Mental DisorderNCT06813066
Simulating Psychotherapeutic Sessions With Generative Artificial Intelligence
A study testing High Levels of Common Therapeutic Factors, Low Levels of Common Therapeutic Factors and Standard motivational interviewing in people with Mental Disorder, run by University Hospital, Basel, Switzerland at 1 site in Switzerland.
Trial summary
The study assesses the potential of using computational models, specifically large language models, to simulate psychotherapeutic sessions, aiming to improve therapy outcomes and advance therapist training through innovative technology. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Mental Disorder
- What is being tested?
- High Levels of Common Therapeutic Factors, Low Levels of Common Therapeutic Factors and Standard motivational interviewing
- Type of treatment
- Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 520 participants
- Where
- 1 siteSwitzerland
- Study dates
- 1 Feb 2025to 31 Aug 2025
- Phase
- Interventional
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Simulation of psychotherapy sessions of conversations between an adult person presenting with a mental or behavioral health problem and a psychotherapist using large language models and 8 real-world transcripts
Who cannot join
- Simulation protocols with severe simulation errors
Trial locations and contacts
1 site in 1 country.
About this study
Official title: Simulating Psychotherapeutic Sessions With Generative Artificial Intelligence: A Proof-of-Concept Study of In Silico Psychotherapy Research
The study assesses the potential of using computational models, specifically large language models, to simulate psychotherapeutic sessions, aiming to improve therapy outcomes and advance therapist training through innovative technology.
Read the detailed description
Health research has evolved significantly, increasingly incorporating computational models that improve our understanding and effectiveness of medical interventions. This shift from traditional to computational methods represents a major advancement in medical research, offering a more sustainable and innovative approach for conceptual advances and therapeutic discovery. In silico models, based on scientific simulation, use computational algorithms to mimic real-world systems or processes. This virtual environment allows researchers to explore phenomena impractical, unethical, dangerous, expensive, or impossible to study otherwise.
Psychotherapy is widely acknowledged as a primary treatment for a variety of mental health conditions, from depression and anxiety to personality disorders, offering significant pathways to recovery and improved quality of life. Yet current methods have shown limited effectiveness, prompting a need for innovative research approaches. In silico psychotherapy research leverages computational simulations, large language models (LLMs), and generative artificial intelligence to explore and refine psychotherapeutic interventions. By simulating human-like conversations, this approach provides insights into therapy dynamics and holds promise for revolutionizing therapist training and expanding treatment techniques.
This study aims to establish a proof-of-concept for simulating psychotherapeutic sessions using LLMs, focusing specifically on motivational interviewing. It involves the simulation of 512 psychotherapy sessions using LLMs as well as 8 real-world psychotherapy transcripts. By modeling human interactions, the study seeks to enhance healthcare delivery, therapist training, and personalized psychotherapy.
- Conditions
- Mental Disorder
- Being tested
- High Levels of Common Therapeutic Factors, Low Levels of Common Therapeutic Factors, Standard motivational interviewing
- Keywords
- In silico Psychotherapy, Artificial intelligence (AI) applications, Motivational Interviewing
- Medical subject headings
- Mental Disorders
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
High Levels of Common Therapeutic FactorsBehavioural
The therapist large language model (LLM) is designed to show high levels of empathy, warmth, and genuineness. This setup aims to create a supportive and trusting therapeutic environment to improve patient engagement. High levels of these positive factors are linked to better psychotherapy outcomes and a stronger therapist-patient relationship.
Low Levels of Common Therapeutic FactorsBehavioural
The therapist LLM for this group is designed to show low levels of empathy, warmth, and genuineness. This setup aims to examine how a less supportive and empathetic therapist affects psychotherapy sessions. Lower levels of these positive behaviors can lead to reduced patient engagement and a weaker therapist-patient relationship, potentially hindering therapy outcomes.
Standard motivational interviewingBehavioural
Motivational interviewing techniques as applied during the sessions on which the transcripts are based.
| Study group | Role | What they receive |
|---|---|---|
| High Levels of Common Therapeutic Factors | Experimental | In this group, the patient-large language model (LLM) interacted with a therapist-LLM prompted to exhibit high levels of positive common factors. Receives: Behavioral: High Levels of Common Therapeutic Factors |
| Low Levels of Common Therapeutic Factors | Experimental | In this group, the patient-large language model (LLM) interacted with a therapist-LLM prompted to exhibit low levels of positive common factors. Receives: Behavioral: Low Levels of Common Therapeutic Factors |
| Transcripts of real intervention sessions | Other | This group consists of published transcripts of real intervention sessions, in which motivational interview techniques have been applied. Receives: Behavioral: Standard motivational interviewing |
What is being measured
The primary outcome is the main question the study is designed to answer.
Simulation's Accuracy in generating Psychotherapeutic Dialogues
Assessment of the simulation's ability to accurately produce psychotherapeutic dialogues that adhere to the principles and techniques of motivational interviewing (MI), as determined by the average global scores of the Motivational Interviewing Treatment Integrity (MITI) code 4.2. The MITI code 4.2 includes various subscales, such as empathy and MI spirit, each scored on a scale from 1 to 5, with lower scores suggesting a need for improvement in MI delivery, while higher scores reflect stronger therapeutic skills and better patient outcomes.
Measured: 12 months
Secondary outcomes (9)
Number of Errors/Deviations
The number of errors or deviations from expected psychotherapeutic practices is counted, providing a quantitative measure of simulation quality. This measure also serves as exclusion criteria from any other assessment.
Measured: 12 months
Metric of Verbal Content (Therapist)
Assessment of the text metrics of the therapist, based on the number of sentences, words, syllables, characters, and lexical diversity.
Measured: 12 months
Metric of Verbal Content (Patient)
Assessment of the text metrics of the patient, based on the number of sentences, words, syllables, characters, and lexical diversity.
Measured: 12 months
Turn-takings
Assessment of the turn-takings, based on the number of exchanges between the therapist and patient within a session, indicating the dynamic interaction flow.
Measured: 12 months
Improvement of Patient
Improvement of the patient is evaluated using an an observer-rated, circularly framed version of the Importance and Confidence Rulers, measuring the simulated patient's psychotherapeutic progress on a circular scale from 0 to 10. Lower scores indicate lower perceived importance or confidence, while higher scores suggest greater perceived importance or confidence in making the change.
Measured: 12 months
Credibility of Patient Behavior
The credibility of the patient's behavior is estimated using a 0 to 10 scale indicating how likely the evaluator found that the participants are real humans or simulations, offering insight into the perceived authenticity of the simulated interactions. The credibility of the 8 real-world transcripts served as a comparison baseline/benchmark for this evaluation. Lower scores indicate lower authenticity of the patient large-language model's (LLM's) simulated behavior, while higher scores suggest higher authenticity of the patient LLM's simulated behavior.
Measured: 12 months
Credibility of Therapist Behavior
The credibility of the therapist's behavior is estimated using a 0 to 10 scale indicating how likely the evaluator found that the participants are real humans or simulations, offering insight into the perceived authenticity of the simulated interactions. The credibility of the 8 real-world transcripts served as a comparison baseline/benchmark for this evaluation. Lower scores indicate lower authenticity of the therapist large-language model's (LLM's) simulated behavior, while higher scores suggest higher authenticity of the therapist LLM's simulated behavior.
Measured: 12 months
Manipulation Check
The implemented level of psychotherapeutic common factors by the therapist-LLM is approximated using the Therapist Empathy Scale (TES) as rough manipulation checks. The TES rates the therapist's ability to understand and share a patient's feelings on a scale from 1 to 7. Higher scores indicate greater empathy, reflecting a stronger connection and understanding of the patient's emotions, while lower scores suggest less empathy.
Measured: 12 months
Manipulation Check
The implemented level of psychotherapeutic common factors by the therapist-LLM is approximated using the Working Alliance Inventory Short Observer form (WAI-S-O) as rough manipulation checks. The Working Alliance Inventory uses 12 items evaluating the perceived therapeutic alliance between the patient and the therapist on a scale of 1 to 7.
Measured: 12 months
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted6 Feb 2025
- Study start1 Feb 2025
- Primary completion31 Aug 2025
- Study completion31 Aug 2025
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Mental DisorderStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Other
- Allocation
- Non-randomised
- Intervention model
- Parallel groups
- Masking
- Single blind
- Who is masked
- Participant
- Enrolment
- 520 participants (actual)
Sponsor and investigators
- Lead sponsor
- University Hospital, Basel, Switzerland
- Sponsor type
- University, hospital or other
- Collaborators
- University of Trier, RWTH Aachen University, University of Basel
- Responsible party
- Sponsor
- Investigators
- Gunther Meinlschmidt, Prof. Dr., Principal investigator, University Hospital and University of Basel
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT06813066
- Sponsor's protocol ID
- 0000-00000; th24Meinlschmidt
- Status last verified
- May 2026
- First submitted
- 3 Feb 2025
- Last updated
- 22 May 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
Study at a glance
From the registry record, last updated by the sponsor on 22 May 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Simulating Psychotherapeutic Sessions With Generative Artificial Intelligence: A Proof-of-Concept Study of In Silico Psychotherapy Research
- ClinicalTrials.gov ID
- NCT06813066
- Acronym / sponsor ID
- 0000-00000; th24Meinlschmidt
- Conditions
- Mental Disorder
- Keywords
- In silico Psychotherapy, Artificial intelligence (AI) applications, Motivational Interviewing
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 520 participants (actual)
- Lead sponsor
- University Hospital, Basel, SwitzerlandUniversity, hospital or other
- Collaborators
- University of Trier, RWTH Aachen University, University of Basel
- Study start
- 1 Feb 2025 (actual)
- Primary completion
- 31 Aug 2025 (actual)
- Study completion
- 31 Aug 2025 (actual)
- First posted
- 6 Feb 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The study assesses the potential of using computational models, specifically large language models, to simulate psychotherapeutic sessions, aiming to improve therapy outcomes and advance therapist training through innovative technology.
Detailed description
Health research has evolved significantly, increasingly incorporating computational models that improve our understanding and effectiveness of medical interventions. This shift from traditional to computational methods represents a major advancement in medical research, offering a more sustainable and innovative approach for conceptual advances and therapeutic discovery. In silico models, based on scientific simulation, use computational algorithms to mimic real-world systems or processes. This virtual environment allows researchers to explore phenomena impractical, unethical, dangerous, expensive, or impossible to study otherwise.
Psychotherapy is widely acknowledged as a primary treatment for a variety of mental health conditions, from depression and anxiety to personality disorders, offering significant pathways to recovery and improved quality of life. Yet current methods have shown limited effectiveness, prompting a need for innovative research approaches. In silico psychotherapy research leverages computational simulations, large language models (LLMs), and generative artificial intelligence to explore and refine psychotherapeutic interventions. By simulating human-like conversations, this approach provides insights into therapy dynamics and holds promise for revolutionizing therapist training and expanding treatment techniques.
This study aims to establish a proof-of-concept for simulating psychotherapeutic sessions using LLMs, focusing specifically on motivational interviewing. It involves the simulation of 512 psychotherapy sessions using LLMs as well as 8 real-world psychotherapy transcripts. By modeling human interactions, the study seeks to enhance healthcare delivery, therapist training, and personalized psychotherapy.
Study design
- Primary purpose
- Other
- Allocation
- Non-randomised
- Intervention model
- Parallel groups
- Masking
- Single blind (participant)
- Number of arms
- 3
| Arm | Type | Receives |
|---|---|---|
| High Levels of Common Therapeutic Factors | Experimental | Behavioral: High Levels of Common Therapeutic FactorsIn this group, the patient-large language model (LLM) interacted with a therapist-LLM prompted to exhibit high levels of positive common factors. |
| Low Levels of Common Therapeutic Factors | Experimental | Behavioral: Low Levels of Common Therapeutic FactorsIn this group, the patient-large language model (LLM) interacted with a therapist-LLM prompted to exhibit low levels of positive common factors. |
| Transcripts of real intervention sessions | Other | Behavioral: Standard motivational interviewingThis group consists of published transcripts of real intervention sessions, in which motivational interview techniques have been applied. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (1 listed)
- Simulation of psychotherapy sessions of conversations between an adult person presenting with a mental or behavioral health problem and a psychotherapist using large language models and 8 real-world transcripts
Key exclusion criteria (1 listed)
- Simulation protocols with severe simulation errors
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| High Levels of Common Therapeutic FactorsThe therapist large language model (LLM) is designed to show high levels of empathy, warmth, and genuineness. This setup aims to create a supportive and trusting therapeutic environment to improve patient engagement. High levels of these positive factors are linked to better psychotherapy outcomes and a stronger therapist-patient relationship. | Behavioural | High Levels of Common Therapeutic Factors |
| Low Levels of Common Therapeutic FactorsThe therapist LLM for this group is designed to show low levels of empathy, warmth, and genuineness. This setup aims to examine how a less supportive and empathetic therapist affects psychotherapy sessions. Lower levels of these positive behaviors can lead to reduced patient engagement and a weaker therapist-patient relationship, potentially hindering therapy outcomes. | Behavioural | Low Levels of Common Therapeutic Factors |
| Standard motivational interviewingMotivational interviewing techniques as applied during the sessions on which the transcripts are based. | Behavioural | Transcripts of real intervention sessions |
Primary outcome
Simulation's Accuracy in generating Psychotherapeutic Dialogues
Time frame: 12 months
Assessment of the simulation's ability to accurately produce psychotherapeutic dialogues that adhere to the principles and techniques of motivational interviewing (MI), as determined by the average global scores of the Motivational Interviewing Treatment Integrity (MITI) code 4.2. The MITI code 4.2 includes various subscales, such as empathy and MI spirit, each scored on a scale from 1 to 5, with lower scores suggesting a need for improvement in MI delivery, while higher scores reflect stronger therapeutic skills and better patient outcomes.
9 secondary outcomes
Number of Errors/Deviations
Time frame: 12 months
Metric of Verbal Content (Therapist)
Time frame: 12 months
Metric of Verbal Content (Patient)
Time frame: 12 months
Turn-takings
Time frame: 12 months
Improvement of Patient
Time frame: 12 months
Credibility of Patient Behavior
Time frame: 12 months
Credibility of Therapist Behavior
Time frame: 12 months
Manipulation Check
Time frame: 12 months
Manipulation Check
Time frame: 12 months
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 22 May 2026.
Related trials for Mental Disorder
Recruiting
Electroacupuncture for Generalized Anxiety Disorder: Clinical Efficacy and Neuroimaging Mechanisms
Generalized Anxiety Disorder
Not yet recruiting
Virtual Reality to Advance Dementia Care and Quality of Life
Dementia, Agitation
Recruiting
Effects of Connective Tissue Massage Plus Biofeedback for Dyssynergic Defecation
Dyssynergic Defecation
RecruitingObservational study
Development of Magnetic Resonance Imaging Techniques for Studying Mood and Anxiety Disorders
Mood Disorders, Anxiety Disorders
Not yet recruitingObservational study
Phase 1: Thrive Together: A Feasibility and Acceptability Evaluation of Peer Mentoring for High Schoolers With ADHD and Their Caregivers
Attention-Deficit/Hyperactivity Disorder (ADHD)
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Gunther Meinlschmidt, Prof. Dr. principal investigator
University Hospital and University of Basel
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing High Levels of Common Therapeutic Factors, Low Levels of Common Therapeutic Factors and Standard motivational interviewing in people with Mental Disorder, run by University Hospital, Basel, Switzerland at 1 site in Switzerland.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 1 inclusion and 1 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 22 May 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Switzerland. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Simulation's Accuracy in generating Psychotherapeutic Dialogues (time frame: 12 months). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 22 May 2026.