Promoting Research, Awareness, and Discussion on AI in Medicine Using #MedTwitterAI: A Longitudinal Twitter Hashtag Analysis

BACKGROUND: Artificial intelligence (AI) has the potential to reshape medical practice and the delivery of healthcare. Online discussions surrounding AI's utility in these domains are increasingly emerging, likely due to considerable interest from healthcare practitioners, medical technology developers, and other relevant stakeholders. However, many practitioners and medical students report limited understanding and familiarity with AI. OBJECTIVE: To promote research, events, and resources at the intersection of AI and medicine for the online medical community, we created a Twitter-based campaign using the hashtag #MedTwitterAI. METHODS: In the present study, we analyze the use of #MedTwitterAI by tracking tweets containing this hashtag posted from 26th March, 2019 to 26th March, 2021, using the Symplur Signals hashtag analytics tool. The full text of all #MedTwitterAI tweets was also extracted and subjected to a natural language processing analysis. RESULTS: Over this time period, we identified 7,441 tweets containing #MedTwitterAI, posted by 1,519 unique Twitter users which generated 59,455,569 impressions. The most common identifiable locations for users including this hashtag in tweets were the United States (378/1,519), the United Kingdom (80/1,519), Canada (65/1,519), India (46/1,519), Spain (29/1,519), France (24/1,519), Italy (16/1,519), Australia (16/1,519), Germany (16/1,519), and Brazil (15/1,519). Tweets were frequently enhanced with links (80.2%), mentions of other accounts (93.9%), and photos (56.6%). The five most abundant single words were AI (artificial intelligence), patients, medicine, data, and learning. Sentiment analysis revealed an overall majority of positive single word sentiments (e.g., intelligence, improve) with 230 positive and 172 negative sentiments with a total of 658 and 342 mentions of all positive and negative sentiments, respectively. Most frequently mentioned negative sentiments were cancer, risk, and bias. Most common bigrams identified by Markov chain depiction were related to analytical methods (e.g., label-free detection) and medical conditions/biological processes (e.g., rare circulating tumor cells). CONCLUSION: These results demonstrate the generated considerable interest of using #MedTwitterAI for promoting relevant content and engaging a broad and geographically diverse audience. The use of hashtags in Twitter-based campaigns can be an effective tool to raise awareness of interdisciplinary fields and enable knowledge-sharing on a global scale.