About this trial
This project conducts exploratory work on a HIPAA-compliant, large language model (LLM)-based tool that integrates structured and unstructured oncology electronic health record (EHR) data to automate the development of tailored SCPs, paired with a patient-facing chatbot to answer questions about the SCP. Unlike generic AI documentation tools, this system establishes benchmarks for SCP development and embeds user-centered design (UCD) directly into prompt engineering and model governance workflows.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Adult cancer survivors
Age +18 years,
Speak and understand English
Affiliated with the Huntsman Cancer Institute.
Disqualifiers
Under age 18
Not affiliated with Huntsman Cancer Institute
Unable to speak or understand English
Trial design
Single group
Treatments tested in this trial
SCP Chatbot
Other interventionA secure LLM pipeline with structured and unstructured EHR data to automatically generate Survivorship Care Plans (SCPs) and develop a patient-facing chatbot to support comprehension. The SCP chatbot will leverage GARDE-Chat, an NCI-funded open-source chatbot platform
Treatment groups
Trial outcomes
Primary outcomes
Feasibility: Recruitment Retention
Feasibility of the interactive AI-SCP and chatbot. This outcome measure will report the proportion of subjects who were retained from recruitment.
Secondary outcomes
Acceptability/Usability: System Usability Scale
Acceptability and usability of the interactive AI-SCP and chatbot. This outcome measure will report the mean System Usability Scale (SUS) score. SUS scores range from 0-100, with higher scores indicating better usability and lower scores indicating worse usability.
Other outcomes
Change in PROMIS Anxiety
To assess preliminary patient-level effects of the interactive AI-SCP and chatbot. This outcome measure will report mean change in PROMIS Anxiety T-scores. PROMIS Anxiety 4a - Adult v1.0 Scores range from 40.3 to 81.6, with lower scores indicating less anxiety and higher scores indicating more anxiety.
Change in Cancer Worry Scale
To assess preliminary patient-level effects of the interactive AI-SCP and chatbot. The Cancer Worry Scale (CWS) uses a 4-point Likert scale to measure cancer-related worry. This outcome measure will report the mean change in CWS score. CWS scores range from 8 to 32, with lower scores indicating less worry and higher scores indicating greater worry.
Sponsors and contacts
Click on the lead sponsor to view all of their trials.
University of Utah
Lead sponsor
Huntsman Cancer Institute
Collaborator
This trial is not recruiting at the moment. You can still explore other options: