 2023]. Available from: https://www.who.int/publications
Biau DJ, Latouche A, Porcher R. Competing events influence estimated survival probability: when is Kaplan-Meier analysis appropriate? Clin Orthop Relat Res 2007; 462: 229-33. DOI: https://doi.org/10.1097/BLO.0b013e3180986753
Austin PC, Lee DS, Fine JP. Introduction to the analysis of survival data in the presence of competing risks. Circulation 2016; 133(6): 601-9. DOI: https://doi.org/10.1161/CIRCULATIONAHA.115.017719
Brenner H, Arndt V, Gefeller O, Hakulinen T. An alternative approach to age adjustment of cancer survival rates. Eur J Cancer 2004; 40(15): 2317-22. DOI: https://doi.org/10.1016/j.ejca.2004.07.007
Angriman F, Ferreyro BL, Munshi L, et al. Accounting for Competing Events When Evaluating Long-Term Outcomes in Survivors of Critical Illness. Am J Respir Crit Care Med 2023; 208(1): 29-35. DOI: https://doi.org/10.1164/rccm.202305-0790CP
Conen D, Rodondi N, Müller A, et al. Validation of the SCORE2 risk prediction models in the UK Biobank. Eur Heart J 2019; 40(22): 1725-35.
Rajaratnam A, Sennik D, Weng SF. Machine learning for cardiovascular risk prediction in low-resource settings. J Am Heart Assoc 2020; 9(10): e016651.
Tahir IS, Vos AG, Damen JAA, Barth RE, Tempelman HA, Grobbee DE, Scheuermaier K, Venter WDF, Klipstein-Grobusch K. Comparative performance of cardiovascular risk prediction models in people living with HIV. BMJ Open 2023; 13(3): e066571. DOI: https://doi.org/10.4102/sajhivmed.v23i1.1395
Lam CSP, Teng TK, Tay WT. Competing risks in heart failure: a review. Heart Fail Rev 2019; 24(2): 257-68.
Livingstone SJ, Guthrie B, Donnan PT, Thompson A, Morales DR. Effect of competing mortality risks on predictive performance of the QRISK3 cardiovascular risk prediction tool in older people and those with comorbidity: external validation population cohort study. BMJ 2022; 376: e068954.
Mettananda C, Sanjeewa I, Benthota Arachchi T, Wijesooriya A, Chandrasena C, Weerasinghe T, et al. Development and validation of a cardiovascular risk prediction model for Sri Lankans using machine learning. PLoS One 2024; 19(10): e0309843. DOI: https://doi.org/10.1371/journal.pone.0309843
De Vries TI, Visseren FLJ. Cardiovascular risk prediction tools made relevant for GPs and patients. Heart 2020; 106(5): 350-2.
Centers for Disease Control and Prevention, National Center for Health Statistics. NHANES linked mortality files. Atlanta: CDC; 2023 [cited 2023]. Available from: https://www.cdc.gov/nchs/data-linkage/mortality.htm
Wickham H, Bryan J. readxl: Read Excel Files. R package version 1.4.3 2023.
Kaplan EL, Meier P. Nonparametric estimation from incomplete observations. J Am Stat Assoc 1958; 53(282): 457-81. DOI: https://doi.org/10.1080/01621459.1958.10501452
World Health Organization. International statistical classification of diseases and related health problems, 10th revision (ICD-10). Geneva: WHO; 2019. https://www.who.int/standards/classifications/classification-of-diseases
Fine JP, Gray RJ. A proportional hazards model for the subdistribution of a competing risk. J Am Stat Assoc 1999; 94(446): 496-509. DOI: https://doi.org/10.1080/01621459.1999.10474144
Austin PC, Fine JP. Practical recommendations for reporting Fine-Gray model analyses for competing risk data. Stat Med 2017; 36(27): 4391-400. DOI: https://doi.org/10.1002/sim.7501
Hageman SHJ, Dorresteijn JAN, Pennells L, van Smeden M, Bots ML, Di Angelantonio E, Visseren FLJ; on behalf of the UCC-SMART Study Group. The relevance of competing risk adjustment in cardiovascular risk prediction models for clinical practice. Eur J Prev Cardiol 2023; 30(16): 1741-7. DOI: https://doi.org/10.1093/eurjpc/zwad202
Shea S, Blaha MJ. Long term risk prediction for heart failure, disparities, and early prevention. JACC Heart Fail 2022; 10(2): 117-9. DOI: https://doi.org/10.1161/CIRCRESAHA.121.320598
Koller MT, Raatz H, Steyerberg EW, Wolbers M. Competing risks and the clinical community: irrelevance or ignorance? Stat Med 2012; 31(11-12): 1089-1097. DOI: https://doi.org/10.1002/sim.4384
Zhang YL, Liu ZR, Liu Z, Bai Y, Chi H, Chen DP, Zhang YM, Cui ZL. Risk of cardiovascular death in patients with hepatocellular carcinoma based on the Fine-Gray model. Front Cardiovasc Med 2024; 11: 10989395. https://www.wjgnet.com/1948-5204/full/v16/i3/844.htm DOI: https://doi.org/10.4251/wjgo.v16.i3.844
Cooper H, Wells S, Mehta S. Are competing-risk models superior to standard Cox models for predicting cardiovascular risk in older adults? Analysis of a whole-of-country primary prevention cohort aged ≥65 years? Int J Epidemiol 2022; 51(2): 604-14. DOI: https://doi.org/10.1093/ije/dyab116
Van Walraven C, Hawken S. Competing risk bias in Kaplan-Meier risk estimates can be corrected. J Clin Epidemiol 2016; 70: 101-5. DOI: https://doi.org/10.1016/j.jclinepi.2015.08.010
Livingstone SJ, Guthrie B, Donnan PT, et al. Predictive performance of a competing risk cardiovascular prediction tool CRISK compared to QRISK3 in older people and those with comorbidity: population cohort study. BMC Med 2022; 20(1): 152. DOI: https://doi.org/10.1186/s12916-022-02349-6
European Society of Cardiology. SCORE2 risk calculator: estimating 10-year cardiovascular risk. Sophia Antipolis: ESC; 2023 [cited 2023]. Available from: https://www.escardio.org
Hippisley-Cox J, Coupland CAC, Bafadhel M, et al. Development and validation of a new algorithm for improved cardiovascular risk prediction. Nat Med 2024; 30: 1440-7. DOI: https://doi.org/10.1038/s41591-024-02905-y
Khan SS, Matsushita K, Sang Y, et al. Development and validation of the American Heart Association Predicting Risk of Cardiovascular Disease EVENTs (PREVENT) equations. Circulation 2023; 147(6): 456-65. https://www.ahajournals.org/doi/10.1161/CIRCULATIONAHA.123.067626
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Policy for Journals/Articles with Open Access
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
Policy for Journals / Manuscript with Paid Access
Authors who publish with this journal agree to the following terms:
- Publisher retain copyright .
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work .
