Testing a Music Listening mHealth Intervention for Stress Reduction in Early Recovery (CalmiFy II)

Summary

The overarching goal of this study is to develop and examine the feasibility of a music-listening intervention that can be deployed in "real time" to regulate emotions and reduce momentary stress among young adults within the first 12 months of recovery from alcohol use disorder. The investigators design the study with two phases to address three aims: Phase I includes the first two aims. For Aim 1, the investigators will conduct formative research with a sample of young adults who have are within 12 months of recovery (N = 30) to identify features of music selections that are most effective in reducing momentary stress in real-world, ambulatory settings. For Aim 2, the investigtors will focus on developing mobile health technology that uses passive sensing and machine learning to automatically predict moments of heightened stress in real-time and suggest specific musical selections when stress is detected. During Phase II (Aim 3), the investigators will test the feasibility of a novel music-listening intervention among a second unique sample of young adults who are within 12 months of recovery from AUD (N = 30). This protocol refers only to Phase II of the larger study.

Conditions

• Alcohol Use Disorder (AUD)

Interventions

BEHAVIORAL

Stress Feedback

The stress feedback draws on a skills-based model of emotion regulation that emphasizes the ability to identify and label emotions, followed by either actively modifying negative emotions or accepting negative emotions when necessary. Participants will receive a prompt to identify their current emotion, followed by questions regarding their current context.

BEHAVIORAL

Music Listening

For the music recommendation component, our system suggests music that is tailored to the individual and the specific context. Because we will use machine learning to predict optimal music features based on physiological, contextual, and musical data, the music items will be naturally suggested based on current emotion and level of intensity as well as the current context and problem type. The music recommendation component is an adaptive playlist that is updated as changes in the user's stress level are detected. To provide personalized music recommendations, we use a supervised learning approach to design an algorithm, referred to as music feature prediction, which predicts optimal values of music features (e.g., energy, valence, instrumentalness, acousticness) that are hypothesized to result in reducing stress. These feature values, referred to as effective music features, are then used to generate a personalized music playlist.

Sponsors & Collaborators

• National Institute on Alcohol Abuse and Alcoholism (NIAAA)

  collaborator NIH

• Washington State University

  lead OTHER

Principal Investigators

• Michael J Cleveland, Ph.D. · Washington State University

Study Design

Allocation

RANDOMIZED

Purpose

TREATMENT

Masking

DOUBLE

Model

SINGLE_GROUP

Eligibility

Min Age

18 Years

Max Age

35 Years

Sex

ALL

Healthy Volunteers

No

Timeline & Regulatory

Start

2026-12-01

Primary Completion

2028-03-01

Completion

2028-03-01