A Semiparametric Mixture Cure Rate Model for Tuberculosis Data

  • B Vijai Research Scholar, Assistant Professor, Department of Statistics, Dharmamurthi Rao Bahadur Calavala Cunnan Chetty’s Hindu College, Chennai, India.
  • PR Jayashree Associate Professor, Department of Statistics, Presidency College, Chennai, India.
  • C Ponnuraja Scientist F, Head, Department of Statistics, NIRT, ICMR, Chennai, India.
Keywords: Cox Proportional Hazards Model, Semiparametric Mixture Cure Model, Promotion Time Cure Model, R Package


Introduction: One of the essential questions in health research is a
patient’s survival. The two primary families of the cure models are the
mixture cure model and the promotion time cure model. A mixture
cure model is a type of survival theory that considers that there are
both susceptible and non-susceptible people in the population under
study, but they will never be exposed to the relevant event.
Methods: A total of 1236 patients with pulmonary tuberculosis were
included in this work, and time to sputum culture conversion was
the event of interest. A major comparison was done between the
failure time distribution and cure probability models for treatment,
gender, weight, drug susceptibility test, and age between adjusted and
unadjusted versions. The R studio version 1.1.447 statistical software
was used for all kinds of statistical analyses.
Results: Models with two different aspects were compared. The
outcomes of Mixture Cure Models (MCM) and Promotion Time Cure
Models (PTCM) were significant, as expected. Estimates for the cure
probability model perform better under MCM than those for the failure
time distribution model. The MCM’s performance has a significant
impact on how well the cure fraction is estimated. It additionally
supports determining the variables that influence the time to sputum
Conclusions: Only the MCM model can distinguish between a treatment’s
impact on an event’s timing and occurrence. It was seen that firstly, the
results of the cure probability model appeared differently in relation
to those of the pure MCM’s failure time distribution model; secondly,
the results of the comparison between MCMs and PTCMs are more

How to cite this article:
Vijai B, Jayashree PR, Ponnuraja C. A
Semiparametric Mixture Cure Rate Model for
Tuberculosis Data. Chettinad Health City Med J.

DOI: https://doi.org/10.24321/2278.2044.202364


Bewick V, Cheek L, Ball J. Statistics review 12: survival analysis. Crit Care. 2004;8(5):389-94. [PubMed] [Google Scholar]

Peng Y. Fitting semiparametric cure models. Comput Stat Data Anal. 2003;41(3-4):481-90.[Google Scholar]

Machin D, Cheung YB, Parma MK. Survival analysis: a practical approach. 2nd ed. Wiltshire: John Wiley; 2005. [Google Scholar]

Othus M, Bansal A, Erba H, Ramsey S. Bias in mean survival from fitting cure models with limited follow-up. Value Health. 2020;23(8):1034-9. [PubMed] [Google Scholar]

Sheng A, Ghosh SK. Effects of proportional hazard assumption on variable selection methods for censored data. Stat Biopharm Res. 2020;12(2):199-209. [PubMed] [Google Scholar]

Yu B, Tiwari RC, Cronin KA, Feuer EJ. Cure fraction estimation from the mixture cure models for grouped survival data. Stat Med. 2004;23(11):1733-47. [PubMed] [Google Scholar]

Santha T, Rehman F, Mitchison DA, Sarma GR, Reetha AM, Prabhaker R; Tuberculosis Research Centre, Indian Council of Medical Research. Split-drug regimens for the treatment of patients with sputum smear-positive pulmonary tuberculosis--a unique approach. Trop Med Int Health. 2004;9(5):551-8. [PubMed] [Google Scholar]

Yamaguchi K. Accelerated failure-time regression models with a regression model of surviving fraction: an application to the analysis of “permanent employment” in Japan. J Am Stat Assoc. 1992;87(418):284-92. [Google Scholar]

Boag JW. Maximum likelihood estimates of the proportion of patients cured by cancer therapy. J R Stat Soc. 1949;11(1):15-53. [Google Scholar]

Berkson J, Gage RP. Survival cure for cancer patients following treatment. J Am Stat Assoc. 1952;47:501-15. [Google Scholar]

Cai C, Zou Y, Peng Y, Zhang J. smcure: an R-Package for estimating semiparametric mixture cure models. Comput Methods Programs Biomed. 2012 Dec;108(3):1255-60. [PubMed] [Google Scholar]

Peng Y, Dear KB, Denham JW. A generalized F mixture model for cure rate estimation. Stat Med. 1998;17(8):813-30. [PubMed] [Google Scholar]

Peng Y, Dear KB. A nonparametric mixture model for cure rate estimation. Biometrics. 2000;56(1):237-43. [PubMed] [Google Scholar]

Zhang J, Peng Y. A new estimation method for the semiparametric accelerated failure time mixture cure model. Stat Med. 2007;26(16):3157-71. [PubMed] [Google Scholar]

Li CS, Taylor JM. A semi-parametric accelerated failure time cure model. Stat Med. 2002;21(21):3235-47. [PubMed] [Google Scholar]

Taylor JM. Semi-parametric estimation in failure time mixture models. Biometrics. 1995;51(3):899-907. [PubMed] [Google Scholar]

Amanpour F, Akbari S, Looha MA, Abdehagh M, Pourhoseingholi MA. Mixture cure model for estimating short-term and long-term colorectal cancer survival. Gastroenterol Hepatol Bed Bench. 2019;12(Suppl1):S37-43. [PubMed] [Google Scholar]