Putting Artificial Intelligence at the Heart of Healthcare – With Help from MIT | MIT News





Artificial intelligence is transforming industries around the world – and healthcare is no exception. A recent Mayo Clinic study found that AI-enhanced electrocardiograms (ECGs) have the potential to save lives by speeding up the diagnosis and treatment of heart failure patients who are seen in the emergency room.

Lead author of the study is Demilade “Demi” Adedinsewo, a non-invasive cardiologist at the Mayo Clinic who actively incorporates the latest advances in AI into cardiac care and draws heavily on her learning experience with the MIT Professional Education.

Identify AI opportunities in healthcare

A dedicated practitioner, Adedinsewo is a Mayo Clinic Florida Women’s Health Fellow and Research Director for the Cardiovascular Disease Fellowship Program. Her clinical research interests include cardiovascular disease prevention, women’s heart health, cardiovascular health disparities, and the use of digital tools in cardiovascular disease management.

Addedinsewo’s interest in AI emerged towards the end of her cardiology fellowship, when she began to learn about its potential to transform the field of healthcare. “I started to wonder how we could leverage AI tools in my field to improve health equity and reduce disparities in cardiovascular care,” she says.

During his fellowship at the Mayo Clinic, Adedinsewo began to examine how AI could be used with ECGs to improve clinical care. To determine the effectiveness of the approach, the team retroactively used deep learning to analyze the ECG results of patients with shortness of breath. They then compared the results with the current standard of care – a blood test scan – to determine whether improving AI improved the diagnosis of cardiomyopathy, a condition in which the heart is unable to properly pump blood to the body. rest of the body. While she understands the clinical implications of the research, she found the components of AI difficult.

“Even though I have a medical degree and a master’s degree in public health, these credentials are not really enough to work in this space,” says Adedinsewo. “I started looking for an opportunity to learn more about AI so that I could speak the language, bridge the gap and bring these revolutionary tools to my field. “

Bridging the Gap at MIT

Addedinsewo’s desire to bring together cutting-edge data science and clinical care led her to vocational training at MIT, where she recently completed the Professional Certificate Program in Machine Learning and AI. To date, she has taken nine courses, including AI Strategies and Roadmap.

“All the classes were excellent,” says Adedinsewo. “I especially enjoyed how professors like Professors Regina Barzilay, Tommi Jaakkola and Stefanie Jegelka provided practical examples from health and other fields to illustrate what we were learning. “

Addedinsewo’s goals align closely with those of Barzilay, MIT’s head of AI Jameel Clinic for Machine Learning in Health. “There are so many areas of healthcare that can benefit from AI,” says Barzilay. “It’s exciting to see practitioners like Demi join the conversation and help identify new ideas for high impact AI solutions. “

Adedinsewo also appreciated the opportunity to work and learn within the large MIT community alongside accomplished peers from around the world, explaining that she learned different things from each person. “It was great to have different perspectives from the course participants who are deploying AI in other industries,” she says.

Put knowledge into action

Armed with its updated AI toolkit, Adedinsewo was able to make a significant contribution to Mayo Clinic research. The team successfully completed and published their ECG project in August 2020, with promising results. Analyzing ECGs from approximately 1,600 patients, the AI-enhanced method was both faster and more efficient, outperforming standard blood tests with a performance measurement (AUC) of 0.89 versus 0.80. This improvement could improve health outcomes by improving diagnostic accuracy and increasing the speed at which patients receive appropriate care.

But the benefits of Addedinsewo’s MIT experience go beyond a single project. Adedinsewo says the tools and strategies she acquired have helped her communicate the complexities of her job more effectively, expanding its reach and impact. “I feel better equipped to explain research – and AI strategies in general – to my fellow clinicians. Now people are reaching out to me asking, “I want to work on this project. Can I use AI to answer this question? ” She said.

Looking to the future powered by AI

What is the next step in Addedinsewo’s research? Integrate AI into the field of cardiology. While AI tools are currently not widely used to assess Mayo Clinic patients, she believes they have the potential to have a significant positive impact on clinical care.

“These tools are still in the research phase,” explains Adedinsewo. “But hopefully in the next few months or years, we can start doing more research on the implementation to see how much they improve care and outcomes for heart patients over time.”

Bhaskar Pant, Executive Director of MIT Professional Education, said: “At MIT Professional Education, we are particularly pleased to be able to provide practitioner-oriented information and tools on machine learning and AI from the expert professors at MIT. frontline health researchers such as Dr Demi. Adedinsewo, who are working on ways to dramatically improve clinical care and health outcomes in cardiac and other patient populations. It is also very much in line with MIT’s mission to “work with others for the good of mankind!” “”




Leave a Comment

x