New Model for Analyzing Time-Dependent Health Data
Author Information
Author(s): Lee Myeonggyun, Troxel Andrea B., Kwon Sophia, Crowley George, Schwartz Theresa, Zeig-Owens Rachel, Prezant David J., Nolan Anna, Liu Mengling
Primary Institution: New York University Grossman School of Medicine
Hypothesis
How do metabolic syndrome indicators affect the risk of developing lung injury in individuals exposed to particulate matter?
Conclusion
The PLSI-Cox model provides insights into the nonlinear effects of metabolic syndrome indicators on lung injury risk.
Supporting Evidence
- The PLSI-Cox model outperformed classical Cox regression when the true relationship was nonlinear.
- BMI had the largest positive effect on the risk of developing lung injury.
- The model allows for the evaluation of nonlinear effects of covariates.
Takeaway
This study created a new way to look at how different health factors change over time and affect lung health, especially for firefighters exposed to harmful particles.
Methodology
The study used a partial-linear single-index Cox model to analyze the effects of time-dependent metabolic syndrome indicators on lung injury risk.
Potential Biases
Potential bias may arise from the assumption of linear effects for baseline confounders.
Limitations
The model assumes no interactions between time-dependent and time-independent covariates, which may not always hold true.
Participant Demographics
Participants included 5,738 individuals from the WTC-FDNY cohort, with cases more likely to be smokers and have higher exposure to particulate matter.
Statistical Information
P-Value
<0.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website