Artificial intelligence has huge potential for many health problems – however there are still many hurdles that must be overcome.  

At a keynote for the Association for Computing Machinery Conference on Health, Inference and Learning this pastweek, Dr. Alan Karthikesalingam, study lead at Google Health UK, described three myths commonly encountered in the path to building and is translating AI models in clinical settings.  

When it comes to implementing deep learning technology , he inquired : “Why is there a difference between expectations and reality? “   

Here are three common misconceptions Karthikesalingam mentioned must be addressed.  

1. More data is all you need for a better version .  

The problem , he said , is that what we might regard as “ground truth ” is more subjective than we believe . One ophthalmologist might look at images of an eye and see moderate degeneration, whereas another would see it as mild.  

“Doctors don’t always agree, ” Karthikesalingam explained .  

The quality of labels seems to make a big difference in this regard .

” Selecting an efficient tagging strategy” is one way to guarantee quality, he said , “but also taking other modeling approaches and bringing them to bear. ”  

2. An accurate model is all you need for a helpful product.  

On the contrary: a human-centered approach is important to building useful products.    

Karthikesalingam’s team discovered that producing AI “onboarding” changed their understanding about what users want from tools .  

“Product usability is incredibly important and contains a whole raft of different sorts of action around which model development must correct , ” he said.  

3. A fantastic product alone is adequate for clinical effects .  

“Post-market, careful independent study takes quite a long time, ” said Karthikesalingam.  

“Implementation and health economic study are critical to adoption of AI products, ” he added.

Overall, examples of deep learning are all around us as consumers – and the medical field will eventually be no exception,” said Karthikesalingam  

“Technology, as it functions well, should make it as simple as possible” to treat patients, he said.

Kat Jercich is senior editor of Healthcare IT News.
Twitter: @kjercich
Healthcare IT News is a HIMSS Media publication.

Leave a Reply

Your email address will not be published. Required fields are marked *