Google Research has developed a system that can monitor your heart rate simply by looking at your face through your smartphone’s front camera. The technology works passively in the background during normal phone use, capturing brief video clips after you unlock your device with face recognition.

This breakthrough matters because it could make heart health monitoring accessible to the five billion smartphone users worldwide, particularly in areas where fitness trackers and medical devices are too expensive or unavailable. More importantly, Google’s system is the first to achieve medical-grade accuracy across all skin tones – addressing a critical bias problem that has plagued pulse oximeters and other health monitoring devices.

How the technology works

The Passive Heart Rate Monitoring (PHRM) system uses a technique called photoplethysmography, which detects tiny changes in how light reflects off your skin as blood flows through it. When you unlock your phone with face recognition, the system captures an 8-second video clip and uses AI to analyze subtle color changes in your face that correspond to your heartbeat.

The system then processes these measurements throughout the day to calculate your resting heart rate – a key indicator of cardiovascular health. Higher resting heart rates are linked to increased risk of heart disease and death from all causes.

Solving the skin tone accuracy problem

Previous heart rate monitoring technologies have struggled with darker skin tones because melanin makes it harder for cameras and sensors to detect the subtle changes needed for accurate readings. This has created serious equity issues in health tech – pulse oximeters, for example, have been shown to provide less accurate readings for Black patients.

Google addressed this by training their system on over 350,000 video clips from nearly 700 diverse participants. They deliberately ensured that:

• At least 25% of participants had light skin (Monk scale 1-4)
• At least 25% had medium skin (Monk scale 5-7)
• At least 33% had dark skin (Monk scale 8-10)

The company also set a strict requirement that the system’s accuracy must not vary by more than 5 percentage points between different skin tone groups.

Real-world testing results

Google tested the system in both controlled laboratory settings and real-world conditions. In the lab study with 365 participants, PHRM achieved less than 10% error compared to medical-grade electrocardiogram readings across all skin tone groups.

The real-world study was particularly ambitious. Google had 231 people install a special app on their personal phones and use them normally for eight days while wearing chest-strap heart monitors and Fitbit devices for comparison. The app captured an average of 231 video clips per day after each face unlock.

Results showed the system achieved:

• 5.04% error for light skin tones
• 5.12% error for medium skin tones
• 7.84% error for dark skin tones

All groups met medical industry accuracy standards of less than 10% error. For daily resting heart rate estimates, the system matched the accuracy of fitness trackers like the Fitbit Charge 6, with less than 5 beats per minute difference on average.

Privacy and practical challenges

The system faces some limitations that Google acknowledges. Success rates were lower for people with darker skin, though accuracy remained high when measurements were successful. The technology also struggles when people are talking or moving their heads significantly during the brief recording window.

Privacy represents another consideration. While Google’s research version required participants to manually approve video uploads after reviewing them, any commercial implementation would need robust on-device processing to protect user data.

Making research resources available

Google is releasing its dataset and a simplified version of the AI model to qualified researchers with institutional approval. This represents the largest and most diverse collection of smartphone-based heart rate monitoring data ever made available for research.

The dataset is restricted to non-commercial research use, and researchers are prohibited from trying to identify individuals or publicly displaying the video content.

This research could eventually make heart health monitoring as simple as unlocking your phone, potentially helping millions of people track cardiovascular health who couldn’t otherwise afford or access fitness trackers or medical monitoring devices.

The post Google develops smartphone heart rate monitoring that works for all skin tones appeared first on mHealth Spot.

AI drug discovery company Owkin has signed a multi-year deal with pharmaceutical giant Sanofi to develop custom AI agents that can autonomously perform complex research tasks. The partnership extends their existing collaboration, which began in 2021 with a €90 million strategic agreement.

The new collaboration represents a shift toward what Owkin calls “embedded AI” – specialized AI systems that work directly within pharmaceutical companies’ existing workflows. These AI agents will be deployed through Owkin’s K Pro platform, which the company describes as an “AI scientist” for pharmaceutical research.

What makes these AI agents different

Unlike general-purpose AI tools, these agents are designed specifically for pharmaceutical work. They can handle tasks across the entire drug development process, from early discovery through clinical trials. The system combines patient data from multiple sources with specialized AI models trained on biological processes.

K Pro aims to help pharmaceutical companies make faster, more informed decisions by automating routine research tasks and providing competitive intelligence. The platform analyzes multimodal patient data – combining genetic information, medical imaging, clinical records, and other biological data.

Building on an existing partnership

Owkin and Sanofi have worked together since 2021, initially focusing on cancer research and patient classification. They later expanded their collaboration to include drug positioning for Sanofi’s immunology treatments. This new agreement represents the next phase of that partnership.

“Building on our collaboration with Sanofi, this marks a shift toward truly embedded AI,” said Thomas Clozel, CEO and co-founder of Owkin. “Sanofi can further harness agentic systems within their own workflows, unlocking the full value of their data to accelerate better decisions across drug development.”

Emmanuel Frenehard, Sanofi’s Chief Digital Officer, said the company is “continually investing in frontier AI solutions with the potential to accelerate and improve decision-making throughout the drug development lifecycle.”

The broader AI drug discovery trend

This partnership reflects a wider trend in pharmaceutical research, where companies are increasingly turning to AI to speed up drug discovery and reduce costs. Traditional drug development can take over a decade and cost billions of dollars, with high failure rates.

Owkin positions this work as part of its mission to achieve what it calls “Biological Artificial Superintelligence” – AI systems that can make therapeutic discoveries beyond what human researchers could achieve alone. The company believes this technology could help automate some of the most complex challenges in pharmaceutical research and development.

The post Owkin partners with Sanofi to build custom AI agents for drug discovery appeared first on mHealth Spot.

A team at the University of Cambridge has completed the first human trial of a vaccine with an active ingredient designed entirely by artificial intelligence. The experimental vaccine showed no significant side effects in 39 healthy volunteers and triggered immune responses against multiple coronavirus strains.

This represents a major shift in how vaccines could be developed. Instead of racing to catch up with new virus variants after they spread, scientists used AI to create a ‘universal’ vaccine that could protect against diseases that don’t even exist yet.

How the AI vaccine works

The researchers fed their AI model genetic sequence data from Sarbeco coronaviruses – a family that includes SARS-CoV-2, the virus behind COVID-19. The machine learning system then designed an antigen containing features common across the entire virus group.

This approach produced what the team calls a ‘super-antigen’ that triggered protective immune responses against:

• SARS-CoV-2 (COVID-19)
• SARS
• Related bat viruses that could cause future pandemics

The trial involved 39 volunteers aged 18-50 at medical facilities in Southampton and Cambridge. All participants showed immune responses without serious side effects.

Breaking the vaccine update cycle

Traditional vaccines face a constant challenge: viruses mutate faster than scientists can update vaccines. This creates an endless cycle of playing catch-up with new variants.

‘We’ve converted vaccine development from being reactive to being future proof,’ said Professor Jonathan Heeney from Cambridge’s Department of Veterinary Medicine, who led the research. ‘Our vaccines will continue to provide protection against viruses even as they mutate into new strains.’

The approach could extend beyond coronaviruses to other diseases that jump between humans, including flu and Ebola.

What comes next

The small trial size means more testing is needed. The next phase will include a larger, more diverse group of participants to better assess the vaccine’s effectiveness across different populations.

If successful, this AI-driven approach could fundamentally change pandemic preparedness. Rather than waiting for the next outbreak to develop vaccines, scientists could create broad-spectrum protection against entire virus families before new threats emerge.

The post Cambridge researchers test first AI-designed vaccine in humans appeared first on mHealth Spot.

Samsung is giving its Galaxy Watch a major health overhaul that finally addresses what most fitness trackers get wrong: turning mountains of biometric data into advice you can actually use. The company announced today that its Samsung Health app will get smarter AI features that focus on practical guidance rather than just tracking numbers.

This matters because most wearables overwhelm users with charts and metrics without explaining what any of it means. Samsung’s approach shifts from passive monitoring to active coaching. The update rolls out June 8 and represents Samsung’s biggest push yet to compete with Apple Watch’s health features, which have long been considered the gold standard in consumer health tech.

Four new features that actually sound useful

Samsung’s health upgrade centers on four main additions that work together to create a clearer picture of your daily wellness:

• Vitals: Analyzes five overnight bio-signals (heart rate, heart rate variability, respiratory rate, skin temperature, and blood oxygen) and only alerts you when something meaningful changes. No more notification spam about minor fluctuations.
• Heart Health Score: Combines sleep, stress, activity, and body composition data into one daily number that shows how your habits affect long-term heart health.
• Daily Cardio Load: Measures how much cardiovascular strain you’ve accumulated and recommends when to push harder or take a break during workouts.
• Fitness Index: Compares your heart rate, VO2 max, and daily steps against similar users to identify strengths and weaknesses in your fitness routine.

Why this approach might work better

The key difference is Samsung’s focus on reducing “alert fatigue” – the problem where fitness trackers send so many notifications that users start ignoring them all. Instead of alerting you every time your heart rate changes, the Vitals feature establishes your personal baseline and only speaks up when something actually noteworthy happens.

This builds on Samsung’s existing Energy Score feature, which already tried to simplify health data into a single daily metric. The company says these new features will help users “understand their physical and mental condition more easily and intuitively,” according to Hon Pak, who leads Samsung’s digital health team.

Better design and ecosystem integration

Samsung is also redesigning the Health app around five core areas: Sleep, Activity, Nutrition, Mindfulness, and Vitals. The new layout puts daily wellness tips and your AI-powered Energy Score front and center, so you can quickly see how different parts of your routine connect.

The company is also adding new features that work across multiple Galaxy devices:

• Enhanced Antioxidant Index: Better tracking of nutritional intake with trend charts showing how diet affects your body over time
• Improved AGEs index: Automatic overnight measurements that build a long-term picture of how lifestyle choices impact your health
• Hearing Health: Uses Galaxy Watch to monitor ambient noise levels and protect your ears during loud commutes or workouts

The bigger health tech battle

This update positions Samsung to compete more directly with Apple Watch’s health features, which have set the bar for consumer health monitoring. Apple has been adding medical-grade features like ECG monitoring and fall detection, while also focusing on making health data more actionable through its Health app.

Samsung’s approach appears focused on AI-powered insights rather than adding more sensors. This makes sense given that most users already struggle to interpret the data from existing sensors. By making the software smarter rather than the hardware more complex, Samsung might find a more sustainable path to health tracking that people actually stick with long-term.

The new features will debut on Samsung’s upcoming Galaxy Watch models, though the company hasn’t announced a specific launch date for the new hardware yet.

The post Samsung Galaxy Watch gets AI health upgrade that actually makes sense appeared first on mHealth Spot.

Mayo Clinic and Microsoft announced a strategic partnership to develop a specialized AI model designed specifically for healthcare applications. The collaboration aims to make Mayo Clinic’s medical expertise more widely accessible while improving experiences for both patients and healthcare providers.

This partnership represents a significant step in the evolution of medical AI, moving beyond general-purpose models to create systems built specifically for healthcare’s unique requirements. The timing comes as healthcare organizations increasingly seek AI solutions that can handle complex medical reasoning and deliver actionable clinical insights.

Combining medical expertise with AI capabilities

The partnership brings together Mayo Clinic’s global healthcare knowledge, anonymized clinical data, and patient insights with Microsoft’s advanced AI and cloud computing technology. The organizations are developing what they call a “frontier AI model” capable of supporting broad clinical reasoning across various healthcare scenarios.

The AI system is designed to analyze diverse clinical information to support:

• Earlier disease diagnoses
• More personalized treatment recommendations
• Better overall patient outcomes
• Complex medical decision-making for care teams

Ownership and deployment strategy

Mayo Clinic will own the AI model, maintaining control over clinical data governance and ensuring responsible AI practices. Microsoft plans to make the system available globally through its Azure Foundry APIs, allowing other healthcare organizations worldwide to access these advanced AI capabilities.

“Mayo Clinic is committed to putting patients first, and we have long believed AI can help transform healthcare,” said Dr. Gianrico Farrugia, Mayo Clinic’s president and CEO. “By combining our clinical expertise and data foundation with Microsoft’s engineering and AI capabilities, we are building something healthcare has never seen before.”

Purpose-built for healthcare challenges

The model differs from general AI systems by incorporating deep clinical context and longitudinal medical understanding. Healthcare AI requires specialized governance and real-world validation that general-purpose models cannot provide.

The system will initially deploy within Mayo Clinic’s clinical environment, where medical professionals can test, refine, and improve it through actual patient care scenarios. This approach allows for continuous development based on real-world medical applications.

“Frontier medical intelligence is around the corner,” said Mustafa Suleyman, CEO of Microsoft AI. “Mayo has unparalleled clinical expertise, de-identified clinical health data and longitudinal medical insights, and we’re thrilled to partner with their world-class physicians to build a state-of-the-art foundation model for healthcare.”

Building on existing platform initiatives

This collaboration builds on Mayo Clinic’s existing technology foundation. Seven years ago, Mayo launched its Platform initiative to transform healthcare from traditional pipeline models to platform-based approaches using anonymized patient data to accelerate medical innovation and discoveries.

The partnership reflects broader industry trends toward specialized AI applications in healthcare, where organizations are moving beyond experimental uses to develop production-ready systems that can meaningfully impact patient care and clinical workflows.

The post Mayo Clinic and Microsoft team up to build specialized AI model for healthcare appeared first on mHealth Spot.

ASUS has launched an AI-powered healthcare ecosystem that connects medical devices directly to clinical decision-making systems. The new platform combines two devices – the ASUS Handheld Ultrasound DuoScan and ASUS VivoWatch 6 Plus – with AI software to help doctors make faster decisions at the patient’s bedside.

The announcement comes as healthcare systems worldwide struggle with staff shortages and increasing patient loads. AI agents – software that can analyze data and recommend actions automatically – are emerging as a potential solution. ASUS surveyed frontline healthcare workers and found 68% expect AI agents to measurably improve clinical workflows.

Portable ultrasound brings hospital imaging anywhere

The ASUS Handheld Ultrasound DuoScan packs 192-element high-definition imaging into a portable device. The dual-probe design comes in two configurations:

• Linear-plus-convex: For abdominal, muscle, blood vessel, and thyroid scans
• Linear-plus-phased array: For heart, abdominal, muscle, and blood vessel imaging

The device has IP68 waterproof and dustproof rating with three hours of battery life. This wireless design means doctors can perform ultrasounds in emergency rooms, intensive care units, or even patients’ homes without being tied to large, stationary machines.

Advanced health watch monitors vital signs continuously

The ASUS VivoWatch 6 Plus builds on the company’s existing health monitoring technology with new features. The watch has a 1.43-inch AMOLED display protected by sapphire crystal glass and a titanium case for durability.

Beyond standard blood pressure and ECG monitoring, the new version adds:

• Sleep breathing movement tracking
• Gait analysis for walking patterns
• Real-time health feedback and coaching

These features aim to detect early signs of chronic diseases and provide personalized health guidance based on continuous data collection.

Connecting devices to clinical decisions

The key innovation is how ASUS connects these devices through what it calls a “medical sandbox.” The system has three layers:

• Sensing layer: The ultrasound and watch devices collect patient data
• Platform layer: ASUS No-Code AI processes and analyzes the information
• Computing layer: ASUS hardware infrastructure runs the AI analysis

This setup creates a closed loop where patient data is continuously captured, analyzed, and turned into actionable recommendations for healthcare providers. The system is designed to work across hospitals, emergency care, and remote healthcare settings.

The healthcare AI market is expected to reach $102 billion by 2028, driven by the need for more efficient patient care and the growing sophistication of AI technology. ASUS is positioning itself to capture part of this market by providing the complete hardware and software stack rather than just individual devices.

The post ASUS unveils AI healthcare ecosystem with smart ultrasound and wearable devices at Computex 2026 appeared first on mHealth Spot.

Withings has released the BodyFit, a new smart scale that brings advanced body composition analysis to a more accessible price point. The device includes many features from the company’s premium Body Scan model, but costs $220 less at $279.95.

The French health tech company has built a reputation for privacy-focused smart scales that integrate well with Apple Health. The BodyFit fills a gap in their lineup between basic weight tracking and clinical-grade body analysis.

How does it work?

The BodyFit’s main feature is its retractable handle, similar to what you’d find on the more expensive Body Scan model. The scale has eight electrodes total:

• Four electrodes in the retractable handle
• Four electrodes in the base platform

When you grip the handle during a weigh-in, the scale uses Bioelectrical Impedance Spectroscopy (BIS) technology across 13 frequencies. This provides what Withings calls a “6-zone body composition scan” that measures fat and muscle mass in different parts of your body.

The company says the BodyFit can capture over 40 data points in just 20 seconds. That’s reportedly three times faster than most competing segmental analysis scales. Withings claims its technology shows 99% correlation for fat mass and 98% for muscle mass when compared against DEXA scans.

Why does it matter?

Body composition tracking has become increasingly important as people focus on overall health rather than just weight loss. The ability to monitor muscle mass separately from fat mass helps users understand whether weight changes come from the right sources.

Previously, this level of detailed analysis required either expensive clinical equipment or premium consumer devices like Withings’ $499.95 Body Scan. The BodyFit makes segmental body composition analysis available at a more mainstream price point.

The main trade-off compared to the Body Scan is the loss of cardiovascular features. The premium model includes a 6-lead ECG and Vascular Age tracking, which take about 90 seconds to complete. For users who want detailed body composition without cardiac diagnostics, the BodyFit provides the core experience for significantly less money.

The context

The smart scale market has grown competitive as health tracking becomes more mainstream. Companies like Withings, Fitbit, and others are pushing beyond basic weight measurement toward more comprehensive health monitoring.

Withings has positioned itself as a premium option with medical-grade accuracy and strong privacy protections. The BodyFit represents the company’s attempt to bring some of that expertise to a broader market while maintaining their quality standards.

The scale includes a slim glass design with ITO coating and a built-in color screen that shows metrics immediately after weighing. The BodyFit is available starting today for $279.95.

The post Withings BodyFit brings advanced body scanning to mid-range smart scales appeared first on mHealth Spot.

Doctors might soon have AI assistants that have been thoroughly tested in a virtual hospital before they ever see a real patient. Researchers from Seoul National University Hospital and Harvard Medical School have built what they call the world’s first “Clinical Environment Simulator” – essentially a flight simulator for medical AI.

The system tests how AI decisions play out in a complete virtual hospital, tracking everything from patient outcomes to whether the emergency room gets backed up. It’s a major step beyond current AI testing, which typically involves feeding historical data to AI systems and checking if they get the right diagnosis.

How does it work?

The simulator runs two engines simultaneously to create a realistic hospital environment. The Patient Engine generates virtual patients whose conditions change over time, just like real patients. It uses disease templates created by specialists and draws from actual electronic medical records to simulate how symptoms might progress or how patients might respond to treatments.

The Hospital Engine tracks all the hospital’s resources in real time:

• Available beds and their current status
• Medical staff schedules and assignments
• Equipment like CT scanners and their wait times
• Priority systems that give critically ill patients first access to resources

When the AI orders a blood test, the simulator assigns the necessary staff step by step, following the actual time requirements. If the AI delays ordering diagnostic tests, a patient with stable chest pain might deteriorate into a heart attack. If it prioritizes a CT scan for one emergency patient, other patients face longer wait times.

Why does it matter?

Current medical AI testing misses the bigger picture. Researchers test whether AI can correctly diagnose pneumonia from an X-ray, but they don’t test what happens when that AI is making decisions in a busy emergency room with limited staff and equipment.

The simulator measures AI performance using a dual scoring system:

• Patient outcomes: survival rates, treatment timing, and adherence to medical guidelines
• Hospital efficiency: length of stay, emergency room throughput, and resource utilization

This approach rewards AI decisions that help individual patients without creating bottlenecks that harm other patients. The system also runs stress tests, simulating extreme scenarios like network failures or multiple emergencies hitting the hospital at once.

Research Professor Seong-Eun Kim notes that while virtual hospitals can’t perfectly predict human physiology, this represents the most practical next step for testing AI in realistic medical environments.

The context

Medical AI has shown impressive results in controlled laboratory settings, but real hospitals are complex systems where every decision has ripple effects. A single AI recommendation can affect not just one patient, but the entire flow of the hospital.

The research, published in Nature Medicine, addresses a critical gap as healthcare systems worldwide consider deploying AI assistants more broadly. Just as pilots train extensively in simulators before flying real planes, this system lets medical AI train in virtual hospitals before working with real patients.

The researchers believe this could be the missing piece that allows doctors to step away from computer screens and return their focus to patient care, knowing their AI assistants have been thoroughly tested in realistic scenarios.

The post Medical AI gets its own flight simulator for training appeared first on mHealth Spot.

Teladoc Health is expanding its reach by partnering with Walmart to offer virtual healthcare services through the retailer’s Better Care platform. The move puts virtual medical consultations alongside everyday shopping, targeting Americans who want convenient and affordable healthcare options.

The partnership reflects a broader trend of healthcare companies working with major retailers to reach patients where they already shop. For Teladoc, it means access to Walmart’s massive customer base. For customers, it means getting medical care without a separate doctor’s visit.

What services are available

Walmart customers can now access three main Teladoc services for $89 per visit, whether they have insurance or pay cash:

• 24/7 urgent care: Video consultations within minutes for common issues like sinus infections, pink eye, UTIs, and cold symptoms
• Dermatology: Upload photos of skin problems for diagnosis within 24 hours by board-certified dermatologists
• Nutrition counseling: One-on-one sessions with registered dietitians for diabetes support, weight management, and meal planning

Prescriptions can be sent directly to Walmart pharmacies, with same-day delivery available in many areas within an hour. Walmart+ members get free delivery.

Why this partnership matters

The collaboration addresses a key problem in American healthcare: access and convenience. Millions of Americans are uninsured or underinsured, making traditional doctor visits expensive. Others simply want faster, more convenient care for routine problems.

“Walmart is where millions of Americans already go for everyday needs, and now, getting care from Teladoc Health can be part of that same experience,” said Kelly Bliss, Teladoc Health’s President of U.S. Group Health.

The timing is significant as virtual care adoption has stabilized after its pandemic boom. Healthcare companies are now focused on integrating virtual services into existing consumer habits rather than creating entirely new behaviors.

Building on existing partnerships

This isn’t Teladoc’s first collaboration with Walmart. The companies already offer BetterHelp mental health services through the same platform, which launched in January.

The expanded partnership shows how both companies view retail healthcare’s future. Walmart has been steadily building its healthcare presence, while Teladoc is working to embed its services in platforms Americans already use regularly.

“Healthcare should be easier to access, easier to understand and more affordable,” said Leslie Fletcher, Vice President of Strategy and Partnerships at Walmart U.S. Health & Wellness.

The move comes as other major retailers like Amazon and CVS also expand their healthcare offerings, creating new competition in the virtual care space.

The post Teladoc Health partners with Walmart to offer virtual care services appeared first on mHealth Spot.

Disney is launching a major patriotic celebration called ‘Disney Celebrates America’ as the United States approaches its 250th anniversary in 2026. The initiative will bring new attractions, shows and themed experiences across Disney’s theme parks over the next year.

The timing isn’t coincidental. Disney has historically capitalized on major national milestones, and the semiquincentennial represents a massive tourism opportunity. With Americans expected to travel domestically for anniversary celebrations, Disney is positioning itself as the premier destination for patriotic family entertainment.

What’s coming to Disney parks

Disney hasn’t released the complete lineup yet, but the company promises experiences that span American history and culture. The celebrations will likely include:

• New fireworks shows with patriotic themes
• Historical character meet-and-greets
• Special parades featuring American landmarks
• Limited-time food offerings inspired by regional American cuisine

Why this matters for Disney’s business

This celebration comes at a critical time for Disney’s parks division. The company has been working to recover attendance levels and boost revenue per guest following recent economic pressures. Themed celebrations typically drive both ticket sales and merchandise revenue.

Disney’s track record with patriotic content is strong. The Hall of Presidents and It’s a Small World have remained popular attractions for decades. The company is betting that American families will pay premium prices for exclusive anniversary experiences.

Competition for patriotic tourism

Disney faces competition from historical sites and other theme parks also planning 250th anniversary events. Colonial Williamsburg, Philadelphia’s Independence Hall, and even Universal Studios are expected to launch their own patriotic programming.

The key difference is Disney’s ability to blend education with entertainment on a massive scale. The company’s Imagineering team has extensive experience creating immersive historical experiences that appeal to multiple generations.

More details about specific attractions and dates will be announced throughout 2025 as Disney builds momentum toward the 2026 anniversary year.

The post Disney unveils massive America-themed celebration ahead of nation’s 250th birthday appeared first on mHealth Spot.