A latent class model for competing risks

M. Rowley, H. Garmo, M. Vanhemelrijck, W. Wulaningsih, B. Grundmark, B. Zethelius, N. Hammar, G. Walldius, Masato Inoue, L. Holmberg, A. C.C. Coolen

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    Survival data analysis becomes complex when the proportional hazards assumption is violated at population level or when crude hazard rates are no longer estimators of marginal ones. We develop a Bayesian survival analysis method to deal with these situations, on the basis of assuming that the complexities are induced by latent cohort or disease heterogeneity that is not captured by covariates and that proportional hazards hold at the level of individuals. This leads to a description from which risk-specific marginal hazard rates and survival functions are fully accessible, ‘decontaminated’ of the effects of informative censoring, and which includes Cox, random effects and latent class models as special cases. Simulated data confirm that our approach can map a cohort's substructure and remove heterogeneity-induced informative censoring effects. Application to data from the Uppsala Longitudinal Study of Adult Men cohort leads to plausible alternative explanations for previous counter-intuitive inferences on prostate cancer. The importance of managing cardiovascular disease as a comorbidity in women diagnosed with breast cancer is suggested on application to data from the Swedish Apolipoprotein Mortality Risk Study.

    Original languageEnglish
    Pages (from-to)2100-2119
    Number of pages20
    JournalStatistics in Medicine
    Volume36
    Issue number13
    DOIs
    Publication statusPublished - 2017 Jun 15

    Fingerprint

    Latent Class Model
    Competing Risks
    Survival Analysis
    Informative Censoring
    Proportional Hazards
    Bayes Theorem
    Apolipoproteins
    Hazard Rate Function
    Longitudinal Studies
    Comorbidity
    Prostatic Neoplasms
    Prostate Cancer
    Cardiovascular Diseases
    Survival Rate
    Hazard Rate
    Survival Function
    Longitudinal Study
    Survival Data
    Bayesian Analysis
    Substructure

    Keywords

    • competing risks
    • heterogeneity
    • informative censoring
    • survival analysis

    ASJC Scopus subject areas

    • Epidemiology
    • Statistics and Probability

    Cite this

    Rowley, M., Garmo, H., Vanhemelrijck, M., Wulaningsih, W., Grundmark, B., Zethelius, B., ... Coolen, A. C. C. (2017). A latent class model for competing risks. Statistics in Medicine, 36(13), 2100-2119. https://doi.org/10.1002/sim.7246

    A latent class model for competing risks. / Rowley, M.; Garmo, H.; Vanhemelrijck, M.; Wulaningsih, W.; Grundmark, B.; Zethelius, B.; Hammar, N.; Walldius, G.; Inoue, Masato; Holmberg, L.; Coolen, A. C.C.

    In: Statistics in Medicine, Vol. 36, No. 13, 15.06.2017, p. 2100-2119.

    Research output: Contribution to journalArticle

    Rowley, M, Garmo, H, Vanhemelrijck, M, Wulaningsih, W, Grundmark, B, Zethelius, B, Hammar, N, Walldius, G, Inoue, M, Holmberg, L & Coolen, ACC 2017, 'A latent class model for competing risks', Statistics in Medicine, vol. 36, no. 13, pp. 2100-2119. https://doi.org/10.1002/sim.7246
    Rowley M, Garmo H, Vanhemelrijck M, Wulaningsih W, Grundmark B, Zethelius B et al. A latent class model for competing risks. Statistics in Medicine. 2017 Jun 15;36(13):2100-2119. https://doi.org/10.1002/sim.7246
    Rowley, M. ; Garmo, H. ; Vanhemelrijck, M. ; Wulaningsih, W. ; Grundmark, B. ; Zethelius, B. ; Hammar, N. ; Walldius, G. ; Inoue, Masato ; Holmberg, L. ; Coolen, A. C.C. / A latent class model for competing risks. In: Statistics in Medicine. 2017 ; Vol. 36, No. 13. pp. 2100-2119.
    @article{6a9f1d98c4864bcc85cdf96816ba34be,
    title = "A latent class model for competing risks",
    abstract = "Survival data analysis becomes complex when the proportional hazards assumption is violated at population level or when crude hazard rates are no longer estimators of marginal ones. We develop a Bayesian survival analysis method to deal with these situations, on the basis of assuming that the complexities are induced by latent cohort or disease heterogeneity that is not captured by covariates and that proportional hazards hold at the level of individuals. This leads to a description from which risk-specific marginal hazard rates and survival functions are fully accessible, ‘decontaminated’ of the effects of informative censoring, and which includes Cox, random effects and latent class models as special cases. Simulated data confirm that our approach can map a cohort's substructure and remove heterogeneity-induced informative censoring effects. Application to data from the Uppsala Longitudinal Study of Adult Men cohort leads to plausible alternative explanations for previous counter-intuitive inferences on prostate cancer. The importance of managing cardiovascular disease as a comorbidity in women diagnosed with breast cancer is suggested on application to data from the Swedish Apolipoprotein Mortality Risk Study.",
    keywords = "competing risks, heterogeneity, informative censoring, survival analysis",
    author = "M. Rowley and H. Garmo and M. Vanhemelrijck and W. Wulaningsih and B. Grundmark and B. Zethelius and N. Hammar and G. Walldius and Masato Inoue and L. Holmberg and Coolen, {A. C.C.}",
    year = "2017",
    month = "6",
    day = "15",
    doi = "10.1002/sim.7246",
    language = "English",
    volume = "36",
    pages = "2100--2119",
    journal = "Statistics in Medicine",
    issn = "0277-6715",
    publisher = "John Wiley and Sons Ltd",
    number = "13",

    }

    TY - JOUR

    T1 - A latent class model for competing risks

    AU - Rowley, M.

    AU - Garmo, H.

    AU - Vanhemelrijck, M.

    AU - Wulaningsih, W.

    AU - Grundmark, B.

    AU - Zethelius, B.

    AU - Hammar, N.

    AU - Walldius, G.

    AU - Inoue, Masato

    AU - Holmberg, L.

    AU - Coolen, A. C.C.

    PY - 2017/6/15

    Y1 - 2017/6/15

    N2 - Survival data analysis becomes complex when the proportional hazards assumption is violated at population level or when crude hazard rates are no longer estimators of marginal ones. We develop a Bayesian survival analysis method to deal with these situations, on the basis of assuming that the complexities are induced by latent cohort or disease heterogeneity that is not captured by covariates and that proportional hazards hold at the level of individuals. This leads to a description from which risk-specific marginal hazard rates and survival functions are fully accessible, ‘decontaminated’ of the effects of informative censoring, and which includes Cox, random effects and latent class models as special cases. Simulated data confirm that our approach can map a cohort's substructure and remove heterogeneity-induced informative censoring effects. Application to data from the Uppsala Longitudinal Study of Adult Men cohort leads to plausible alternative explanations for previous counter-intuitive inferences on prostate cancer. The importance of managing cardiovascular disease as a comorbidity in women diagnosed with breast cancer is suggested on application to data from the Swedish Apolipoprotein Mortality Risk Study.

    AB - Survival data analysis becomes complex when the proportional hazards assumption is violated at population level or when crude hazard rates are no longer estimators of marginal ones. We develop a Bayesian survival analysis method to deal with these situations, on the basis of assuming that the complexities are induced by latent cohort or disease heterogeneity that is not captured by covariates and that proportional hazards hold at the level of individuals. This leads to a description from which risk-specific marginal hazard rates and survival functions are fully accessible, ‘decontaminated’ of the effects of informative censoring, and which includes Cox, random effects and latent class models as special cases. Simulated data confirm that our approach can map a cohort's substructure and remove heterogeneity-induced informative censoring effects. Application to data from the Uppsala Longitudinal Study of Adult Men cohort leads to plausible alternative explanations for previous counter-intuitive inferences on prostate cancer. The importance of managing cardiovascular disease as a comorbidity in women diagnosed with breast cancer is suggested on application to data from the Swedish Apolipoprotein Mortality Risk Study.

    KW - competing risks

    KW - heterogeneity

    KW - informative censoring

    KW - survival analysis

    UR - http://www.scopus.com/inward/record.url?scp=85013832798&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85013832798&partnerID=8YFLogxK

    U2 - 10.1002/sim.7246

    DO - 10.1002/sim.7246

    M3 - Article

    C2 - 28233395

    AN - SCOPUS:85013832798

    VL - 36

    SP - 2100

    EP - 2119

    JO - Statistics in Medicine

    JF - Statistics in Medicine

    SN - 0277-6715

    IS - 13

    ER -