Atreya Naik

Title drafted today and will be submitted by Atreya

Started Nov. 30, 2023

Abstract or project description

Please refer to the shared doc of the final draft of the paper https://docs.google.com/document/d/1LwlDabJnc6vCE90qf8T4qhOhgqyQsciSAC1YmpPoIfI/edit

Abstract: In the United States, chemical pollution, water pollution, and air pollution, all severely undermine marine and human life because inhaling these pollutants can affect vital organs,including the heart, brain, and liver because of their harmful properties. Many prior studies have shown that pollutants can increase the risk of obtaining life-threatening diseases in humans. This study will be performed at a state/regional granularity and will explore if different types of pollutants increase cancer incidence rate. The endeavor of this project is to determine the strength of the correlation between the prevalence of certain types of cancer and environmental factors across specific regions in the United States using the Pearson Correlation Metric as a mathematical tool across three years (2018-2020). Accordingly, we analyzed 36 different types of cancer (e.g. Cervix, Hodgkin Lymphoma, Leukemia) and 12 pollutant metrics (e.g. Ozone, Lead, Total toxic pounds in Majors). To this end, a python script has been developed to clean, pre-process, and analyze the publicly available datasets. The results of this study can contribute to understanding why people living inside certain geographical clusters are more susceptible to certain diseases because of the prevalence of harsh pollutant metrics such as ozone, total water pollutant pounds, and lead in those regions. Additionally, this study can potentially help prevent premature deaths caused by cancer in the United States and help explain why certain clusters in the United States have abnormally high cancer-incidence rates compared to other clusters.