Asking AI about AI in Medicine

I had a brief chat with the OpenAI ChatGPT about noise, radiology, and AI in medicine:

Human: Summarize the book Noise by Daniel Kahneman
AI: Noise by Daniel Kahneman is a book that examines how our minds work in a noisy, uncertain world. It dives into the cognitive biases and heuristics we use to make decisions with limited information, and explains how they can lead us astray. The book covers topics such as perception, intuition, and decision-making, and explores how noise and confusion can shape our lives and our thinking.

Human: How does the book argue that noise impacts radiology?
AI: In Noise, Daniel Kahneman argues that noise can have a major impact on radiology. He explains that radiologists are often subject to cognitive biases like confirmation bias and anchoring bias, which can lead them to make decisions that are not in the best interest of their patients. Additionally, he shows how noise can affect diagnostic accuracy and decision-making, making it harder for radiologists to provide accurate treatments and diagnoses.

Human: How could radiology address those limitations?
AI: Radiologists can address the limitations of noise in radiology by taking steps to reduce cognitive biases and increase accuracy. These steps include utilizing evidence-based decision-making, double-checking results for accuracy, and employing advanced imaging technologies such as computer-aided detection systems. Additionally, radiologists should strive to keep up with advances in medical technology and imaging techniques so that they can identify any noise or errors in their images.

Human: What are the current limitations in utilizing AI in radiology?
AI: Currently, one of the biggest limitations in utilizing AI in radiology is the potential for errors and false positives. While AI systems have the potential to be more accurate than human radiologists, there is still a risk that the AI system will miss diagnoses or misinterpret images. Additionally, AI systems can be costly to implement, and require significant computing power, which may not be feasible in many medical settings.

Human: What would be the easiest type of medicine to outsource to AI?
AI: The easiest type of medicine to outsource to AI would be administrative tasks such as scheduling appointments and completing insurance forms. AI can quickly and accurately complete these types of tasks, saving time and resources for medical professionals.

Even the machines think there’s some low-hanging fruit out there.


I’m bumping my own post here because the swag bag registration deadline is coming up on December 5. Registering through the link here is also one of those effortless ways you can support this site while doing what you were going to do anyway.

I’m very much looking forward to speaking again this coming year at the Physician Wellness & Financial Literacy Conference (aka WCICON23), which will take place March 1-4 at the very nice JW Marriott Desert Ridge in Phoenix. If you have a CME fund to burn, I can’t think of anything else I’d rather spend it on.



Code WCIPhoenix200 will net you $200 off an in-person registration. If you’re still on the fence, the deadline for the goody bag is December 5th. If your plans change, you can also downgrade to virtual through January 25.

Improving my Figs

I finally broke down and bought a pair of Figs so I could try to fit in with young folk.

But I had to do a little surgery with my seam ripper:

Just because I want to pretend I can pull off squeezing into some joggers doesn’t mean I want four(!) separate branding labels on a pair of scrubs of all things.

Now they’re closer to the fantasy world where the generic hospital scrub pants have regular pockets.

Physician Survey Signup Bonuses

Survey company offerings vary a lot by level of training and specialty, but several do offer bonuses to all comers for signing up (or when you attempt a survey or two):

I maintain an up-to-date list of healthcare survey companies here. Some of those links are also referrals that help support this site–so if signing up meets your needs/desires, thank you for supporting my writing.

Explanations for the 2022 Official Step 3 Practice Questions

Here are my explanations for the August 2022 update of the official practice materials.

The asterisks (*) signify one of the only two new questions compared with the prior set.

My explanations for the old 2020 set are here and the 2018/2019 set are here. There were 71 new questions in 2020 vs 2019, so going through that older set may still be worth your time. The one before that, which I explained here, was revised in November 2017.

You can find my thoughts on preparing for Step 3 here. Since writing that post, the main substantive change in the exam has been the ability to schedule CCS on a nonconsecutive day. In short, I think the free materials and UWorld should be enough for most folks. If you want book recs, they’re in that post. If you need another question source, I haven’t tried any of them, but you can get 10% off the popular BoardVitals if you’re interested by using code BW10.

As for this free 137-question practice exam, Blocks 1 and 2 are “Foundations of Independent Practice” (FIP). These should take up to 1 hour each. Blocks 3 and 4 are “Advanced Clinical Medicine” (ACM). These should take up to 45 minutes each. Total practice time should be no more than 3:30 if taken under test-day conditions.

Continue reading