Within five years, all of Mount Sinai’s IT systems will include some form of AI

(Editor’s note: This is part two of this interview. To read part one, Click here.)

Dr. Bruce Darrow, Chief Medical Information Officer and interim Chief Digital and Information Officer at Mount Sinai Health System in New York This week we offered some thoughts on why artificial intelligence plays such a big role in healthcare and how AI could one day take some (emphasis on “some”) cases away from doctors.

In this Q&A, Darrow takes an in-depth look at how Mount Sinai is using AI – and how the company plans to expand its use. He discusses how long the healthcare system has been using AI for clinical care, the principles clinical and IT leaders follow when considering clinical AI use cases, and the AI ​​implementations Mount Sinai has implemented today. In the video accompanying this article, Darrow also describes what determines whether an AI initiative at Mount Sinai is likely to succeed.

Q. How long has Mount Sinai been using AI for clinical care, and where is the healthcare system using it?

A. You might think that the use of AI is a more recent development. It depends on where you draw the line and where you make the definition.

We’ve been using algorithmic healthcare and ways to use computer-based decision support for many, many years. The first real application of AI was in 2013. It was more than a decade ago at Mount Sinai, where at that time the first use case we reported or published on was the use of AI algorithms to find patients in the hospital who would probably get a disease. very sick before they reached that point and their results were even worse.

And by using AI to find them earlier in their care, we were able to significantly increase their chances of surviving their hospital stay. So that was over 10 years ago.

And a lot of the work that we’ve done at Mount Sinai over the last ten to twelve years has been in the area of ​​what I would call predictive AI, finding patients who are likely to get sick, finding patients who are likely to get sick become a condition that would benefit from having that knowledge, bringing in the right skills, bringing in the right expertise, bringing the right treatments into the patient’s care earlier in the process.

Over the past two years, we’ve been looking at ways to use AI to streamline care, not necessarily specifically related to clinical care, but ways to make care easier for our patients, to streamline operational components, and to start automating some of the things that doctors and other healthcare team members do that take a lot of time, that can be set up and the prep work done for them.

Q. What principles does Mount Sinai use when considering clinical AI use cases?

A. This is very important. As I said, we have been using AI for over a decade, and when it became clear that AI was going to be a growing part of our patient care portfolio over the last two or three years, we discovered that we needed to be intentional about this. how we were going to use it.

At Mount Sinai, the principles we adhered to were that the use of AI for clinical care must be safe, effective, equitable and ethical. It is clear that we need to safely and effectively have tools that make a difference in a patient’s care. They have to work. They must serve a purpose that advances care.

Ethical and fair in terms of how we ensure we bring these tools to all our patients in a way that aligns with our mission as an organization.

Q. What AI use cases does Mount Sinai currently have?

A. Most of the AI ​​we use comes from essentially three different pipelines. We are fortunate that at Mount Sinai we have a very talented and committed team of data scientists, implementation scientists, artists and other team members who can use a learning platform, a data pipeline, to create, test and use our own AI algorithms. for the care of our patients.

They have published widely and have been recognized for this. David Rich, the president of Mount Sinai Hospital, and Robbie Freeman, our Chief Nurse Information Officer and vice president within Digital and Technology Partners for Innovation, have been very active with their teams.

Some examples of this include finding patients before they become sick enough to require ICU care, identifying with greater accuracy than existing tools whether a patient in the hospital is likely to be at risk for falls, identifying patients at risk for malnutrition or pressure ulcers. so that we can bring it to the attention of the appropriate members of the healthcare team.

These are great additions to the care that our nurses, our physicians, our social workers and our registered dietitians already provide to our patients in the hospital setting.

We have a lot of homegrown knowledge and expertise, and we have actually been doing that since about 2016. In the past five years we have seen a growing amount of imaging AI. These are all FDA-approved tools and software algorithms that we can use for our patients.

Many of these do not, as I said in yesterday’s discussion, replace the radiologist or the physician, but make the radiologist’s work more accurate, efficient, and faster. An example is if you imagine that there are twenty patients who have had CTS of the head, which is a computed tomography of the head, to detect abnormalities, including a stroke or bleeding in the head.

If a doctor looks at a list of twenty of them, he or she may not know. They can be in order of when the images were acquired. But if you have AI running in the background and it says, out of these twenty, look at these two first because these are the two that, according to the algorithm, probably have something that looks abnormal. That’s good for the doctors.

They focus their attention on the right tests first, and it’s good for the patients because they’re more likely to get their care if we think it can make a difference in their care. There is a fair amount of imaging AI for both diagnostic accuracy and to ensure we have the right selection of where to focus attention.

The third area where I see a lot of AI is in the tools offered by our existing software or other software vendors in the community. Almost every piece of software we use at Mount Sinai, if it doesn’t have AI built into it yet, I think I could have AI built into it within the next three to five years.

It’s just the way technology is developing. Our electronic health record system contains AI that we consider and validate and decide whether or not to use in healthcare. Everything from email to presentation documents to video collaboration we use will have an element of AI.

BONUS CONTENT: Click here to watch a video of this interview, which also includes Dr. Bruce Darrow discusses what determines whether an AI initiative at Mount Sinai is likely to succeed and what his colleagues at other hospitals and healthcare systems can take away from it.

Editor’s Note: This is the ninth in a series of articles from top voices in healthcare IT discussing the use of artificial intelligence in healthcare. To read the first part, about Dr. John Halamka from the Mayo Clinic: Click here. To complete the second interview with Dr. To read Aalpen Patel at Geisinger, click here. To read the third, with Helen Waters of Meditech, click here.

To read the fourth, with Sumit Rana from Epic, Click here. To read the fifth, with Dr. General Brigham’s Rebecca G. Mishuris, click here. To read the sixth, with Dr. Melek Somai of the Froedtert & Medical College of Wisconsin Health Network, click here. To read the seventh, together with Dr. Brian Hasselfeld of Johns Hopkins Medicine, click here. And to read the eighth, with Craig Kwiatkowski, senior vice president and CIO at Cedars-Sinai, click here.

The HIMSS AI in Healthcare Forum will take place September 5-6 in Boston. More information and registration.

Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.