Aprile, 2022

Today, Fitbit received clearance from the U.S. Food and Drug Administration for our new PPG (photoplethysmography) algorithm to identify atrial fibrillation (AFib). The algorithm will power our new Irregular Heart Rhythm Notifications feature on Fitbit.[71d620]

You’ve got rhythm, but is it irregular?

AFib is a form of irregular heart rhythm that affects nearly 33.5 million people globally, and individuals with AFib have five times higher risk of stroke. Unfortunately, AFib can be difficult to detect as there are often no symptoms and episodes can come and go.

Our new PPG AFib algorithm can passively assess your heart rhythm in the background while you’re still or asleep. If there’s anything that might be suggestive of AFib, you’ll be notified through our Irregular Heart Rhythm Notifications feature — allowing you to talk with your healthcare provider or seek further assessment to help prevent a significant medical event, such as stroke.

So how does PPG AFib detection work?

When your heart beats, tiny blood vessels throughout your body expand and contract based on changes in blood volume. Fitbit’s PPG optical heart-rate sensor can detect these volume changes right from your wrist. These measurements determine your heart rhythm, which the detection algorithm then analyzes for irregularities and potential signs of atrial fibrillation.

The clinical validation for Fitbit’s PPG algorithm is supported by data from the landmark Fitbit Heart Study, which launched in 2020 and enrolled 455,699 participants over five months. The study was conducted entirely virtually during the pandemic, making it one of the largest remote studies of PPG-based software to date. Data presented at the 2021 American Heart Association Scientific Sessions found that the Fitbit PPG detections correctly identified AFib episodes 98% of the time, as confirmed by ECG patch monitors.

Because AFib can be so sporadic, the optimal way to screen for it is through heart rate tracking technology when the body is still or at rest — making overnight detection when people are asleep especially important. The unique capabilities of Fitbit devices — especially its 24/7 heart rate tracking and long battery life — give it the potential to accelerate identification through long-term heart rhythm assessment.

All the ways to monitor heart health with Fitbit

With today’s FDA clearance of our PPG-based algorithm, Fitbit now provides two ways to detect AFib. Fitbit’s ECG app, which takes a spot-check approach, allows you to proactively screen yourself for possible AFib and record an ECG trace that you can then review with a healthcare provider. Additionally, the new PPG-based algorithm allows for long-term heart rhythm assessment that helps identify asymptomatic AFib that could otherwise go undetected.

The Fitbit PPG-based algorithm and Irregular Heart Rhythm Notifications feature will soon be available to consumers in the U.S. across a range of heart-rate enabled devices. We want to make AFib detection as accessible as possible to help reduce the risk of potentially life-threatening events — like stroke — and ultimately improve overall heart health for everyone. We’ll continue to work with the BMS-Pfizer Alliance to develop educational content for patients and healthcare providers that will help identify and support people in the U.S. with irregular heart rhythms consistent with atrial fibrillation.

Visit our site to learn more about our PPG technology.

It was an honor and a privilege to attend a special event in the Bulgarian capital, Sofia, today to launch INSAIT, the Institute for Computer Science, Artificial Intelligence and Technology. INSAIT is a new AI and computer science research institute that will provide truly world-class facilities.

It’s fantastic to see the country where I was born leading the charge in bridging Eastern Europe to the world-stage in computer science research.

The institute is modeled on the computer science departments of renowned institutions such as MIT, UC Berkeley and the Max-Planck Institute, and is backed by the Bulgarian government with an endowment fund of nearly $100 million. Its computer science and AI research will span topics such as machine learning, quantum computing, information security, robotics and many more. Within two years, INSAIT expects faculty and students to publish papers in top conferences.

Google is investing $3 million over the next three years to provide INSAIT with cloud computing resources and access to itsTensor Processing Unit Research Cloud, a specialized infrastructure for running high-performance machine learning models. Supported with additional investment from DeepMind and Amazon Web Services, INSAIT aims to attract and develop the best researchers, engineers and top PhD and MSc students.

I know there’s no shortage of talented researchers, computer scientists and engineers in Eastern Europe – indeed, Sofia is already ranked asone of Europe’s top tech cities – but historically, the lack of local facilities, funding and support has meant limited opportunities for basic research. INSAIT has been created in partnership with two of the world’s leading technology universities, ETH Zurich and EPFL Lausanne, and its supervisory and advisory boards consist of leading researchers who are committed to help the institute achieve its ambitious goals.

INSAIT opens in September, and I know the team is particularly keen to receive applications from women and other groups that are often underrepresented in the world of tech.

Google is delighted to support these efforts, and I cannot wait to see what new innovation emerges from this promising venture.

Over the last few years we’ve seen a rise in bad actors using the internet for illegal activities, and we see it in our work. Every single day we stop more than 100 million harmful emails from reaching our users, and we routinely work with law enforcement to combat nefarious actors. But across the web, people are caught in romance scams, loan scams, and investment scams every day — and older Americans are often the most vulnerable.

Raising public awareness can help people avoid becoming victims. But for more emergent illicit behaviors and scams, lawsuits are an effective tool for establishing a legal precedent, disrupting the tools used by scammers, and raising the consequences for bad actors. That’s why last December we used our resources to file a lawsuit to combat illegal activity in the botnet industry and have used legal action to defend small businesses from scammers masquerading as Google. With these actions, we establish legal precedent to help stop similar cyber threats and scams.

Today, we’re building on this work by taking legal action against an actor who was operating fraudulent websites and using Google products as a part of their scheme. The actor used a network of fraudulent websites that claimed to sell basset hound puppies — with alluring photos and fake customer testimonials — in order to take advantage of people during the pandemic.

This type of scheme follows a similar script to many online scams where malicious actors pretend to be someone they are not to convince victims to give them money for something they will never receive. The Better Business Bureau recently announced that pet scams now make up 35% of all online shopping scams reported to them, and this particular scam targeted people at their most vulnerable, just as the pandemic led to a record spike in people wanting to own pets. (According to Google Search Trends, searches for “Adopt a Dog” spiked at the start of the pandemic as people spent more time at home. By the end of 2020, 70% of Americans reported owning a pet.)

Sadly, this scam disproportionately targeted older Americans, who can be more vulnerable to cyberattacks. The FTC and FBI report that older people are scammed out of an estimated $650 million per year.

That’s why we’re taking proactive action to set a legal precedent, protect victims, disrupt the scammer’s infrastructure, and raise public awareness. Of course, legal action is just one way we work to combat these types of scams. We build our security into all of our products and use machine learning to filter new threats, and our CyberCrime Investigation Group investigates misconduct and sends referrals to various law enforcement agencies including the Department of Justice to combat nefarious actors engaging in a wide range of scams including pets, covid relief, romance, and tech support scams.

Here are some additional steps you can take to help spot a pet scam:

• See the pet in person (or on a video call) before paying any money. This way, you are able to see the seller and the actual pet for sale. More often than not, scammers won’t comply with the request.
• Use verified payment methods. ​​Avoid wiring money or paying with gift cards or prepaid debit cards. And before you pay, research prices for what you’re looking to purchase. If someone is advertising a product at a deeply discounted price, you could be dealing with a fraudulent offer.
• Reverse image search. Search to see if the item or product is a stock image or stolen photo. Using Google Chrome, place the cursor over the photo and right click, then choose the option “Search Google for image.” If that picture shows up in a number of places, you’re likely dealing with a scam.
• Search online for the seller. Ask for the company name, number and street address. See what Google search results pop up. If you can’t find anything, the name and address are likely fake.

We will continue to work with federal and state agencies and law enforcement to ensure our consumers are better protected from fraud online.