Digital Reflections: Evaluating the Impact of AI-Enhanced Diaries on Mental Health

Last registered on April 09, 2024


Trial Information

General Information

Digital Reflections: Evaluating the Impact of AI-Enhanced Diaries on Mental Health
Initial registration date
April 03, 2024

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
April 09, 2024, 2:08 PM EDT

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


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

Request Information

Primary Investigator

ETH Zurich

Other Primary Investigator(s)

PI Affiliation
ETH Zurich
PI Affiliation
ETH Zurich
PI Affiliation
University of Zurich

Additional Trial Information

On going
Start date
End date
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
This pilot study examines whether an AI enhanced journaling application can improve mental wellbeing outcomes, in a sample of university students. Participants are recruited from the subset of students who take advantage of the university's counselling service, but enter the surveys and application anonymously. This pilot randomizes intensity of treatment, varying the length of the trial from 2 to 4 weeks. We collect information on the users mental wellbeing through standardised scales and a set of demographics.
External Link(s)

Registration Citation

Ash, Elliott et al. 2024. "Digital Reflections: Evaluating the Impact of AI-Enhanced Diaries on Mental Health." AEA RCT Registry. April 09.
Experimental Details


Subjects are provided with an AI powered diary for self-reflection.
Intervention Start Date
Intervention End Date

Primary Outcomes

Primary Outcomes (end points)
PHQ-9, GAD-7
Primary Outcomes (explanation)
Two mental health scores, based on each questionnaire.

Secondary Outcomes

Secondary Outcomes (end points)
Self-reported effectiveness of the application.
Secondary Outcomes (explanation)
Three outcomes, whether subjects used the app when they needed emotional advice, whether the advice was helpful, and whether they felt better afterwards.

Experimental Design

Experimental Design
To check for preliminary effects of AI journaling, in the pilot we employ a 1x2 between-subjects design. We vary the length of treatment that is endogenous, either 2 weeks or 4 weeks of usage allowed.
Experimental Design Details
Not available
Randomization Method
Performed by Qualtrics
Randomization Unit
Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters
Sample size: planned number of observations
Sample size (or number of clusters) by treatment arms
33% 2 weeks treatment, 66% 4 weeks treatment
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Not performed for the pilot study, given small sample size.

Institutional Review Boards (IRBs)

IRB Name
ETH Zurich Ethics Commission
IRB Approval Date
IRB Approval Number
EK 2023-N-184