Synthesizing Risk Factors for Alcohol Use Disorder Using a Large Language Model

Alcohol Use Disorder remains a pervasive public health concern shaped by complex interactions among biological, psychological, and social determinants. Using large language models, this study systematically synthesizes key risk factors for Alcohol Use Disorder from fifty highly cited articles in the Web of Science Core Collection, published between 2021 and 2025. OpenAI’s GPT-4.1 was used to extract and rank determinants based on their association strength. Results highlight fourteen major domains, including hazardous drinking patterns, genetic predisposition, adverse childhood experiences, psychiatric comorbidities, and socioeconomic status, as consistently influential. Validation against expert manual review confirms high reliability for text-based synthesis, while accuracy is limited for interpreting tables and figures. These findings demonstrate the value of an artificial intelligence-driven literature review for informing comprehensive strategies to address the multifactorial nature of Alcohol Use Disorder.