TY  - JOUR
AU  - Tan, Tze Chin
AU  - Roslan, Nur Emillia Binte
AU  - Li, James Weiquan
AU  - Zou, Xinying
AU  - Chen, Xiangmei
AU  - Santosa, Anindita
PY  - 2023
DA  - 2023/12/28
TI  - Patient Acceptability of Symptom Screening and Patient Education Using a Chatbot for Autoimmune Inflammatory Diseases: Survey Study
JO  - JMIR Form Res
SP  - e49239
VL  - 7
KW  - conversational agents
KW  - digital technology in medicine
KW  - rheumatology
KW  - early diagnosis
KW  - education
KW  - patient‒physician interactions
KW  - autoimmune rheumatic diseases
KW  - chatbot
KW  - implementation
KW  - patient survey
KW  - digital health intervention
AB  - Background: Chatbots have the potential to enhance health care interaction, satisfaction, and service delivery. However, data regarding their acceptance across diverse patient populations are limited. In-depth studies on the reception of chatbots by patients with chronic autoimmune inflammatory diseases are lacking, although such studies are vital for facilitating the effective integration of chatbots in rheumatology care. Objective: We aim to assess patient perceptions and acceptance of a chatbot designed for autoimmune inflammatory rheumatic diseases (AIIRDs). Methods: We administered a comprehensive survey in an outpatient setting at a top-tier rheumatology referral center. The target cohort included patients who interacted with a chatbot explicitly tailored to facilitate diagnosis and obtain information on AIIRDs. Following the RE-AIM (Reach, Effectiveness, Adoption, Implementation and Maintenance) framework, the survey was designed to gauge the effectiveness, user acceptability, and implementation of the chatbot. Results: Between June and October 2022, we received survey responses from 200 patients, with an equal number of 100 initial consultations and 100 follow-up (FU) visits. The mean scores on a 5-point acceptability scale ranged from 4.01 (SD 0.63) to 4.41 (SD 0.54), indicating consistently high ratings across the different aspects of chatbot performance. Multivariate regression analysis indicated that having a FU visit was significantly associated with a greater willingness to reuse the chatbot for symptom determination (P=.01). Further, patients’ comfort with chatbot diagnosis increased significantly after meeting physicians (P<.001). We observed no significant differences in chatbot acceptance according to sex, education level, or diagnosis category. Conclusions: This study underscores that chatbots tailored to AIIRDs have a favorable reception. The inclination of FU patients to engage with the chatbot signifies the possible influence of past clinical encounters and physician affirmation on its use. Although further exploration is required to refine their integration, the prevalent positive perceptions suggest that chatbots have the potential to strengthen the bridge between patients and health care providers, thus enhancing the delivery of rheumatology care to various cohorts. 
SN  - 2561-326X
UR  - https://formative.jmir.org/2023/1/e49239
UR  - https://doi.org/10.2196/49239
UR  - http://www.ncbi.nlm.nih.gov/pubmed/37219234
DO  - 10.2196/49239
ID  - info:doi/10.2196/49239
ER  -