Back to History Current Version

Feasibility and effectiveness of an artificial intelligence enhanced application for student wellbeing: pilot trial of the Mind Tutor.

Last registered on February 03, 2022

Pre-Trial

Trial Information

General Information

Title
Feasibility and effectiveness of an artificial intelligence enhanced application for student wellbeing: pilot trial of the Mind Tutor.
RCT ID
AEARCTR-0008933
Initial registration date
February 03, 2022

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
February 03, 2022, 5:56 PM EST

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

Primary Investigator

Affiliation
Oxford Brookes University

Other Primary Investigator(s)

PI Affiliation
Oxford Brookes University
PI Affiliation
Oxford Brookes University

Additional Trial Information

Status
In development
Start date
2022-02-14
End date
2022-04-15
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
The current study aims to test a digital tool – The Mind Tutor - which was developed in conjunction with students and university wellbeing services, in order to provide students with tools to use to manage their wellbeing whist at university. Mind Tutor integrates academic support with wellbeing support based on feedback from students. Mind Tutor uses an artificial intelligence (AI) tool, whereby users interact with a chatbot. Mind Tutor was developed to address five key areas relating to student wellbeing and attainment.
We aim to recruit a minimum of 400 first year undergraduate students into the study
The primary objectives of this study are
a) To determine the impact of the Mind Tutor on subjective wellbeing over a 6 week period in comparison to an inactive control group and;
b) To determine the overall feasibility of delivering a 6 week RCT to assess the effectiveness of the Mind Tutor on subjective wellbeing in university students.
External Link(s)

Registration Citation

Citation
Davies, Emma, Christian Ehrlich and Sarah Hennelly. 2022. "Feasibility and effectiveness of an artificial intelligence enhanced application for student wellbeing: pilot trial of the Mind Tutor. ." AEA RCT Registry. February 03. https://doi.org/10.1257/rct.8933-1.1
Sponsors & Partners

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information
Experimental Details

Interventions

Intervention(s)
Mind Tutor integrates academic support with wellbeing support based on feedback from students. Mind Tutor uses an artificial intelligence (AI) tool, whereby users interact with a chatbot. Mind Tutor was developed to address five key areas relating to student wellbeing and attainment.
Intervention (Hidden)
The Mind Tutor – development and content
The current study aims to test a digital tool – Mind Tutor- which was developed in conjunction with students and university wellbeing services, in order to provide students with tools to use to manage their wellbeing whist at university. MIND TUTOR integrates academic support with wellbeing support based on feedback from students. MIND TUTOR uses an artificial intelligence (AI) tool, whereby users interact with a chatbot.
Mind Tutor was developed to address five key areas relating to student wellbeing and attainment. Data from student wellbeing services, student support, a focus group study and consultation with students in a lecture (see Appendix B for a summary of the data from these areas) were used to select the five areas, which are outlined below:
1. Anxiety - As one of the most common mental health problems faced by students anxiety is important focus for the MIND TUTOR (Thorley, 2017). Research suggests that both generalised anxiety and social anxiety are concerns in the UK student population (Broglia et al., 2021).
2. Mood -Students commonly present to university counselling service with symptoms of depression (Broglia et al., 2021). Mood related topics also relate to coping with feelings of low mood, anger, sadness and worry and enhancing positive emotions (Thorley, 2017).
3. Managing academic work - Academic distress is another common reason that students attend wellbeing services at universities in the UK (McKenzie et al., 2015). Working to deadlines, setting goals relating to assignments and understanding how to get support are key issues in enabling students to manage their academic work.
4. Transitions/ balance - Becoming independent in work and life, balancing work and social life and feeling a sense of autonomy are further challenges that students face (Thorley, 2017). Our data shows that while this transition is an exciting time for students, there are uncertainties that may lead to a loss of confidence or distress. Balance is a key aspect here as shown within our focus groups and lecture survey.
5. Relationships – creating and maintaining connections with others - Connecting with other people is vital. When students move away from home they must develop new friendships as well as stay connected to others at home and elsewhere. As friends may be the first people they turn to when they are feeling worried about studying or their wellbeing, then maintaining new connections is also important. Some students report feeling under pressure to maintain friendships by socialising more than they want to, which may include increased drinking or use of other substances through perceived or actual peer pressure. This is particularly the case for students who feel they have missed out on social activities because of the pandemic. However a fear of missing out (FOMO) has been prevalent in student populations for a number of years (Crawford et al., 2021)
Other topics for consideration in later version of the Mind Tutor included accessing services and signposting, increasing knowledge about mental health, challenging stigma (including self-stigma), dealing with finances.
Within the MIND TUTOR, participants interact with a chatbot (the ‘Mind Tutor’), which identifies which of the five topics they need help with. Once this is identified, the Mind Tutor directs the participant to receive one of five interventions. Participants may then complete a further intervention, or all possible interventions within that topic. They may also go back to the main menu and start looking at another topic. The interventions consist of the following behaviour change techniques and/or tools.
1. Provision of information
Mental Health Literacy (MHL) refers to “knowledge of how to prevent mental disorders; recognition of when a disorder is developing; knowledge of help-seeking options and treatments available; knowledge of effective self-help strategies for milder problems, and first aid skills to support others who are developing a mental disorder or are in a mental health crisis.” (Jorm, 2012). Some studies have shown that students have low levels of MHL overall, and that those who need help the most are the least likely to seek it (Gorczynski et al., 2017). Thus, the MIND TUTOR includes information about the five topics with the aim of increasing knowledge of the issues as a starting point.
2. Goal setting
Given that students need to succeed in their academic goals whilst maintaining high levels of subjective wellbeing, the introduction of goal-setting techniques is of vital importance as goal setting has been shown to improve goal-performance but also can help students maintaining high levels of subjective well-being. Examples of goal-setting techniques the students are introduced are: learning goals (Grant & Dweck, 2003), implementation intentions (Gollwitzer, 1999) as well as exercises based on the goal-striving reasons framework (Ehrlich & Milston, 2022).
3. Mindfulness
Low dose mindfulness has been shown to be effective in improving psychological resilience and coping, and in reducing exam stress in undergraduate populations (Galante et al., 2021; Loucks et al., 2021). Digital mindfulness programmes similarly apparently have potential to target anxiety in students (Lahtinen & Salmivalli, 2020). Mindfulness has also been shown to have potential to improve inter and intra-personal relationships, sleep, self-care, and self-regulation (Jiang et al., 2021; Leyland et al., 2018; Pratscher et al., 2018; Viskovich & De George-Walker, 2019). The integration of digital mindfulness with practical task-orientated goal setting, which also has potential to improve students' wellbeing, might have a greater culminate impact on psychological wellbeing than the two alone.
4. Skills and actions
Taking a small step towards a larger goal, or developing a new coping strategy to deal with feelings of unease can alleviate feelings of worry in the short term. Thus, the MIND TUTOR includes a number of suggested skills and actions for participants to try out. These include writing down feelings, taking a break and going outside, taking exercise and making a study calendar.
5. Reframing
Reframing is a technique to aid with coping in stressful situations. Students may encounter numerous new and unfamiliar stressors when they enter university. It is normal to feel worried when facing a new situation, and recognising that this is a natural reaction may assist in learning to manage stress (Hughes et al., 2011). Thus, the MIND TUTOR includes micro-articles on each topic to highlight that it is normal to feel certain ways.
Intervention Start Date
2022-02-14
Intervention End Date
2022-04-01

Primary Outcomes

Primary Outcomes (end points)
a) Wellbeing as measured by the Short Warwick Edinburgh Mental Wellbeing Scale (SWEMWBS) (Ng Fat et al., 2017).
b) Feasibility of a 6 week RCT
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
a) Life satisfaction, PANAS, Mindfulness, self-efficacy
b) Recruitment, retention, engagement, acceptability
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
This is a two arm randomised controlled trial.
Experimental Design Details
Randomization Method
Randomisation occurs automatically in Qualtrics
Randomization Unit
Individual.
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
400 individual students
Sample size: planned number of observations
400 individual students
Sample size (or number of clusters) by treatment arms
200 in each condition
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
This sample size based on a sample size calculation conducted in GPower for a linear multiple regression analysis to address differences between the intervention and control group on the primary outcome measure with a small to medium effect size ( f2=0.1), 95% power and an alpha level of p=.001. This is for a model to include up to 6 predictors to allow for the time one score on the primary outcome measure, group (intervention/ control) and up to four other co-variates to be entered into the model (gender/institution/degree subject/age). This also allows for incomplete cases to be dropped from the analysis if needed.
IRB

Institutional Review Boards (IRBs)

IRB Name
Oxford Brookes University
IRB Approval Date
2021-09-21
IRB Approval Number
L21256

Post-Trial

Post Trial Information

Study Withdrawal

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Intervention

Is the intervention completed?
Yes
Intervention Completion Date
November 30, 2015, 12:00 +00:00
Data Collection Complete
Yes
Data Collection Completion Date
December 31, 2015, 12:00 +00:00
Final Sample Size: Number of Clusters (Unit of Randomization)
na
Was attrition correlated with treatment status?
No
Final Sample Size: Total Number of Observations
402 participants
Final Sample Size (or Number of Clusters) by Treatment Arms
One too many = 99; Imagery = 97; Drinks meter = 104; Control = 102
Data Publication

Data Publication

Is public data available?
No

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Program Files

Program Files
No
Reports, Papers & Other Materials

Relevant Paper(s)

Abstract
Aim: To assess the effectiveness of two personalised digital interventions (OneTooMany and Drinks Meter) compared to controls.
Method: Randomised controlled trial (AEARCTR-0001082). Volunteers for the study, aged 18-30, were randomly allocated to one of two interventions or one of two control groups and were followed up four weeks later. Primary outcomes were AUDIT-C, drinking harms and preloading.
Drinks Meter provided participants with brief screening and advice for alcohol in addition to normative feedback, information on calories consumed and money spent. OneTooMany presented a series of socially embarrassing scenarios that may occur when drinking, and participants were scored according to if/ how recently they had been experienced.
Results: The study failed to recruit and obtain sufficient follow-up data to reach a prior estimated power for detecting a difference between groups and there was no indication in the analysable sample of 402 subjects of a difference on the primary outcome measures (Drinks Meter; AUDIT-C IRR=0.98 (0.89-1.09); Pre-loading IRR=1.01 (0.95-1.07); Harms IRR=0.97 (0.79-1.20); OneTooMany; AUDIT-C IRR=0.96 (0.86-1.07); Pre-loading IRR=0.99 (0.93-1.06); Harms IRR=1.16 (0.94-1.43).
Conclusion: Further research is needed on the efficacy of such instruments and their ingredients. However, recruitment and follow-up are a challenge.
Citation
Emma L Davies, Adam J Lonsdale, Sarah E Hennelly, Adam R Winstock, David R Foxcroft, Personalized Digital Interventions Showed no Impact on Risky Drinking in Young Adults: A Pilot Randomized Controlled Trial, Alcohol and Alcoholism, Volume 52, Issue 6, November 2017, Pages 671–676, https://doi.org/10.1093/alcalc/agx051

Reports & Other Materials