New Issue: Orbital Catastrophe Ahead? Read Now

To Save Patients from Extreme Heat, a Hospital Is Turning to AI

AI could be used to comb through electronic health records and warn vulnerable people about dangerous heat waves

In the foreground, a woman in a green shirt lies on wall in the shade with a bottle of water in her hands. In the background, a teen girl is lying on her side in the shade and another woman sits on the stairs behind her

Tourists try to escape the effects of a heat wave in Washington, D.C., last week.

Andrew Harnik/Getty Images

CLIMATEWIRE | When extreme heat hits the Boston area, emergency departments are packed with people who are dehydrated, experiencing kidney or heart problems, or are having heat cramps.

Now a health care system that serves 2.5 million patients across Massachusetts is turning to artificial intelligence for help.

“The stress of the heat exacerbates those conditions, and we’ll see a 10 percent jump of people in the emergency department not just for heat illness, but also weakness or syncope or other conditions due to the heat,” said Paul Biddinger, chief preparedness and continuity officer at Mass General Brigham, the nonprofit academic health system that is working on a new alert system to warn people about the dangers of heat waves.


On supporting science journalism

If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.


In February, MGB was one of five applicants to join a Sustainability Accelerator run by IBM. The program seeks to help communities facing environmental and economic stress through technology. It had received more than 100 proposals for how to use AI to advance climate sustainability and resilience.

The idea is simple: Use AI to comb through electronic health records to find patients who have health conditions or take medications that might make them particularly vulnerable to heat. The AI program would warn them when a heat wave is coming and tell patients how to protect themselves so they don’t end up in an emergency room. The tool would include security features to protect patient health information.

Ideally, the combination of personalized information, real-time heat data, and "actionable messages" will help empower patients to protect themselves.

“We think patients will pay more attention if it is their doctor, their hospital saying, ‘Hey, you’re at risk and here’s what to do,’ than if they just see on the news that it will be hot tomorrow,” Biddinger said.

Heat kills an estimated 2,300 people every year in the United States, more than any other type of extreme weather event, and results in the hospitalization of thousands of others. Those numbers are expected to increase as climate change turbocharges temperatures, with one estimate calculating that emergency rooms could be inundated with an additional 235,000 visitors each summer. The same report, by the Center for American Progress, estimated that health care costs related to extreme heat would amount to $1 billion annually.

Mass General Brigham offers training for doctors and nurses about how climate change could affect patients. Some particularly vulnerable patients with complex or overlapping medical conditions are assigned case workers to discuss those risks.

“Just as we want our patients to control their blood sugar if they have diabetes or not be exposed to poor air quality if they have a respiratory disease, trying to help them protect themselves from heat by communicating when they are at high risk is a health care responsibility, and we are trying to do better,” Biddinger said.

But proactively warning patients is a tall order for humans to do on their own.

Patients with complicated medical conditions are assigned care managers, who follow patients more closely and will contact them before a heat wave strikes to “support their health.” But there’s not enough staff to reach everyone who has a heart or kidney condition, or those whose homes might not have air conditioning.

The AI program is still being developed, but Biddinger said he envisions it having a chatbot function, so patients can ask questions when they receive an alert.

“Our primary care doctors are so overwhelmed these days, and we don’t want them to be stuck on hold waiting for their doctor when we can use AI to help them identify cooling centers or public places with air conditioning where they can go to stay cool,” he said.

The AI alert system is meant to be a pilot program so the technology can be developed with IBM over the next two years. If it works, it could be shared with other hospitals.

“This is not being developed as a profits-driven product. It’s meant to be a service to the community that health centers across the country could use to support their patients, too,” Biddinger said.

Reprinted from E&E News with permission from POLITICO, LLC. Copyright 2025. E&E News provides essential news for energy and environment professionals.

Subscribe to Support Independent Journalism

Great science journalism requires human expertise, time, effort and creativity. And it costs money. That’s why I and the journalists here at Scientific American hope you’ll join our community.

When you subscribe, you are supporting staff and freelance journalists who are passionate about telling science stories that are true, important and compelling. Our editors and reporters are often experts in their fields, which means they understand the nuances of big discoveries and can untangle the breakthroughs from the hype. With a subscription, you are also supporting rigorous fact-checking to ensure the words we publish are precise and accurate. And you’re supporting original illustrations, graphics and photos that bring you closer to an advanced laboratory, an ice sheet in Antarctica or a space mission in orbit. You’re helping us craft other types of high-quality journalism as well: Our newsletters are carefully written, edited and curated by staffers you have or will come to know and love. Our Science Quickly podcast is based on original reporting, collaboration with editors and scientists and exacting production.

Subscriptions keep this engine running so we can continue to deliver thoughtful, rigorous and independent science journalism to you. In an era of viral misinformation, this work is crucial. If you value what we do, I hope you’ll consider joining us as a subscriber

Thank you,

Jeanna Bryner, Editor in Chief, Scientific American

Subscribe