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.
Documented diagnosis of lymphoma, as defined by ICD-10 codes C81-C88 or multiple myeloma, as defined by ICD codes C90.0-C90.02
Dr. David Russler-Germain: Outpatient Lymphoma Clinic
Dr. Michael Slade: Outpatient Multiple Myeloma Clinic
Dr. Dilan Patel: Outpatient Lymphoma Clinic
None
Single group
GPT-QPL
Other interventionA 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).
Changes in communicative self-efficacy
* 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.
Changes in perceived amount of cancer information received as measured by an abbreviated version the EORTC QLQ - INFO25
* 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 - INFO25
* 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 appointments
* 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 tasks
* 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.
Click on the lead sponsor to view all of their trials.
