Medical History TakingCHAT-HXNCT07860762
Augmenting Clinical Workflow With a Structured Chatbot for Patient History Collection and Diagnostic Support
An observational study of Medical History Taking and Artificial Intelligence in Clinical Workflow, run by Massachusetts General Hospital at 1 site in Germany.
Trial summary
Doctors spend much of each visit collecting the patient's medical history, and incomplete histories can delay diagnosis. This study tests an AI chatbot that interviews patients before their appointment and produces a structured summary of their history for the doctor. Read more about this study
- Who is it for?
- Ages 18 years and older, women only
- Conditions the study is for
- Medical History Taking, Artificial Intelligence in Clinical Workflow, Outpatient Clinical Encounter
- What is being tested?
- AI-Based Structured History-Taking Chatbot
- Type of treatment
- Pill or oral medicine
- How many people
- 100 participants
- Where
- 1 siteGermany
- Study dates
- 2 Oct 2026to 1 Oct 2027
- Phase
- Observational
- Are there results?
- Not yet: the study is under way
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
- Women only
- No healthy volunteers
- Adult, Older adult
Study population: Adult women presenting for the first time, or with a new complaint, to the general gynecology outpatient clinic, the gynecology emergency clinic, or as referrals to the gynecology outpatient clinic at the first study site (Leipzig University Hospital, Germany). Patients are recruited consecutively in the clinic waiting area by trained study staff. Additional sites may be added later.
Who may be able to join
- Women 18 years or older
- First presentation or new complaint at the gynecology outpatient clinic (self-presentation, emergency, or referral)
- Sufficient German language skills to complete a structured patient interview independently
- Able to complete study participation without external support
- Written informed consent
Who cannot join
- Acute emergency requiring immediate treatment (for example, impaired consciousness, hemodynamic instability, or acute bleeding requiring immediate care)
- Lack of legal or decisional capacity to consent
- Insufficient language skills
- Severe cognitive, visual, or motor impairment preventing tablet use
- Previous participation in this study
- Refusal or withdrawal of consent
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
Germany1 site
Universität Leipzig
Leipzig, 04103
Bahriye Aktas, +49 341 97 23400, bahriye.aktas@medizin.uni-leipzig.de
About this study
Official title: Prospective Observational Evaluation of a Structured, Agentic AI Chatbot for Pre-Visit Patient History Collection and Diagnostic Support in Outpatient Clinical Workflows
Doctors spend much of each visit collecting the patient's medical history, and incomplete histories can delay diagnosis. This study tests an AI chatbot that interviews patients before their appointment and produces a structured summary of their history for the doctor. Adult patients at the first study site, a university gynecology outpatient clinic in Germany, answer the chatbot's questions on a tablet before the doctor visit. The doctor then takes the history and examines the patient as usual, without seeing the chatbot's output. Only after the doctor has finished planning care does the doctor review the chatbot's summary and rate its usefulness and accuracy. The chatbot does not change patient care. Patients also rate the ease of use and acceptability of the chatbot. The investigators will report how useful doctors find the summaries, how complete and correct the summaries are, and how patients experience the tool.
Read the detailed description
This is a prospective, observational study of an AI-based, structured history-taking tool used before a clinical visit. The tool uses large language models and follows a fixed interview plan with defined topic blocks, such as chief complaint, current history, past conditions, medications, allergies, specialty-specific history, and social and family history. It produces a structured history summary, a list of possible diagnoses, and suggested workup steps. In earlier benchmarking on more than 670 simulated and clinical cases, the system captured most clinically relevant history items and flagged clinically important warning signs.
The study is designed so that the tool does not influence care. Participants give written informed consent, then complete the AI interview on a study tablet using a pseudonymous study ID. Participants enter no name, birth date, or address. Participants then complete a short questionnaire on usability and acceptance. The treating physician takes a full history, examines the patient, and documents a plan without access to the AI output. Only afterward does the physician receive the AI output and complete a structured evaluation of its completeness, correctness, plausibility, and usefulness. No follow-up contact occurs after the visit.
The study is not randomized and has no control arm. The physician's independently obtained history serves as the reference standard. The first site is the Department of Gynecology at Leipzig University Hospital, with about 100 patients and 8 to 15 physicians. Analysis is descriptive, with subgroup comparisons by reason for visit. Additional sites may be added later. The study is a collaboration between Leipzig University Hospital and Massachusetts General Hospital and Harvard Medical School.
- Conditions
- Medical History Taking, Artificial Intelligence in Clinical Workflow, Outpatient Clinical Encounter
- Being tested
- AI-Based Structured History-Taking Chatbot
- Keywords
- Large language model, Agentic AI, Chatbot, Patient History Collection, Pre-visit intake, Clinical decision support, Diagnostic support, Usability, Structured Interview, Digital Health
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI-Based Structured History-Taking ChatbotOther
A large language model-based agentic chatbot that conducts a structured, pre-visit history interview on a study tablet and generates a history summary, differential diagnosis list, and workup suggestions. The output is released to the treating physician only after the physician has completed an independent history, examination, and care plan, and does not influence patient care.
| Study group | Role | What they receive |
|---|---|---|
| Adult Clinic Patients | Adult patients with a first presentation or new complaint at the participating outpatient clinic who consent to complete the AI-based pre-visit history interview and questionnaire. Their physician completes routine care blinded to the AI output, then evaluates the AI-generated summary. Receives: Other: AI-Based Structured History-Taking Chatbot |
What is being measured
The primary outcome is the main question the study is designed to answer.
Proportion of AI history summaries rated useful by the evaluating physician
After completing routine care, the treating physician rates the usefulness of the AI-generated history summary on a 5-point Likert scale (1 = not useful at all, 5 = very useful). The outcome is the proportion of summaries rated 4 or higher, reported with a 95% Wilson confidence interval.
Measured: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Secondary outcomes (9)
Completeness of the AI-generated history
Percentage of items from a standardized history grid that the AI captured correctly, reported overall and by history domain.
Measured: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Correctness of the AI-generated history
Proportion of factually incorrect or missing clinically relevant items in the AI history, per physician review.
Measured: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Plausibility of AI differential diagnoses
Physician rating of plausibility on a 1-5 Likert scale, and concordance of the AI differential with the physician's working diagnosis.
Measured: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Plausibility of AI workup recommendations
Physician rating of the AI's suggested diagnostic workup on a 1-5 Likert scale.
Measured: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Identification of clinically relevant red flags
Proportion of clinically relevant red flags correctly recognized by the AI versus not recognized, per physician review.
Measured: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Patient usability (System Usability Scale)
Patient-completed System Usability Scale, score 0-100, higher scores indicating better usability.
Measured: Same day as the enrollment visit, immediately after the AI interview or after the physician consultation (up to approximately 1 day)
Patient acceptance and willingness to use the tool again
Patient-reported acceptance, comprehensibility, empathy, comfort, trust, and willingness to use again, each on a 1-5 Likert scale.
Measured: Same day as the enrollment visit, immediately after the AI interview or after the physician consultation (up to approximately 1 day)
Duration of the AI interaction
Time in minutes for the patient to complete the AI interview, recorded automatically by the system.
Measured: During the AI interview at the enrollment visit (approximately 15 minutes)
Physician-estimated time savings
Physician's estimate, in minutes, of the time the AI history would save in clinical workflow.
Measured: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted6 Oct 2026
- Study start2 Oct 2026 (estimated)
- Primary completion28 Feb 2027 (estimated)
- Study completion1 Oct 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (1)Papers the sponsor has linked to this study.
- Other trials for Medical History TakingStudies of the same condition, open and under way.
- More trials run by Massachusetts General HospitalThe sponsor's other registered studies.
- 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
- Observational
- Observational model
- Cohort
- Time perspective
- Prospective
- Enrolment
- 100 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Massachusetts General Hospital
- Sponsor type
- University, hospital or other
- Collaborators
- University of Leipzig
- Responsible party
- Principal investigator, Sonu Subudhi, Massachusetts General Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07860762
- Sponsor's protocol ID
- 2026P001764
- Other IDs
- 201/26-ek
- Acronym
- CHAT-HX
- Status last verified
- Sep 2026
- First submitted
- 30 Sep 2026
- Last updated
- 7 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data will not be shared with outside researchers. Participants consented under a German ethics-approved form that permits only fully anonymized, aggregated data to be shared with collaborating study partners for analysis and publication. Data are pseudonymized, are classified as health data under GDPR, and remain on servers of the clinical site. De-identified aggregate results will be reported in publications.
Publications
Steinbuch S, de Vos-Hillebrand L, O'Neill-Dee C, Wu I, Steinbuch H, Kulcsar Z, Ranjan A, Verma A, Landsberg J, Dietrich D, Hardin CC, Jain RK, Subudhi S. Comparative Performance of agentic AI and Physicians in Taking Clinical History across Leading Large Language Models (LLMs). medRxiv [Preprint]. 2026 Jan 25:2026.01.23.26344723. doi: 10.64898/2026.01.23.26344723.
PubMed 41646794
Study at a glance
From the registry record, last updated by the sponsor on 7 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Prospective Observational Evaluation of a Structured, Agentic AI Chatbot for Pre-Visit Patient History Collection and Diagnostic Support in Outpatient Clinical Workflows
- ClinicalTrials.gov ID
- NCT07860762
- Acronym / sponsor ID
- CHAT-HX / 2026P001764
- Conditions
- Medical History Taking, Artificial Intelligence in Clinical Workflow, Outpatient Clinical Encounter
- Keywords
- Large language model, Agentic AI, Chatbot, Patient History Collection, Pre-visit intake, Clinical decision support, Diagnostic support, Usability
- Study type
- Observational
- Recruitment status
- Not yet recruiting
- Enrolment
- 100 participants (estimated)
- Lead sponsor
- Massachusetts General HospitalUniversity, hospital or other
- Collaborators
- University of Leipzig
- Study start
- 2 Oct 2026 (estimated)
- Primary completion
- 28 Feb 2027 (estimated)
- Study completion
- 1 Oct 2027 (estimated)
- First posted
- 6 Oct 2026 (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.
Doctors spend much of each visit collecting the patient's medical history, and incomplete histories can delay diagnosis. This study tests an AI chatbot that interviews patients before their appointment and produces a structured summary of their history for the doctor. Adult patients at the first study site, a university gynecology outpatient clinic in Germany, answer the chatbot's questions on a tablet before the doctor visit. The doctor then takes the history and examines the patient as usual, without seeing the chatbot's output. Only after the doctor has finished planning care does the doctor review the chatbot's summary and rate its usefulness and accuracy. The chatbot does not change patient care. Patients also rate the ease of use and acceptability of the chatbot. The investigators will report how useful doctors find the summaries, how complete and correct the summaries are, and how patients experience the tool.
Detailed description
This is a prospective, observational study of an AI-based, structured history-taking tool used before a clinical visit. The tool uses large language models and follows a fixed interview plan with defined topic blocks, such as chief complaint, current history, past conditions, medications, allergies, specialty-specific history, and social and family history. It produces a structured history summary, a list of possible diagnoses, and suggested workup steps. In earlier benchmarking on more than 670 simulated and clinical cases, the system captured most clinically relevant history items and flagged clinically important warning signs.
The study is designed so that the tool does not influence care. Participants give written informed consent, then complete the AI interview on a study tablet using a pseudonymous study ID. Participants enter no name, birth date, or address. Participants then complete a short questionnaire on usability and acceptance. The treating physician takes a full history, examines the patient, and documents a plan without access to the AI output. Only afterward does the physician receive the AI output and complete a structured evaluation of its completeness, correctness, plausibility, and usefulness. No follow-up contact occurs after the visit.
The study is not randomized and has no control arm. The physician's independently obtained history serves as the reference standard. The first site is the Department of Gynecology at Leipzig University Hospital, with about 100 patients and 8 to 15 physicians. Analysis is descriptive, with subgroup comparisons by reason for visit. Additional sites may be added later. The study is a collaboration between Leipzig University Hospital and Massachusetts General Hospital and Harvard Medical School.
Study design
- Observational model
- Cohort
- Time perspective
- Prospective
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| Adult Clinic Patients | – | Other: AI-Based Structured History-Taking ChatbotAdult patients with a first presentation or new complaint at the participating outpatient clinic who consent to complete the AI-based pre-visit history interview and questionnaire. Their physician completes routine care blinded to the AI output, then evaluates the AI-generated summary. |
Who may qualify
- Ages
- 18 years and older
- Sex
- Female only
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- Adult women presenting for the first time, or with a new complaint, to the general gynecology outpatient clinic, the gynecology emergency clinic, or as referrals to the gynecology outpatient clinic at the first study site (Leipzig University Hospital, Germany). Patients are recruited consecutively in the clinic waiting area by trained study staff. Additional sites may be added later.
Key inclusion criteria (5 listed)
- Women 18 years or older
- First presentation or new complaint at the gynecology outpatient clinic (self-presentation, emergency, or referral)
- Sufficient German language skills to complete a structured patient interview independently
- Able to complete study participation without external support
- Written informed consent
Key exclusion criteria (6 listed)
- Acute emergency requiring immediate treatment (for example, impaired consciousness, hemodynamic instability, or acute bleeding requiring immediate care)
- Lack of legal or decisional capacity to consent
- Insufficient language skills
- Severe cognitive, visual, or motor impairment preventing tablet use
- Previous participation in this study
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 |
|---|---|---|
| AI-Based Structured History-Taking ChatbotA large language model-based agentic chatbot that conducts a structured, pre-visit history interview on a study tablet and generates a history summary, differential diagnosis list, and workup suggestions. The output is released to the treating physician only after the physician has completed an independent history, examination, and care plan, and does not influence patient care. | Other | Adult Clinic Patients |
Primary outcome
Proportion of AI history summaries rated useful by the evaluating physician
Time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
After completing routine care, the treating physician rates the usefulness of the AI-generated history summary on a 5-point Likert scale (1 = not useful at all, 5 = very useful). The outcome is the proportion of summaries rated 4 or higher, reported with a 95% Wilson confidence interval.
9 secondary outcomes
Completeness of the AI-generated history
Time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Correctness of the AI-generated history
Time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Plausibility of AI differential diagnoses
Time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Plausibility of AI workup recommendations
Time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Identification of clinically relevant red flags
Time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Patient usability (System Usability Scale)
Time frame: Same day as the enrollment visit, immediately after the AI interview or after the physician consultation (up to approximately 1 day)
Patient acceptance and willingness to use the tool again
Time frame: Same day as the enrollment visit, immediately after the AI interview or after the physician consultation (up to approximately 1 day)
Duration of the AI interaction
Time frame: During the AI interview at the enrollment visit (approximately 15 minutes)
Physician-estimated time savings
Time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 7 Oct 2026.
- Results publication: PubMed 41646794Steinbuch S, de Vos-Hillebrand L, O'Neill-Dee C, Wu I, Steinbuch H, Kulcsar Z, Ranjan A, Verma A, Landsberg J, Dietrich D, Hardin CC, Jain RK, Subudhi S. Comparative Performance of agentic AI and Physicians in Taking Clinical History across Leading Large Language Models (LLMs). medRxiv [Preprint]. 2026 Jan 25:2026.01.23.26344723. doi: 10.64898/2026.01.23.26344723.
- Individual participant dataSharing planned: No. Individual participant data will not be shared with outside researchers. Participants consented under a German ethics-approved form that permits only fully anonymized, aggregated data to be shared with collaborating study partners for analysis and publication. Data are pseudonymized, are classified as health data under GDPR, and remain on servers of the clinical site. De-identified aggregate results will be reported in publications.
Related trials for Medical History Taking
Not yet recruitingObservational study
AI-CLINIC: A Prospective Multisite Feasibility and Safety Study of AI-Assisted Pre-Consultation History-Taking in Outpatient Cardiology
Symptom Tracking, Cardiology
Enrolling by invitationObservational study
Safety, Feasibility, and Acceptability of the MINERVA Voice Conversational Agent for Emergency Department History-Taking
History Taking, Artificial Intelligence (AI)
RecruitingObservational study
A US Study That Observes How Parkinson's Disease Changes Over Time in Patients Who Still Have Movement Symptoms Despite Taking Parkinson's Medications
Parkinson's Disease
Not yet recruiting
Assessing the Level of Awareness Regarding the Unique Medical Needs of the LGBTQ+ Community Among Emergency Department Physicians, as Well as Their Attitudes Toward Taking Medical Histories, Examining, and Treating Patients From This Community.
LGBTQ
RecruitingObservational study
Using Anonymous Data From A Digital Tool for Medical History-Taking To Improve Healthcare Services
Health Services Research
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.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Medical History Taking and Artificial Intelligence in Clinical Workflow, run by Massachusetts General Hospital at 1 site in Germany.
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 5 inclusion and 6 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: opening soon, as of the sponsor's last update on 7 Oct 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 Germany. 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?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Sonu Subudhi, MBBS, PhD (617-726-8051, ssubudhi@mgh.harvard.edu), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Proportion of AI history summaries rated useful by the evaluating physician (time frame: Same day as the enrollment visit, after routine care is complete (up to approximately 1 day)). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07860762, which also lists 1 linked publication.
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 7 Oct 2026.