Sign up for our daily briefing

Make your busy days simpler with Axios AM/PM. Catch up on what's new and why it matters in just 5 minutes.

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Catch up on coronavirus stories and special reports, curated by Mike Allen everyday

Catch up on coronavirus stories and special reports, curated by Mike Allen everyday

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Denver news in your inbox

Catch up on the most important stories affecting your hometown with Axios Denver

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Des Moines news in your inbox

Catch up on the most important stories affecting your hometown with Axios Des Moines

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Minneapolis-St. Paul news in your inbox

Catch up on the most important stories affecting your hometown with Axios Twin Cities

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Tampa Bay news in your inbox

Catch up on the most important stories affecting your hometown with Axios Tampa Bay

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Charlotte news in your inbox

Catch up on the most important stories affecting your hometown with Axios Charlotte

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Eric Risberg / AP

Using the Apple Watch and artificial intelligence, health startup Cardiogram reports they could detect a type of abnormal heart rhythm with 97% accuracy by analyzing data from the watch's heart sensor.

Why it matters: Atrial fibrillation affects an estimated 2.7 million people in the U.S. and is a predictor of heart attack, stroke and dementia. The abnormal rhythms are the cause of 1 in 4 strokes. In many cases, there are no symptoms and though people are monitored for weeks to try to catch the abnormalities, months can pass before they occur, so they are missed. The researchers hope by continuously monitoring for abnormalities they can lower the number of undiagnosed cases.

Methodology: The researchers collected heart rate and EKG measurements from 6,158 Apple Watch users who are part of the UCSF Health eHeart study. 166 of them had been diagnosed with atrial fibrillation. Their measurements were used to train a neural network to tell the difference between normal and abnormal heart rhythms. They then tested the AI in 51 patients who were in the hospital for a procedure to reset their heart rate and found it could detect atrial fibrillation with 97% accuracy compared to an electrocardiogram.

Bigger picture: The study is the latest demonstration of how AI might find its way into medicine. Stanford researchers recently reported an AI could analyze images to detect skin cancer and Google has taken a similar approach to screen for diabetic retinopathy.

What's needed: More testing with more people. Cardiogram also plans to hone the algorithm and test it against "gold standard" EKG measurements. The researchers reported 90% specificity meaning roughly 1 in 10 detections was a false positive. "The real challenge isn't the tech, but framing the implementation of these new tools in a way that maximizes benefit for health care while minimizing risk of over treatment due to false positives," says Mintu Turakhia from the Stanford Center for Digital Health, who adds "this is promising work."

Go deeper

Tech scrambles to derail inauguration threats

Illustration: Sarah Grillo/Axios

Tech companies are sharing more information with law enforcement in a frantic effort to prevent violence around the inauguration, after the government was caught flat-footed by the Capitol siege.

Between the lines: Tech knows it will be held accountable for any further violence that turns out to have been planned online if it doesn't act to stop it.

Dave Lawler, author of World
5 hours ago - World

Uganda's election: Museveni declared winner, Wine claims fraud

Wine rejected the official results of the election. Photo: Sumy Sadruni/AFP via Getty

Yoweri Museveni was declared the winner of a sixth presidential term on Saturday, with official results giving him 59% to 35% for Bobi Wine, the singer-turned-opposition leader.

Why it matters: This announcement was predictable, as the election was neither free nor fair and Museveni had no intention of surrendering power after 35 years. But Wine — who posed a strong challenged to Museveni, particularly in urban areas, and was beaten and arrested during the campaign — has said he will present evidence of fraud. The big question is whether he will mobilize mass resistance in the streets.

Off the Rails

Episode 1: A premeditated lie lit the fire

Photo illustration: Sarah Grillo/Axios. Photo: Chip Somodevilla/Getty Images

Beginning on election night 2020 and continuing through his final days in office, Donald Trump unraveled and dragged America with him, to the point that his followers sacked the U.S. Capitol with two weeks left in his term. Axios takes you inside the collapse of a president with a special series.

Episode 1: Trump’s refusal to believe the election results was premeditated. He had heard about the “red mirage” — the likelihood that early vote counts would tip more Republican than the final tallies — and he decided to exploit it.

"Jared, you call the Murdochs! Jason, you call Sammon and Hemmer!”