Abstract / Summary
Radiation exposure has long been recognized as an important environmental and medical factor influencing cancer development. However, estimating the magnitude of cancer risk from radiation remains challenging due to variations in exposure levels, study populations, and measurement techniques. The aim of this study is to synthesize existing scientific evidence on radiation exposure and cancer risk using artificial intelligence-driven meta-analysis. The specific objectives are to: analyze published studies on ionizing radiation and cancer incidence, apply artificial intelligence tools to extract and standardize radiation dose data, and evaluate dose–response relationships between radiation exposure and cancer risk. A systematic review of peer-reviewed literature was conducted using major scientific databases including PubMed, Science Direct, and Web of Science. Selected studies reporting radiation dose and cancer outcomes were analyzed using AI-assisted data extraction and statistical modeling. The results show a clear positive correlation between increasing radiation dose and cancer risk, particularly for leukemia, thyroid cancer, and other solid tumors. AI-based analysis enabled the identification of dose-response patterns across heterogeneous datasets. The findings highlight the importance of integrating medical physics principles, radiation dosimetry, and artificial intelligence techniques to improve cancer risk assessment. This approach provides valuable insights for radiation protection, medical imaging practices, and public health policy development. The study also incorporates environmental radiation exposure to provide a broader assessment of radiation-related cancer risks from both medical and natural sources.