Assessing the performances of a chatbot to collect real-life data of patients with migraine (Preprint)

BACKGROUND There are many scales for screening or assessing the impact of a disease. These scales are generally used to diagnose or assess the severity of a disease and are carried out by doctors. The Vik Migraine chatbot helps patients suffering from headaches through personalized text messages, it could be used to collect patient-reported outcomes. OBJECTIVE The aims of this study were (1) to assess the feasibility of collecting a chatbot-mediated reference scale, (2) perform a remote diagnosis of the severity of the migraines and (3) assess the patient satisfaction and engagement with the chatbot. METHODS This study was conducted in France from December 2019 to March 2020. Voluntary users of the chatbot Vik Migraine were recruited online. They had to be adults and suffer from chronic migraines. An adapted version of the IHS questionnaire was presented to the participants by text messages. The Lickert scale ranging from 1 to 5 was used to assess overall satisfaction with the use of Vik Migraine. RESULTS We included 636 participants with migraines or headaches. A total of 89.94% (572) participants had fully completed the IHS questionnaire (8 items), 4.72% (30) had partially completed it and 5.35% (34) had refused to complete it. The evaluation of overall satisfaction shows that a total of 80.7% (513) of users agreed or strongly agreed with the affirmation that Vik Migraine provides quality answers about the pathology or its information. CONCLUSIONS We hypothesized that a virtual assistant built to support migraine patients could be used to retrieve patient data remotely, such as medical assessment scales. The study confirmed this hypothesis and showed that users were strongly engaged through to chatbot: out of the total number of participants, we observed a very low number of uncompleted questionnaires.