Protocol for a bandit-based response adaptive trial to evaluate the effectiveness of brief self-guided digital interventions for reducing psychological distress in university students: The Vibe Up Study
Kit Huckvale, Leonard Hoon, Eileen Stech, Jill M. Newby, Wu Yi Zheng, Jin Han, Rajesh Vasa, Sunil Gupta, Scott Barnett, Manisha Senadeera, Stuart Cameron, Stefanus Kurniawan, Akash Agarwal, Joost Funke Kupper, Joshua Asbury, David Willie, Alasdair Grant, Henry Cutler, Bonny Parkinson, Antonio Ahumada‐Canale, Joanne R. Beames, Rena Logothetis, Marya Bautista, Jodie Rosenberg, Artur Shvetcov, Thomas P. Quinn, Andrew Mackinnon, Santu Rana, Truyen Tran, Simon Rosenbaum, Kon Mouzakis, Aliza Werner‐Seidler, Alexis E. Whitton, Svetha Venkatesh, Helen ChristensenmedRxiv2022 · DOI
University students face high levels of psychological distress, yet traditional face-to-face interventions are often resource-intensive and difficult to scale. While digital self-guided tools like mindfulness apps show promise, it remains unclear which specific interventions are most effective for different individuals. The "Vibe Up" study addresses this gap by using a novel, AI-driven trial design to rank the effectiveness of brief digital interventions—mindfulness, physical activity, and sleep hygiene—in reducing distress.
The Intervention Arms
The study compares three distinct two-week digital self-guided interventions against an active control group (mood tracking). Each intervention is designed to be brief and accessible, targeting common stressors through various media formats including video, audio, and infographics.
Summary of Mindfulness and Physical Activity modules.
As shown in the intervention summaries, the mindfulness arm includes an introduction and five guided practices delivered via video and audio. The physical activity arm focuses on the benefits of exercise, goal setting, and a 7-minute HIIT workout.
Complementing these, the sleep hygiene arm utilizes infographics to educate students on sleep habits, environment, and daily activities that impact sleep quality, as detailed in the module summary above.
AI-Adaptive Trial Design
Unlike traditional randomized controlled trials (RCTs) that use static allocation, the Vibe Up study employs a contextual multi-arm bandit-based AI-adaptive trial. This methodology involves up to 12 sequential "mini-trials." After each mini-trial, a Gaussian Process regression algorithm updates the allocation ratios based on the performance of each arm.
The "contextual" aspect is crucial: the algorithm considers a participant's baseline distress level (Normal/Mild, Moderate, or Severe). Instead of seeking a single "best" treatment for everyone, the AI identifies which intervention works best for students at specific severity levels. This approach balances "exploitation" (allocating more participants to the currently best-performing arm) with "exploration" (continuing to test other arms to ensure data robustness) using an Upper Confidence Bound (UCB) acquisition function.
Data Collection and Personalization
The primary outcome is the change in the 21-item Depression, Anxiety, and Stress Scale (DASS-21) total score from pre- to post-intervention. In addition to self-reported surveys and Ecological Momentary Assessment (EMA) via the "Vibe Up" app, the study utilizes digital phenotyping. Passive sensor data (accelerometer, gyroscope, and GPS) from participants' smartphones are collected to explore whether behavioral signals can predict clinical outcomes.
Significance and Future Directions
By shifting from a static trial to a learning system, the Vibe Up study aims to reach definitive conclusions more efficiently than traditional methods. A "Value of Information" (VoI) analysis will quantify the economic and societal benefits of this AI approach. If successful, this framework could lead to a self-optimizing public health tool that provides personalized mental health "nudges" at scale, ensuring students receive the most effective intervention for their specific needs.
Summary updated
Abstract
ABSTRACT Introduction Meta-analytic evidence confirms a range of interventions, including mindfulness, physical activity and sleep hygiene, can reduce psychological distress in university students. However, it is unclear which intervention is most effective. Artificial intelligence (AI) driven adaptive trials may be an efficient method to determine what works best and for whom. The primary purpose of the study is to rank the effectiveness of mindfulness, physical activity, sleep hygiene and an active control on reducing distress, using a multi-arm contextual bandit-based AI-adaptive trial method. Furthermore, the study will explore which interventions have the largest effect for students with different levels of baseline distress severity. Methods and analysis The Vibe Up study is a pragmatically-oriented, decentralised AI-adaptive group sequential randomised controlled trial (RCT) comparing the effectiveness of one of three brief, two week digital self-guided interventions (mindfulness, physical activity, or sleep hygiene) or active control (ecological momentary assessment) in reducing self-reported psychological distress in Australian university students. The adaptive trial methodology involves up to 12 sequential mini-trials that allow for the optimisation of allocation ratios. The primary outcome is change in psychological distress (DASS-21 total score) from pre-intervention to post-intervention. Secondary outcomes include change in depression, anxiety, and stress (measured by DASS-21 subscales) from pre-intervention to post-intervention. Planned contrasts will compare the four groups (i.e., the three intervention and control) using self-reported psychological distress at pre-specified time points for interim analyses. The study aims to determine the best performing intervention, as well as ranking of other interventions. Ethics and dissemination Ethical approval was sought and obtained from the UNSW Sydney Human Research Ethics Committee (HREC A, HC200466). A trial protocol adhering to the requirements of the Guideline for Good Clinical Practice [1] was prepared for and approved by the Sponsor, UNSW Sydney (Protocol number: HC200466_CTP). Registration details The trial is registered with the Australian New Zealand Clinical Trials Registry (AC-TRN12621001223820). STRENGTHS AND LIMITATIONS OF THIS STUDY Strengths The study addresses an important clinical question using novel, advanced methods The trial uses short-duration interventions designed to improve coping responses to transient stressors, which addresses the most common needs of university students A value of information analysis is included to compare the value of the new trial methods with traditionalapproaches Digital phenotyping is used to explore smartphone sensor information with clinical outcomes Weaknesses More than 12 mini-trials might be required to determine the ranking for the interventions The interventions may prove to be of the same level of effectiveness for each level of severity Interventions other than those examined in this study, such as CBT, may be more effective and remain untested The methodology assumes that the three digital interventions are configured to deliver similar doses and/or have approximate fidelity with standard methods
BibTeX
@misc{huckvale2022protocol,
author = {Kit Huckvale and Leonard Hoon and Eileen Stech and Jill M. Newby and Wu Yi Zheng and Jin Han and Rajesh Vasa and Sunil Gupta and Scott Barnett and Manisha Senadeera and Stuart Cameron and Stefanus Kurniawan and Akash Agarwal and Joost Funke Kupper and Joshua Asbury and David Willie and Alasdair Grant and Henry Cutler and Bonny Parkinson and Antonio Ahumada‐Canale and Joanne R. Beames and Rena Logothetis and Marya Bautista and Jodie Rosenberg and Artur Shvetcov and Thomas P. Quinn and Andrew Mackinnon and Santu Rana and Truyen Tran and Simon Rosenbaum and Kon Mouzakis and Aliza Werner‐Seidler and Alexis E. Whitton and Svetha Venkatesh and Helen Christensen},
title = {{Protocol for a bandit-based response adaptive trial to evaluate the effectiveness of brief self-guided digital interventions for reducing psychological distress in university students: The Vibe Up Study}},
year = {2022},
doi = {10.1101/2022.12.05.22283129},
howpublished = {medRxiv},
}