Skip to content

An AI-Generated, Personalized Question Prompt List Intervention for Patients With Hematologic Cancers

Feasibility and Preliminary Efficacy of GPT-QPL: An AI-Generated, Personalized Question Prompt List Intervention for Patients With Hematologic Cancers

Status
Recruiting
Phases
Unknown
Study type
Interventional
Source
ClinicalTrials.gov
Registry ID
NCT07226934
Enrollment
40
Registered
2025-11-12
Start date
2025-12-26
Completion date
2026-08-31
Last updated
2026-06-01

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Lymphoma, Multiple Myeloma

Keywords

Generative Artificial Intelligence, Healthcare, Cancer, Communication

Brief summary

The goal of this study is to evaluate the feasibility and preliminary efficacy of an artificial intelligence (AI)-generated personalized question prompt list (a list of suggested questions to ask during outpatient appointments) for patients with hematologic cancers. The intervention will involve tailoring a standardized prompt to patients' individual characteristics and concerns. This prompt will then be used to ask Washington University's (WashU) HIPAA compliant ChatGPT to generate personalized question lists for outpatient appointments. Analyses will assess the impact of personalized QPLs on patients' question-asking behavior; communicative self-efficacy; and self-reported amount and satisfaction with information obtained about their disease and its treatment. Sub-analyses will explore patterns in questions generated by WashU ChatGPT. Patients will also provide feedback pertaining to the perceived helpfulness and ease-of-use of WashU-ChatGPT-generated question lists, as well as their attitudes and intentions regarding use of AI chatbots and whether they would engage in pre-appointment AI-assisted question brainstorming independently in the future.

Interventions

OTHERGPT-QPL

A research team member will generate a QPL that is personalized to the patient's demographics (from EHR screening and Baseline Demographic Survey) and concerns (from Distress Thermometer Problem Checklist and Interview).

Sponsors

Washington University School of Medicine
Lead SponsorOTHER

Study design

Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
HEALTH_SERVICES_RESEARCH
Masking
NONE

Eligibility

Sex/Gender
ALL
Age
18 Years to 99 Years
Healthy volunteers
No

Inclusion criteria

Eligibility Criteria as determined by Electronic Health Record (EHR) Screening: * Documented diagnosis of lymphoma, as defined by ICD-10 codes C81-C88 or multiple myeloma, as defined by ICD codes C90.0-C90.02 * Has a scheduled follow-up appointment at a participating outpatient oncology clinic within the next month. Participating clinics include: * Dr. David Russler-Germain: Outpatient Lymphoma Clinic * Dr. Michael Slade: Outpatient Multiple Myeloma Clinic * Dr. Dilan Patel: Outpatient Lymphoma Clinic * Undergoing infusion or injection-based systemic therapy intended to cure or manage the disease, as opposed to regimens delivered solely for palliative purposes, at a frequency of once every 1-4 weeks. * For eligible patients with lymphoma, this includes, but is not limited to, commonly prescribed treatment combinations such as R-CHOP (Rituximab, Cyclophosphamide, Doxorubicin/Hydroxydaunorubicin, Vincristine, and Prednisone) for Non-Hodgkin Lymphoma, or ABVD (Adriamycin/Doxorubicin, Bleomycin, Vinblastine, and Dacarbazine) for Hodgkin Lymphoma-both regimens that are frequently administered every three weeks * For patients with multiple myeloma, eligibility will include patients in the "induction" phase of chemotherapy treatment, which frequently requires patients to come in for outpatient appointments once every four weeks as well as patients in a maintenance phase of treatment that otherwise requires them to attend outpatient appointments at a frequency of every one to four weeks * Between the ages of 18-99 at enrollment (Patients older than 99 will be excluded so that the study team is able to elicit questions from WashU ChatGPT using a standardized prompt that describes the patient's age only as specifically as a 10-year decade range (i.e., "I am a patient in my 20's, 30's, 40's, etc. Patients who are 18 or 19 years old will be described in the following manner: "I am a young adult patient in my late teens"). * Able to consent to medical care independently (does not have a legally authorized representative or documented diagnosis of cognitive impairment) Eligibility Criteria as determined by subsequent recruitment phone call or In-person approach after a clinic appointment: * Does not have visual impairments or English literacy limitations that would interfere with ability to engage in an intervention that requires being able to read material on an electronic device and on paper and communicate aloud during appointments with health care providers, based on patient self-report * Able to use email (consent form will be distributed electronically through DocuSign and associated emails), based on successful completion of electronic informed consent

Design outcomes

Primary

MeasureTime frameDescription
Changes in communicative self-efficacyAppointment 1 (pre-intervention) and appointment 2 (post-intervention) (estimated to be 12 weeks)* Communicative self-efficacy is measured by Self-efficacy survey . * Dependent samples t-tests will be used to assess within-subject changes. * The Self-Efficacy survey consists of two scales containing 10 questions each, with answers ranging from 1=not successful to 5=very successful or 1=not confident to 5=very confident. The total score on each scale ranges from 10-50 with a higher score on Scale 1 (the PEPPI-5) representing higher self-efficacy related to communicating with physicians in general and a higher score on Scale 2 (researcher-designed questions based on Social Cognitive Theory) representing higher self-perceived success at communication with the physician during the immediately preceding appointment.

Secondary

MeasureTime frameDescription
Changes in perceived amount of cancer information received as measured by an abbreviated version the EORTC QLQ - INFO25Appointment 1 (pre-intervention) and appointment 2 (post-intervention) (estimated to be 12 weeks)* Dependent samples t-tests will be used to assess within-subject changes. * The abbreviated version of the EORTC QLQ-INFO 25 being used for this outcome consists of three scales containing a total of 13 questions ranging from 1=not at all to 4=very much. Raw scores are converted using linear transformations. The total score range for each scale is 0-100. A higher score on Scale 1 represents a higher perceived degree of information received about cancer diagnosis, a higher score on Scale 2 represents a higher perceived degree of information received about medical tests, and a higher score on Scale 3 represents a higher perceived degree of information received about cancer treatment.
Changes in satisfaction with cancer information received as measured by the EORTC QLQ - INFO25Appointment 1 (pre-intervention) and appointment 2 (post-intervention) (estimated to be 12 weeks)* Dependent samples t-tests will be used to assess within-subject changes. * An additional single item scale from the EORTC QLQ - INFO 25 will be used to measure satisfaction with cancer information received. The answer ranges from 1=not at all to 4=very much. The raw score is converted using the same linear transformation as other EORTC QLQ-INFO 25 scales. The total score range is 0-100, and a higher score represents higher satisfaction with cancer information received.
Changes in the number of questions asked during appointmentsAppointment 1 (pre-intervention) and appointment 2 (post-intervention) (estimated to be 12 weeks)* Number of questions asked is measured by audio recordings of the clinic appointments. * Dependent samples t-tests will be used to assess within-subject changes.
Changes in self-reported degree of intention to use AI chatbots for healthcare tasksAppointment 1 (pre-intervention) and appointment 2 (post-intervention) (estimated to be 12 weeks)* Self-reported degree of intention is measured by one-item AI Chatbot Use survey consisting of a 7-point Likert Scale question asking how frequently participants intend to use AI chatbots for healthcare tasks within the next month. The answer ranges from 1=Never to 7=Several times a day. The total score range is 1-7, and a higher score represents more frequent intended use of AI chatbots for healthcare tasks. * Dependent samples t-tests will be used to assess within-subject changes.

Countries

United States

Contacts

CONTACTJessica Hahne, MA, MPH
hahne.j@wustl.edu314-935-6173
PRINCIPAL_INVESTIGATORJessica Hahne, MA, MPH

Washington University School of Medicine

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Jun 2, 2026