Survival analysis of women diagnosed with breast cancer in Angola

Jaime A. Jerónimo; Dulce Gomes; Patrícia A. Filipe; Jaime A. Jerónimo; Dulce Gomes; Patrícia A. Filipe

doi:10.3934/mbe.2026068

Mathematical Biosciences and Engineering

2026, Volume 23, Issue 7: 1869-1885. doi: 10.3934/mbe.2026068

Previous Article Next Article

Research article Special Issues

Survival analysis of women diagnosed with breast cancer in Angola

1.
Universidade Católica de Angola and Instituto Superior de Administração e Finanças (ISAF), Luanda, Angola
2.
Centro de Investigação em Matemática e Aplicações (CIMA), Instituto de Investigação e Formação Avançada, Universidade de Évora, Évora, Portugal
3.
Departamento de Matemática, Escola de Ciência e Tecnologia, Universidade de Évora, Évora, Portugal
4.
Departamento de Métodos Quantitativos para Gestão e Economia, Iscte Business School and Business Research Unit (BRU-IUL), Iscte-Instituto Universitário de Lisboa, Lisboa, Portugal

Received: 04 March 2026 Revised: 12 May 2026 Accepted: 22 May 2026 Published: 30 June 2026

Breast cancer is the most common cancer among women and represents 24.5% of all cancer cases worldwide. As there are few studies on the subject in Angola, it is particularly interesting to characterize the survival of women diagnosed with breast cancer in that country. The collected data set contains all diagnosed patients followed up at the Angolan Cancer Control Institute (IACC) between 2013 and 2022. However, due to the impact of COVID-19, the data set under analysis consists of the prepandemic period (2013 to 2019). The aim is to study the population diagnosed with cancer in the country, not only descriptively but also to check which factors influence the survival time of patients from diagnosis to death from breast cancer. To this end, various methods are applied to see which best describes the time until the event under study occurs. Namely, this study examines survival analysis models, beginning with the well-known Cox proportional hazards model. It then transitions to parametric models based on exponential and Weibull distributions and finally explores generalizations of these models that offer greater flexibility. To achieve this flexibility in the survival distribution, we adopt the proportional hazards framework proposed by Younes and Lachin but applying a new approach by Royston and Parmar. The results show that the median survival time from breast cancer in the observed women was 560 days. The variables that were revealed to be significant risk factors were age, stage of the disease, and body mass index. According to Akaike's criterion, the flexible proportional hazards model with one knot proved to be the most appropriate model for these data.
- breast cancer,
- parametric models,
- semiparametric models,
- Royston–Parmar models,
- survival analysis
Citation: Jaime A. Jerónimo, Dulce Gomes, Patrícia A. Filipe. Survival analysis of women diagnosed with breast cancer in Angola[J]. Mathematical Biosciences and Engineering, 2026, 23(7): 1869-1885. doi: 10.3934/mbe.2026068

Related Papers:

Abstract

Breast cancer is the most common cancer among women and represents 24.5% of all cancer cases worldwide. As there are few studies on the subject in Angola, it is particularly interesting to characterize the survival of women diagnosed with breast cancer in that country. The collected data set contains all diagnosed patients followed up at the Angolan Cancer Control Institute (IACC) between 2013 and 2022. However, due to the impact of COVID-19, the data set under analysis consists of the prepandemic period (2013 to 2019). The aim is to study the population diagnosed with cancer in the country, not only descriptively but also to check which factors influence the survival time of patients from diagnosis to death from breast cancer. To this end, various methods are applied to see which best describes the time until the event under study occurs. Namely, this study examines survival analysis models, beginning with the well-known Cox proportional hazards model. It then transitions to parametric models based on exponential and Weibull distributions and finally explores generalizations of these models that offer greater flexibility. To achieve this flexibility in the survival distribution, we adopt the proportional hazards framework proposed by Younes and Lachin but applying a new approach by Royston and Parmar. The results show that the median survival time from breast cancer in the observed women was 560 days. The variables that were revealed to be significant risk factors were age, stage of the disease, and body mass index. According to Akaike's criterion, the flexible proportional hazards model with one knot proved to be the most appropriate model for these data.

References

[1]	Global cancer observatory: Cancer today, France: International Agency for Research on Cancer. Available from: https://gco.iarc.who.int/today.
[2]	H. Moet, Message from the WHO regional director for Africa, world cancer day, Botswana, 2024. Available from: https://www.afro.who.int/regional-director/speeches-messages/world-cancer-day-2024.
[3]	H. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, et al., Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA Cancer J. Clin., 71 (2021), 209–249. https://doi.org/10.3322/caac.21660 doi: 10.3322/caac.21660
[4]	D. R. Cox, Regression models and life-tables, J. R. Stat. Soc. B (Methodol.), 34 (1972), 187–202.
[5]	P. Royston, M. K. B. Parmar, Flexible parametric proportional-hazards and proportional-odds models for censored survival data, with application to prognostic modelling and estimation of treatment effects, Stat. Med., 21 (2002), 2175–2197. https://doi.org/10.1002/sim.1203 doi: 10.1002/sim.1203
[6]	J. P. Klein, H. C. Houwelingen, J. G. Ibrahim, T. H. Scheike, Handbook of Survival Analysis, 1$^{st}$ edition, Chapman and Hall/CRC, 2014.
[7]	N. Younes, J. Lachin, Link-based models for survival data with interval and continuous time censoring, Biometrics, 53 (1997), 1199–1211. https://doi.org/10.2307/2533490 doi: 10.2307/2533490
[8]	F. J. Aranda-Ordaz, On two families of transformations to additivity for binary response data, Biometrika, 68 (1981), 357–363. https://doi.org/10.1093/biomet/68.2.357 doi: 10.1093/biomet/68.2.357
[9]	J. O. Fernandes, C. Cardoso-Filho, M. B. Kraft, A. S. Detoni, B. N. Duarte, J. Y. Shinzato, et al., Differences in breast cancer survival and stage by age in off-target screening groups: A population-based retrospective study, AJOG Global Rep., 3 (2023), 100208. https://doi.org/10.1016/j.xagr.2023.100208 doi: 10.1016/j.xagr.2023.100208
[10]	R Core Team, R: A language and environment for statistical computing, 2023. Available from: https://cran.r-project.org.
[11]	Posit team, RStudio: Integrated development environment for R, PBC, Boston, MA, 2025. Available from: http://www.posit.co.
[12]	E. L. Kaplan, P. Meier, Nonparametric estimation from incomplete observations, J. Am. Stat. Assoc., 53 (1958), 457–481. https://doi.org/10.1080/01621459.1958.10501452 doi: 10.1080/01621459.1958.10501452
[13]	N. Mantel, Evaluation of survival data and two new rank order statistics arising in its consideration, Cancer Chemother. Rep., 50 (1966), 163–170.
[14]	D. W. Hosmer, S. Lemeshow, S. May, Applied Survival Analysis: Regression Modeling of Time-to-Event Data, 2$^{nd}$ edition, John Wiley & Sons, Inc., Hoboken, 2008. https://doi.org/10.1002/9780470258019
[15]	C. Jackson, Flexsurv: A platform for parametric survival modeling in R, J. Stat. Software, 70 (2016), 1–33. https://doi.org/10.18637/jss.v070.i08 doi: 10.18637/jss.v070.i08

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)