There has always been a lot of talk about what artificial intelligence (AI) can do in healthcare. However, when we look at solutions implemented, successfully in use in a live setting and at any scale, there are only a handful of examples. I believe dentistry provides an interesting area for AI to make an impact. In order to make this a reality, we need to revisit how we design, deploy and operate AI solutions. A systematic review of studies between 2000 and 2018 exploring machine learning solutions applied to clinical problems revealed that only 2% were prospective and were often proof of concept solutions. An EU report published in 2021 reviewing AI in healthcare across its member states found that actual adoption was limited to specific departments and use cases. Two review papers and a report from the Alan Turing Institute assessed 647 AI tools developed to help with the COVID-19 pandemic; none were suitable for clinical use.
展开▼