An interventional study of Virtual agent and Human agent in Lung Cancer, sponsored by Duke University. Withdrawn at 1 site in United States. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-05-29.
Sponsored by Duke University · Not applicable, Interventional, and Health services research
The purpose of this study is to compare the use of a virtual agent vs. a human agent when onboarding oncology patients over the telephone to Remote Patient Monitoring (RPM) devices. RPM devices are instruments that a patient can use to measure their own weight and vital signs. Both the virtual and human agents will be available by telephone to instruct the patient on how to use the RPM devices to measure weight, blood pressure, heart rate, temperature, and oxygen saturation. Patients will be randomized to either the virtual or human agent, have assessments of their medical and oncological history, overall well-being, body measurements, and vital signs, and will complete questionnaires about their experience.
7,243 studies on the registry are indexed under Lung Neoplasms; 1,557 are open to participants now.
Browse Lung Neoplasms studies →Duke University is the lead sponsor of 2,025 studies on the registry; 275 are open to participants now.
Of its 194 completed or terminated interventional studies of FDA-regulated products, 159 (82%) have results posted.
Counted across the registry records on this site, refreshed daily.
Planning to return to Duke Cancer Center clinic for three days in a row
Native fluency of spoken English as determined by the investigator
Vitals as collected by the clinic using Duke maintained equipment must be within the ranges specified by the remote patient monitoring devices.
Exclusion Criteria:
Device: Virtual agent
Other: Human agent
The virtual agent is an interactive audio agent that is similar to voice agents that interact with callers in many industries today. They create a very human-like interaction in contrast to more traditional virtual call agents that can only respond to menu options (e.g. "choose "1" for appointments, choose "2" for questions about your bill", etc.). The virtual agent is engineered to accomplish the very specific task of onboarding the patient on use of the RPM devices. It is trained to understand normal human English speech, detects emotional tone and frustration of callers, and is trained to deescalate when appropriate.
The human agent will onboard the patient on use of the RPM devices.
Usability of virtual agent vs. human agent for onboarding patients to RPM devices as assessed by the System Usability Scale (SUS)
The SUS is a questionnaire that assesses perceived usability. It includes 10 five-point items with alternating positive and negative tone. The final score is a number 0-100 with a higher score indicating better usability.
Time frame: Day 1, Day 2, Day 3
Description of the patient experience when using a virtual agent in the context of teaching a patient as assessed by the patient experience survey.
The patient experience survey includes 3 open-ended questions about experience with the training process, input on using monitoring devices at home, and any other important information for the researchers to know. Descriptive analysis will be conducted within each arm.
Time frame: Day 3
Identification of opportunities to improve the use of a virtual agent in the context of teaching a patient as assessed by the patient experience survey.
The patient experience survey includes 3 open-ended questions about experience with the training process, input on using monitoring devices at home, and any other important information for the researchers to know. Descriptive analysis will be conducted within each arm.
Time frame: Day 3
Plan to share: No
No publications or documents are linked to this record.
This study is withdrawn, as verified in May 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Duke University