Evaluate the feasibility of using a chatbot combined with continuous activity monitoring to proactively identify, appropriately triage and help manage patients' symptoms during cancer treatment Determine whether such an early outpatient clinic-based intervention can decrease rates of excess triage visits Correlate changes in activity and early symptom management to emergency department visits, unplanned inpatient hospitalizations and treatment breaks
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
OTHER
Masking
NONE
Enrollment
70
The automated chatbot will check in with the patient on two pre-specified days between scheduled outpatient visits. The chatbot will follow pre-specified symptom algorithms and classify symptoms as requiring high, intermediate and low risk follow ups. High risk symptoms will trigger a same day nursing/physician visit or telemedicine call/video. Intermediate risk symptoms will trigger a nursing triage visit or telemedicine call/video on the next day or treatment day. Low risk symptoms will notify the treating physician to address the symptoms at the next scheduled on treatment visit (OTV). If adjustments are needed in the chat bot triage algorithms, they will be updated in real time to decrease risk for adverse patient events.
Abramson Cancer Center of the University of Pennsylvania
Philadelphia, Pennsylvania, United States
Number of triage visits
Difference between Poisson event rates of triage visits between intervention and control arms
Time frame: 13 weeks
Count of unplanned inpatient hospitalization
Time frame: 13 weeks
Count of treatment breaks
Time frame: 13 weeks
Count of emergency department visits
Time frame: 13 weeks
Quality of Life scores
Time frame: 13 weeks
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.