Lung function typically reaches its peak around the age of 25 years and then begins to decline after a period of plateauing. Accelerated decline in lung function can lead to reduced forced expiratory volume in 1 second (FEV1) and forced vital capacity (FVC) later in life. Individuals with below-average lung function trajectories are more likely to suffer from non-communicable diseases, particularly chronic respiratory diseases, and experience earlier mortality. These trajectories are the result of multiple, dynamic, and often cumulative gene-environment (G-E) interactions throughout the life course.
Developing a multimodal model to predict lung function trajectories (e.g., FEV1/FVC decline and FEV1 decline) could allow for tailored preventive measures and have significant public health implications.
Several questions remain unanswered: How can we develop a precise prediction model for lung function trajectories? How can we translate this emerging scientific knowledge into clinical practice?Previous studies have identified lung function trajectories using data-driven approaches (e.g., group-based modeling) or statistical modeling (e.g., mixed models with random effects), focusing primarily on early life factors or genetic influences. In this study, we aim to address these gaps by using a comprehensive set of multimodal data, including sociodemographic information, early life factors, anthropometric parameters, physical examination results, genomic data, and proteomic data, to develop a robust prediction model for lung function trajectories and explore its clinical implications in general population
