School of Mathematical & Statistical Sciences Faculty Publications
Document Type
Article
Publication Date
10-31-2025
Abstract
Background: Lung and Bronchus cancer is the most fatal type of cancer in the United States. According to the American Cancer Society, there were more than 127,000 deaths from lung cancer in 2023. Lung cancer care cost 23.8 billion dollars in 2020. In Texas, only 22.8% of lung cancer patients survived 5 years or more past diagnosis based on 2012-2018 data.
Aim: This study evaluates the survival length of lung and bronchus cancer patients in Texas using advanced statistical and machine learning methods applied to an 11-year cohort study from Surveillance, Epidemiology, and End Results Program. It also quantifies the causal effect of early (localized) versus late (distant) stage at diagnosis on survival time of those patients. Additionally, it explores the influence of demographic and available clinical factors to assess disparities in survival across different groups.
Methodology: We performed classical survival analyses, followed by causal survival analysis to study the average years lost among different patient groups. Additionally, we performed survival random forest and survival neural network modeling. Finally, we conducted causal inference and causal survival random forest to estimate and predict the average treatment effect of early-stage diagnosis on lung cancer patient survival.
Results: Stage and age are the two most important factors in predicting the survival of patients with lung and bronchus cancer. Lung cancer patients diagnosed with the regional stage have about twice the risk of dying as those in the localized stage at any time, and this risk increases as the stage advances. We also find that the average extended lifetime of the localized stage group was about 4 years compared to survivors diagnosed with the distant stage. It can also extend the probability of survival by up to 50%.
Conclusion: Our study underscores the need for early screening, diagnosis and improving equity in lung cancer patients care, which could lead to improved outcomes and reduced mortality in this high-risk population.
Impact: Understanding lung and bronchus cancer survival using advanced causal inference and predictive modeling techniques, highlights the critical importance of early-stage diagnosis, showing that patients diagnosed at localized stages have a substantially higher survival probability. This research underscores the necessity of promoting early screening and equitable cancer care to improve survival rates and healthcare outcomes for lung and bronchus cancer patients.
Recommended Citation
Mohamed, Z., Fofana, S., Cobos, E., Tripathi, M. K., & Oraby, T. (2025). Causal predictive modeling of survival of lung and bronchus cancer patients diagnosed during 2010-2011 in Texas. PloS one, 20(10), e0333477. https://doi.org/10.1371/journal.pone.0333477
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Publication Title
PLoS One
DOI
10.1371/journal.pone.0333477
Comments
Copyright: © 2025 Mohamed et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.