“Always go too far, because that is where you will find the truth.” Albert Camus, author of The Plaque
Our second Clinician Series focused on imaging so involved many subspecialists from radiology, cardiology, pathology, ophthalmology, and dermatology. The robust discussions were both interesting and insightful for all those attended.
Here are the top 10 highlights from the meeting:
1 There remains serious challenges with healthcare data, from access to accuracy. For the AI to work so much work remains to be done in this area.
2 The AI support for projects from various centers ranged from in house data scientists to outsourcing the expertise.
3 AI as a resource, for it to be even more effective and efficient, can be combined with other technologies such as cloud computing.
4 As AI matures in clinical decision support and medical imaging, we need to consider the consequences and costs of overdiagnosis as a result of increased screening.
5 The generalizability of models remains an issue, as many models from academic centers and vendors fail to generalize in the real world (the accuracy vs generalizability paradigm).
6 The performance of models needs to be coupled to clinical relevance and/or impact for true value for these models.
7 We need to focus on bias of AI tools during all phases: planning, data, model, and deployment so that we minimize the bias (we learn a lot about ourselves).
8 Artificial intelligence is a resource that can be embedded in the entire continuum of image workflow, from acquisition of signals to actionable items to patient care.
9 AI in medicine is a team sport: there needs to be a special synergy between clinicians and data scientists.
10 Clinicians can be involved in AI in their subspecialty without knowing or learning to program; their clinical insights and wisdom are very valuable and needed for AI in their domain.
We would like to invite you to our next exciting Clinician Series in September with the focus on Primary Care (Internal medicine, precision medicine, population and global health, pediatrics, etc) with a special Healthcare Executives track.
We are also planning to host an in-person AIMed22 Annual Global Summit in January of 2022 at the sublime Ritz-Carlton resort in Laguna Niguel, southern California. This summit promises to be the most enthralling yet, with Drs. Eric Topol and Daniel Kraft among the keynote speakers. We are all very much looking forward to seeing each other in person for human-to-human conversations and networking about not only AI for healthcare but about everything else as well.