{"title":"Personalized prediction of esophageal cancer risk based on virtually generated alcohol data.","authors":"Oswald Ndi Nfor, Pei-Ming Huang, Ming-Fang Wu, Ke-Cheng Chen, Ying-Hsiang Chou, Mong-Wei Lin, Ji-Han Zhong, Shuenn-Wen Kuo, Yu-Kwang Lee, Chih-Hung Hsu, Jang-Ming Lee, Yung-Po Liaw","doi":"10.1186/s12967-025-06383-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Esophageal cancer (EC) presents a significant public health challenge globally, particularly in regions with high alcohol consumption. Its etiology is multifactorial, involving both genetic predispositions and lifestyle factors.</p><p><strong>Methods: </strong>This study aimed to develop a personalized risk prediction model for EC by integrating genetic polymorphisms (rs671 and rs1229984) with virtually generated alcohol consumption data, utilizing advanced artificial intelligence and machine learning techniques. We analyzed data from 86,845 individuals, including 763 diagnosed EC patients, sourced from the Taiwan Biobank. Eight machine learning models were employed: Bayesian Network, Decision Tree, Ensemble, Gradient Boosting, Logistic Regression, LASSO, Random Forest, and Support Vector Machines (SVM). A unique aspect of our approach was the virtual generation of alcohol consumption data, allowing us to evaluate risk profiles under both consuming and non-consuming scenarios.</p><p><strong>Results: </strong>Our analysis revealed that individuals with the genotypes rs671 = AG and rs1229984 = CC exhibited the highest probabilities of developing EC, with values ranging from 0.2041 to 0.9181. Notably, abstaining from alcohol could decrease their risk by approximately 16.29-49.58%. The Ensemble model demonstrated exceptional performance, achieving an area under the curve (AUC) of 0.9577 and a sensitivity of 0.9211. This transition from consumption to abstinence indicated a potential risk reduction of nearly 50% for individuals with high-risk genotypes.</p><p><strong>Conclusion: </strong>Overall, our findings highlight the importance of integrating virtually generated alcohol data for more precise personalized risk assessments for EC.</p>","PeriodicalId":17458,"journal":{"name":"Journal of Translational Medicine","volume":"23 1","pages":"379"},"PeriodicalIF":6.1000,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11951777/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Translational Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12967-025-06383-9","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Esophageal cancer (EC) presents a significant public health challenge globally, particularly in regions with high alcohol consumption. Its etiology is multifactorial, involving both genetic predispositions and lifestyle factors.
Methods: This study aimed to develop a personalized risk prediction model for EC by integrating genetic polymorphisms (rs671 and rs1229984) with virtually generated alcohol consumption data, utilizing advanced artificial intelligence and machine learning techniques. We analyzed data from 86,845 individuals, including 763 diagnosed EC patients, sourced from the Taiwan Biobank. Eight machine learning models were employed: Bayesian Network, Decision Tree, Ensemble, Gradient Boosting, Logistic Regression, LASSO, Random Forest, and Support Vector Machines (SVM). A unique aspect of our approach was the virtual generation of alcohol consumption data, allowing us to evaluate risk profiles under both consuming and non-consuming scenarios.
Results: Our analysis revealed that individuals with the genotypes rs671 = AG and rs1229984 = CC exhibited the highest probabilities of developing EC, with values ranging from 0.2041 to 0.9181. Notably, abstaining from alcohol could decrease their risk by approximately 16.29-49.58%. The Ensemble model demonstrated exceptional performance, achieving an area under the curve (AUC) of 0.9577 and a sensitivity of 0.9211. This transition from consumption to abstinence indicated a potential risk reduction of nearly 50% for individuals with high-risk genotypes.
Conclusion: Overall, our findings highlight the importance of integrating virtually generated alcohol data for more precise personalized risk assessments for EC.
期刊介绍:
The Journal of Translational Medicine is an open-access journal that publishes articles focusing on information derived from human experimentation to enhance communication between basic and clinical science. It covers all areas of translational medicine.