Step Away: Comparing a Chatbot-delivered Alcohol Intervention With a Smartphone App

Can a Chatbot-delivered Alcohol Intervention Engage Users and Enhance Outcomes Over a Smartphone App? Development and Feasibility Testing of a StepAway 'Bot'

A wide gap exists between the number of people needing alcohol treatment and those actually receiving it. This study builds on a previous one that indicated that smartphone-based intervention can help increase the number of people who receive alcohol intervention services and decrease treatment barriers. Improvements to the previously developed app, Step Away, will be made. In addition, a new method of delivering the Step Away intervention via an online, interactive chatbot, will be developed with the goal of improving engagement and effectiveness. Participants will be recruited and outcomes between the two interventions examined to determine if the Step Away chatbot has enhanced user engagement, intervention fidelity and outcome efficacy in comparison to the Step Away app amongst a group of problem drinkers. Participants will also be interviewed to determine their perceptions of both interventions with a view towards understanding barriers to user engagement.

A wide gap exists between the number of individuals needing alcohol treatment and those actually receiving it. Technologically-delivered interventions may dramatically increase the number of individuals who receive needed alcohol intervention services due to their ability to circumvent treatment barriers. Smartphones are the ideal devices to provide empirically-supported intervention assistance whenever and wherever it is needed. Our research team previously developed and tested a stand-alone, self-administered smartphone-based intervention system for alcohol use disorders that was based on empirically supported face-to-face treatments (the Location-Based Monitoring and Intervention for Alcohol Use Disorders (LBMI-A) system). A revised and improved iPhone-based version, Step Away, was developed. Step Away usage data indicate that user engagement with modules that are not "pushed" to the user is relatively low, which is a problem that many health apps experience. A new method of delivering Step Away through an artificially intelligent (AI) chatbot will be developed that holds potential for providing enhanced user engagement and effectiveness as it can reach out through a text interface to introduce new intervention steps and respond to the user with Step Away's in-the-moment help with having a craving, experiencing distress or needing social support. The first phase of this study will focus on developing a Step Away chatbot and enhance the existing Step Away app's user interface. The second phase will entail a pilot study to determine if the Step Away chatbot has enhanced user engagement, intervention fidelity and outcome efficacy in comparison to the Step Away app amongst a group of problem drinkers. Participants will be interviewed to determine their perceptions of both interventions with a view towards understanding barriers to user engagement. Finally, this project will set the stage for a further, large-scale evaluation of Step Away, the content of which will be determined by the outcome of the pilot study.

Participants randomly assigned to this arm will access the Step Away smartphone-based mobile application immediately upon enrollment.

Participants randomly assigned to this arm will access the Step Away mobile, text-based, interactive AI chatbot immediately upon enrollment.

Participants randomly assigned to this arm will be provided access to the Step Away smartphone-based mobile application three months after enrollment.

The Step Away chatbot utilizes AI technology to provide mobile, web-based, person-centered, behavioral-based interventions and timely support for individuals seeking to reduce their alcohol use. Participants interact with the chatbot through interactive text. The Step Away chatbot is informed by the following theoretical constructs: (1) motivational enhancement; (2) relapse prevention; and (3) community reinforcement. It uses the Relapse Prevention (RP) model, which is informed by cognitive behavioral theory and has evolved to reflect the dynamic, non-linear relationships between contextual triggers and coping, as mediated by motivation, mood, and self-efficacy. It proactively encourages the user to identify and include supportive others in treatment; to identify and plan non-drinking, recreational activities; and to develop other non-drinking lifestyle skills and strategies.

The Step Away app is a smartphone-based mobile intervention system. It is informed by three theoretical constructs that are considered the most important "active ingredients" for person-centered, behavioral-based intervention and treatment in addictions: (1) motivational enhancement; (2) relapse prevention; and (3) community reinforcement. Step Away uses the Relapse Prevention (RP) model, which is informed by cognitive behavioral theory and has evolved to reflect the dynamic, non-linear relationships between contextual triggers and coping, as mediated by motivation, mood, and self-efficacy. Step Away proactively encourages the user to identify and include supportive others in treatment; to identify and plan non-drinking, recreational activities; and to develop other non-drinking lifestyle skills and strategies.

The Timeline Followback (TLFB) will be used to gather information on alcohol and drug use. The TLFB method has demonstrated good test-retest reliability and high correlations with prospective daily recording methods for quantifying alcohol use. In the current study, a 30-day online version will be administered at baseline and the 4 month post-intervention follow-up assessment. Online versions of the TLFB have been shown to have high correlations with phone and in-person interviewer administered versions of the TLFB The TLFB will be used to calculate the following drinking variables: average (mean) drinks per week, days abstinent, and heavy drinking days. Heavy drinking days will be defined as days with 4 or more standard drinks for women and 5 or more standard drinks for men.

The Short Inventory of Problems - Revised (SIP-R) is a self-report inventory of adverse consequences associated with drug and alcohol use. It is comprised of 17 questions scored on a 4-point Likert scale from 1 (never) to 4 (daily or almost daily). Item responses are summed to produce a total score and five subscale scores (physical, intrapersonal, social responsibility, interpersonal, and impulse control). Higher scores indicate more life problems related to alcohol use. In populations of problem drinkers, the SIP-R has demonstrated good concurrent validity and internal consistency. The SIP-R will be administered at baseline and follow-up to examine between group changes over time. Scale ranges from 17 to 68.

The Timeline Followback (TLFB) will be used to gather information on alcohol and drug use. The TLFB method has demonstrated good test-retest reliability and high correlations with prospective daily recording methods for quantifying alcohol use. In the current study, a 30-day online version will be administered at baseline and the 4 month post-intervention follow-up assessment. Online versions of the TLFB have been shown to have high correlations with phone and in-person interviewer administered versions of the TLFB The TLFB will be used to calculate the following drinking variables: average (mean) drinks per week, days abstinent, and heavy drinking days. Heavy drinking days will be defined as days with 4 or more standard drinks for women and 5 or more standard drinks for men.

The Timeline Followback (TLFB) will be used to gather information on alcohol and drug use. The TLFB method has demonstrated good test-retest reliability and high correlations with prospective daily recording methods for quantifying alcohol use. In the current study, a 30-day online version will be administered at baseline and the 4 month post-intervention follow-up assessment. Online versions of the TLFB have been shown to have high correlations with phone and in-person interviewer administered versions of the TLFB The TLFB will be used to calculate the following drinking variables: average (mean) drinks per week, days abstinent, and heavy drinking days. Heavy drinking days will be defined as days with 4 or more standard drinks for women and 5 or more standard drinks for men.

Given that the main underlying theoretical framework of Step Away is motivational enhancement (ME), we want to examine readiness to change as a mediating variable. We will utilize the Readiness to Change Treatment Version (RCQTV) in this study to assess this construct. The RCQTV has been shown to have solid reliability and validity and has been modified for individuals contemplating or engaged in treatment for alcohol problems. Scale ranges from -8 to 8; higher scores represent higher motivation to change.

Intervention utilization data is used to calculate how frequently participants used the app or the chatbot during the study period. Means and standard deviations will be used to calculate this measure. Unit of measure is the number of times a user clicked on the app or the chabot during the study period.

Retrospective qualitative interviews conducted with 10 chatbot and 10 app users to understand how they used technology and their recommendations for improving the experience. Semi-structured interviews were conducted with participants who had completed follow-up assessments. Participants were purposefully selected to maximize variation in the app (n=10) or the chatbot (n=10) usage. Eleven core interview questions were asked of both app and chatbot users, plus an additional chatbot user question about their experience with and impressions of the chatbot's conversational quality. A random number generator was used to select the 5 high users and 5 low users of each intervention. Qualitative analysis software was used to identify themes related to perceived helpfulness, barriers, motivators, and improvements; key themes related to these topics are reported here. No quantitative data were collected during the interviews.

Inclusion Criteria: being 18 years of age or older being a problem drinker, i.e., having a score of 8 or higher for men and 6 or higher for women on the United States Alcohol Use Disorders Identification Test (USAUDIT) drinking 5 or more (for men ages 18-65), or 4 or more (for women and men over age 65), standard drinks on at least one occasion during the last 90 day owning either an iPhone or Android smartphone with an accompanying cellular and data plan U.S. residency able to read and text in English Exclusion Criteria: being more than 30 days abstinent at baseline being in alcohol or drug abuse treatment currently being pregnant or nursing having a moderate to severe level of alcohol use disorder, i.e., having a score of 20 or higher on the USAUDIT unwilling or unable to complete follow-up assessment non-U.S. residency unable to read or text in English

Dulin PL, Gonzalez VM, Campbell K. Results of a pilot test of a self-administered smartphone-based treatment system for alcohol use disorders: usability and early outcomes. Subst Abus. 2014;35(2):168-75. doi: 10.1080/08897077.2013.821437.

Dulin P, Mertz R, Edwards A, King D. Contrasting a Mobile App With a Conversational Chatbot for Reducing Alcohol Consumption: Randomized Controlled Pilot Trial. JMIR Form Res. 2022 May 16;6(5):e33037. doi: 10.2196/33037.