Using Responsible Artificial Intelligence (AI) to Predict Online Therapy Outcome and Engagement

This study is to develop AI-based models for the personalised prediction of treatment engagement and treatment outcomes in patients engaging in digital psychotherapy. A large, real-world dataset of patients in a digital psychotherapy program will be used to train AI algorithms. Responsible AI algorithms will be developed by describing, accounting for, and mitigating bias due to severity of mental disturbances in AI-based models, in addition to considering bias due to other sensitive attributes, such as gender, ethnicity, and socio-demographic status.

Study Overview

• Status: Completed
• Conditions: Mental Disorders; Mental Health Care
• Intervention / Treatment: Other: AI-Based Prediction of Treatment Engagement and Outcomes

Detailed Description

Mental disorders contribute greatly to the global disease burden, but many people do not have access to mental health care. This treatment gap is partly due to structural (e.g., availability) and attitude-related (e.g. fear of stigma) barriers in health care seeking. Digital therapeutics (DTx) in the form of digital mental health interventions or digital psychotherapy may be the solution to this problem. The integration of Information and Communication Technology (ICT) and mental health care has the potential to increase the efficiency of care delivery and enables personalisation of treatments. Artificial Intelligence (AI)-based analysis of large datasets from digital psychotherapy programs may allow developing and validating personalised prediction models. The prediction of individual engagement and the early identification of untoward engagement patterns may improve personalisation of DTx, which could help reduce nonadherence and improve treatment outcome. The personalised prediction of DTx outcomes and engagement patterns may be achieved by implementing AI-based approaches, such as Machine Learning prediction models. Personalised prediction models may lead to a better understanding of who profits most from what kind of DTx in a real-world setting. Taken together, personalisation of DTx treatment outcomes and engagement may i) improve decision making processes in patient-clinician dyads, ii) improve efficiency of digital psychotherapy, iii) reduce suffering of patients, and iv) reduce direct and indirect cost related to mental health care. There is a need to account for potential discrimination due to mental health in AI-based predictions models. Unbiased and non- discriminating AI is often referred to as responsible AI. Accounting for bias in AI-based prediction models based on a specific dataset is especially important in mental health care to prevent acceleration of health discrimination.

This study is to develop AI-based models for the personalised prediction of treatment engagement and treatment outcomes in patients engaging in digital psychotherapy. A large, real-world dataset of patients in a digital psychotherapy program will be used to train AI algorithms. Responsible AI algorithms will be developed by describing, accounting for, and mitigating bias due to severity of mental disturbances in AI-based models, in addition to considering bias due to other sensitive attributes, such as gender, ethnicity, and socio-demographic status. The aim of the proposed project is to estimate AI-based prediction models of treatment engagement and outcomes based on data from the Online Therapy Unit by Prof. Heather Hadjistavropoulos from the University of Regina, Canada. The Online Therapy Unit dataset contains a large amount of data on DTx from people with mental disorders (collected as part of research trials in the Online Therapy Unit from 2013 to 2021) and is derived from the publicly funded, internet-delivered, cognitive behaviour therapy (iCBT) program in Saskatchewan, Canada. In sum, the Online Therapy Unit dataset is highly suitable as a training and test dataset for AI-based prediction models, as it comprises a large number of participants, longitudinal data retrieved from the real world opposed to a clinical trial, and a rich set of predictive features.

• Study Type: Observational
• Enrollment (Actual): 6671

Contacts and Locations

Study Locations

• Switzerland
  • Basel, Switzerland, 4031
    • University Hospital Basel, Department of Psychosomatic Medicine

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

Participants at the publicly funded, internet-delivered, cognitive behaviour therapy (iCBT) program in Saskatchewan, Canada. The program provides symptom screenings and an eight-week transdiagnostic iCBT program called the Wellbeing Course. In Saskatchewan, this transdiagnostic iCBT program has been integrated into the public mental health care, for example by assigning clinicians in community mental health clinics to the Online Therapy Unit and by encouraging therapists to direct patients to this service. Data was collected as part of research trials in the Online Therapy Unit from 2013 to 2021.

Description

Inclusion Criteria:

• Participants that were screened as eligible to take part in a Wellbeing Course trial offered at the Online Therapy Unit between Nov 4 2013 and Dec 21 2021.
• Participants that consented to the use of their data to evaluate and improve iCBT services.
• Accessed Lesson 1 of the course content and completed baseline questionnaires.

Exclusion Criteria:

• Data will only be excluded in case of errors in data collection

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Change in Patient Health Questionnaire 9-item (PHQ9) (percent change)	Change in PHQ9 (percent change) to evaluate symptom improvement vs. no symptom improvement pre- to post-digital psychotherapy intervention. Patient Health Questionnaire (PHQ-9): Total = /27 ; Depression Severity: 0-4 none, 5-9 mild, 10-14 moderate, 15-19 moderately severe, 20-27 severe.	week 1 until week 8
Change in General Anxiety Disorder-7 Questionnaire (GAD7) (percent change)	Change in General Anxiety Disorder-7 Questionnaire (GAD7) to evaluate symptom improvement vs. no symptom improvement pre- to post-digital psychotherapy intervention. Score 0-4: Minimal Anxiety · Score 5-9: Mild Anxiety · Score 10-14: Moderate Anxiety · Score greater than 15: Severe Anxiety.	week 1 until week 8

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of messages sent by client	Patients' engagement with the digital psychotherapy intervention by assessing the number of patient messages	week 1 until week 8
Number of messages received by client	Patients' engagement with the digital psychotherapy intervention by assessing the number of therapist messages	week 1 until week 8
Number of phone calls to physician notes	Patients' engagement with the digital psychotherapy intervention by assessing the number of phone calls	week 1 until week 8
Number of times client logged in	Patients' engagement with the digital psychotherapy intervention by assessing the number of lessons accessed	week 1 until week 8

Collaborators and Investigators

• Sponsor: University Hospital, Basel, Switzerland
• Investigators: Principal Investigator: Gunther Meinlschmidt, Prof., University Hospital Basel, Department of Psychosomatic Medicine

Publications and helpful links

General Publications

• Roemmel N, Bahmane S, Hadjistavropoulos HD, Nugent M, Lieb R, Meinlschmidt G. Prediction of treatment outcome in patients receiving internet-delivered cognitive behavioural therapy for depressive and anxiety symptoms: a machine learning analysis of data from a healthcare-embedded longitudinal study. BMJ Open. 2025 Sep 3;15(9):e097651. doi: 10.1136/bmjopen-2024-097651.

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2023
• Primary Completion (Actual): December 6, 2024
• Study Completion (Actual): September 3, 2025

Study Registration Dates

• First Submitted: February 24, 2023
• First Submitted That Met QC Criteria: February 24, 2023
• First Posted (Actual): March 7, 2023

Study Record Updates

• Last Update Posted (Estimated): November 18, 2025
• Last Update Submitted That Met QC Criteria: November 14, 2025
• Last Verified: November 1, 2025

More Information

Terms related to this study

• Keywords: Depressive symptoms; Anxiety symptoms; Artificial Intelligence (AI); Bias; Digital Therapeutics (DTx); Internet-delivered, Cognitive Behaviour Therapy (iCBT); Information and Communication Technology (ICT); Explainable Artificial Intelligence (XAI); Digital psychotherapy; Personalised prediction models; AI-based prediction models; Online Therapy Unit; Wellbeing Course
• Additional Relevant MeSH Terms: Behavioral Symptoms; Behavior; Anxiety Disorders; Depression; Mental Disorders; Health Services Administration; Health Care Quality, Access, and Evaluation; Diagnosis; Health Care Evaluation Mechanisms; Quality of Health Care; Outcome Assessment, Health Care; Outcome and Process Assessment, Health Care; Prognosis; Treatment Outcome
• Other Study ID Numbers: 2022-02263; th23Meinlschmidt

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No