Digital Health

New Johns Hopkins research highlights success of digital tools in curbing childhood obesity

A recent study led by researchers at Johns Hopkins Children’s Center, in collaboration with several academic institutions, suggests that integrating digital feedback with traditional in-clinic counselling for parents could help prevent obesity in young children who are at high risk. By using text messaging and digital tools to reinforce advice on nutrition, activity, and play, the study indicates a significant potential for curbing childhood obesity and related long-term health risks.

The research, co-led by Eliana Perrin, M.D., M.P.H., Bloomberg Distinguished Professor of Primary Care at the Johns Hopkins University Schools of Medicine, Nursing, and Public Health, will be published in the Journal of the American Medical Association (JAMA) and presented at the Obesity Society’s “Obesity Week” conference in San Antonio. This study builds on decades of research highlighting the increased risk of lifelong obesity, cardiovascular disease, diabetes, and other serious conditions for young children with obesity, particularly within low-income and minority groups.

According to data from the U.S. Centers for Disease Control and Prevention (CDC), approximately 1 in 5 school-aged children had obesity in 2017–18, a figure that has only grown due to the COVID-19 pandemic. Efforts to lower these rates have often focused on in-person counselling, which has had limited success. In response, the Johns Hopkins team developed a new digital approach to support the Greenlight Program, an intervention designed by Perrin and colleagues that previously relied solely on written materials and in-person counselling during paediatric visits.

Building on prior knowledge, Perrin noted, “We found that parents are eager for more information to help their children grow up healthy, and the vast majority of parents own smartphones.” With this in mind, the researchers expanded the Greenlight Program to incorporate digital messaging, with the goal of sustaining healthier behaviours as paediatric visits become less frequent after age two.

In collaboration with Vanderbilt University and five other institutions, the research team recruited nearly 900 parent-infant pairs from medical centres including Duke University, University of Miami, New York University/Bellevue Hospital Centre, University of North Carolina, Stanford University, and Vanderbilt University Medical Centre. The study began with infants aged 21 days or younger who were born after 34 weeks, at a healthy weight, and had no chronic medical conditions that might influence weight gain.

Approximately 45% of the participants identified as Hispanic, 20% as white, and nearly 16% as Black, with over half experiencing low health literacy and nearly 16% facing food insecurity. To assess the intervention’s effectiveness, parent-infant pairs were randomly assigned into two groups. Both groups received Greenlight Program materials, which included age-appropriate booklets and in-person counselling from primary care providers about nutrition, physical activity, sleep, and screen time.

Half of the group, however, received an additional digital intervention: a system of interactive text messages sent every two weeks in English or Spanish to support health behaviour goals such as reducing sugary drinks or minimising screen time. These messages were personalised and linked to a web-based “dashboard” where parents could track progress and self-rate their goal achievements. Depending on parents’ feedback, the digital system provided immediate suggestions, motivational tips, and reminders to reinforce health behaviours.

Results from the study reveal that children whose parents received digital feedback, along with in-person counselling, showed healthier weight-for-length growth curves over the first two years of life compared to those who received only in-clinic counselling. At the two-year mark, children in the digital group had a reduction in weight-for-length ratio of 0.33 kg/m, an amount researchers deemed meaningful for effective obesity prevention. Moreover, the prevalence of obesity was notably lower in the digital intervention group, with around 7% of children developing obesity compared to 13% in the clinic-only group, representing an adjusted relative reduction of nearly 45%.

The digital approach proved especially beneficial in populations with the highest risk factors for obesity. “The digital services could have significant impact if implemented on a broader scale,” the researchers noted, as the intervention’s effect was observed as early as 4 months and remained consistent throughout the two-year study period.

Dr Perrin highlighted the importance of these findings, noting, “Most young children with obesity do not outgrow it. What is exciting from our study is that we prevented those children who would have had an unhealthy weight from the outset, helping them to achieve a healthier weight that can support lifelong health.”

The study also found that the digital intervention was particularly effective among children from food-insecure households, Hispanic and non-Hispanic Black children, and those with limited health literacy. Perrin underscored the potential of this programme in reducing health disparities, stating, “If we can prevent obesity in these children at greatest risk, we can also create better health equity in the future.”

The research team hopes to track the participants’ health outcomes as they grow, aiming to gather more data on the long-term impacts of early obesity prevention through digital intervention.

Additional contributors to the study include William Heerman, Russell Rothman, Jonathan Schildcrout, Aihua Bian, Laura Adams, and Evan Sommer from Vanderbilt University Medical Centre; Lee Sanders from Stanford University; Kori Flower from the University of North Carolina at Chapel Hill; Alan Delamater from the University of Miami; Melissa Kay from Wake Forest University; Charles Wood from Duke University; Rachel Gross and H. Shonna Yin from New York University; along with other Greenlight investigators.

NHS to trial AI tool that predicts health risks and early death

The NHS in England is set to trial an innovative artificial intelligence (AI) tool designed to predict individuals’ risk of developing or worsening heart disease, as well as the likelihood of early mortality, through the use of electrocardiogram (ECG) readings. This cutting-edge technology, known as AI-ECG risk estimation (AIRE), represents a significant step forward in preventive healthcare, potentially enabling more precise treatment approaches and optimising NHS resources.

Developed by researchers at Imperial College London in collaboration with Imperial College Healthcare NHS Trust, AIRE is trained to interpret ECG results to forecast the progression of heart disease and identify individuals at heightened risk of early death. The research team used extensive datasets from international sources to train the AI model, allowing it to make predictive assessments regarding whether individuals might experience new health conditions, deteriorating heart health, or even mortality within a defined period.

The ECG, a commonly used test that records electrical signals in the heart, offers a visual representation of the electrical activity within and across the heart’s various chambers. The AIRE technology has been specifically developed to interpret these signals and assess the potential risk to an individual’s long-term health. Dr Fu Siong Ng, a reader in cardiac electrophysiology at Imperial College London and consultant cardiologist at both Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust, emphasised the tool’s reliability, stating, “Our work has shown that this AI model is a credible and reliable tool that could, in future, be programmed for use in different areas of the NHS to provide doctors with relevant risk information.”

In a study published on 24 October 2024 in The Lancet Digital Health, researchers found that AIRE correctly classified individuals’ risk of mortality over a ten-year span in 78% of cases, categorising risk levels from high to low. These findings suggest the tool could play an instrumental role in identifying people at risk early on, allowing for more targeted healthcare interventions and potentially improving health outcomes.

Clinical trials aimed at evaluating the real-world effectiveness of AIRE are scheduled to commence in 2025, involving patients at both Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospitals NHS Foundation Trust. These trials will assess whether the insights provided by AIRE can actively improve patient outcomes and aid clinical decision-making processes.

Dr Ng expressed optimism regarding AIRE’s potential impact on patient care and resource management within the NHS, explaining, “This could have a positive impact on how patients are treated, and ultimately improve patient longevity and quality of life. It could also reduce waiting lists and allow more efficient allocation of resources. We believe this could have major benefits for the NHS, and globally.” He further added, “The important next step is to test whether using these models can actually improve patient outcomes in clinical studies.”

Looking ahead, researchers at Imperial College London are hopeful that AIRE could become an integrated part of NHS services within the next five years. This predictive AI tool has the potential to transform how clinicians assess and respond to heart disease risks, moving beyond traditional ECG applications.

Professor Bryan Williams, the chief scientific and medical officer at the British Heart Foundation, which provided funding for the research, highlighted the significance of this advancement. “This large, exciting study offers a glimpse into how AI could be used to improve diagnosis of heart disease,” he said. “ECGs have been used to assess the heart for over a century, and this research has demonstrated the extraordinary power of AI to gain important health insights from a routine test.”

Professor Williams underscored the broader implications of the technology, noting that, “This could take the use of ECGs beyond what has previously been possible, by helping assess risk of future heart and health problems, as well as risk of death. We look forward to seeing how AI can be piloted in routine clinical practice and how this will help accelerate and inform clinical decision-making, ensuring patients receive the most timely and effective treatment and support.”

With its potential to reshape cardiovascular care and early mortality risk assessment, AIRE offers a promising advancement for the NHS and the global healthcare community alike.

Artificial intelligence promises to revolutionise hospital quality reporting, study finds

A pilot study led by researchers at the University of California San Diego School of Medicine suggests that advanced artificial intelligence (AI) could revolutionise hospital quality reporting, making it faster, simpler, and more efficient while maintaining high levels of accuracy. This transformation, researchers argue, could pave the way for enhanced health care delivery by easing the reporting process and optimising resource use.

The study’s findings, published on 21 October 2024 in the New England Journal of Medicine (NEJM) AI, reveal that a large language model (LLM)-driven AI system can accurately process hospital quality metrics, reaching a 90 per cent agreement rate with traditional manual reporting. The potential impact, the authors say, could be profound, as the system may replace laborious manual methods with a faster, more reliable approach.

In partnership with the Joan and Irwin Jacobs Centre for Health Innovation (JCHI) at UC San Diego Health, the study’s researchers demonstrated that LLMs could accurately abstract complex quality measures, including those required for the challenging CMS SEP-1 measure, which evaluates severe sepsis and septic shock. This capability is a key milestone, as the SEP-1 measure alone demands a rigorous 63-step review of patient records, a process which often takes weeks and requires multiple reviewers.

Aaron Boussina, the lead author and postdoctoral scholar at UC San Diego School of Medicine, expressed optimism about the transformative impact of AI on health care systems. “The integration of LLMs into hospital workflows holds the promise of transforming health care delivery by making the process more real-time, which can enhance personalised care and improve patient access to quality data,” he said. “As we advance this research, we envision a future where quality reporting is not just efficient but also improves the overall patient experience.”

Traditional SEP-1 reporting involves a painstaking review of detailed patient records, a task that currently requires weeks of staff time across multiple reviewers. By using LLMs, however, the study found that hospitals could vastly reduce both the time and resources needed for this process. AI systems could rapidly scan patient charts and generate critical insights within seconds, automating significant portions of the abstraction process while maintaining accuracy.

This AI-driven approach not only simplifies reporting but also allows health care staff to redirect their focus from manual administrative tasks to patient care. “We remain diligent on our path to leverage technologies to help reduce the administrative burden of health care and, in turn, enable our quality improvement specialists to spend more time supporting the exceptional care our medical teams provide,” said Chad VanDenBerg, co-author of the study and chief quality and patient safety officer at UC San Diego Health.

Beyond simplifying processes, the study highlights several other potential benefits of using AI for quality reporting:

1. Increased Accuracy and Error Reduction: LLMs can detect and correct errors in real time, reducing discrepancies in reporting.
2. Reduced Administrative Costs: Automation of routine tasks allows for significant cost savings.
3. Near Real-Time Quality Assessments: LLMs can provide more immediate quality evaluations, enabling quicker responses to patient care needs.
4. Scalability Across Various Health Settings: The adaptability of LLMs means they could be applied in different health care environments with ease, potentially standardising quality reporting.

The study’s next steps involve validating these findings through larger trials and working towards implementing the system in real-world health care settings. The researchers are hopeful that, in time, this innovation will support reliable, efficient data and reporting methods that are essential for quality care provision.

The study authors include Shamim Nemati, Rishivardhan Krishnamoorthy, Kimberly Quintero, Shreyansh Joshi, Gabriel Wardi, Hayden Pour, Nicholas Hilbert, Atul Malhotra, Michael Hogarth, Amy Sitapati, Karandeep Singh, and Christopher Longhurst, all affiliated with UC San Diego.

The research was partially funded by the National Institute of Allergy and Infectious Diseases (1R42AI177108-1), the National Library of Medicine (2T15LM011271-11 and R01LM013998), the National Institute of General Medical Sciences (R35GM143121 and K23GM146092), and JCHI.

Telemedicine and low-carbohydrate diet drive diabetes remission and medication reduction in long-term study

A recent study published in Diabetes Research and Clinical Practice has demonstrated the significant impact of a telemedicine intervention aimed at helping people living with type 2 diabetes (T2D) adhere to a very low-carbohydrate diet to induce nutritional ketosis. The findings show that this remote care approach led to notable health improvements over five years, including sustained weight loss, better cardiometabolic health, and reduced dependency on diabetes medications, with a remarkable portion of participants achieving long-term remission from the disease.

Study Background:

Historically, type 2 diabetes has been regarded as a chronic, progressive condition that requires lifelong management. However, emerging research has shown that certain therapies can effectively reverse the disease, lowering glycated haemoglobin (HbA1c) levels and reducing the need for glucose-lowering medications. This has opened the door to the possibility of medication-free diabetes remission, where HbA1c levels are maintained below 6.5% for at least three months without medication. Achieving remission is associated with significant long-term health benefits, as hyperglycaemia is linked to an increased risk of diabetes-related complications.

Among the various approaches to managing T2D, carbohydrate restriction has shown promise in improving cardiovascular health and glycaemic control. However, most studies have focused on shorter durations, often limited to two years or less. This study sought to explore the long-term effects of a telemedicine-driven, low-carbohydrate dietary intervention over five years.

Study Overview:

The study aimed to assess the long-term outcomes of a telemedicine intervention on individuals with T2D, examining factors such as blood sugar control, weight management, medication use, and overall cardiometabolic health. Participants were individuals living with T2D who had a body mass index (BMI) above 25. Initially, these participants were recruited for a two-year study comparing continuous care interventions (CCI) with usual care (UC). At the conclusion of the two years, participants in the CCI group were offered the opportunity to continue with the intervention for an additional three years.

Of the original 194 participants in the CCI group, 169 chose to continue for the full five years. The entire intervention was delivered remotely via a mobile application, without any in-person consultations. The app facilitated nutritional guidance and diabetes medication management, all handled through telemedicine.

Participants were encouraged to follow a highly restricted carbohydrate diet, consuming less than 30 grams of carbohydrates daily to achieve and maintain nutritional ketosis. The app allowed individuals to track their weight, blood glucose, and beta-hydroxybutyrate (BHB) levels, while also providing access to health coaches, physicians, and a peer support community.

Key Findings:

At the end of the five-year study, the average age of participants was 54.2 years, with nearly 68% of the cohort being female. Notably, 20% of the participants had achieved remission from diabetes, defined as HbA1c levels below 6.5% without the need for glucose-lowering medications or using only metformin. Among those who achieved remission at the two-year mark, an impressive 57.6% remained in remission at five years, demonstrating the durability of the intervention.

In terms of health improvements, participants saw a 0.3% reduction in HbA1c levels, a 7.6% decrease in body weight, and a 30.6% drop in fasting insulin levels over the course of the study. Cardiometabolic health markers also improved, with HDL cholesterol levels rising by 17.4% and high-sensitivity C-reactive protein (hs-CRP), an inflammation marker, dropping by 43.6%. These positive changes occurred despite a significant reduction in the use of diabetes medications.

A substantial proportion of participants experienced weight loss, with 61.3% achieving a 5% reduction in body weight and nearly 40% maintaining a 10% weight loss. Factors contributing to remission included lower fasting insulin levels, better adherence to the dietary protocol, weight loss, reduced reliance on potent diabetes medications, and a shorter duration of diabetes.

Over the course of the study, the proportion of participants using diabetes medications dropped from 85.2% to 71.3%. Use of medications other than metformin fell from 55.7% to 32.8%, and the average daily insulin dose significantly decreased from the baseline.

Statistical Analysis:

To evaluate the changes in health markers over time, the researchers employed a variety of statistical models. Linear mixed-effects models were used to account for within-subject variations and correlations over the five-year period. These models were adjusted for key covariates, including age, sex, and the duration of diabetes. The results showed statistically significant improvements in HbA1c, fasting insulin, and cardiovascular markers, confirming the robustness of the intervention’s effects.

Comparison with Other Studies:

When compared to other well-known lifestyle intervention trials, this study’s remission rates were notably higher. For instance, the Look AHEAD trial reported a remission rate of 7.3% over four years, and the DiRECT trial achieved a 13% remission rate after five years. In contrast, 20% of participants in this telemedicine intervention reached remission at five years, with 32.5% achieving HbA1c levels below 6.5% without the use of medication or only using metformin. The higher rates of remission in this study may be attributed to the sustained carbohydrate restriction and continuous support provided through the remote care model.

Conclusions:

The findings from this study suggest that a low-carbohydrate diet, combined with continuous remote care, can lead to significant long-term health benefits for people living with type 2 diabetes. After five years, 20% of participants had achieved diabetes remission, with 15 out of 24 participants maintaining remission for four consecutive years. Additionally, 32.5% of participants were able to achieve HbA1c levels below 6.5% without the need for glucose-lowering medications, or only using metformin.

Even those who did not reach full remission still experienced meaningful improvements, including stable blood glucose levels, reduced reliance on medications, and improvements in cardiovascular health. The study also highlighted the reduction in inflammation and other markers of cardiovascular risk, with a 40% decrease in the medication effect score further demonstrating the clinical value of this intervention.

The strengths of the study include its long duration and the broad applicability of the intervention, making it suitable for people with type 2 diabetes at various stages of the disease. However, it is worth noting the study’s limitations, including the absence of a comparison group over the full five-year period and the lack of racial diversity among the participants.

Overall, the study underscores the potential for telemedicine-driven, low-carbohydrate dietary interventions to provide lasting health benefits, including the possibility of diabetes remission and reduced medication dependence, for people living with type 2 diabetes.

Harvard’s new AI model identifies potential treatments for rare diseases using existing drugs

Recent advancements in biological AI models have shown significant potential in the development of new medications. But can these technologies also be leveraged to find treatments for rare diseases using drugs that are already available? Researchers at Harvard Medical School aimed to explore this possibility with their new foundation model, TxGNN, which is specifically designed to identify existing drugs that could treat rare diseases lacking current therapies.

The TxGNN model, introduced in a paper published in Nature, is considered the first AI system to focus on repurposing already approved drugs to target rare diseases for which there are no treatments presently available on the market.

Although each rare disease individually affects a small number of people, the collective impact of the over 7,000 classified rare conditions is significant, affecting around 300 million people worldwide, according to The Lancet. Yet, only 5–7% of these conditions have drugs that are currently approved by the Food and Drug Administration (FDA). Interestingly, nearly one-third of all drugs approved by the FDA eventually gain approval for multiple uses, with some being applied to as many as 10 different indications, the authors of the study explain.

However, the challenge lies in the fact that discovering new applications for these drugs has historically been an unpredictable and serendipitous process. As the research team describes, it often relies on healthcare professionals accidentally uncovering these new uses while treating people.

“Predicting the efficacy of all drugs against all diseases would enable us to select medications with fewer side effects, design more effective treatments that target multiple points within a disease’s pathway, and systematically repurpose existing drugs for new therapeutic purposes,” the authors note.

The rise of AI-driven breakthroughs, such as Google’s AlphaFold protein prediction model, which won the Nobel Prize for Chemistry this year, has ignited an explosion of generative AI applications in drug discovery. Numerous companies are also developing models aimed at drug repurposing, according to GlobalData.

The Harvard team behind TxGNN claims their model is approximately 50% more effective than existing repurposing models in identifying potential drug candidates. Additionally, it is reported to be 35% better at predicting contraindications, which are reasons a specific drug may not be appropriate for an individual.

What sets TxGNN apart is its broader scope compared to many other AI models designed for drug discovery. As explained in a Harvard announcement of the research, while most models tend to concentrate on a single disease or a small group of related conditions, TxGNN is designed to comprehensively identify shared “mechanisms based on genomic underpinnings” between rare diseases and more common, better-understood conditions.

The tool has been trained on publicly available data sources such as DNA information and clinical notes and was validated using nearly 1.3 million de-identified patient records from Mount Sinai Hospital in New York. A notable feature of the TxGNN model is its explainer component, which clarifies the reasoning behind each prediction, offering a step-by-step breakdown of the decision-making process.

In a bid to encourage further scientific discoveries, the team has made TxGNN freely available to other researchers.

“This is precisely where we see the promise of AI in reducing the global disease burden, in finding new uses for existing drugs, which is also a faster and more cost-effective way to develop therapies than designing new drugs from scratch,” said Marinka Zitnik, one of the paper’s authors and an assistant professor of biomedical informatics at Harvard Medical School’s Blavatnik Institute.

This initiative highlights the potential of AI not just in the development of entirely new drugs but also in identifying existing medications that could be repurposed, offering faster, more efficient pathways to treatment for people living with rare diseases.

Surge in digital health investment as purchasers focus on value, outcomes, and patient-centred care

The latest survey from the Peterson Health Technology Institute (PHTI) highlights a significant increase in the planned investment in digital health solutions by health plans, employers, and healthcare systems. This upward trend is expected to continue throughout the coming year as these groups prioritise value and measurable outcomes in their purchasing decisions.

Detailed Insights from the 2024 State of Digital Health Purchasing Survey

The 2024 State of Digital Health Purchasing survey, developed in collaboration with NORC at the University of Chicago, offers a comprehensive analysis of current trends in digital health adoption. The survey not only sheds light on the evolving landscape of digital health but also provides key data on spending, contracting approaches, and future priorities in this rapidly growing field.

Ongoing Expansion in Digital Health Spending

This survey gathered responses from 332 decision-makers responsible for acquiring digital health solutions. The findings reveal a continued commitment to digital health innovation and investment across a broad spectrum of purchaser groups. Notably, the data indicates:

1. Employers: An overwhelming 97% of employers plan to maintain or increase their digital health expenditure.
   
2. Health Systems: A significant 86% of healthcare systems intend to sustain or grow their digital health spending.
   
3. Health Plans: 84% of health plans also expect to maintain or expand their investment in these technologies.

The broad adoption of digital health solutions reflects the increasing recognition of their role in enhancing patient care and improving operational efficiencies across the healthcare sector.

Factors Fueling the Surge in Digital Health Investment

Several key drivers underpin this surge in investment:

1. Rising Consumer Demand: The growing appetite among individuals for accessible and convenient digital health solutions is a major catalyst for increased spending across all purchaser groups.
   
2. Improving Health Outcomes: Digital health technologies are widely acknowledged for their potential to elevate the quality of care and improve health outcomes for people, which is a strong motivator for purchasers.
   
3. Economic Efficiency: Particularly for health plans, the ability to reduce costs through the use of digital health solutions is a primary reason for heightened investment.

These factors highlight the dual appeal of digital health solutions: not only do they meet the needs and preferences of individuals, but they also promise better outcomes and cost savings for healthcare providers and payers.

Trends in Contracting and Performance Measurement

The survey also reveals emerging trends in how digital health contracts are structured and how their performance is assessed:

1. Short-Term Contracts: The majority of contracts between purchasers and digital health providers have a duration of two years or less. This allows purchasers to regularly evaluate the effectiveness of the solutions and adjust their strategies as needed.
   
2. Risk-Based Contracts: Performance-based contracts, which link payment to the achievement of specific outcomes, are increasingly common. The survey indicates that 79% of purchasers are using these risk-based arrangements for at least some of their digital health solutions.
   
3. Outcome-Focused Evaluations: Health plans and healthcare systems are particularly focused on health outcomes when evaluating the performance of their digital health contracts. In contrast, employers are more likely to assess success based on user adoption rates and engagement levels.

This emphasis on performance and outcomes is part of a broader trend towards evidence-based decision-making in healthcare, ensuring that digital health solutions deliver tangible benefits to both individuals and organisations.

Top Priorities in Disease Areas

The survey also highlights the priority areas where digital health solutions are being deployed. Purchasers are focusing on the following key conditions and areas of care:

• Diabetes
• Preventive Care
• Mental Health
• Cardiovascular Disease
• Primary Care

These areas reflect the most pressing healthcare needs that digital health solutions are being leveraged to address, offering potential for both improved health outcomes and enhanced healthcare delivery.

Expert Perspective: Bridging Demand and Evidence-Based Solutions

Commenting on the findings, Caroline Pearson, Executive Director of the Peterson Health Technology Institute, emphasised the opportunity for digital health companies to align more closely with the needs of purchasers. She stated:

“Health plans, employers, and providers want to meet continued demand for digital health solutions, while ensuring the solutions they purchase have strong evidence that they improve health and generate economic efficiencies. This survey shows that there is a valuable opportunity for digital health companies to better align their offerings with what purchasers need and want, which in turn, will allow more people to access these tools and the benefits they can bring.”

Pearson’s remarks underline the critical importance of providing digital health solutions that are not only innovative but also backed by robust evidence of their effectiveness in improving health and creating efficiencies in care delivery.

Conclusion: A Growing Market with Clear Priorities

The 2024 State of Digital Health Purchasing survey provides a detailed picture of a rapidly expanding market, where purchasers are increasingly focused on value, outcomes, and patient-centred care. As digital health solutions continue to evolve, those that can demonstrate their ability to enhance health outcomes, engage users effectively, and deliver economic benefits will be in high demand. For healthcare systems, employers, and health plans alike, the message is clear: investment in digital health is here to stay, and the focus on performance and measurable outcomes will only grow stronger.

Digital pathology to enhance precision and efficiency in diagnostics

NYU Langone Health has revolutionised disease diagnosis through the launch of its digital pathology programme, moving from traditional microscope-based examination to high-definition digital imaging. This transformation allows for real-time sharing of diagnostic images across the hospital network, bringing unprecedented clarity in the viewing of human tissue samples, while also reducing diagnosis time and fostering collaboration. This development enhances a critical yet often overlooked aspect of patient care.

“For as long as pathology has existed, we’ve been bent over microscopes in our offices, manually reviewing slides that have been physically delivered to us,” said Dr. Syed T. Hoda, Director of Digital Pathology, Clinical and Bone and Soft Tissue Pathology at NYU Langone. Dr. Hoda is one of about 100 bone and soft tissue pathologists in the United States. “As of this week, images can be sent to the appropriate pathologist in real-time, regardless of where a patient is being treated in our network.”

This digital shift is especially timely, as the healthcare system is grappling with a shortage of pathologists amidst rising disease rates. A limited number of specialists are tasked with confirming diagnoses that impact millions of people. The adoption of digital pathology not only boosts the efficiency of pathologists’ workloads, but it also addresses risks associated with physical slides, such as storage complications, degradation over time, and delays in delivering results. These improvements will contribute to a more resilient healthcare system.

In addition to enhancing efficiency, the programme is also creating new employment opportunities. NYU Langone is hiring 24 digital pathology coordinators, introducing a new career path within the healthcare industry.

Dr. Joan F. Cangiarella, Vice Chair of Clinical Operations in the Department of Pathology at NYU Grossman School of Medicine, highlighted the intense nature of pathologists’ work. “Our team examines tissue samples from individuals we may never meet, agonising over microscopic details that could have life-altering consequences. Now, with digital pathology, we can perform these tasks at a much higher level, further enhancing the exceptional care we already provide.”

This transition to digital also paves the way for artificial intelligence (AI) to assist in diagnostics, offering an exciting prospect for future advancements in healthcare.

“As one of the first health systems in the United States to fully adopt digital pathology, NYU Langone is advancing disease detection for its patients and, through the integration of AI, initiating a paradigm shift that could help alleviate an impending bottleneck in the healthcare system,” said Nader Mherabi, Executive Vice President and Vice Dean, Chief Digital and Information Officer at NYU Langone.

Exploring the potential of AI, Dr. Sean Hacking, Director of Digital Pathology Research, elaborated: “This programme will expand our diagnostic toolkit. Digital images will fuel the AI models we’re developing to detect cancer and other diseases at the earliest, most crucial stages, which can profoundly affect the treatment options available to individuals.”

The digital pathology programme aims to reduce the time between testing and treatment, improve collaboration among medical teams, and potentially increase the direct involvement of pathologists in patient care. Already, the impact is being felt across the hospital network.

“Just yesterday, I attended our first fully ‘digital’ tumour board,” shared Dr. Hoda. “I was able to instantly access entire cases while we discussed patients in real-time. In the past, retrieving glass slides from storage could delay clinical decisions by hours or even days. For someone awaiting a diagnosis, that wait can feel like an eternity.”

NYU Langone Health has established a long-term partnership with Philips to integrate cutting-edge digital pathology technology. Martijn Hartjes, Clinical Informatics Business Leader at Philips, echoed Mherabi’s enthusiasm, describing digital pathology as a foundation for expanding the capabilities of pathologists.

“NYU Langone Health is setting a new standard for precision diagnosis and treatment by fully embracing digital workflows in pathology. In other laboratories, we’ve seen efficiency improvements of 15 to 25 percent per case,” Hartjes said. “Digital pathology also supports the integration of AI, which can further enhance efficiency and unlock new possibilities in disease detection. At Philips, we understand the challenges of transitioning from analogue to digital processes, so we are committed to delivering technology and services that simplify this transition and empower clinicians to provide better care to more patients.”

NYU Langone Health is a leading, patient-centred academic medical institution, recognised for its excellence in patient care, education, and research. For three consecutive years, Vizient, Inc. has ranked NYU Langone as the No. 1 comprehensive academic medical centre in the United States. U.S. News & World Report has also placed nine of its clinical specialties among the top five nationwide. The health system offers a wide range of medical services across six inpatient locations, the Perlmutter Cancer Center, and more than 300 outpatient facilities across the New York area and Florida. NYU Langone’s network also includes two medical schools and a vast research enterprise.

New Regulatory Innovation Office to accelerate AI and emerging technologies in UK healthcare

The UK Government, led by Science and Technology Secretary Peter Kyle, has announced the establishment of a new Regulatory Innovation Office (RIO) aimed at facilitating the safe deployment of artificial intelligence (AI) and other advanced technologies within the healthcare sector. This new initiative is designed to streamline the regulatory process, allowing innovative products and services to reach the market more quickly while ensuring that safety and efficacy standards are maintained.

The RIO is set to play a key role in reducing bureaucratic barriers for businesses looking to introduce new technologies, thus enabling faster access to these advancements for the public and contributing to economic growth. The Department for Science, Innovation and Technology (DSIT) issued a press release on 8 October 2024, stating that the RIO will “support regulators to update regulation, speeding up approvals, and ensuring different regulatory bodies work together smoothly.”

The RIO’s initial focus will encompass four key areas of technology: AI and digital innovations in healthcare, connected and autonomous technology, engineering biology, and space. The office will collaborate closely with the Department of Health and Social Care to ensure that AI solutions, such as advanced AI training software for surgeons, are implemented safely within the healthcare system.

Peter Kyle emphasised the broader impact of RIO’s work, stating: “From breakthroughs that could help doctors diagnose illnesses earlier to satellite navigation for more accurate weather forecasting and getting emergency supplies to where they are needed, quickly and effectively, RIO will make sure UK companies are at the forefront of the next generation of technologies.” His statement highlights the potential for AI and emerging technologies to revolutionise various sectors, including healthcare, logistics, and emergency response.

The DSIT is currently seeking applications for the RIO’s first chair. This individual will be tasked with “leading the charge in backing business and safe innovation, and working with regulators and partners to shape a regulatory environment that is fit for the future.” This leadership role will be crucial in guiding the RIO’s efforts to create a regulatory framework that both supports innovation and ensures safety for users.

The new office aims to facilitate better coordination among different regulatory bodies and eliminate outdated regulations that may hinder innovation. The RIO will provide continuous feedback to the government on regulatory barriers that need addressing and set priorities for regulators to align with the government’s broader objectives. Additionally, it will support regulators in developing the necessary skills and capabilities to manage emerging technologies, thereby fostering economic growth.

The RIO will be housed within DSIT, integrating the existing roles of the Regulatory Horizons Council and the Regulators’ Pioneer Fund. By consolidating these functions, the RIO aims to create a more cohesive approach to regulating new technologies.

On the same day as the RIO’s announcement, the government also detailed its approach to regulating quantum technologies, in response to a report from the Regulatory Horizons Council on this field. This represents an initial step towards regulating innovations in quantum technology, which is expected to play a pivotal role in developing powerful computational capabilities across sectors, from healthcare to national security.

In addition to the RIO, the UK government has been actively investing in the advancement of quantum technology. In July 2024, DSIT announced a £100 million funding initiative to support research hubs dedicated to quantum technology. These hubs will focus on applications like quantum-enhanced blood tests, faster MRI scanning technology, and advanced surgical procedures and treatments. Such innovations promise to bring significant improvements to the healthcare sector, enabling more accurate diagnostics and novel treatment methods.

In parallel, the Medicines and Healthcare products Regulatory Agency (MHRA) has also taken steps to adapt its regulatory approach to emerging technologies. In May 2024, the MHRA launched the “AI Airlock,” a regulatory sandbox designed to address the unique challenges associated with medical devices that use AI. This initiative is intended to create a controlled environment where developers and regulators can collaborate to ensure that AI-driven medical devices meet safety and performance standards before they reach the market.

With the RIO and initiatives like the AI Airlock, the UK is positioning itself as a leader in the safe adoption of AI and other cutting-edge technologies in healthcare. By fostering a more adaptable and forward-thinking regulatory environment, the RIO aims to ensure that the benefits of these innovations are realised more swiftly, improving patient care and outcomes while supporting the growth of the UK’s technology sector.

Proposed staged rollout of Eli Lilly’s Mounjaro by NHS England includes digital solutions for wider access

The National Health Service (NHS) in England is exploring a phased introduction of the obesity treatment tirzepatide (Mounjaro, developed by Eli Lilly), driven by concerns over potentially high demand for the medication. The phased approach aims to ensure that individuals with the greatest clinical need receive the treatment first, while also preparing the system to meet the broader demand effectively.

The National Institute for Health and Care Excellence (NICE) initiated a three-week consultation on these proposals from NHS England, with final guidance expected to be published in December, 2024. This consultation period is intended to gather input from stakeholders on how best to manage the introduction of tirzepatide within the NHS framework.

Clinical Effectiveness and Pricing

Tirzepatide has shown greater effectiveness in promoting weight loss compared to diet and exercise support alone, as well as when compared with semaglutide alongside similar lifestyle support. Clinical trials have highlighted its potential to significantly aid people with obesity in achieving weight reduction. In its draft guidance issued in June, an independent committee from NICE recommended the use of the weekly injection for individuals with obesity. The treatment is priced at £122 per month for the maximum dose of 15 mg.

Eligibility Criteria for the Rollout

In its application to NICE, NHS England has outlined a staged approach for the rollout of tirzepatide. Initially, the drug will be made available to individuals with a body mass index (BMI) over 40 who also have at least three out of four specified weight-related health conditions: hypertension, dyslipidaemia, obstructive sleep apnoea, and cardiovascular disease. In subsequent stages, eligibility will be expanded to include those with a BMI over 40 plus two weight-related conditions, and eventually those with a BMI over 40 plus one weight-related condition.

This prioritisation aims to ensure that those with the most pressing health needs are given access to the medication first. NHS England estimates that nearly 250,000 people could be eligible for tirzepatide during the first three years of its phased introduction.

Exploring Digital and Community Services for Broader Access

To facilitate a smooth rollout and ensure timely delivery of the medication, NHS England is exploring innovative ways of administering tirzepatide, including digital and community-based services. These new models of care will be tested and evaluated to determine the most suitable and cost-effective approaches for providing weight loss support to an increasing number of individuals over the next nine years. The aim is to ensure that those eligible for the treatment receive the necessary dietary and exercise support alongside the medication, whether through primary or secondary care services.

NICE has acknowledged that the proposed length of the rollout is “unprecedented.” The extended timeframe is intended to ensure that resources are effectively managed and that the NHS can adapt its service delivery to accommodate the large number of people who may benefit from the new medication.

Reactions from Health Experts and Stakeholders

Sam Roberts, Chief Executive of NICE, emphasised the potential of this new generation of weight loss treatments to bring significant health benefits to people with obesity and to prevent the development of more serious health complications. Roberts stated, “Because of the very large number of people who could potentially benefit, NICE accepts that a phased rollout is required. However, we now need to hear from stakeholders on the proposals we have received from NHS England.”

Stephen Powis, NHS National Medical Director, supported the phased approach, highlighting its focus on those with the highest clinical need. He noted that this method allows time for the NHS to develop “new and innovative services through which other weight loss treatments can also be delivered.” These innovations aim to streamline the integration of tirzepatide into existing healthcare services and to accommodate future advances in weight management.

Simon Cork, a senior lecturer in physiology at Anglia Ruskin University, described the planned rollout of tirzepatide as a “key milestone in the future of obesity treatment.” He stressed the importance of providing comprehensive support to those receiving the medication, including tailored exercise programmes and personalised dietary guidance. Cork warned, “Without this high level of wraparound care, the NHS risks wasting money on these medications by not achieving the highest levels of weight loss possible. It is not clear whether the NHS has the capacity to provide this high level of wraparound care in the community to achieve this.”

A Strategic Move for Long-term Impact

The proposed phased rollout of tirzepatide represents a strategic move to address obesity care within the NHS while balancing demand and resource availability. By focusing initially on individuals with the highest need and considering the use of digital platforms to enhance accessibility, the NHS aims to maximise the impact of tirzepatide on public health. The feedback gathered during the NICE consultation will play a critical role in shaping the final approach, ensuring that the introduction of tirzepatide aligns with the needs of both patients and the healthcare system.

As the rollout progresses, the NHS and NICE will continue to evaluate and adjust their strategies, seeking to provide effective obesity care to a wider range of individuals while maintaining a sustainable approach to managing this new and promising medication.

£1.2 million grant fuels development of AI platform for early arthritis detection

Henley Business School has secured a significant grant of £1.2 million to develop an innovative machine learning system aimed at improving the early detection and referral of rheumatic and musculoskeletal diseases (RMDs). The project, known as RMD-Health, seeks to transform the way these conditions are identified and managed, offering a pathway to quicker diagnoses and more effective treatment options for individuals living with these conditions.

The initial pilot of RMD-Health is scheduled for 2026-2027, with trials planned at both the Royal Berkshire NHS Foundation Trust and Oxford University Hospitals NHS Foundation Trust. This pilot phase is critical for refining the AI system and moving it toward regulatory approval and subsequent commercialisation, ensuring that it meets the stringent requirements necessary for integration into the broader healthcare system.

The funding for this initiative is provided through a collaboration between the National Institute for Health and Care Research (NIHR), the Engineering and Physical Sciences Research Council, the Health Innovation Partnership, and Henley Business School. This financial support underscores the importance of addressing the pressing challenges associated with RMDs.

RMDs, which encompass conditions like inflammatory arthritis, affect up to one-third of the UK population and represent a leading cause of disability. These conditions place a considerable burden on both individuals and the healthcare system, often resulting in chronic pain, mobility issues, and substantial impacts on daily life.

Professor Weizi (Vicky) Li, who leads the project and serves as a professor of informatics and digital health at Henley Business School, highlighted the economic and healthcare challenges posed by RMDs. She noted, “With an estimated annual cost of £1.8 billion in sick leave and work-related disability for rheumatoid arthritis alone, the current RMD referral system faces huge challenges.”

Professor Li explained how RMD-Health aims to revolutionise the referral process, saying, “Our machine-learning system presents a new approach to RMD referrals. Unlike existing solutions, which often rely on the advice and guidance from already stretched rheumatology specialists, we’re introducing a machine learning-based decision support system enabling doctors to refer patients more accurately and promptly, ultimately leading to quicker and more effective treatment.”

One of the major issues with the current referral process is the delay in accessing specialised care for RMDs, which often results in individuals having to attend multiple GP appointments before receiving the appropriate care. Between 2019 and 2021, GPs accurately identified early inflammatory arthritis in only 40% of cases, leading to an increased workload for secondary care clinicians who must review a large volume of unnecessary referrals.

Dr. Antoni Chan, the project’s co-lead and a consultant rheumatologist at Royal Berkshire NHS Foundation Trust, emphasised the potential impact of the RMD-Health system. He stated, “This exciting and innovative project represents a major step forward in the early detection and referral of RMD, promising improved patient outcomes, reduced healthcare costs and increased efficiency across our healthcare system.” Dr. Chan also noted that during experimental trials at the trust, the AI tool demonstrated “significantly higher accuracy” than traditional clinical criteria and clinicians’ assessments.

Looking ahead, Dr. Chan expressed optimism about the project’s timeline, stating, “With this grant, we fully expect to be on track for regulatory approval at the end of three years.” The goal is to ensure that the system is ready for widespread use, offering tangible improvements in the early detection and management of RMDs.

The development of RMD-Health involves a collaborative effort that brings together AI experts, secondary care specialists, GPs, industry stakeholders, and patient representatives. This partnership aims to create a comprehensive software prototype that will lay the foundation for the future integration of RMD-Health into the NHS, ensuring that the system is both effective and practical for everyday use in clinical settings.

The project is led by Henley Business School, part of the University of Reading, in partnership with several key organisations, including the Royal Berkshire NHS Foundation Trust, the RBFT Health Data Institute, Oxford University Hospitals NHS Foundation Trust, Health Innovation Oxford and Thames Valley, Buckinghamshire, Oxfordshire and Berkshire West Integrated Care Board, and patient leaders. This consortium aims to ensure that the needs of patients remain at the forefront of the system’s development, making it as user-centred as possible.

In a related development, Flok Health, an AI-driven physiotherapy clinic tailored for people experiencing musculoskeletal issues, is set to be implemented within the NHS by autumn 2024. This initiative, announced in June 2024, aims to address the backlog in physiotherapy services and reduce waiting times for those seeking treatment. The deployment of Flok Health, alongside projects like RMD-Health, highlights the growing role of AI in transforming the delivery of healthcare for musculoskeletal conditions across the UK.

With the backing of this £1.2 million grant, the RMD-Health project is poised to make a significant difference in the early detection and referral process for RMDs, ultimately improving the quality of life for those affected and alleviating the pressure on an already strained healthcare system.

Development of new AI algorithm could revolutionise drug discovery say researchers

Researchers from King’s College London and Imperial College London have developed an innovative AI algorithm that has the potential to significantly accelerate drug discovery. This computer-based tool, known as Drug Synthesis using Monte Carlo (DrugSynthMC), is designed to enhance the diversity of chemical structures within drug libraries, creating thousands of drug-like molecules in just seconds.

Revolutionising Drug Discovery with AI

DrugSynthMC aims to overcome one of the major challenges in drug discovery: the limitations of existing drug libraries. These libraries often contain compounds that have been extensively studied and catalogued, leaving little room for the exploration of novel molecules. The new algorithm addresses this issue by generating a vast array of chemically diverse compounds, opening up new possibilities for drug candidates that may have previously been overlooked.

Dr Filippo Prischi, senior lecturer in molecular biochemistry at King’s College London and co-senior author of the study, highlighted the breakthrough:

“We showed that DrugSynthMC can expand the chemical diversity of compounds in available libraries, overcoming the limitations of existing drug collections.”

This capability is crucial because virtual-library screening—a process that relies on computational tools to sift through vast databases of known compounds—is a vital step in early-stage drug discovery. The objective is to identify chemical structures that have a high probability of binding to specific drug targets. Once promising compounds are identified, they undergo optimisation and testing in laboratory settings, both in cell cultures and animal models, before advancing to clinical trials.

Breaking Free from Traditional Limitations

Traditional methods of virtual-library screening are confined to compounds already known and catalogued. This limitation restricts researchers from discovering truly novel chemical entities, which could offer fresh approaches to treating diseases. DrugSynthMC breaks free from these constraints, allowing for the generation of new, previously unconsidered molecules.

At its core, the AI algorithm utilises a technique called Monte Carlo Tree Search, a mathematical method that calculates possible outcomes based on predefined actions. This sophisticated approach allows the algorithm to systematically build chemical structures in a simple text format. It follows a set of instructions designed to maximise the key properties of orally available drugs, such as solubility, synthesis feasibility, and safety.

Success in Creating Drug-Like Molecules

One of the remarkable achievements of DrugSynthMC is its ability to produce a large proportion of molecules that meet the desired criteria for drug development. The generated compounds are not only easy to synthesise but also soluble and non-toxic—key features for developing orally administered drugs.

The team behind this AI innovation believes that DrugSynthMC can be used to identify and refine molecules targeting proteins associated with various diseases. This could potentially lead to the discovery of novel treatments for conditions that currently have limited therapeutic options.

Their findings were published in the Journal of Chemical Information and Modeling on 9 September 2024.

A Promising Future for AI-Driven Drug Discovery

Dr Olivier Pardo, reader in cancer cell signalling at Imperial College London and co-senior author of the study, expressed his enthusiasm about the potential applications of DrugSynthMC:

“Even though this is a fairly simple algorithm, it’s far more efficient than anything more complex that has been tested or published out there and will become very useful in AI-driven drug discovery for bespoke therapeutic targets.”

One of the most promising aspects of this new tool is that it is publicly available, allowing the wider scientific community to use and build upon it. This collaborative approach could hasten progress in drug discovery, particularly in the development of treatments for diseases where current options are inadequate.

As the use of AI in drug discovery continues to grow, tools like DrugSynthMC may pave the way for faster, more efficient research, potentially leading to breakthroughs in therapeutic development for a wide range of conditions. The accessibility of this tool ensures that researchers across the globe can contribute to and benefit from this technology, propelling the field of drug discovery into a new era.

Digital health investments hold the key to preventing millions of deaths from noncommunicable diseases

An additional investment of just US$0.24 per patient per year in digital health interventions, such as telemedicine, mobile messaging, and chatbots, could save over 2 million lives from noncommunicable diseases (NCDs) over the next decade. This is according to a new report released by the World Health Organization (WHO) and the International Telecommunication Union (ITU). The report also highlights that this small investment could avert around 7 million acute medical events and hospitalisations, substantially reducing the pressure on healthcare systems globally.

The publication, titled “Going Digital for Noncommunicable Diseases: The Case for Action“, was launched during an event hosted by the Government of The Gambia at the 79th United Nations General Assembly. The launch was a collaborative effort between the ITU and WHO.

“The future of health is digital. But to make this vision a reality, we need both resources and collaboration,” stated WHO Director-General Dr Tedros Adhanom Ghebreyesus. “No single organisation can do it alone. We call on governments, partners, and donors to come together, invest strategically, and ensure that these life-saving innovations reach those who need them most.”

ITU Secretary-General Doreen Bogdan-Martin echoed this sentiment, saying, “The digital revolution has the potential to unleash a health revolution. At ITU, universal meaningful connectivity is a priority because digital is a catalyst for delivering targets in key sectors such as health and education. We call for greater collaboration between the health and tech sectors, including the development of strong digital public infrastructure, which is essential for delivering digital health services that can benefit people everywhere without leaving anyone behind.”

The Burden of Noncommunicable Diseases

Noncommunicable diseases, such as cardiovascular disease, cancer, diabetes, and chronic respiratory conditions, account for over 74% of global deaths each year. Many of these deaths are preventable. Despite progress in tackling these conditions, integrating digital health technologies into mainstream healthcare systems remains a significant challenge. The report underlines the urgency of adopting these technologies to scale up effective interventions and lessen the growing burden on healthcare systems worldwide.

Four major risk factors related to lifestyle and environment — tobacco use, unhealthy diet, harmful alcohol consumption, and physical inactivity — drive physiological changes in the body that increase the likelihood of NCDs. These factors contribute to raised blood pressure, obesity, elevated blood glucose levels, and high cholesterol. Digital tools, such as mobile messaging and chatbots, can help individuals understand and manage these modifiable risk factors, encouraging them to develop healthier habits and reduce their risk of NCDs.

The Role of Digital Health Tools

For individuals living with noncommunicable diseases, ongoing monitoring and long-term specialised care are often essential. Digital health interventions like telemedicine can help individuals overcome barriers to accessing healthcare services, such as distance or limited availability of specialists. These tools also provide real-time data for healthcare professionals, enabling them to make more informed decisions regarding their patients’ care.

While over 60% of countries have developed national digital health strategies, many face difficulties integrating these new technologies into their existing healthcare infrastructure. The report urges countries to invest in digital public infrastructure and promote the use of interoperable standards. This approach would help overcome significant obstacles to unlocking the full potential of digital health.

A Call for Global Collaboration

The report serves as a blueprint for action and supports both the WHO Global Initiative on Digital Health and the Global Strategy on Digital Health 2020-2025. The WHO, the ITU, and the United Nations Inter-Agency Task Force on the Prevention and Control of NCDs (UNIATF) Secretariat, in collaboration with the Be He@lthy, Be Mobile programme, are committed to providing tailored strategic planning and advocacy support to governments.

Dr Tedros and Doreen Bogdan-Martin emphasised the importance of collaboration between governments, tech innovators, and healthcare providers. Digital health technologies hold the promise of transforming healthcare and ensuring that individuals everywhere, regardless of location, can access the care they need. However, for this promise to be realised, both financial investment and concerted global cooperation are required.

By making digital health a central part of healthcare infrastructure, we have the potential to not only save millions of lives but also to significantly alleviate the strain on healthcare systems, particularly in low- and middle-income countries. The time for action is now. By investing strategically in digital health, we can prevent millions of unnecessary deaths and ensure a healthier future for all.

A Future Built on Digital Innovation

This report calls on governments and stakeholders to prioritise the development of digital infrastructure that supports healthcare delivery and public health initiatives. The blueprint laid out in the report highlights the need for strong, interoperable systems that can scale up interventions, ultimately leading to better health outcomes for individuals living with NCDs.

As digital technologies continue to evolve, they offer unprecedented opportunities to improve healthcare accessibility, efficiency, and effectiveness. By leveraging these innovations, we can address some of the most pressing health challenges of our time and move closer to a future where no one is left behind in the pursuit of health equity.