JCARM Journal of Contemporary Academic Research and Methodologies JCARM 3139-7247 Ivory and Finch Publishers 10.5281/zenodo.23280595 JCARM_SEP_26_174 Review Article Artificial Intelligence–Driven Meta-Analysis of Radiation Exposure and Cancer Risk: A Medical Physics Perspective PYELSHAK YUSUF Department of Health Information Management, School of Health Information Management. Plateau state College of Health Information Management. pyelshaky2014@gmail.com Yakubu Ngwan Bala Department of Public Health, School of Environmental Health. Plateau state College of Health Information Management. E.J. Azi Department of Public Health, Faculty of Health Science. Plateau state University Bokkos. Samuel Irimiya Gonam Department of Health Information Management, School of Health Information Management. Plateau state College of Health Information Management Iliya Pam Nathaniel Department of Medical Imaging Science, School of Medical Laboratory, Plateau State college of Health Technology Zawan 10 10 2026 1 8

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.

 Artificial Intelligence Radiation Exposure Cancer Risk Medical Physics Meta-Analysis. 30 09 2026 05 10 2026 Copyright © 2026 by the authors This article is distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. References Airola, K. (2022). Artificial intelligence for radiation meta-analysis: Methods and applications. Journal of Medical Informatics, 15(3), 45–58. Brenner, D. J., & Hall, E. J. (2007). Computed tomography—An increasing source of radiation exposure. New England Journal of Medicine, 357(22), 2277–2284. Hall, E. J., & Giaccia, A. J. (2019). Radiobiology for the radiologist (8th ed.). Wolters Kluwer. International Commission on Radiological Protection (ICRP). (2007). The 2007 recommendations of the ICRP (Publication 103). Preston, D. L., Ron, E., Tokuoka, S., Funamoto, S., Nishi, N., Soda, M., & Kodama, K. (2007). Solid cancer incidence in atomic bomb survivors: 1958–1998. Radiation Research, 168(1), 1–64. United Nations Scientific Committee on the Effects of Atomic Radiation (UNSCEAR). (2020). Sources, effects and risks of ionizing radiation. United Nations. World Health Organization (WHO). (2016). Ionizing radiation, health effects and protective measures. WHO Press.