ABSTRACT
Objective Our goal is to establish the feasibility of using an artificially intelligent chatbot in diverse healthcare settings to promote COVID-19 vaccination. Methods We designed an artificially intelligent chatbot deployed via short message services and web-based platforms. Guided by communication theories, we developed persuasive messages to respond to users' COVID-19-related questions and encourage vaccination. We implemented the system in healthcare settings in the U.S. between April 2021 and March 2022 and logged the number of users, topics discussed, and information on system accuracy in matching responses to user intents. We regularly reviewed queries and reclassified responses to better match responses to query intents as COVID-19 events evolved. Results A total of 2479 users engaged with the system, exchanging 3994 COVID-19 relevant messages. The most popular queries to the system were about boosters and where to get a vaccine. The system's accuracy rate in matching responses to user queries ranged from 54% to 91.1%. Accuracy lagged when new information related to COVID emerged, such as that related to the Delta variant. Accuracy increased when we added new content to the system. Conclusions It is feasible and potentially valuable to create chatbot systems using AI to facilitate access to current, accurate, complete, and persuasive information on infectious diseases. Such a system can be adapted to use with patients and populations needing detailed information and motivation to act in support of their health.
ABSTRACT
Objective: Our goal is to establish the feasibility of using an artificially intelligent chatbot in diverse healthcare settings to promote COVID-19 vaccination. Methods: We designed an artificially intelligent chatbot deployed via short message services and web-based platforms. Guided by communication theories, we developed persuasive messages to respond to users' COVID-19-related questions and encourage vaccination. We implemented the system in healthcare settings in the U.S. between April 2021 and March 2022 and logged the number of users, topics discussed, and information on system accuracy in matching responses to user intents. We regularly reviewed queries and reclassified responses to better match responses to query intents as COVID-19 events evolved. Results: A total of 2479 users engaged with the system, exchanging 3994 COVID-19 relevant messages. The most popular queries to the system were about boosters and where to get a vaccine. The system's accuracy rate in matching responses to user queries ranged from 54% to 91.1%. Accuracy lagged when new information related to COVID emerged, such as that related to the Delta variant. Accuracy increased when we added new content to the system. Conclusions: It is feasible and potentially valuable to create chatbot systems using AI to facilitate access to current, accurate, complete, and persuasive information on infectious diseases. Such a system can be adapted to use with patients and populations needing detailed information and motivation to act in support of their health.
ABSTRACT
BACKGROUND: Electronic health records are now the norm in US healthcare. Bidirectional patient portals allow frequent communication between patients and their healthcare team. Many studies have examined the importance of patient engagement and trust between patients and their healthcare team, typically in the context of face-to-face interactions. Little is known about how patient trust and engagement are built or enhanced through electronic communications. COVID-19 provided a unique time in history for this novel exploration. OBJECTIVE: Our objective was to learn how patients experience trust formation through electronic communication (patient messaging and video visits) with their healthcare team. DESIGN: Our research was guided by grounded theory methodology. Qualitative interviews were conducted between February and December 2020 with patients or their caregivers from an internal medicine clinic in Colorado. PARTICIPANTS: Fifty-one participants were recruited by age group and gender to represent the clinic's adult ambulatory care demographics. Seven were patients' caregivers who were purposefully recruited. Average age was 53 with an educated, middle class, and largely white predominance in our eventual sample. APPROACH: Thirty-minute semi-structured interviews were conducted using an interview guide informed by a validated physician-patient trust scale. Interviews were conducted by telephone, recorded via Zoom, and transcribed. Results were analyzed and coded in ATLAS.ti utilizing the constant comparative method, with two coders. KEY RESULTS: Patients experienced enhanced trust in their healthcare team through electronic communications. Interpersonal and system factors contributed to trust formation. Promptness of reply was the most salient factor in trust formation with a majority desiring same day response. CONCLUSIONS: Patients now rely on electronic communication with their healthcare team. Opportunities exist to leverage this to improve health outcomes. Important research in expanded demographic groups, along with ambulatory healthcare redesign, will be necessary to optimize benefits of electronic communication with patients and meet patient expectations.