Abstract—This paper presents a dual-contribution study: (1) a systematic review of the use of digital technologies for alcohol use disorder monitoring and detection, and (2) a pilot analysis integrating data from commercial wearable devices, specifically Fitbit, with electronic health records in a real-world setting. The systematic review synthesizes evidence from 20 empirical studies across five categories—wearables, mHealth, smartphone applications, virtual reality, and serious games—highlighting the feasibility, limitations, and research gaps of current digital monitoring and detection of Alcohol Use Disorder (AUD). Utilizing accelerometer data from participants in the All of Us program, we analyzed the influence of key features and physical activity on alcohol consumption patterns. An exploratory inference-driven predictive modeling framework was developed to examine associations between wearable activity metrics and alcohol abuse status. Our findings highlight the significant potential of wearable technology in monitoring and addressing alcohol abuse, providing early detection and intervention opportunities. Notably, the pilot analysis identified a counterintuitive positive association between vigorous physical activity and alcohol abuse, suggesting the need for further research and context-sensitive interpretation of behavioral data. Despite the promising results, the study acknowledges limitations related to data representation and volunteer-based data collection, indicating a need for more granular and diverse data in future research. This research underscores the transformative potential of wearable technology and data analytics in improving individual health outcomes and public health initiatives related to alcohol abuse.
 
Keywords—logistic regression, wearable devices, predictive modeling, digital health, passive sensing, machine learning, mHealth, electronic health records, alcohol use disorder


Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).