Applying machine learning to construct an association model for lung cancer and environmental hormone high-risk factors and nursing assessment reconstruction.

Abstract

To utilize machine learning techniques to develop an association model linking lung cancer and environmental hormones to enhance the understanding of potential lung cancer risk factors and refine current nursing assessments for lung cancer. This study is exploratory in nature. In Stage 1, data were sourced from a biological database, and machine learning methods, including logistic regression and neural-like networks, were employed to construct an association model. Results indicate significant associations between lung cancer and blood cadmium, urine cadmium, urine cadmium/creatinine, and di(2-ethylhexyl) phthalate. In Stage 2, 128 lung adenocarcinoma patients were recruited through convenience sampling, and the model was validated using a questionnaire assessing daily living habits and exposure to environmental hormones. Analysis reveals correlations between the living habits of patients with lung adenocarcinoma and exposure to blood cadmium, urine cadmium, urine cadmium/creatinine, polyaromatic hydrocarbons, diethyl phthalate, and di(2-ethylhexyl) phthalate. According to the World Health Organization's global statistics, lung cancer claims approximately 1.8 million lives annually, with more than 50% of patients having no history of smoking or non-traditional risk factors. Environmental hormones have garnered significant attention in recent years in pathogen exploration. However, current nursing assessments for lung cancer risk have not incorporated environmental hormone-related factors. This study proposes reconstructing existing lung cancer nursing assessments with a comprehensive evaluation of lung cancer risks. The findings underscore the importance of future studies advocating for public screening of environmental hormone toxins to increase the sample size and validate the model externally. The developed association model lays the groundwork for advancing cancer risk nursing assessments.