MULTIPREVENT: Integrated screening for smoking-related multimorbidity using low-dose chest computed tomography

Area of Science:

• Public Health
• Epidemiology
• Biomedical Informatics

Background:

• Tobacco consumption is a major risk factor for lung cancer and other non-communicable diseases (NCDs).
• Individual genetic predispositions exacerbate age-dependent risks for NCDs.
• Comprehensive health assessment is needed for effective risk prediction of multimorbidity.

Purpose of the Study:

• To validate low-dose computed tomography (LDCT) combined with biomarkers, functional tests, and genomic profiling for comprehensive health assessment.
• To develop AI-based risk prediction models for multimorbidity in adults.
• To establish data-driven, AI-supported prevention strategies for reducing morbidity and mortality.

Main Methods:

• Prospective epidemiological design with 3000 participants from the MOLTEST-BIS cohort.
• Two follow-up assessments including LDCT, spirometry, blood pressure, anthropometrics, biomarkers, and questionnaires.
• Genetic profiling and integration of clinical, imaging (radiomics), molecular, and genetic data using machine learning.

Main Results:

• The MULTIPREVENT study is expected to yield significant scientific, clinical, and infrastructural data.
• This data will form the basis for future integrated public health prevention initiatives.
• AI-based risk prediction models will be developed.

Conclusions:

• Linking imaging, biochemical markers, genetic susceptibility, and clinical data longitudinally is key.
• AI-supported prevention strategies will target tobacco-exposed adults to reduce morbidity and mortality.
• The project will serve as a model for population-based multimorbidity prevention programs.