Digital Health

New AI initiative in Devon aims to improve stroke treatment outcomes by analysing extensive medical data

A pioneering research initiative led by the Royal Devon University NHS Foundation Trust, in collaboration with the NIHR Applied Research Collaboration South West Peninsula (PenARC) and the University of Exeter, is harnessing artificial intelligence (AI) and machine learning to transform stroke treatment across the United Kingdom. This innovative project aims to enhance outcomes for people affected by stroke by improving how clot-dissolving treatments are delivered.

Personalising Stroke Care Through AI

The research focuses on the use of thrombolysis—a time-sensitive treatment that involves administering medication to break down blood clots in the brain, thereby limiting the extent of disability following a stroke. While thrombolysis has the potential to significantly improve recovery outcomes, it is only appropriate for certain individuals and must be administered rapidly after the onset of stroke symptoms.

Currently, thrombolysis is provided to approximately 11% of people experiencing a stroke in the UK. In the South West of England alone, more than 1,000 individuals receive this treatment each year. However, national data reveals considerable variation in both the speed and frequency with which thrombolysis is delivered in hospitals, contributing to inequities in care.

The newly launched research initiative—entitled SAMueL 2 (Stroke Audit Machine Learning 2)—seeks to address this variation through the integration of AI into a national stroke audit, the first initiative of its kind globally. By analysing extensive datasets, the team has developed a decision-support tool that helps clinicians identify which people are most likely to benefit from thrombolysis, based on their individual clinical characteristics. This tool is designed to ensure that treatment is delivered both more quickly and more equitably.

Harnessing National Stroke Data

Building on earlier research, the SAMueL 2 team employed sophisticated computer modelling to investigate why thrombolysis rates differ so significantly between hospitals. The models also helped to predict outcomes for individuals who received thrombolysis compared to those who did not, shedding light on the factors most strongly associated with positive recovery outcomes.

Professor Martin James, Consultant Stroke Physician and Honorary Clinical Professor at the University of Exeter Medical School, explained:

“SAMueL analysis includes nationwide data from a quarter of a million stroke cases, and by using this data, we can provide each hospital with a tailored target for thrombolysis. When teams have used this as a benchmark, they’ve been able to treat more patients, more effectively.

Stroke has a life-changing impact, so it’s inspiring to see how research like this can lead to more personalised, faster treatment and better outcomes for patients and their families.”

The project represents a significant step forward in the use of AI in clinical practice, setting a precedent for how data-driven approaches can inform more nuanced and equitable healthcare delivery. By drawing on patient-level data from across the country, the tool enables NHS trusts to benchmark their performance, optimise treatment pathways, and ultimately improve care for those affected by stroke.

Supporting National Health Goals

This research is part of a wider programme funded by the National Institute for Health and Care Research (NIHR) and aligns with the government’s ambition to increase equitable access to thrombolysis. It underscores the critical role of personalised, data-informed medicine in addressing one of the UK’s leading causes of death and long-term disability.

By combining clinical insight with advanced analytical tools, the SAMueL 2 initiative is not only enhancing individual outcomes but also shaping the future of stroke care at a national level.

Artificial intelligence enhances hospital screening for opioid use disorder, reducing readmissions and costs

Opioid use disorder (OUD) continues to pose a major public health challenge in the United States. Individuals living with OUD who are admitted to hospital face an elevated risk of overdose, repeated hospitalisation, and a host of related complications. Research has shown that providing addiction treatment during hospital stays can improve health outcomes and reduce mortality. Yet, despite its potential benefits, screening for OUD within hospitals remains inconsistent. Many individuals at high risk are discharged before having the opportunity to see an addiction specialist—a factor strongly associated with increased rates of overdose following discharge.

In an effort to address these shortcomings, a research team led by Dr Majid Afshar at the University of Wisconsin–Madison, with support from the National Institutes of Health (NIH), explored whether artificial intelligence (AI) could play a meaningful role. The team had previously developed an AI-driven screening tool designed to identify hospitalised individuals at risk of OUD. This tool analyses data from electronic health records (EHRs) to detect patterns that may suggest the presence of OUD. When such patterns are identified, the system notifies healthcare providers and may recommend a referral to an addiction medicine specialist, alongside other appropriate interventions.

In their latest study, published in Nature Medicine on 3 April 2025, the researchers assessed whether the AI tool could increase the likelihood that individuals at risk would be seen by an addiction specialist during their hospital stay. The study also examined whether use of the AI system had any effect on hospital readmission rates within 30 days of discharge.

The study encompassed over 51,000 adults admitted to the University of Wisconsin Hospital. It was conducted in two phases. The initial, or baseline, phase took place between March and October in both 2021 and 2022, involving roughly 34,000 patients. During this period, data were collected on how clinicians assessed patients’ risk of OUD and the outcomes of those assessments, without the use of AI tools.

The second phase, from March to October 2023, focused on evaluating the AI screener in practice. During this period, the AI tool was employed to assist in evaluating over 17,000 patients. In total, 727 consultations with addiction medicine specialists were conducted during the study’s entire duration.

Findings indicated that the AI tool was just as effective as clinician-led assessments in prompting referrals to addiction specialists. Notably, individuals assessed with the help of the AI screener were 47% less likely to be readmitted to hospital within 30 days of discharge compared to those assessed without it.

The study also demonstrated potential cost savings. Each avoided readmission was estimated to reduce healthcare expenditure by approximately $6,800. These results suggest that integrating AI into hospital workflows could increase access to addiction support, enhance clinical efficiency, and lead to substantial cost savings for healthcare systems.

“AI holds promise in medical settings, but many AI-based screening models have remained in the development phase, without integration into real-world settings,” said Dr Afshar. “Our study represents one of the first demonstrations of an AI screening tool embedded into addiction medicine and hospital workflows, highlighting the pragmatism and real-world promise of this approach.”

As hospitals grapple with the ongoing burden of opioid use disorder, this research provides compelling evidence for the adoption of AI-driven screening tools. By identifying at-risk individuals earlier and linking them to appropriate care, such technology may not only improve outcomes for individuals living with OUD but also help health systems operate more efficiently and equitably.

Generative AI chatbot effectively reduces symptoms of depression, anxiety, and eating disorders in clinical trial

A groundbreaking randomised controlled trial conducted by Dartmouth College has found that a generative artificial intelligence (GenAI) chatbot can significantly reduce symptoms of depression, generalised anxiety, and eating disorders. The study is the first of its kind to assess the clinical efficacy of a GenAI-based mental health intervention, offering a promising step forward in the use of artificial intelligence for therapeutic purposes.

The research, led by clinicians at Dartmouth, evaluated Therabot, an AI-powered mental health chatbot developed in 2019. In total, 210 participants were enrolled in the study, of whom 106 presented with clinically significant symptoms of major depressive disorder, generalised anxiety disorder, or were identified as being at high risk for feeding and eating disorders. These participants received access to Therabot and were encouraged to interact with the chatbot daily for 30 days. Following this intervention phase, participants could continue to use the chatbot for an additional four weeks, though without daily reminders. Assessments were conducted at baseline, four weeks, and eight weeks.

Therabot offers structured mental health support through a conversational interface. Users may either initiate sessions on demand or respond to scheduled notifications. The chatbot delivers tailored psychological interventions through question prompts, empathetic replies, and affirming statements designed to meet the user’s expressed needs. According to the developers, this continuity of interaction fosters a deeper therapeutic experience, closely mirroring aspects of traditional human-delivered psychotherapy.

Despite the growing popularity of GenAI applications in wellness and companionship, they have not previously been studied for their capacity to deliver clinical-grade mental health care. “To date, conversational agents using GenAI have fallen under general purpose, wellness, or companion applications, rather than software intended for the diagnosis and treatment of mental health disorders,” the authors noted in the study.

The results were striking. Participants diagnosed with major depressive disorder experienced a 51% reduction in symptoms at both the four- and eight-week assessments. Those living with generalised anxiety disorder saw a 31% reduction in symptoms, while individuals at risk for feeding and eating disorders experienced a 19% reduction. Notably, none of the participants were taking psychiatric medication during the study period, suggesting that the improvements were attributable to the chatbot intervention itself.

Engagement levels were high: participants used Therabot on average 24 days out of the 30-day intervention period and spent approximately 6.18 hours interacting with the chatbot. On average, participants sent 260 messages, indicating sustained and active use.

The study also explored users’ perceptions of the chatbot’s utility and emotional connection. Participants reported that Therabot was intuitive and easy to use, and many said they felt better after engaging with it. Moreover, the quality of the therapeutic relationship—referred to as therapeutic alliance—was found to be comparable to that experienced with human therapists. The authors observed that key elements of psychosocial therapy, including empathy and shared goals, were effectively established through Therabot—something previously considered difficult or impossible to achieve with non-generative AI systems.

As part of the safety protocol, clinicians closely monitored Therabot’s responses. In 15 instances, they contacted participants due to safety concerns such as suicidal ideation. On 13 occasions, researchers intervened to correct inappropriate or inaccurate chatbot responses. Despite these incidents, the authors concluded that the intervention was overall safe and well tolerated.

Importantly, the study emphasised the broader implications of scalable AI-powered mental health tools. While traditional, evidence-based psychosocial treatments are known to be effective, they are often labour-intensive and limited by resource constraints. As the study notes, “Although empirically validated psychosocial treatments exist, they are resource intensive, and limited in scalability and accessibility, leading to fewer than half of the people with a mental health disorder receiving care.”

The potential for GenAI tools to alleviate pressure on overstretched behavioural health systems is significant, especially as waiting lists for mental health services continue to grow. Unlike rule-based AI chatbots, which rely on predefined responses set by programmers, GenAI systems offer dynamic and personalised interactions. This adaptability enables a deeper and more human-like therapeutic experience, which may enhance both efficacy and engagement.

If further validated through larger trials and real-world implementation studies, tools like Therabot could transform the digital mental health landscape, making quality support more accessible to individuals across a wide range of conditions.

Participants in the control arm of the study did not receive access to Therabot until after the conclusion of the trial.

PAHO launches new virtual programme to advance digital skills among health workers across the Americas

The Pan American Health Organization (PAHO) has announced the launch of its new Digital Literacy Programme for Health Sector Personnel, a fully online initiative aimed at enhancing the digital capabilities of individuals working in health care throughout the Americas. This programme is a direct response to growing demands for digitally enabled health services and aims to bridge the digital divide within the health workforce by fostering equitable, accessible, and technology-driven care systems.

As health care systems across the world continue to evolve with digital innovation, the Region of the Americas still faces significant disparities in access to and effective utilisation of digital health tools. These include electronic health records, mobile applications for patient monitoring, telemedicine platforms, and epidemiological alert systems. The programme seeks to address these challenges by upskilling personnel and preparing them to integrate digital technologies into daily practice to improve service delivery, coordination, and quality of care.

“This programme aims to close those gaps by equipping health personnel with key knowledge to lead change in their workplaces,” said Marcelo D’Agostino, Unit Chief for Information Systems and Digital Health at PAHO. “With renewed competencies for the digital world, the Region will move toward more resilient and equitable health systems,” he added.

The initiative is built around a robust and interdisciplinary curriculum that will provide participants with foundational and advanced competencies in a range of digital domains. These include:

• Digital transformation in health systems
• Artificial intelligence and its application in health care
• Data governance and ethical data management
• Telehealth and remote care services
• Vital statistics and their digital integration
• Health information interoperability
• Big data analytics for public health
• Infodemic management and combating health misinformation
• Digital diplomacy and international health cooperation

The programme has been structured as an immersive and flexible learning journey, offering a blend of technical modules, interactive policy dialogues with regional and global experts, keynote presentations, and collaborative learning forums. Real-world case studies from the Region will help ground theory in practice, and a self-assessment tool will allow participants to tailor the programme to their individual learning needs and professional goals.

Delivered through PAHO’s Virtual Campus for Public Health, the sessions are entirely free of charge and accessible in both English and Spanish, with simultaneous interpretation available. Additional thematic courses will also be offered to deepen knowledge in specific areas of interest.

By investing in the digital literacy of people working across the health sector—from front-line professionals to administrative and managerial staff—PAHO hopes to support the development of health systems that are interconnected, interoperable, and inclusive. This vision aligns with the call made by the Ministers of Health of the Americas during PAHO’s 59th Directing Council in 2021, which urged the Organisation to lead efforts towards the digital transformation of health care, ensuring that no one is excluded from accessing the highest possible level of health and well-being in the digital age.

The Digital Literacy Programme for Health Sector Personnel will officially launch on Wednesday, 16 April 2025. PAHO and the World Health Organization (WHO) are inviting all health workers across the Americas to register and participate in this important initiative, which promises to equip the workforce with the skills needed to thrive in an increasingly digital health landscape.

Pioneering project aims to revolutionise medical devices through adaptive 4D engineering

Researchers at the University of Birmingham and Imperial College London have launched a groundbreaking three-year initiative to advance the design and performance of medical devices by addressing the dynamic nature of the human body over time.

The project, titled 4D Engineering of Healthcare Technologies (4D Health Tech), seeks to fundamentally rethink how medical devices are developed by integrating the concept of time as a critical design factor. The goal is to improve the adaptability, longevity, and functionality of medical technologies as individuals grow, move, heal, and age.

Dr Sophie Cox, project lead from the University of Birmingham, explained:

“Our bodies change over time as we grow, move and regenerate, but products designed to replace or repair our bodies typically neglect the dimension of time, compromising their function and lifespan. Our vision is to transform the way we engineer medical devices.”

Traditional medical devices are often static in design, unable to respond effectively to gradual physiological changes. For example, implants for children must be replaced as they grow, while adult bone implants may not degrade in harmony with tissue regeneration. These limitations can lead to reduced effectiveness, increased risk of complications, and the need for repeated surgical interventions.

The 4D Health Tech project will explore innovative approaches to these challenges by promoting the development and use of materials that degrade in a controlled and predictable manner. Such materials could enable devices to better support healing processes, reduce the need for replacement surgeries, and align more closely with individual recovery patterns.

In addition to novel materials, the project will investigate advanced design methodologies, state-of-the-art manufacturing techniques, and patient-specific testing protocols. The aim is to create adaptable medical technologies that reflect the diversity of the population and provide improved outcomes across the lifespan.

Crucially, the inclusion of time as a “fourth dimension” in medical engineering represents a significant shift in how devices are conceptualised and built. By accounting for time-dependent biological changes, researchers hope to unlock new functionalities in medical technologies and significantly extend their usable life. This could not only benefit individuals receiving care but also contribute to more efficient use of resources within the NHS.

The project is backed by £1.2 million in funding from the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI). It is one of several projects supported under a broader £10 million investment in response to the Tomorrow’s Engineering Research Challenges (TERC) report. This report identifies key areas in which engineering research can support the UK’s long-term economic, environmental, and societal priorities.

Jane Nicholson, Executive Director for Research at EPSRC, commented:

“Engineering is the cornerstone to a more sustainable, successful and thriving future for the UK. From developing renewable energy solutions to creating smart cities, engineering innovations are driving progress in every sector. These new networks will address the strategic challenges outlined by the TERC report. Together, these researchers present a hugely ambitious, thoughtful response to the economic, environmental and social challenges we all face.”

The launch of the 4D Health Tech initiative aligns with recent national developments in medical technology regulation and evaluation. In February 2025, the National Institute for Health and Care Excellence (NICE) announced a public consultation on proposed changes to its HealthTech programme, which aims to streamline the evaluation of innovative medical technologies for adoption within the NHS.

This follows updated guidance issued in January 2025 by the Medicines and Healthcare Products Regulatory Agency (MHRA), intended to assist medical device manufacturers in preparing for new post-market surveillance (PMS) regulations. These regulations, which come into effect on 16 June 2025, are designed to ensure ongoing safety and performance monitoring of medical technologies in clinical use.

Together, these policy shifts and research initiatives signal a growing national commitment to fostering innovation in medical technology, ensuring that future devices are not only cutting-edge, but also responsive to the complex and evolving needs of people receiving care.

Patients say drugmakers would earn more trust by offering digital health tools and services

People living with chronic health conditions are increasingly calling for pharmaceutical companies to broaden their focus beyond drug development and take a more active role in delivering healthcare services—particularly through digital platforms. That’s the key takeaway from a new survey report published by ixlayer and Ipsos.

The survey, conducted in January 2025, gathered responses from over 400 adults living with at least one long-term health condition, such as asthma, Type 2 diabetes, heart disease, or eczema. A significant majority—nearly three-quarters—said they would value support from pharmaceutical companies in overcoming the barriers they face when trying to access care. Over 80% of respondents went a step further, agreeing that pharmaceutical companies should actively provide resources that simplify access to healthcare and treatment.

One of the most prominent themes to emerge from the data is the enthusiasm for digital tools. A striking 86% of participants reported using at least one digital health solution. These included patient portals, telehealth services, pharmacy delivery platforms, wearable health monitors, and at-home diagnostic tools. The appeal of these technologies was rooted in their convenience, cost-effectiveness, and ability to enhance communication with healthcare providers.

However, patients also expressed frustration with the current digital healthcare landscape. Many reported having to juggle multiple platforms, each with its own login systems and interfaces, which often led to technical difficulties. These issues, respondents indicated, present an opportunity for pharmaceutical companies to step in and provide more seamless, integrated, and reliable digital services.

The survey revealed that doing so would have a notable impact on public perception. An overwhelming 92% of participants said their view of the pharmaceutical industry would improve if companies offered comprehensive online health tools. Currently, fewer than one in five believe that pharmaceutical companies genuinely prioritise patients’ needs.

When asked about the role they see for the industry in improving access through technology, one respondent commented:

“They have a role in helping people and patients get the medications and assistance they need; they should be constantly working to minimise the steps in between being prescribed and getting their medicines.”

Participants were also asked to identify which features they would like pharmaceutical companies to provide. Top priorities included the ability to schedule virtual or in-person appointments with healthcare providers, order prescriptions online, access lab testing, and securely share diagnostic results and health data with care teams. Additionally, people expressed strong support for insurance coverage of digital services—identifying this as the most important factor in improving their perception of the industry.

More than 70% of respondents indicated that they would be likely to use each of these digital offerings if made available.

Pouria Sanae, co-founder and CEO of ixlayer, said the findings reflect a shift in expectations around pharmaceutical companies’ responsibilities in the modern healthcare ecosystem:

“Patients don’t just want treatment from pharma—they want seamless, digital-first healthcare experiences that fit into their lives.”

Some pharmaceutical companies have already begun to respond to this shift by launching digital platforms aimed at centralising healthcare services and improving the user experience.

Eli Lilly, for instance, launched LillyDirect in early 2024. The platform enables users to book both virtual and in-person medical appointments and offers access to Lilly’s medications at reduced costs. Its services target a range of conditions, including diabetes, migraine, obesity, sleep apnoea, and more recently, Alzheimer’s disease.

Similarly, Pfizer introduced PfizerForAll in mid-2023. This platform connects users with healthcare providers and includes tools to locate vaccines, order diagnostic tests and treatments from Pfizer and other manufacturers. The service currently supports care for conditions including migraine, COVID-19, influenza, respiratory syncytial virus (RSV), pneumococcal pneumonia, and atrial fibrillation.

Pfizer has also integrated additional features, such as a link to the American Cancer Society’s CancerRisk360 tool, and a generative AI-powered chatbot designed to respond to health and wellness queries.

While the expansion of such platforms has been generally well received by the public, they have also drawn scrutiny from U.S. lawmakers, particularly in relation to prescribing practices associated with the telehealth features. Nonetheless, the appetite for these services among patients is clear.

The message from the survey is unequivocal: people want more than medication. They want pharmaceutical companies to deliver holistic, user-friendly, and accessible digital solutions that support them in managing their health day-to-day. And in doing so, pharma companies stand to gain not just goodwill—but potentially greater trust and long-term engagement from the very individuals they serve.

Pioneering medical database offers unprecedented insight into obesity and related conditions

A new medical database is revolutionising how healthcare professionals understand and manage obesity by automatically compiling detailed clinical data from people living with obesity and those affected by associated conditions. Spearheaded by Kobe University in Japan, the initiative is being hailed as a critical advancement for public health, research, and the development of new therapies.

“Obesity is at the root of many diseases,” says Ogawa Wataru, an endocrinologist at Kobe University.

Obesity has long been recognised as a contributing factor in a wide range of health conditions, including type 2 diabetes, hypertension, gout, coronary heart disease, and stroke. By enabling earlier intervention and more precise treatment, better data about these links has the potential to significantly improve outcomes for individuals and reduce strain on public healthcare systems.

Yet despite the widespread prevalence of obesity, obtaining reliable and comprehensive data has remained a persistent challenge. Most existing data sources are either incomplete or designed primarily for administrative purposes, such as insurance reimbursement, which limits their usefulness in clinical research or treatment planning.

Ogawa was driven to address this gap after observing the complex health challenges experienced by people living with obesity in daily clinical practice.

“Witnessing the complex health challenges faced by obese patients in daily clinical practice inspired me to seek a solution that more accurately reflects their true condition,” he explains.

To create a more accurate picture, Ogawa and his team developed a novel data collection system that links a variety of medical data points, including patient examinations, disease incidence, prescription records, and laboratory test results. The system is built on Japan’s digital medical record infrastructure and anonymises and updates patient data automatically whenever an individual visits one of the seven participating healthcare institutions.

The result is the Japan Obesity Real-world Big-data Integrated Database (J-ORBIT) — a dynamic, anonymised repository of real-world clinical information that captures the multifaceted nature of obesity and its related health conditions.

“This database system now enables the efficient collection and analysis of comprehensive clinical information related to obesity management – something that was not possible before,” notes Ogawa, who leads the project under the auspices of the Japan Society for the Study of Obesity (JASSO).

In their first published analysis, featured in the Journal of Diabetes Investigation, Ogawa and his team examined data from 1,169 individuals out of the approximately 3,000 currently enrolled in the J-ORBIT database. The findings offer valuable insights: most participants had three or more obesity-related conditions, particularly those linked to diabetes. The data also challenged some prevailing assumptions about the strength of associations between obesity and certain diseases.

Moreover, the research revealed that important treatment strategies — such as behavioural therapy — are underutilised in clinical practice. And because J-ORBIT captures a wide spectrum of clinical data, the team identified a surprisingly high prevalence of conditions not typically associated with obesity, such as menstrual irregularities and female infertility.

J-ORBIT was designed to interface with another major national database: J-DREAMS, a project run by the Japan Diabetes Society that collects data specifically from people with diabetes. Ogawa, who was also involved in managing J-DREAMS, saw an opportunity to create a sister system focused on obesity. Where both databases operate in the same institution, relevant data is extracted and automatically shared between the two.

“I was involved in the management of J-DREAMS and wanted to develop a similar database specifically for obesity management,” Ogawa explains.

This integration enables researchers working on either diabetes or obesity to access more nuanced, context-rich datasets. However, it also means that people living with both obesity and diabetes may be disproportionately represented in the J-ORBIT dataset.

One of the most impactful aspects of the new system is its ability to identify which individuals may benefit most from weight loss, and to flag appropriate treatment options tailored to their condition. This has drawn the attention of the pharmaceutical industry, particularly as new anti-obesity medications come to market.

“Several companies developing anti-obesity drugs have provided funding for the system, and some of them have already started research using the data,” says Ogawa. “So as obesity treatment undergoes a major transformation, a database like J-ORBIT will be of great importance.”

By offering a more accurate and holistic view of the lives and health of people affected by obesity, J-ORBIT represents a significant step forward. It supports not only more effective individual care but also broader public health efforts, and may well prove essential to the next generation of obesity treatment and prevention.

Amazon’s palm-scanning technology enters healthcare: NYU Langone Health adopts biometric check-ins

New York University’s Langone Health has announced the adoption of Amazon’s palm recognition technology for patient check-ins, marking a significant step in the integration of biometric technology into healthcare settings.

The announcement, made at a major health information technology conference, positions NYU Langone as the first healthcare provider to implement Amazon One, a biometric authentication system that has already been deployed in commercial settings such as stadiums, universities, and Whole Foods supermarkets.

Why This Matters

The introduction of Amazon’s palm-scanning technology is aimed at improving the efficiency and security of patient identification. Traditionally, verifying a person’s identity upon arrival for a medical appointment requires presenting an identification document or providing personal details to administrative staff. The new biometric system streamlines this process, allowing individuals to authenticate their identity quickly and seamlessly with a simple palm scan.

Participation in the programme will be optional for patients, ensuring that those who prefer traditional check-in methods can continue to use them.

How It Works

Individuals visiting NYU Langone Health facilities will have the option to scan their palm at designated check-in stations. The technology works by capturing and encrypting a person’s unique palm signature, linking it to their electronic health record within NYU Langone’s system. This eliminates the need for manual ID verification, potentially reducing wait times and administrative bottlenecks at reception desks.

According to a press release from Amazon, the biometric data collected by Amazon One will not include healthcare records from providers. The system solely functions as an identity verification tool and does not store or process any medical information.

Privacy and Security Measures

Amazon has emphasised that security and privacy are key priorities in the deployment of this technology. All palm scan data will be encrypted, and individuals will retain control over their biometric information. Those who choose to participate can unenrol from Amazon One at any time and request that their data be permanently deleted, according to the company’s official statement.

The Bigger Picture

While Amazon’s palm-scanning system is expected to offer a more convenient check-in experience, it does not address broader interoperability issues within healthcare IT. Many individuals continue to face the frustration of completing multiple paper forms each time they visit a healthcare provider, as disparate electronic health record systems are often unable to communicate seamlessly with one another.

Despite these ongoing challenges, the integration of biometric authentication in healthcare settings represents a step towards modernising patient interactions and enhancing security. As biometric technology becomes more widely accepted, its role in streamlining administrative processes in healthcare is likely to expand.

Looking Ahead

The adoption of Amazon One at NYU Langone Health signals the growing influence of tech companies in healthcare innovation. If successful, this initiative could pave the way for further biometric applications in hospitals and clinics across the United States and beyond, potentially transforming how individuals interact with medical institutions.

For now, the convenience of skipping the hassle of fishing for an ID card when running late to an appointment may be an appealing prospect for many. However, the long-term impact of such technology on healthcare security, accessibility, and interoperability remains to be seen.

AI tool used to predict falls and illnesses expands across the NHS

An advanced artificial intelligence (AI) tool capable of predicting an individual’s risk of falling with 97% accuracy is being implemented across the NHS. The system, developed by healthcare technology company Cera, is expected to prevent up to 2,000 falls and hospital admissions daily, significantly reducing strain on the health service while improving patient safety and well-being.

The AI-driven system is already in use across more than two-thirds of NHS Integrated Care Systems (ICSs) and is integrated into over two million home care visits per month. By continuously monitoring key health indicators such as blood pressure, heart rate, and body temperature, the software identifies early warning signs of deterioration, enabling timely intervention by healthcare professionals.

This predictive capability is transforming the way care is delivered, supporting individuals to remain in their own homes rather than requiring hospitalisation. Each day, the tool generates up to 5,000 high-risk alerts, allowing clinicians and care teams to respond proactively. The AI system has already contributed to a reduction in hospital admissions by as much as 70%, ensuring more efficient use of NHS resources.

Dr Vin Diwakar, National Director of Transformation at NHS England, emphasised the importance of the technology in improving patient care and operational efficiency across the NHS. He said:

“This new tool now being used across the country shows how the NHS is harnessing the latest technology, including AI, to not only improve the care patients receive but also to boost efficiency across the NHS by cutting unnecessary admissions and freeing up beds ahead of next winter, helping hospitals to mitigate typical seasonal pressures.

“We know falls are the leading cause of hospital admissions in older people, causing untold suffering, affecting millions each year and costing the NHS around £2 billion, so this new software has the potential to be a real game-changer in the way we can predict, prevent and treat people in the community.

“This AI tool is a perfect example of how the NHS can use the latest tech to keep more patients safe at home and out of hospital, two cornerstones of the upcoming 10-year Health Plan that will see shifts from analogue to digital, and from hospital to community care.”

The Scale of Falls and Their Impact on NHS Resources

Falls remain the single largest cause of emergency hospital admissions among older people. Current estimates suggest that approximately 30% of individuals aged 65 and over—equating to around 2.5 million people—and nearly 50% of those aged 80 and above experience at least one fall each year. These incidents account for over four million hospital bed days annually, with a financial burden on the NHS exceeding £2 billion.

By introducing AI-driven fall prediction, the NHS aims to tackle this major public health issue proactively. The tool’s deployment aligns with the government’s strategy to enhance community-based care, leveraging digital solutions to prevent avoidable hospitalisations.

AI Technology to Detect Early Signs of Winter Viruses

Beyond fall prevention, the AI software is also designed to detect the early symptoms of seasonal illnesses, including COVID-19, influenza, respiratory syncytial virus (RSV), and norovirus. By recognising signs of infection before they escalate, NHS and social care teams can intervene earlier, potentially preventing the need for hospital treatment.

Cera’s system is also equipped to automate administrative tasks such as scheduling home visits and generating care plans, freeing up valuable time for healthcare professionals to focus on direct patient care.

Stephen Kinnock, Minister for Social Care, highlighted the importance of AI in modernising healthcare delivery. He stated:

“This is smart, preventative healthcare in action, and exactly the kind of transformation we’re championing in our 10-year health plan – shifting from treating sickness to preventing it, from hospital to community care, and from analogue to digital solutions.”

Cera’s Commitment to Transforming Home Healthcare

Cera, the organisation behind the AI-driven care tool, has been at the forefront of integrating AI technology into home healthcare services. Dr Ben Maruthappu, Founder and Chief Executive of Cera, reinforced the company’s commitment to improving health outcomes through digital innovation:

“At Cera, we’ve seen first-hand how AI can transform health outcomes for high-risk and vulnerable individuals: preventing illness and injury, radically reducing avoidable hospitalisations, and empowering people to live longer, healthier lives, in their own homes.

“We’re delighted to partner with the NHS to roll out our technology – keeping older and vulnerable people across the country out of hospital and safe at home.”

In January 2025, Cera completed a funding transaction worth over $150 million (£123 million) to expand its AI-powered home healthcare solutions further. This investment is expected to accelerate the adoption of predictive care technology across the UK, reinforcing efforts to make healthcare more proactive, personalised, and efficient.

As the NHS continues to navigate increasing demand and seasonal pressures, the widespread implementation of AI-driven health monitoring could prove to be a crucial step in reducing hospital admissions, optimising resources, and improving patient outcomes.

Kaiser Permanente implements AI to redirect routine patient messages

Researchers at Kaiser Permanente have demonstrated how artificial intelligence (AI) can be deployed to manage the overwhelming number of patient messages, potentially liberating physicians from routine queries that consume their valuable time. This innovative strategy, detailed in a recent publication in JAMA Network Open, employs real-time natural language processing (NLP) algorithms to categorise patient communications, thereby routing them efficiently to the most suitable responders.

The study, led by Kristine Lee, M.D., associate executive director of virtual medicine and technology at The Permanente Medical Group, reveals that using AI to label and redirect messages allowed for 31.9% of over 4.7 million patient messages to be addressed before they could reach an individual physician’s inbox. Instead, these were handled by a regional team consisting of medical assistants, teleservice representatives, pharmacists, and other doctors.

Lee explains, “Physicians today balance in-person care with virtual consultations, including video visits and secure messaging. While they appreciate these diverse interaction modes, they also require support to manage the increasing workload effectively. Our findings suggest that AI, coupled with strong workflow systems, could significantly aid this process.”

The Desktop Medicine Program at Kaiser Permanente developed the NLP system by training it on approximately 20,000 patient messages previously annotated by triage nurses and physicians. Implemented into the electronic health record system in May 2022, the NLP initially focused on adult and family medicine and was updated bi-monthly. By October 2022, the program expanded to include paediatric communications.

During the period from April to August 2023, the study examined the handling of 4.7 million messages, with 77.6% being categorised with at least one label. Messages related to medication were the most frequent, accounting for 32.8%, with many messages receiving dual labels, such as those combining skin conditions and medication issues (41.1%).

Over the five months, more than 1.5 million messages were successfully resolved by the regional team. These included straightforward inquiries concerning pharmacy hours or medication refills, which were diverted from physicians’ inboxes, thereby easing their workload, as noted by Vincent Liu, M.D., lead author of the study.

The researchers also highlighted the potential of message categorisation in identifying and responding to care trends, such as increases in specific infectious diseases. They acknowledged that the system could still be improved, particularly in handling messages with multiple labels or those that remain unlabelled. Future enhancements might include incorporating more advanced AI models, such as GPT-4.

“The high volume of messages our physicians receive hasn’t been completely addressed yet, but it’s rewarding to see how technology can help us manage these communications more effectively in real time,” said Jennifer Manickam, M.D., chair of adult and family medicine technology leads at The Permanente Medical Group.

Other healthcare providers have also experimented with AI to optimise the management of patient messages. For example, Ochsner Health has initiated a pilot programme using generative AI to compose draft responses to routine patient requests, which clinicians then review and personalise before dispatch.

As Kaiser Permanente and other organisations continue to explore AI’s potential, the landscape of physician-patient communication is set for significant transformation, promising to enhance the efficiency and quality of healthcare delivery.

Two in three physicians now use AI in healthcare as adoption jumps 78% in one year

The use of artificial intelligence (AI) in healthcare among physicians has grown significantly in the past year, with adoption rates increasing by 78% from 2023 to 2024. A newly released survey from the American Medical Association (AMA) highlights this trend, showing that nearly two-thirds (66%) of physicians now use AI tools in their practice. Despite some lingering concerns, enthusiasm for AI in healthcare is on the rise, as many physicians recognise its potential benefits.

Rapid Growth in AI Adoption Among Physicians

According to the AMA survey, 66% of physicians reported using AI for various tasks in 2024, compared to just 38% in 2023. The most common applications include:

• Documentation support – assisting with billing codes, medical charting, and visit notes.
• Clinical documentation generation – creation of discharge instructions, care plans, and progress notes.
• Translation services – aiding in multilingual communication with patients.
• Summarisation of medical research – condensing complex medical literature and standards of care.
• Assistive diagnosis – providing clinical decision support.
• Patient engagement – facilitating chatbot interactions and personalised health recommendations.

These AI-driven tools are increasingly being integrated into clinical workflows to enhance efficiency and improve patient care outcomes.

Shifting Physician Sentiments Toward AI

The AMA survey, which gathered insights from nearly 1,200 physicians across various specialties and employment settings, examined changes in attitudes toward AI from summer 2023 to autumn 2024. The findings indicate a positive shift:

• 35% of physicians reported that their enthusiasm for AI now outweighs their concerns, up from 30% in 2023.
• Only 25% of physicians expressed that their concerns about AI outweigh their enthusiasm, a drop from 29% the previous year.
• 40% of physicians stated that they remain equally excited and concerned about AI.

Dr Jesse M. Ehrenfeld, MD, MPH, Immediate Past President of the AMA, commented on these findings, stating:

“The AMA survey illustrates that physicians are increasingly intrigued by the assistive role of health AI and the potential of AI-enabled tools to reduce administrative burdens, enhance diagnostic accuracy, and personalise treatments.”

Key Insights from the AMA Survey

The survey outlines four major takeaways that provide deeper insight into how physicians view AI:

1. AI Usage in Practice Has Grown Substantially
   • In 2024, only 33% of physicians reported not using AI in any capacity, a significant drop from the 62% of physicians who reported non-usage in 2023.
2. Positive Sentiment and Enthusiasm for AI is Increasing
   • Physicians are recognising AI’s advantages in patient care, with 68% reporting that AI provides at least some benefit—an increase of five percentage points from 2023.
3. Reducing Administrative Burden is a Key Area of AI Opportunity
   • 57% of physicians identified administrative task automation as AI’s greatest potential benefit, particularly in clinical documentation.
4. Physicians Require Certain Conditions to Increase AI Adoption
   • Physicians identified several factors necessary for improving AI trust and adoption, including a feedback loop, data privacy assurances, seamless workflow integration, and sufficient training.
   • 47% of respondents ranked increased oversight as the top regulatory action required to enhance trust in AI adoption.

Dr Ehrenfeld further emphasised the importance of addressing these challenges:

“There remain unresolved physician concerns with the design of health AI and the potential of flawed AI-enabled tools to put privacy at risk, integrate poorly with EHR systems, offer incorrect conclusions or recommendations, and introduce new liability concerns. Increased oversight ranked as the top regulatory action needed to increase physician confidence and adoption of AI.”

How Physicians Are Using AI in 2024

Among the surveyed physicians who reported using AI, the most common applications saw notable increases from 2023 to 2024:

These statistics reflect the growing reliance on AI to streamline documentation, enhance communication, and provide clinical decision support.

Regulatory and Policy Considerations

As AI adoption in healthcare expands, the AMA is advocating for policies to ensure the responsible development, deployment, and use of AI. Their advocacy principles focus on:

• Healthcare AI oversight – ensuring proper regulatory frameworks.
• Transparency in AI use – defining when and what disclosures should be made regarding AI use.
• Generative AI policies and governance – establishing ethical and operational standards.
• Physician liability protections – clarifying legal responsibilities in AI-assisted decision-making.
• AI data privacy and cybersecurity – safeguarding sensitive patient information.
• Payer use of AI – ensuring fair and unbiased automated decision-making in insurance coverage.

Conclusion

The AMA’s latest survey underscores the rapid expansion of AI adoption in healthcare, with physicians increasingly leveraging AI to improve efficiency and patient outcomes. While enthusiasm is growing, the need for robust oversight, clear regulations, and continued education remains critical to fostering trust and maximising the benefits of AI in medicine.

As AI tools continue to evolve, their role in supporting physicians and enhancing patient care is expected to become even more prominent. The challenge moving forward will be ensuring these technologies are seamlessly integrated into clinical workflows while maintaining high standards for accuracy, security, and physician oversight.

Apple expands health research efforts with large-scale study on physical and mental well-being

Aiming to Bridge the Gap Between Technology and Healthcare

Apple is significantly expanding its health research ambitions by launching a large-scale, longitudinal study to monitor changes in physical and mental well-being. This initiative will leverage data collected from Apple’s ecosystem of devices—including iPhones, Apple Watches, and AirPods—as well as third-party devices. The study is designed to explore a broad spectrum of health and disease areas, with a particular focus on understanding the relationships between different aspects of health, such as mobility, cardiovascular function, mental well-being, and social determinants.

The new Apple Health Study builds upon Apple’s previous research efforts, which began over five years ago with three medical studies investigating the Apple Watch’s capabilities in tracking cardiovascular health and mobility, hearing changes, and reproductive health. This latest initiative takes a more comprehensive approach, seeking to assess the intricate connections between physical health, mental health, and lifestyle factors, including whether a person lives alone or with family.

A Holistic Approach to Health Monitoring

Apple’s goal is to identify signals within an individual’s health data that may indicate the early onset of medical conditions. By analysing these signals, researchers hope to enhance early detection efforts, ultimately improving outcomes for a variety of conditions. Apple executives and researchers have highlighted that health conditions often manifest through changes in multiple areas of the body, making it essential to consider a holistic view of health data.

One area of particular interest is the link between hearing health and cognitive function. Researchers are keen to explore whether monitoring changes in hearing could help reduce the risk of cognitive decline. Other potential avenues for investigation include the impact of mental well-being on heart rate, the role of sleep in influencing exercise performance, and the long-term effects of daily habits on overall health.

By incorporating wearable technology into the study, Apple aims to provide researchers with unprecedented insights into how lifestyle choices and daily behaviours shape long-term health outcomes.

A Large-Scale, Diverse Study Population

Apple has emphasised its commitment to enrolling a diverse and extensive participant base for the study, although specific enrolment targets have not yet been disclosed. The study will be conducted in collaboration with Brigham and Women’s Hospital, a renowned research institution and a primary teaching affiliate of Harvard Medical School. This partnership builds on Apple’s previous collaboration with the hospital, which, along with the American Heart Association, helped launch the Apple Heart and Movement Study in 2019.

As with Apple’s previous studies, the Apple Health Study will be accessible through the Research app, allowing participants to contribute data remotely, without the need for in-person visits. This virtual study model enables continuous data collection over extended periods, offering a more detailed picture of how various health factors evolve over time.

Leveraging Research for Product Innovation

Since the launch of the Research app, Apple has gained “valuable insights” that have informed the development of new health features across its devices, according to Sumbul Desai, M.D., Apple’s vice president of health. These advancements include the Vitals app on the Apple Watch and the Walking Steadiness feature on iPhone, both of which help users monitor key health indicators.

“These features have surfaced new insights in areas of health that have long been undervalued, like menstrual and hearing health,” Desai explained. “Research and validation are part of the foundation of all of our work in health, supporting the innovative features we bring to our users across devices. We’re thrilled to bring forward the Apple Health Study, which will only accelerate our understanding of health and technology across the human body, both physically and mentally.”

The Apple Health Study will investigate a wide range of health domains, including activity levels, ageing, cardiovascular and circulatory health, cognition, hearing, menstrual health, mental well-being, metabolic health, mobility, neurological function, respiratory health, and sleep patterns.

A Vision for the Future of Health Technology

Apple’s latest research effort underscores the growing role of consumer technology in advancing medical understanding. The study aims not only to explore health trends but also to inform the development of future Apple products, potentially leading to new tools that help individuals manage their health more effectively.

“We’ve only just begun to scratch the surface of how technology can improve our understanding of human health,” said Calum MacRae, M.D., Ph.D., a cardiologist, professor of medicine at Harvard Medical School, and principal investigator of the Apple Health Study at Brigham and Women’s Hospital. “We are excited to be part of the Apple Health Study, as it will continue to explore connections across different areas of health using technology that so many people carry with them every day.”

By integrating real-world health data with cutting-edge research, Apple continues to position itself at the forefront of digital health innovation, paving the way for more personalised and accessible healthcare solutions in the future.