Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Aug 7, 2019
Date Accepted: Oct 23, 2019
Artificial Intelligence vs Physicians for Breast Cancer Patients' Information: a blind, randomized controlled non-inferiority trial
ABSTRACT
Background:
The data regarding the use of conversational agents in oncology are scarce. INCASE is a non-inferiority randomized, controlled, blind trial that compared the information given by the Vik chatbot vs a multidisciplinary group of physicians to breast cancer patients. Patients were women with breast cancer in treatment or in remission.
Objective:
The aim of the INCASE study was to verify whether a conversational agent was able to provide answers to breast cancer patients with a level of satisfaction similar to the answers given by a group of physicians.
Methods:
The EORTC QLQ-INFO25 questionnaire was adapted and used to compare the quality of the information provided to patients by the physician or the chatbot. The primary outcome was to show that the answers given by the Vik chatbot to common questions asked by breast cancer patients about their therapeutic management are at least as satisfying as answers given by a multidisciplinary medical committee. The secondary objective was to compare for each INFO25 item the average scores obtained by the chatbot and by the physicians.
Results:
A total of 142 patients were included and randomized into two groups of 71. They were all female with a mean age of 42 years (SD 19). The answers provided by the group of physician's received an average rating of 2.82, while patients assessing Vik's answers gave an average rating of 2.89. The difference between success rates in the physicians’ group and Vik’s group was -0.03 (95% CI [-0.07; 0.00]). The binomial test showed the non-inferiority (p < 1e-14) of the chatbot’s answers.
Conclusions:
This is the first study that rigorously assessed a conversational agent used to inform cancer patients. The EORTC INFO25 scores from the chatbot were found to be non-inferior to the scores of the physicians. Conversational agents may save patients with minor health concerns from a visit to the doctor. This could allow clinicians to spend more time to treat patients who need a consultation the most. Clinical Trial: registered in the ClinicalTrials.gov database (NCT03556813)
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.