This study is designed to contribute to the growing body of evidence on the efficacy of digital health interventions. By rigorously evaluating the impact of the AI system on vaccine knowledge and acceptance, the study aims to inform future health communication strategies and policies. It stands as a potential model for integrating AI into public health initiatives, showcasing how technology can be harnessed to improve health outcomes on a large scale.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
HEALTH_SERVICES_RESEARCH
Masking
TRIPLE
Enrollment
430
The conversational AI system based on LLM processes user queries with a sophisticated generation, decision, action, and safety framework to provide optimal feedback. The system has several key features. Firstly, it utilizes retrieval-augmented in-context learning to enhance responses generated by the LLM, sourcing information from trustworthy websites. Secondly, it includes Guardrail module that addresses potential harmful content in the LLM-generated responses by clarifying and validating the content before delivery. Furthermore, the AI system is equipped with Self-checking memory module that retains essential clinical characteristics across multi-turn dialogues, ensuring the continuity and consistency of its interactions with users. The educational content about vaccination was derived from the official website of World Health Organization (https://www.who.int/news-room/questions-and-answers/item/vaccines-and-immunization-what-is-vaccination).
A printed brochure whose content about vaccination was derived from the official website of World Health Organization (https://www.who.int/news-room/questions-and-answers/item/vaccines-and-immunization-what-is-vaccination).
Zhongshan Ophthalmic Center
Guangzhou, Guangdong, China
Acceptance of vaccines
Vaccine acceptance was evaluated based on responses to the question, 'Based on your actual situation, please choose the extent of your willingness to get vaccinated.' The response options were: Absolutely refuse, Refuse but uncertain about the future, Have not considered it yet, Accept but still considering, and Completely willing. Vaccine acceptance was considered if the participant selected 'Completely willing.
Time frame: Day 14
Hesitancy of vaccination
The Vaccine Hesitancy Scale was developed based on the "3Cs" model (confidence, complacency, and convenience) by the SAGE Working Group on Vaccine Hesitancy, encompassing three aspects: confidence, complacency, and convenience. It utilizes a Likert 5-point scale (Strongly Disagree, Disagree, Neutral, Agree, Strongly Agree) for scoring. For the complacency dimension, aspect, scoring is reversed with "Strongly Agree" to "Strongly Disagree" rated as 5 to 1 points, respectively. In contrast, other items follow the standard scoring, where "Strongly Agree" to "Strongly Disagree" are scored from 1 to 5 points. Confidence is measured by perceived vaccine safety and efficacy. Complacency is assessed through perceived necessity of the vaccine and the severity of the preventable diseases. Convenience is evaluated by the perceived ease of transportation and appointment scheduling.
Time frame: Day 14
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.