Cancer is one of the major global health challenge and tobacco use and alcohol consumption significantly contribute as risk factors, predominantly for stomach, liver, lungs, esophagus and oral cancers. The interplay between lifestyle factors and genetic traits further complicates disease progression, underscoring the need for early detection and precise risk assessment. The presented systematic review explores how artificial intelligence (AI) and deep learning (DL) techniques such as advanced convolutional neural networks (CNNs) and transfer learning are used to improve the diagnosis of cancers linked to smoking and alcohol consumption. It aims to provide a detailed review of existing studies on the detection of these cancers and associated symptoms, highlighting the role of AI-driven methods with high accuracy. The article discusses advancements that focus on Explainable AI (XAI) to enhance transparency, multi-modal data integration for comprehensive diagnostics and strategies to improve model generalizability across diverse populations. The main emphasis of the review article is placed on AI methods used for identifying symptoms and pathophysiological patterns associated with smoking and alcohol induced cancers, as well as techniques for detecting these substances in patient records and imaging data.
Modi et al. (2026) studied this question.