S79 Exploring the Link Between Indoor Radon Exposure and Pancreatic Cancer Incidence Through AI-Based Analysis

Introduction: Pancreatic cancer (PC) is a highly lethal malignancy, with global cases rising by 145% from 1990 to 2021. Despite medical advances, its 5-year survival rate remains below 35%. Environmental factors like radon, a radioactive gas concentrated indoors, is a confirmed cause for lung cancer. Prior research suggests that radon exposure may also be linked with an increased risk of PC. This study employs artificial intelligence, specifically artificial neural networks, to analyze the potential impact of radon on pancreatic cancer incidence. Methods: Age-standardized PC incidence data (1975 to 2021) from at least 20 U.S. states were obtained from the SEER database. County-level mean radon levels were sourced from the U.S. Environmental Protection Agency map, which classifies counties into 3 radon potential zones: Zone 1 (>150 Bq/m³, high exposure) to Zone 3 (<75 Bq/m³, low exposure). Counties were categorized by radon, and state-level aggregate radon exposure was correlated with PC incidence. Artificial neural networks was used to model PC incidence and project trends under evolving environmental conditions, controlling for confounders such as smoking, socioeconomic status, and healthcare access from the Global Burden of Disease 2021 dataset. Results: Pancreatic cancer (PC) incidence varied geographically, with higher radon levels positively associated (P < 0.001). Regions with high radon had PC rates 1.8 times higher (95% CI: 1.3–2.4, P < 0.001) than areas with low radon. In 2021, New York State predominantly classified as Zone 1, reported a pancreatic cancer (PC) incidence of 3617 (95% CI, 3021–4184). In comparison, Illinois, with a majority of Zone 2 areas, recorded an incidence of 2436 (95% CI, 2058–2837), while Georgia, primarily Zone 3, had an incidence of 1945 (95% CI, 1678–2242) over the same period. Projections indicate a 12% (95% CI: 8%–17%) increase in PC incidence by 2050 due to worsening radon exposure, driven by modern residential architecture and occupant behaviors. Conclusion: This study underscores the potential association of radon on PC incidence. High radon exposure amplifies risk, likely due to the interplay of DNA damage from radon-induced alpha particles. With climate change altering these factors, proactive measures like radon mitigation are essential.

Authors

Publication Details

Journal
The American Journal of Gastroenterology
Published
2025-10-01
DOI
https://doi.org/10.14309/01.ajg.0001126776.88522.d1
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

S79 Exploring the Link Between Indoor Radon Exposure and Pancreatic Cancer Incidence Through AI-Based Analysis

Hira Hanif, Anthony A. Donato, Iman Waheed Khan, Errol J. Philip et al.
The American Journal of Gastroenterology
Radiomics and Machine Learning in Medical Imaging
article

S79 Exploring the Link Between Indoor Radon Exposure and Pancreatic Cancer Incidence Through AI-Based Analysis

Hira Hanif, Anthony A. Donato, Iman Waheed Khan, Errol J. Philip, Muhammad Mueed Khan
article en

Abstract

Introduction: Pancreatic cancer (PC) is a highly lethal malignancy, with global cases rising by 145% from 1990 to 2021. Despite medical advances, its 5-year survival rate remains below 35%. Environmental factors like radon, a radioactive gas concentrated indoors, is a confirmed cause for lung cancer. Prior research suggests that radon exposure may also be linked with an increased risk of PC. This study employs artificial intelligence, specifically artificial neural networks, to analyze the potential impact of radon on pancreatic cancer incidence. Methods: Age-standardized PC incidence data (1975 to 2021) from at least 20 U.S. states were obtained from the SEER database. County-level mean radon levels were sourced from the U.S. Environmental Protection Agency map, which classifies counties into 3 radon potential zones: Zone 1 (>150 Bq/m³, high exposure) to Zone 3 (<75 Bq/m³, low exposure). Counties were categorized by radon, and state-level aggregate radon exposure was correlated with PC incidence. Artificial neural networks was used to model PC incidence and project trends under evolving environmental conditions, controlling for confounders such as smoking, socioeconomic status, and healthcare access from the Global Burden of Disease 2021 dataset. Results: Pancreatic cancer (PC) incidence varied geographically, with higher radon levels positively associated (P < 0.001). Regions with high radon had PC rates 1.8 times higher (95% CI: 1.3–2.4, P < 0.001) than areas with low radon. In 2021, New York State predominantly classified as Zone 1, reported a pancreatic cancer (PC) incidence of 3617 (95% CI, 3021–4184). In comparison, Illinois, with a majority of Zone 2 areas, recorded an incidence of 2436 (95% CI, 2058–2837), while Georgia, primarily Zone 3, had an incidence of 1945 (95% CI, 1678–2242) over the same period. Projections indicate a 12% (95% CI: 8%–17%) increase in PC incidence by 2050 due to worsening radon exposure, driven by modern residential architecture and occupant behaviors. Conclusion: This study underscores the potential association of radon on PC incidence. High radon exposure amplifies risk, likely due to the interplay of DNA damage from radon-induced alpha particles. With climate change altering these factors, proactive measures like radon mitigation are essential.

The American Journal of GastroenterologyVol. 120(10S2)
Openalex Percentile: Top 55%
Radiomics and Machine Learning in Medical Imaging
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.