Artificial Intelligence vs Physicians for Breast Cancer Patients' Information

Artificial Intelligence vs Physicians for Breast Cancer Patients' Information : a Blind, Randomized, Controlled Study

Chatbots (contraction of "chat" and "robot") are a computer software program that use statistical learning and aim to simulate a conversation by text or voice message. The use of these chatbots was evaluated as part of the increase in therapeutic adherence and information on well-being and mental health.

In clinical studies, chatbots are useful in gathering information through questionnaires directly submitted during conversations or through keyword analyzes. There is no longer any delay between the moment the patient notices a side effect, for example, and the moment when the patient announces it during a consultation. The responses given by the chatbot do not constitute medical advice and only provide information on the treatments envisaged or in progress in the context of the management of breast cancer.

The main objective of the study is to show that the chatbot Vik's answers to the common questions asked by breast cancer patients about their therapeutic management are at least as satisfactory as answers given by a committee of multidisciplinary doctors

Study Overview

• Status: Completed
• Conditions: Breast Cancer
• Intervention / Treatment: Other: survey

Detailed Description

A total of 20 most frequently asked questions will be defined on a cohort of 150 breast cancer patients. These questions will be asked on the one hand to the chatbot Vik and on the other hand to a multidisciplinary medical committee (surgeon oncologist, medical oncologist and oncologist radiotherapist). The scientific quality of the responses of the two groups will be validated by a second multidisciplinary group of physicians, independent of the first.

A cohort of 150 patients will then be randomized blind and in 1 to 1 to receive the responses of the chatbot Vik and the answers of the doctors' committee. Each patient will then have to answer the EORTC QLQ-INFO255-7 questionnaire, evaluating the quality of the medical information.

• Study Type: Observational
• Enrollment (Actual): 150

Contacts and Locations

Study Locations

• France
  • Montpellier, France, 34000
    • Wefight

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: Female

• Sampling Method: Non-Probability Sample

Study Population

Women with breast cancer or in remission

Description

Inclusion Criteria:

• over 18 years
• paitents with breast cancer

Exclusion Criteria:

• Patient unable to formulate his opposition
• Patient with cancer other than breast cancer

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Group Vik; women over the age of 18 with breast cancer or remission	Other: survey; non-inferiority study, randomized, blind, excluding health product, with no risk or constraint, in which all the acts are performed in the usual way and do not modify the patient's management.
Group physicians; women over the age of 18 with breast cancer or remission	Other: survey; non-inferiority study, randomized, blind, excluding health product, with no risk or constraint, in which all the acts are performed in the usual way and do not modify the patient's management.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Quality of Patient information	The quality of the participating patient's information about their disease and their treatment will be assessed using the standardized EORTC QLQ-INFO25 survey.	Through study completion, an average of 3 months

Collaborators and Investigators

• Sponsor: Wefight

Publications and helpful links

General Publications

• Bibault JE, Chaix B, Guillemasse A, Cousin S, Escande A, Perrin M, Pienkowski A, Delamon G, Nectoux P, Brouard B. A Chatbot Versus Physicians to Provide Information for Patients With Breast Cancer: Blind, Randomized Controlled Noninferiority Trial. J Med Internet Res. 2019 Nov 27;21(11):e15787. doi: 10.2196/15787.

Study record dates

Study Major Dates

• Study Start (Actual): November 1, 2018
• Primary Completion (Actual): December 1, 2018
• Study Completion (Actual): January 20, 2019

Study Registration Dates

• First Submitted: May 31, 2018
• First Submitted That Met QC Criteria: June 13, 2018
• First Posted (Actual): June 14, 2018

Study Record Updates

• Last Update Posted (Actual): April 25, 2019
• Last Update Submitted That Met QC Criteria: April 23, 2019
• Last Verified: April 1, 2019

More Information

Terms related to this study

• Keywords: Natural Language Processing; Chatbot; Patient information; Conversational agent
• Additional Relevant MeSH Terms: Skin Diseases; Neoplasms; Neoplasms by Site; Breast Diseases; Breast Neoplasms
• Other Study ID Numbers: INCASE0518

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No