
New Wearable Algorithm Improves Fitness Tracking in Obesity
In two studies conducted in a total of 52 people for 1838 minutes in a lab and 14,045 minutes in a 'free-living' situation, the algorithm performed mostly as well or better than 11 'gold-standard' algorithms designed by other researchers using research-grade devices, achieving over 95% accuracy in people with obesity in real-world situations.
The algorithm bridges an important gap in fitness technology — that most wearable devices are using algorithms validated mainly in people without obesity, said Nabil Alshurafa, PhD, Feinberg School of Medicine, Northwestern University, in Chicago.
Alshurafa was motivated to create the algorithm after attending an exercise class with his mother-in-law, who had obesity. His mother-in-law worked hard, but her effort barely showed on the leaderboard. He realized that most current fitness trackers use activity-monitoring algorithms developed for people without obesity.
'Commercial devices calibrate their accelerometer-to-calorie models using data mostly from people with normal BMI, using algorithms that rely on 'average' gait and metabolism,' he told Medscape Medical News. 'But people with obesity are known to exhibit differences in walking gait, speed, resting energy expenditure, and physical function. When you feed 'average' motion to kcal [kilocalories] mappings for people with different gait patterns, the math does not always line up.'
This may be particularly true for people with obesity who wear fitness trackers throughout the day on their hip, rather than their wrist, because of differences in gait patterns and other body movements.
The study was published online in Scientific Reports . The anonymized dataset and code and documentation are publicly available for use by other researchers.
'More Inclusive and Reliable'
Researchers in Alshurafa's lab developed and tested the open-source, dominant-wrist algorithm specifically tuned for people with obesity. The algorithm estimated metabolic equivalent of task (MET) values per minute from commercial smartwatch sensor data and compared them to actigraphy-based energy estimates in people with obesity.
In an in-lab study, 27 participants performed activities of varying intensities while wearing a smartwatch and a metabolic cart — a mask that measures the volume of oxygen the wearer inhales and the volume of carbon dioxide the wearer exhales to calculate their energy burn in kcals and their resting metabolic rate.
The activities included, among others, typing on a computer, lying still on the floor doing nothing, walking slowly on a treadmill, doing pushups against a door, and following along with an aerobics video. Each activity was performed for 5 minutes, followed by 5 minutes of rest. The researchers compared the fitness tracker results against the metabolic cart results.
Another 25 participants wore a smartwatch and a body camera for 2 days in a free-living study. The body camera enabled the researchers to visually confirm when the algorithm over- or under-estimated kcals.
The in-lab analysis included 2189 minutes of data and the free-living analysis included 14,045 minutes of data.
Compared to the metabolic cart, the new algorithm achieved lower root mean square error across various sliding windows (analyses of continuous and overlapping data streams).
In the free-living study, the algorithm's estimates fell within ±1.96 SDs of the best actigraphy-based estimates for 95.03% of minutes.
'Our proposed method accurately estimated METs compared to 11 algorithms primarily validated in nonobese populations, suggesting that commercial wrist-worn devices can provide more inclusive and reliable [energy expenditure] measures using our algorithm,' the authors wrote.
Challenges Ahead
More work needs to be done before apps for iOS and android driven by the new algorithm are available for use later this year, Alshurafa said. Because the model is tuned for users with obesity, 'we need a reliable way to obtain BMI or body composition, and possibly ways of turning on and off the algorithm over time or perhaps modifying the algorithm as people's fitness level changes.'
'Because we've optimized for the dominant hand, we'll need clear user guidance, and possibly user-interface prompts, to drive this cultural shift in watch placement,' he said.
To ensure accuracy across diverse users, activities, and wear styles, the team will conduct field testing and pool anonymized data.
'Power, size, and regulatory requirements may force trade-offs, so we'll work closely with device manufacturers on adaptive calibration routines and streamlined firmware,' Alshurafa said. 'But the real priority is training and tailoring our systems on truly diverse data and being transparent about who's represented in that data. Too many commercial devices skip this, leading users to assume they work universally when their models actually have limitations.'
For now, clinicians should be aware that the app has only been validated so far in individuals with obesity wearing their tracker on the dominant wrist and use outside that population or on the nondominant wrist may yield less accurate calorie estimates, he added. 'Beyond those parameters, though, the algorithm is ready for deployment and offers a powerful new tool for personalized activity monitoring.'
Mir Ali, MD, a bariatric surgeon and medical director of MemorialCare Surgical Weight Loss Center at Orange Coast Medical Center in Fountain Valley, California, agreed that an algorithm that more accurately reflects exercise and energy expenditure of patients with obesity would be helpful, and that 'any improvements' would likely be beneficial for patients and clinicians.
That said, 'a larger study comparing the new algorithm vs currently available devices would provide more validation,' Ali, who was not involved in the study, told Medscape Medical News .
In addition, 'research elucidating exercise goals and calorie expenditure for obese patients could be helpful to better counsel patients on what is the optimal goal for weight loss,' he said.
Ali noted that 'trackers for heart disease and pulmonary problems may be useful to help patients attain cardio-pulmonary improvement' — and indeed, Alshurafa's team will be looking at ways to tailor fitness trackers for diabetes and hypertension going forward.
This study is based on work supported by the National Institute of Diabetes and Digestive and Kidney Diseases, the National Science Foundation, the National Institute of Biomedical Imaging and the National Institutes of Health's National Center for Advancing Translational Sciences.
Alshurafa and Ali declared no competing interests.
Hashtags

Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles


Forbes
31 minutes ago
- Forbes
AI Skill Stacks: How Teens Can Future-Proof Their Careers Today
skill stacking helps teen prepare for AI economy Pick a major. Get a degree. Find a job. That roadmap guided generations to middle-class stability, but it's crumbling for today's teenagers. Their parents climbed predictable career ladders in industries that existed for decades. Today's teens will work in fields that don't yet have names, using tools that haven't been invented, solving problems we can't imagine. Consider this: Artificial intelligence now writes code, diagnoses diseases, and creates art. Meanwhile, entirely new roles emerge monthly, such as prompt engineers, AI ethicists, and virtual reality architects. Universities can't build curricula fast enough to keep pace. The answer isn't more credentials. It's skill stacking—intentionally combining abilities that amplify each other's value. A teenager who codes, designs graphics, and leads student government isn't just well-rounded. They're positioning themselves for careers in user experience, tech policy, or digital product management—fields that reward exactly this combination of technical skill, visual thinking, and leadership ability. The best part? Teens don't need to wait for college or permission to start. They can begin building their stack today, using the time and freedom they have right now to experiment, fail, and discover what combination of skills makes them uniquely valuable. What Is a Skill Stack In An AI World? A skill stack is your toolkit of abilities that, when combined, create value beyond the sum of its parts. Unlike deep specialization in a single field, a stack leverages both breadth and depth. Consider a teenager who learns basic Python coding, develops an eye for graphic design, and builds strong communication skills through the debate club. On their own, each skill is valuable—but together, they open doors to careers in user experience research, product design, or tech-driven marketing roles. In the age of AI, humans maintain an edge when they bring together technical, creative, and social skills. According to the World Economic Forum, skills such as creativity, critical thinking, and resilience are among the top 10 skills that employers will prioritize by 2025. Machines can analyze data, but they can't design innovative solutions that also resonate emotionally. They can process language, but they can't truly persuade, lead, or create culture. Why Teens Can Build AI-Ready Skills Now Teenagers are actually at the perfect stage to embrace this way of thinking. They're in a low-stakes environment where it's okay to experiment and fail. Free or low-cost learning resources are widely available to them. Many already have informal skill stacks developing through their hobbies, part-time jobs, or extracurricular activities. For example, a teenager who streams video games (technical literacy and audience engagement), edits highlight reels for social media (creativity and digital tools), and manages a Discord community (leadership and communication) is already developing skills without realizing it. What they need now is intention—to see how their interests and efforts fit into a broader strategy for their future. The 5 Key AI-Era Skill Categories At the very least, teens need to become fluent in the language and logic of technology. This doesn't mean everyone must become a programmer, but it does mean that everyone should understand the basics of how AI, algorithms, and data systems work. Ways to build this skill: As technology raises new dilemmas about privacy, fairness, and bias, those who can think critically and ethically will stand out. This is about asking good questions, analyzing consequences, and resisting easy answers. Ways to build this skill: Regardless of how advanced AI becomes, humans will continue to value clear, persuasive, and empathetic communicators. Writing, public speaking, and interpersonal skills are essential for success. Ways to build this skill: AI can replicate patterns, but humans create the patterns. Creativity—whether in art, design, storytelling, or problem-solving—is a uniquely human strength. Ways to build this skill: Even if they never start a business, teens benefit from thinking like an entrepreneur—spotting opportunities, taking initiative, and building something from nothing. Programs that teach entrepreneurial thinking help develop skills that can be applied to any career path. Ways to build this skill: How Teens Can Start Building AI-Ready Skills Today Getting started doesn't have to be overwhelming. Here are practical steps teens can take right now: Take one free online course this summer. Platforms like Coursera, edX, and Khan Academy have thousands of options. Start a project. Launch a blog, start a YouTube channel, or organize a community clean-up. Join a club or group. Whether it's coding, business, robotics, or the arts, being around others also builds collaboration skills. Find a mentor. Reach out to professionals or older students for advice and guidance. Reflect regularly. Keep a journal or portfolio of what you're learning and how your stack is growing. What Parents & Educators Can Do To Support AI-Ready Learning Parents and teachers play a critical role in fostering this mindset. Instead of pushing teens toward a single "safe" path, they can: At WIT (Whatever It Takes), the organization I founded in 2009, we've seen how early exposure to skill stacking through entrepreneurship education transforms young people's confidence and capabilities. Our graduates don't just start businesses—they become problem solvers who can adapt to whatever challenges they encounter. The AI Economy Belongs To Stack Builders The AI-driven future belongs to those who can adapt, recombine, and apply their skills in creative ways. For teens, the earlier they start stacking, the higher they can climb. In an AI-dominated economy, it's no longer enough to specialize narrowly and hope your role doesn't get automated. What makes you indispensable is your ability to bring together technical fluency, critical thought, creativity, communication, and entrepreneurial grit—skills that complement rather than compete with artificial intelligence. The good news? Teens already have everything they need to start stacking. All it takes is intention, action, and the willingness to keep learning in a world where AI amplifies human potential rather than replacing it.
Yahoo
34 minutes ago
- Yahoo
You Can Still See the Aurora Borealis Tonight. Here's Where the Brightest Lights Will Glow
The Fourth of July holiday will bring explosive light shows on Friday night, but many folks will see much quieter and calmer lights in the sky tonight, as recent solar activity will continue to bring the Aurora Borealis to several US states. Wednesday night marks the winding down of a Kp 4 magnetic storm that the Space Weather Prediction Center reported starting late Monday evening. The K-Index measures the horizontal impact of geomagnetic storms, and a Kp4 or Kp 5 rating results in what the National Oceanic and Atmospheric Administration calls a "moderate" aurora. As Wednesday night turns into Thursday morning, the aurora will pull back a little and become less visible, unless you're on the northern border with Canada. According to the Space Weather Prediction Center, Wednesday night's aurora will be visible in Alaska, Washington state, Idaho, Montana, Wyoming, North and South Dakota, Minnesota, Wisconsin, Michigan, and Maine. The northernmost sections of New York, Vermont and New Hampshire might get lucky as well. Alaska and Canada will have the best views by a wide margin, with virtually the entire state of Alaska getting coverage. Much like with the Earth's weather, space weather prediction can be hit or miss. So if you're in any of the above states, it's worth taking a look if you're up that late. The magnetic storm may be slightly stronger or weaker than forecast, which will affect how far south the northern lights reach. This event won't be as strong as the epic show we saw in May 2024. The standard space viewing tips all apply here. You'll get a better view if you get away from the city and suburbs to avoid light pollution. Weather will play a role as well, since any clouds will obfuscate the view. If you attempt to photograph the aurora, we recommend using long exposure times to give your camera more time to soak in the light. Other than that, you'll want to look toward the northern horizon to give yourself the best chance at a good view, since (as you may've guessed) that's where the northern lights originate.
Yahoo
42 minutes ago
- Yahoo
How Crypto's Most Boring Token Became the U.S. Treasury's $200 Billion Lifeline – And Why It Could Hit $2 Trillion
Benzinga and Yahoo Finance LLC may earn commission or revenue on some items through the links below. Major banks are scrambling to launch stablecoins as digital tokens emerge as an unexpected lifeline for U.S. Treasury markets The crypto world's most boring investment might just become Wall Street's most important player. Stablecoins—digital tokens pegged to the dollar—are quietly positioning themselves as a crucial buyer of U.S. government debt, potentially absorbing hundreds of billions in Treasury securities over the next decade. Stablecoins now account for roughly $200 billion in Treasury and repo market investments—about 80% of the $256 billion stablecoin market, according to Reuters. Don't Miss: — no wallets, just price speculation and free paper trading to practice different strategies. Grow your IRA or 401(k) with Crypto – . At last week's Money Fund Symposium in Boston, State Street Global Advisors CEO Yie-Hsin Hung highlighted the growing influence of stablecoins across traditional financial markets.' 'But here's the kicker,' Hung noted. 'Stablecoins are growing fast, and most likely, will outpace the growth of Treasury supply.' The mechanics are surprisingly straightforward. When Circle, the company behind USDC stablecoin, sees demand for its tokens increase by $10 billion, it must purchase $10 billion in Treasuries to maintain the crucial 1:1 peg to the dollar. It's a simple equation that's creating a powerful feedback loop. This timing couldn't be better for the U.S. Treasury. With expectations of up to $1 trillion in new government debt issuance by year-end, participants are desperately searching for reliable buyers. Enter stablecoins: a growing class of investors that must buy Treasuries by design, not choice. 'If they do indeed squeeze this supply balloon on Treasuries and rely on the front end of the curve for debt issuance, we think that one of the justifications is that all this demand coming from stablecoins gives Treasury Secretary Scott Bessent cover to make that shift to the shorter end,' explained Mark Cabana, head of U.S. rates strategy at BofA Securities. Trending: New to crypto? on Coinbase. The demand from traditional finance is reaching fever pitch. Adam Ackermann, head of portfolio management at Paxos, said he's fielding calls from the world's largest banks with an urgent message: 'I need a stablecoin in eight weeks. How can we get one?' This corporate rush intensified after the U.S. Senate passed the GENIUS Act recently—landmark legislation creating a regulatory framework for stablecoins. While the Republican-controlled House still needs to pass its version before reaching President Doanld Trump's desk, the bill's advancement has unleashed pent-up institutional demand. Standard Chartered estimates the stablecoin market could explode from today's $256 billion to $2 trillion by 2028 if the legislation becomes law. That would represent roughly $1.6 trillion in additional Treasury demand—a massive injection into government debt markets. But not everyone is celebrating this digital gold rush. Ackermann, despite being in the business of issuing stablecoins, is sounding a cautionary note: 'What's somewhat concerning is we're just at this fever pitch right now. It's great for the industry, but we need to start to put some guardrails on things.' His concern reflects broader questions about what happens when crypto markets experience their inevitable volatility. If stablecoin demand suddenly contracts, will Treasury markets face an equally dramatic reduction in buying pressure? There's also the concentration risk. Currently, just two companies—Circle and Tether—dominate the stablecoin landscape. A regulatory crackdown or operational issue at either could ripple through Treasury markets in unpredictable investors, this trend presents both opportunities and considerations: Treasury Impact: Increased stablecoin demand could provide a floor for short-term Treasury prices, potentially benefiting money market funds and short-duration bond strategies. Crypto Correlation: The deeper integration between stablecoins and Treasury markets could create new transmission channels between crypto volatility and traditional fixed income. Regulatory Risk: The entire thesis depends on favorable regulation. Any setbacks to stablecoin legislation could dramatically alter the demand dynamics. Long-term Sustainability: While $200 billion represents less than 2% of the overall Treasury market today, BofA's Cabana expects stablecoins to become 'an incremental demand source over the next three to five, certainly 10 years.' The convergence of crypto innovation and traditional finance is creating unexpected solutions to age-old problems. Stablecoins may have started as a niche crypto product, but they're evolving into a critical piece of U.S. debt market infrastructure. Whether this represents a sustainable solution or a new source of systemic risk remains to be seen. What's certain is that the boring world of government debt just got a lot more interesting—and potentially a lot more volatile. Read Next: Named a TIME Best Invention and Backed by 5,000+ Users, Kara's Air-to-Water Pod Cuts Plastic and Costs — Image: Shutterstock This article How Crypto's Most Boring Token Became the U.S. Treasury's $200 Billion Lifeline – And Why It Could Hit $2 Trillion originally appeared on Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data