1 · Integrative review
Mobile-health technologies for monitoring Alcohol Use Disorder
A comprehensive overview of how mobile health (mHealth) technologies are used to monitor and support people with AUD. The review synthesises evidence from studies using smartphones, breathalyzers and wearable sensors to track alcohol use and related behaviours in near-real time. It highlights that smartphone-based ecological momentary assessment and breathalyzer devices are the most frequently studied technologies, showing promise for improving monitoring and supporting interventions. Evidence varies across device types, and challenges remain around sustained adherence and implementation. The paper also discusses how emerging predictive models using continuous data may help personalise care and optimise treatment outcomes.
Valentina Navarro-Ovando, Sterre van Schie, Imme Garrelfs, Jop Rijksbaron, Cristian Rodriguez Rivero, Ron Mathôt, Glenn Dumont. “Current approaches using remote monitoring technology in alcohol use disorder: an integrative review”. In: Alcohol and Alcoholism 60.4 (2025). Available via PubMed (PMID: 40501058). doi: 10.1093/alcalc/agaf032.
Read here
2 · Conference paper
Predicting AUD treatment outcomes with machine learning
This conference paper explores the feasibility of using breathalyzer-based monitoring systems combined with machine learning to predict treatment outcomes in individuals with AUD. Using data from daily breathalyzer measurements, nearly 80,000 observations from 246 patients, the study tested several predictive models to anticipate treatment dropout and the likelihood of a drinking event within the next week. Complex models, particularly a multilayer Long Short-Term Memory (LSTM) neural network, performed well at predicting drinking events, while ensemble models were more effective for dropout prediction. These early findings support integrating machine learning with objective biosensor data to enhance real-world monitoring.
Valentina Navarro-Ovando, Jop Rijksbaron, Glenn Dumont, Cristian Rodriguez Rivero. “Breathalyzer as a Remote Monitoring and Support System for AUD: Early Findings on Dropout and Relapse Prediction Using Machine Learning”. In: Artificial Intelligence in Healthcare. Second International Conference, AIiH 2025, Cambridge, UK, September 8–10, 2025, Proceedings, Part II. Vol. 16039. Lecture Notes in Computer Science. Springer, 2025, pp. 187–200. doi: 10.1007/978-3-032-00656-1_14.
Read here
