Bouttell J, Bartler M, Bolton S. Prediction of Relapse Using Digital Technology in People in Recovery From Substance Use Disorders: Early Economic Evaluation With a Case Study of the Subreal App. JMIR Form Res. 2026;10:e87186. doi:10.2196/87186
The study evaluated the potential economic value of the Subreal app, a preclinical digital health technology (Technology Readiness Level 4) designed to support early detection of relapse risks in people with alcohol use disorder (AUD) and opioid use disorder (OUD). The app combines heart rate variability, pupillary light reflex, artificial intelligence–enhanced predictive algorithms, and real-time physiological and behavioral data. The analysis used predictive modeling to estimate costs per relapse and quality-adjusted life years (QALY) for different time points. The analysis used a short-term 1-year horizon, a moderate 5-year horizon, and a long-term 20-year time horizon for people who have achieved abstinence after treatment for alcohol or opioid misuse. In this study, people who had completed treatment and achieved abstinence with AUD and OUD were treated as separate populations. These groups represented 44% and 30%, respectively, of adults in UK substance abuse treatment in 2023–2024. For AUD, the model estimated very small QALY gains and cost savings of £129, £256, and £256 over 1-, 5-, and 20-year horizons, respectively, producing net monetary benefits (NMBs) of £163, £299, and £300. Savings per AUD relapse avoided were £1642 in the first year and higher thereafter. For OUD, QALY gains were also very small, while cost savings were £261, £2747, and £2750, with NMBs of £397, £3529, and £3757. This cost-effectiveness analysis suggests that Subreal has the potential to be cost-effective and cost-saving, with benefits increasing over longer time horizons. However, relapse rates most strongly influenced the results. Future research should focus on evidence comparing the Subreal app with standard care across different populations.