AI Doctor

CHAPTER 5Diagnostics

DIAGNOSTICS IS the first frontier for artificial intelligence (AI) in healthcare. Much of what happens in healthcare is about collecting data (symptoms, exam data, labs, genetics, etc.) and interpreting it to make determinations about a patient's health or medical issues. We've developed great capabilities in diagnostic testing over the last century. Often, a piece of data can clinch a diagnosis, such as a CT scan that shows a stroke or bleed in the context of a patient with neurological issues or a urinalysis that shows a urinary tract infection in someone with lower abdominal pain.

Lab results often have a normal range and if something is out of that range, the abnormal result is used to diagnose the cause of an issue. Sometimes, the interpretation is much more subjective and requires careful examination of an X‐ray or an MRI scan, looking for abnormalities in different areas such as the bones, kidneys, or abdomen. This is a prime area for AI algorithms to assist clinicians. AI could also help when there's a large amount of information to interpret (e.g. genetics) or a combination of information from different sources. It's my opinion that with the explosion of medical information about each individual, AI will soon be a necessity and not a luxury, allowing us to interpret what all of this information means for each individual.

Let's see what AI is capable of, as well as what the short‐term applications are and what will be possible in the long term but ...