Sensible Solutions for Refurbished Radiology

This Is Why AI Tools Can Help Radiologists

Posted by Vikki Harmonay on Tue, Nov 21, 2017 @ 16:11 PM

Mention the term AI in a room filled with radiologists and you’ll probably hear a comment like, “AI is going to make us obsolete” but AI Radiology Tools.jpgdon't fear,  according to radiologist and informatics expert Paul Chang radiologists shouldn’t hesitate to embrace AI, “because it’s going to help you be more efficient at what you are good at…and help you do the stuff you don’t like doing, or where you can make a mistake.”

Let’s look at a historical picture

Not that long ago, imaging was the main revenue center for most hospitals.  However, there’s been a shift to bundled payments and population wellness management contracting.  As a result, radiology is evolving as a cost center, which isn’t a bad thing, according to Chang.  

He noted that IT is also cost center, but his facility’s IT department is fine on their budget.  Why?  Because of what IT and informatics can do to help hospital physicians and administrators achieve in both quality and safety.  He believes imaging informatics need to harness the power of big data.  He also believes applying AI is ultimately more efficient.

Chang used this as an example:  when you buy a car, it should come with floor mats for free, but they don’t.  But we’ve learned that people will pay for things like floor mats if they are rolled into the cost of the investment, or cost of the car.  Likewise, if radiologists present AI as a “floormat” in their clinical settings, administrators will be more likely to invest in it.

Chang pointed out how AI improves efficiency, safety and better outcomes through informatics and AI.  He said, ““As a radiologist, I used to hate calling down to the ER,” he said. “I had to stop what I was doing ...wait while someone found the attending ER doctor I needed...but if I saw something on an image that might kill the patient in six months like a lung nodule, then I had to make sure the ER doc knew about it, to make a notation in the medical record for a follow-up.”

With the addition of AI at his facility, this process is now automated without human intervention.  He believes assigning this task to AI instead of trusting people to remember to do these things (which people are bad at remembering) it will free up time for physicians and radiologists to do more of what they are good at, like reading images.    In addition, by using automated AI systems to program the parameters in CT or MRI exams, Chang experienced an 80% reduction in turnaround time. This means the technologies can be more efficient while physicians can spend more time with their patients.

A recent article in Health IT News talks about accessing the promises of technology.

Health Fidelity’s chief architect Raj Tiwari and Cognoa CEO Brent Vaughn both believe that AI and machine learning are augmentative tools. They emphasized that size matters among data sets, real world applicability is a must and the tools (AI) must be trained and validated. Tiwari said, “AI is a tool that enhances our capability, allowing humans to do more than what we could on our own. It’s designed to augment human insight, not replace it. For example, a doctor can use AI to access the distilled expertise of hundreds of clinicians for the best possible course of action. This is far more than he or she could ever do by getting a second or third opinion.”

Healthcare AI tools often rely on data sets orders of magnitude smaller than other industries, and thus require that the AI developers have a deeper industry knowledge and understanding of the data.  Why?  Because coding mistakes and date misinterpretation are amplified in smaller data sets.

Tiwari added, “Since the training and validation data sets often are much smaller in healthcare, the differences between populations can become exacerbated,” he explained. “For example, primary and secondary or tertiary care settings can see dramatically different incident rates for different events. An AI tool that is good at predicting a particular outcome in one setting might have a much higher error rate in the other setting.”

As technology continues to advance, AI will be more present in every industry.  Chang encourages radiologists and informatics specialists to keep an open mind and be willing to see which technologies will end up being new industry standards. 

Talk to the experts at Atlantis Worldwide

At Atlantis Worldwide, we know that change is the only constant in the medical imaging industry.  At the same time, we also know that often the wise decision for medical facilities is to buy refurbished technology to provide top care for their patients while new technological advances are put to the test.  To find out more about refurbished medical imaging equipment and their extensive warranties and service contracts, talk to one of our experts today.

Some blogs you may have missed:

Meet the author: Vikki Harmonay 

New Call-to-action


Topics: Medical Imaging News, More Than Just Imaging Solutions