AI Tool Creates ‘Digital Twins’ of Patients to Forecast Future Health
Key Takeaways:
- New DT-GPT model creates virtual patient replicas to predict individual health trajectories with notable accuracy.
- The model outperformed 14 leading machine learning systems and demonstrated effective zero-shot predictions.
- Technology could accelerate drug development and shift healthcare towards more predictive and personalised practice.
Introduction
A new artificial intelligence model capable of generating virtual patient representations and forecasting future health outcomes has been described as a potential breakthrough for clinical research. The system, developed by researchers at the University of Melbourne, uses large language model (LLM) techniques to create personalised digital twins that mirror each individual’s clinical profile.
How the DT-GPT model was developed
The research team trained an existing large language model on three extensive datasets containing thousands of electronic health records. These datasets included information on people living with Alzheimer’s disease, people with non-small cell lung cancer, and people admitted to intensive care units. The aim was to equip the model with sufficient breadth of clinical data to enable it to generate detailed patient-level predictions.
The resulting tool, named DT-GPT, analysed each person’s medical history, such as laboratory values, diagnoses, and treatments. Using this information, it constructed a virtual counterpart for every individual and projected how their condition might evolve under ongoing clinical care.
Predictive performance and validation
Crucially, the model was not shown any actual health outcomes during training. This allowed researchers to rigorously assess the accuracy of its predictions once the model generated forecasts.
Associate Professor Michael Menden, lead researcher, explained the approach:
“For each patient, we created a virtual replica by initialising the model with their individual clinical profile.”
He added:
“For example, we created virtual twins of 35,131 intensive care unit (ICU) patients and accurately predicted what would happen to their magnesium levels, oxygen saturation and their respiratory rate over a 24 hour period, based on their laboratory results from the previous day.”
When benchmarked against 14 state-of-the-art machine learning models, DT-GPT consistently outperformed them in predictive accuracy.
Implications for clinical trials and personalised medicine
Researchers believe the tool has significant implications for the future of clinical trials. Because the model can simulate potential outcomes for large groups of virtual participants, it may help streamline drug development processes by reducing time and cost associated with early-stage testing.
Associate Professor Menden said:
“This technology paves the way for a shift from reactive to predictive and personalised medicine.”
He continued:
“It could enable doctors to anticipate if their patient’s health will deteriorate so they can intervene earlier.
“It could also be used to predict negative side effects of medications, allowing doctors to tailor treatment plans to suit each patient’s unique characteristics and medical history, ultimately increasing the chances of a positive health outcome.”
Conversational interface and handling of complex data
One of DT-GPT’s strengths is its ability to interpret large volumes of complex, unstructured clinical data. The system also includes a conversational interface that functions similarly to a chatbot, enabling clinicians and researchers to query the model directly and explore the reasoning behind specific predictions.
Zero-shot predictions: an advanced capability
Because DT-GPT is based on generative AI, it can also perform zero-shot predictions. These are informed estimates of clinical values that the model has not been explicitly trained to predict.
Associate Professor Menden illustrated this:
“To use an analogy, it’s like asking the model to predict how tall someone will grow without providing the person’s height records and only giving their previous weight and shoe sizes.”
He noted a key finding:
“Our model accurately predicted how lactate dehydrogenase (LDH) levels changed in non-small cell lung cancer patients 13 weeks after they started therapy, despite not training the model for this purpose.
“We compared it to traditional machine learning models, which were specifically trained for 69 clinical variables, including LDH, which we in comparison only educated guessed.
“Very surprisingly, the DT-GPT’s zero-shot predictions, its untrained guesses, were more accurate in 18 percent of cases.”
The study was recently published in NPJ Digital Medicine.
Next steps: expanding to other conditions
The team responsible for developing DT-GPT, in collaboration with the Royal Melbourne Women’s Hospital, have now established the foundation for a new company that will apply digital twin technology to support people living with endometriosis. This work highlights the potential wider applicability of the model across different medical conditions.
Read More
New AI Model Predicts Donor Viability and Could Cut Wasted Organ Transplant Efforts by 60%
Key Takeaways:
- A new machine learning model developed at Stanford University predicts whether a donor is likely to die within the critical timeframe needed for safe organ recovery.
- The system reduced futile liver procurement attempts by 60% and outperformed senior transplant surgeons.
- The tool could improve efficiency, reduce resource waste and expand access for people waiting for a donor organ.
A data-driven approach to a long-standing challenge
Thousands of people worldwide remain on transplant waiting lists, with demand far exceeding the supply of suitable donor organs. For people who require a liver transplant, recent advances have broadened access by enabling the use of donors who die following cardiac arrest. These cases, known as donations after circulatory death (DCD), have significantly increased potential donor numbers.
However, almost half of DCD liver transplant procedures are cancelled. In every case, timing is critical. After life support is withdrawn, the donor must die within 45 minutes to protect liver viability. If death occurs outside this narrow window, surgeons often reject the organ because of the increased risk of complications for the recipient.
This contributes to substantial resource waste, operational strain on transplant centres and missed opportunities for people waiting for life-saving surgery.
A new predictive tool outperforms top surgeons
Researchers, clinicians and scientists at Stanford University have developed a machine learning model designed to improve prediction accuracy around donor viability. The tool estimates whether a donor is likely to die within the period during which their organs remain suitable for transplantation.
The model surpassed the predictions of highly experienced surgeons and reduced the rate of futile procurements by 60%. Futile procurements occur when surgical teams begin preparing for a transplant but cannot proceed because the donor dies too late for the organ to remain viable.
Dr Kazunari Sasaki, clinical professor of abdominal transplantation and senior author of the study, explained the significance of the advance. “By identifying when an organ is likely to be useful before any preparations for surgery have started, this model could make the transplant process more efficient,” he said. “It also has the potential to allow more candidates who need an organ transplant to receive one.”
The findings were published in The Lancet Digital Health.
How the model works
The machine learning tool was trained using data from more than 2,000 donors across multiple US transplant centres. It analyses neurological, respiratory and circulatory indicators to estimate a donor’s progression towards death more accurately than previous tools or clinical judgment alone.
During retrospective and prospective testing, the model maintained strong predictive accuracy even when some donor data were missing. Researchers emphasised that this makes it especially practical for real-world clinical settings, where data completeness can vary.
Addressing resource strain and improving outcomes
Currently, transplant centres primarily rely on surgeons’ judgment to assess whether a donor is likely to die within the necessary timeframe. These predictions can vary considerably and may lead to unnecessary preparation of operating theatres, mobilising teams and allocating resources that ultimately go unused.
A reliable, data-driven tool has the potential to improve decision-making, reduce operational burden and ensure that efforts are more closely aligned with the likelihood of a successful transplant.
As the research team noted, the model demonstrates “the potential for advanced AI techniques to optimise organ utilisation from DCD donors”.
Next steps
The team now plans to adapt and test the model for heart and lung transplantation. If successful, this approach could transform prediction processes across multiple organ types, improving access for people waiting for donor organs and enhancing the efficiency of transplant systems worldwide.
Read More
Digital and AI Strategies Emerge as Central to Expanding Health System Capacity, Survey Finds
Key Takeaways:
- Health system leaders increasingly view AI and digital health as essential to expanding capacity without adding buildings or clinical staff.
- Surveyed executives highlight persistent system pressures, including unaffordable care, limited access to primary care, and insufficient management of people’s health and wellbeing.
- Most leaders believe that fundamental operational change, underpinned by AI and digital tools, will be necessary to create sustainable, proactive models of care.
Introduction
A new report from the healthcare advisory firm Chartis suggests that digital health and artificial intelligence are now central pillars in health system leaders’ strategies to expand capacity, improve access, and operate more sustainably. The findings come from the firm’s fifth annual digital transformation survey, conducted in September 2025, which examined the perspectives of 150 health system executives on their progress and priorities in digital transformation.
Persistent pressures on healthcare delivery
The survey underscores the mounting pressures facing health systems today. Executives identified several entrenched challenges that continue to shape healthcare delivery:
- Unaffordable care was cited by 61 per cent of respondents as a major concern.
- Insufficient management of people’s long-term health and wellness was highlighted by 52 per cent.
- Limited timely access to primary care was reported by 49 per cent of leaders.
More than half of surveyed leaders believe that the sustainability of current care delivery models will decline further over the coming five years.
A shift from reactive to proactive care
In response to these pressures, there is widespread agreement that health systems must undergo fundamental change. According to the survey, nine in ten executives feel that organisations need to move away from reactive care and adopt more proactive, anticipatory models.
AI and digital health solutions are now widely considered critical to achieving this shift. The report notes that 90 per cent of leaders are already prioritising investments in digital and AI capabilities to support operational transformation.
AI and digital tools to expand capacity
Executives emphasised the importance of AI and digital health in increasing capacity while avoiding costly infrastructure or workforce expansion. Over the next five years, leaders expect these capabilities to be essential for serving more people without increasing physical space or clinical headcount.
Key priorities include:
- Freeing clinicians’ time for direct care through the use of AI (reported as very important by 52 per cent).
- Maximising access to clinical expertise using digital tools (51 per cent).
- Developing digitally enabled referral channels (45 per cent).
- Building hospital-at-home models as an alternative to inpatient care (36 per cent).
Expanding reach and access to care
Leaders also highlighted a strong need to extend the reach of healthcare services. More than half (53 per cent) stated that expanding delivery through initiatives such as care-at-home or mobile clinics is very important to improving access.
Several digital approaches were identified as particularly valuable for enhancing timely and convenient access:
- AI coaches to answer people’s questions (44 per cent).
- Connected devices and remote diagnostics to gather real-time health data (43 per cent).
- AI-enabled risk prediction to identify emerging health issues (43 per cent).
Supporting personalised patient journeys
Personalisation is another priority area, with leaders recognising the potential of digital platforms and AI to tailor the patient journey. The survey found:
- 52 per cent view offering multiple digital communication channels as very important for personalising the experience.
- 48 per cent believe that enhanced data collection and AI-supported analytics will be key to developing personalised care plans.
Call to action from Chartis
Tom Kiesau, co-author of the report and chief AI and digital officer at Chartis, emphasised the urgency of acting on these insights. He stated in the press release:
“Organisations need to capitalise on the momentum in this moment – and ensure that they are truly realising the potential presented by AI and digital capabilities to drive needed business transformation at scale.”
Ambient AI Helps 93% of Doctors Provide Patients with Their “Full Attention”, Sutter Health Study Shows
Key Takeaways:
- Ambient augmented intelligence significantly reduced after-hours documentation and cognitive burden among participating clinicians, with 93 percent reporting they could give patients their full attention.
- Burnout indicators improved, with self-reported after-hours note-taking falling sharply and overall stress scores declining following the pilot’s introduction.
- Despite early challenges around EHR integration and note customisation, clinicians expressed strong enthusiasm for continued use and future development of the technology.
Introduction: Tackling documentation burden with ambient AI
For many clinicians, the administrative workload associated with electronic health record (EHR) systems extends well into the evening, contributing to frustration, diminished work satisfaction and widespread burnout. At Sutter Health in California, leaders have undertaken a substantial effort to determine whether ambient augmented intelligence (AI) could help relieve this pressure and restore time and attention to patient care.
A recent pilot study, published in JAMA Network Open, involved physicians and non-physician providers across the organisation. Participants reported spending less time on after-hours notes, feeling more present with patients during consultations and experiencing early signs of reduced stress. Although limitations remain, the findings suggest that carefully implemented AI-supported documentation could contribute meaningfully to clinician well-being.
National data from the American Medical Association (AMA) illustrate the scale of the problem. Burnout rates among physicians peaked at 62.8 percent in 2021, before falling back to near-2011 levels by 2023. Clinicians remain 82 percent more likely to report burnout than workers in other fields, according to research published in Mayo Clinic Proceedings.
The documentation challenge: A core driver of burnout
The EHR has long been identified as a key contributor to rising workload. Prior research shows that clinicians are “spending two hours of desktop medicine documenting for every hour that they’re spending with patients,” noted Veena Jones, MD, a paediatrician and Sutter Health’s Chief Medical Information Officer, speaking at the 2025 American Conference on Physician Health in Boston.
Sutter Health is a member of the AMA Health System Member Program, which supports health systems with enterprise-level tools designed to strengthen leadership and improve the future of clinical care.
Dr Jones highlighted the cumulative impact of documentation on clinician well-being: “Another national survey showed that about 77 percent of physicians reported that these excessive documentation tasks were leading to longer clinic hours or the need to work from home. Those clinicians who indicated that they had a more favourable view and experience and were highly satisfied with the EHR were less likely to be burned out, which can suggest that changes made to the EHR, particularly through documentation, may be able to provide some relief to this.”
Pilot design: Bringing ambient AI to 100 clinicians
The pilot involved 100 clinicians across multiple specialties and eight medical groups in Northern and Central California. Leaders intentionally recruited a diverse cohort, including primary care clinicians, various specialty clinicians and informatics champions who could model the technology for peers.
Survey findings following the pilot demonstrated significant improvements:
- The proportion of clinicians reporting they spent one hour or less each week on after-hours notes rose from 14 percent to 54 percent.
- The percentage who felt able to give patients their full attention increased from 58 percent to 93 percent.
- Burnout scores dropped from 42 percent to 35 percent.
Cheryl Stults, PhD, senior scientist at the Sutter Health Centre for Health Systems Research, described reductions in cognitive burden: “Regarding task load and cognitive burden, all three of the measures – difficulty accomplishing note writing performance, having to complete notes at a hurried and rush pace, and just the overall mental demand from these tasks – decreased statistically significantly from the pre to the post period.”
The AMA continues to lead efforts to reduce administrative strain through targeted support and system reforms to help clinicians rediscover a greater sense of professional fulfilment.
Early limitations: Integration and customisation gaps
Despite promising outcomes, clinicians identified several challenges during the pilot. These included limited EHR integration, reduced freedom to customise note formats and gaps in specialty-specific templates for physical examinations.
Stults noted: “Despite all of the benefits, there were also some challenges and limitations that they noted from their experience with AI. When our pilot was launched back in April 2024, at the time it was not fully integrated into the EHR. Physicians either had to copy and paste into the EHR or do an additional step to incorporate it into that.”
Since the pilot, full EHR integration has been implemented, resolving one of the most significant issues.
Clinicians also wanted greater flexibility in document structure. As Stults explained: “Additionally, physicians were unhappy that they were unable to customise or format the progress note for future ones, so if they like their note formatted a certain way, they would have to do it every single time – they wanted a way for the AI to remember or to have a level of permanent customisation.” The inclusion of clinicians from a wide range of specialties was intentional, helping ensure templates could be refined more effectively over time.
Participants also sought further functionalities, such as greater accuracy in direct dictation and more precise word-for-word transcription.
Despite these limitations, enthusiasm remained high. As one clinician commented, “I’m very committed to making this work and I really believe that AI will be the way we chart in the future.”
The AMA’s broader work in digital health includes the recent launch of the AMA Centre for Digital Health and AI, designed to ensure clinicians have a strong voice in shaping the use of AI technologies in patient care.
Scaling responsibly: Support over mandates
Following full integration into the EHR, Sutter Health transitioned from the pilot phase to systemwide expansion. Clinicians opted in using a simple self-service form, and most were able to implement the technology after completing two short e-learning modules.
Dr Jones explained: “Part of the uncertainty of knowing how this would go drove us towards a staged monthly implementation where we had our physicians indicate interest with subsequent onboarding. Once we had full EHR integration, we began a self-enrolment process, which was a really simple form. If anyone wants it, they go to our site, they sign up and within a month they will be provisioned.”
Training was streamlined as well. Early analysis suggested that more than two-thirds of clinicians felt confident going live without intensive support. As a result, Sutter Health created a self-guided e-learning module consisting of two seven-minute videos.
Clinical champions remained available to provide at-the-elbow guidance, while a digital academy support team carried out follow-up and troubleshooting.
The AMA’s STEPS Forward webinar, “AI Tools for Documentation: The Newest Member of the Care Team,” provides further insight into how ambient AI can support clinicians and improve care delivery.
Monitoring use and supporting adoption
Sutter Health monitors engagement through monthly utilisation reports. Dr Jones described the organisation’s proactive outreach strategy: “We run monthly reports looking at utilisation and have the team do targeted outreach to those who are not using it to say: Hey, can we help you? And if not, we actually go through a licence repurposing programme.”
This targeted support has helped increase adoption considerably. In March, Sutter Health also became the first organisation to launch a fully integrated inpatient workflow with its ambient AI vendor. This decision came only after the integrated tools demonstrated sufficient maturity to support hospital-based documentation.
As of September, the organisation has been extending the self-service enrolment model across hospitals and emergency departments (EDs).
The shift in clinician demand has been striking. As Dr Jones observed, the usual dynamic of “pushing” new technology has shifted towards clinicians actively requesting access: “The pull versus push has been incredible. In my career, this is one of the most exciting things to be a part of because physicians are pulling for it, and they want it. We have over 1.2 million notes written and that’s increasing at 50,000 a week.”
Read More
AI-Supported Telehealth Enhances Hip Surgery Recovery in Regional Australia
Key Takeaways:
- A co-designed, digitally supported recovery pathway is helping people in regional Australia access surgeon-approved post-operative hip care without the need for long-distance travel.
- The Panacea Pathway integrates predictive analytics and AI-generated insights to monitor progress, identify risks early, and support safer and more consistent recovery at home.
- More than 3,000 at-home clinical appointments have been delivered, with patients reporting greater confidence, improved continuity of care, and fewer missed appointments.
Addressing gaps in regional post-operative care
Hip replacement surgery is among Australia’s most frequently performed orthopaedic operations, and the demand for this intervention continues to grow as the population becomes older. However, people living in regional areas remain disproportionately affected by barriers to appropriate post-operative follow-up. Many must travel long distances to attend surgeon or specialist reviews, face reduced access to multidisciplinary care, and often lack the reassurance that accompanies regular in-person monitoring.
Recognising these persistent challenges, the Fortius Institute for Musculoskeletal Research (FIMR), working in partnership with the Sunshine Coast Orthopaedic Group, identified an opportunity to reshape the recovery experience. Together, they developed the Panacea Pathway: a digitally supported, surgeon-approved rapid recovery pathway delivered directly into people’s homes by nurse practitioners through a Nurse Concierge model.
Co-designing a digital recovery service
To turn this concept into a structured clinical pathway, FIMR partnered with the University of the Sunshine Coast to design the Nurse Concierge service specifically for people recovering from hip arthroplasty. This collaboration was supported by the Queensland Government’s Regional University Industry Collaboration (RUIC) programme, delivered by CSIRO, which connects regional universities with small and medium-sized enterprises to facilitate research partnerships across Queensland.
For the Sunshine Coast Orthopaedic Group, the RUIC partnership offered access to advanced research expertise and data capabilities that would not have been available independently. With direct support from the University of the Sunshine Coast, the team was able to gather a broader and more detailed dataset, providing a stronger foundation for training AI tools using real-world clinical information.
This work resulted in a clinical care pathway combining surgeon-approved best practice with at-home delivery by nurse practitioners. The approach integrates predictive analytics and AI-driven insights to remotely monitor each person’s progress, detect early signs of risk, and support timely intervention. In doing so, it reduces the physical and practical burden on patients while promoting safer and more consistent recovery outcomes.
“Seeing our research directly improve patients’ lives has been incredibly rewarding, and this project is demonstrating our approach is leading to safer, better and faster recovery for patients undergoing major orthopaedic surgery,” said Professor Nick Ralph from the University of Sunshine Coast.
He added: “Working alongside clinicians through the RUIC partnership meant we could refine our data collection methods in real-time, building the robust dataset needed to develop an evidence-based care pathway.”
Impact and future direction
Early feedback on the at-home Nurse Concierge service has been highly positive. More than 3,000 at-home clinical appointments have already been completed, substantially reducing travel time for regional participants and resulting in fewer missed follow-up appointments. Many patients reported feeling more confident in their recovery journey, emphasising the value of personalised monitoring and consistent contact with the same nurse practitioner.
“This project has demonstrated how remote care and digital health tools can reimagine the patient journey,” said Dr Stephanie Chaousis, Head of Digital Innovation at FIMR.
“By combining clinical expertise with data-driven insights, we’re not just improving recovery outcomes – we’re establishing a new standard for musculoskeletal care.”
The extensive dataset collected through the programme is now informing further enhancements to the pathway for joint replacement patients. Building on the success of the hip surgery pilot, the Sunshine Coast Orthopaedic Group intends to expand the Panacea Pathway to include knee replacement procedures.
With its strong foundation in real-world data, interdisciplinary collaboration, and AI-enabled monitoring, the Panacea Pathway offers a scalable model that could be adopted across hospital networks. Its principles have the potential to inform future clinical guidelines and broaden access to safer, more equitable recovery pathways for people throughout Australia.
Read More
American Medical Association Establishes Centre for Digital Health and AI to Place Physicians at the Forefront of Technological Innovation
Key Takeaways:
- The American Medical Association (AMA) has launched the Centre for Digital Health and AI to ensure physicians play a central role in shaping and integrating emerging technologies in medicine.
- The Centre will focus on policy leadership, clinical workflow integration, education, and collaboration to guide the responsible use of digital and AI tools in healthcare.
- The initiative aims to bridge enthusiasm for AI among physicians with practical strategies that safeguard data privacy, reliability, and patient-centred outcomes.
A new centre to shape the future of digital health
The American Medical Association (AMA) has announced the launch of its Centre for Digital Health and AI, an initiative designed to position physicians at the heart of digital transformation in healthcare. The Centre aims to guide the development, implementation, and regulation of technologies such as artificial intelligence (AI), ensuring they serve both clinicians and patients effectively.
While digital health tools and AI systems are progressing at an unprecedented pace, their potential can only be fully realised when developed with clinical insight. Without physician involvement, these technologies risk introducing new administrative burdens and failing to integrate meaningfully into healthcare practice.
By embedding physicians throughout the entire technology lifecycle – from concept to deployment – the AMA seeks to ensure innovations enhance clinical workflows, reduce friction in practice, and ultimately improve patient outcomes.
Physician leadership in the age of AI
“Augmented Intelligence will be a defining force in the future of health care, but right now we are barely scratching the surface of its potential. Digital health tools are everywhere and the technology has limitless opportunity, but if you don’t understand clinical practice or clinical workflow, even the best tools will never be fully implemented,” said John Whyte, MD, MPH, CEO and Executive Vice President of the AMA.
“By launching this Centre, the AMA is leading in this space so physicians have a say in the technology and clinical care of the future. Our goal is to harness innovation responsibly and effectively, so it improves patient care and reduces unnecessary burdens on physicians,” he added.
Dr Whyte’s comments highlight a key challenge within healthcare innovation: ensuring that technological progress aligns with the realities of clinical practice. The AMA’s new Centre seeks to act as both a bridge and a safeguard – connecting the rapid pace of technological development with the values and needs of medical professionals and their patients.
Key areas of focus
The Centre for Digital Health and AI will concentrate on four principal areas:
1. Policy and Regulatory Leadership
The Centre will collaborate with regulators, policymakers, and technology leaders to develop benchmarks and guidance for the safe and effective use of AI and digital health tools. This includes contributing to policy discussions around data protection, algorithmic transparency, and equitable access to digital innovation.
2. Clinical Workflow Integration
Recognising that even the most advanced tools can fail without proper clinical fit, the Centre will create opportunities for doctors to inform how AI and digital tools are designed. The goal is to ensure technologies enhance both clinician and patient experience by supporting efficiency and accuracy in clinical decision-making.
3. Education and Training
The AMA will equip physicians and health systems with the skills and knowledge needed to adopt AI responsibly. Training programmes will help clinicians understand how to interpret AI outputs, evaluate new technologies, and integrate them seamlessly into everyday practice.
4. Collaboration and Partnership
The Centre will foster partnerships across the technology, research, government, and healthcare sectors to encourage innovation that aligns with patient needs and ethical standards. This collaborative approach aims to ensure that AI applications in medicine remain grounded in clinical realities and societal priorities.
Balancing enthusiasm and caution
Recent AMA surveys reveal growing physician enthusiasm for AI’s potential in medicine. Approximately two-thirds of physicians have already incorporated AI-enabled tools into some aspect of their practice, demonstrating the rapid pace of adoption. However, the same surveys show that one in four physicians remains more concerned than excited, citing ongoing issues around data privacy, reliability, and patient safety.
The AMA’s Centre for Digital Health and AI intends to bridge this divide – helping physicians feel confident in leveraging AI while addressing legitimate concerns. By guiding ethical integration and promoting education, the AMA hopes to create a healthcare environment where digital innovation enhances both care quality and professional satisfaction.
A step towards responsible innovation
As digital transformation reshapes the healthcare landscape, the AMA’s initiative underscores the importance of responsible innovation led by clinical expertise. The Centre for Digital Health and AI represents a strategic step toward embedding physician insight into every stage of technological development – ensuring that the promise of AI and digital tools translates into real-world improvements for patients and practitioners alike.
Read More
AI Model Could One Day Help Prevent Childhood Obesity by Counting Bites
Key Takeaways:
- Researchers at Penn State have developed an artificial intelligence (AI) system capable of counting how many bites a child takes during a meal, achieving around 70% accuracy compared to human observers.
- Eating too quickly increases the risk of obesity in children because the body has less time to register fullness, leading to overeating.
- The AI system, named ByteTrack, may in future help parents, clinicians, and researchers monitor and guide children’s eating habits in real-world environments.
AI and eating behaviours: A new frontier in obesity prevention
The faster a child eats, the greater their risk of developing obesity, according to researchers from the Penn State Department of Nutritional Sciences. However, accurately measuring bite rate—the number of bites taken during a meal—has long posed a challenge. Traditionally, this requires a researcher to watch and manually record each bite from hours of video footage, limiting most studies to small, controlled laboratory environments.
In a collaborative effort between Penn State’s Departments of Nutritional Sciences and Human Development and Family Studies, researchers have created an AI model designed to automate this process. Their pilot study, published in Frontiers in Nutrition, shows that the system is currently around 70% as effective as a human observer in counting bites. Although still under development, the researchers believe the technology could eventually help identify when a child needs to slow their eating rate or adjust their eating behaviour.
The link between eating speed and obesity
“When we eat quickly, we do not give our digestive tract time to sense the calories,” explained Professor Kathleen Keller, the Helen A. Guthrie Chair of Nutritional Sciences at Penn State and co-author of the study. “The faster you eat, the faster it goes through your stomach, and the body cannot release hormones in time to let you know you are full. Later, you may feel like you have overeaten, but when this behaviour repeats, faster eaters are at greater risk for developing obesity.”
Keller’s research group has previously demonstrated that a faster bite rate, especially when combined with larger bite size, correlates with a higher likelihood of obesity in children. Other studies have also linked larger bite size to an increased risk of choking.
“Bite rate is often the target behaviour for interventions aimed at slowing eating rate,” noted Dr Alaina Pearce, research data management librarian at Penn State and co-author of the study. “This is because bite rate is a stable characteristic of children’s eating style that can be targeted to reduce their eating rate, intake, and ultimately risk for obesity.”
Manually recording bite rate, however, is both labour-intensive and costly. As Keller pointed out, “Measuring bite rate is tedious, labour-intensive work, meaning it is expensive, which often limits the amount of data considered in bite rate studies.”
Using AI to support healthier habits
To overcome these limitations, Yashaswini Bhat, a doctoral candidate in nutritional sciences and lead author of the study, set out to develop the first AI-powered bite counter designed specifically for studying children’s eating behaviours.
“I have an interest in AI and data science, but I had never developed a system like this one,” Bhat explained.
She partnered with Associate Professor Timothy Brick, from Penn State’s Department of Human Development and Family Studies, to create a system capable of detecting children’s faces within videos and identifying when a child takes a bite.
“An experienced and knowledgeable collaborator like Dr Brick was invaluable to this project,” Bhat added.
The team trained the system using 1,440 minutes of video footage from Keller’s Food and Brain Study, funded by the National Institute of Diabetes and Digestive and Kidney Diseases. The footage featured 94 children aged seven to nine, each consuming four meals with identical foods on different occasions.
Researchers manually identified bites in 242 videos to train the AI. Once the system had been trained to recognise what a bite looks like, it was tested on an additional 51 videos. The AI’s results were then compared to those of human researchers.
Promising early results
“The system we developed was very successful at identifying the children’s faces,” Bhat said. “It also did an excellent job identifying bites when it had a clear, unobstructed view of a child’s face.”
While the AI was 97% as effective as a human observer at recognising faces, it achieved about 70% accuracy in counting bites. Bhat noted that challenges arose when children were partially obscured, turned away from the camera, or engaged in behaviours such as chewing on their spoons or playing with their food—actions common among younger participants.
“The system was less accurate when a child’s face was not in full view of the camera or when a child chewed on their spoon or played with their food, as often happens toward the end of a meal,” Bhat said. “Chewing on a utensil sometimes appeared to be a bite, and this complicated the task for the AI model.”
Next steps for the ByteTrack system
Although still in its early stages, the researchers view the pilot as an important step toward automating bite rate analysis. The system, called ByteTrack, will continue to be refined so it can distinguish between bites and similar movements such as sipping a drink.
“The eventual goal is to develop a robust system that can function in the real world,” Bhat said. “One day, we might be able to offer a smartphone app that warns children when they need to slow their eating so they can develop healthy habits that last a lifetime.”
The research was supported by the National Institute of Diabetes and Digestive and Kidney Diseases, the National Institute of General Medical Sciences, the Penn State Institute for Computational and Data Sciences, and the Penn State Clinical and Translational Science Institute.
Read More
Implementing AI in the NHS Proves More Complex than Anticipated, Study Finds
Key Takeaways:
- A UCL-led study revealed that introducing AI diagnostic tools across NHS hospitals faced major challenges with governance, contracts, IT integration and staff training.
- By June 2025, 18 months after contracting was meant to be completed, over one-third of trusts (23 out of 66) had not yet implemented the AI systems in clinical practice.
- Researchers recommend stronger project management, more staff education on AI, and realistic timelines to ensure successful integration.
Background to the study
A major study led by researchers at University College London (UCL) has found that implementing artificial intelligence (AI) in NHS hospitals is considerably more difficult than policymakers and healthcare leaders initially expected. The study, published in The Lancet eClinicalMedicine on 10 September 2025, examined a £21 million NHS England programme launched in 2023. The programme aimed to introduce AI technology for diagnosing chest conditions, including lung cancer, across 66 NHS hospital trusts.
The research team conducted in-depth interviews with hospital staff and AI suppliers to understand how the tools were procured, set up, and used, while also identifying both the challenges encountered and the strategies that proved helpful in supporting implementation.
Delays and barriers to implementation
The study revealed that contracting and procurement processes took between four and ten months longer than expected. By June 2025, 18 months after contracting had been scheduled for completion, one-third of the hospital trusts (23 out of 66) were still not using the AI diagnostic systems in clinical practice.
Dr Angus Ramsey, principal research fellow at the UCL Department of Behavioural Sciences and Health and first author of the study, explained:
“Our study provides important lessons that should help strengthen future approaches to implementing AI in the NHS.
We found it took longer to introduce the new AI tools in this programme than those leading the programme had expected.
A key problem was that clinical staff were already very busy – finding time to go through the selection process was a challenge, as was supporting integration of AI with local IT systems and obtaining local governance approvals.
Services that used dedicated project managers found their support very helpful in implementing changes, but only some services were able to do this.
Also, a common issue was the novelty of AI, suggesting a need for more guidance and education on AI and its implementation.”
Key challenges identified
Researchers highlighted a range of challenges that slowed or complicated implementation, including:
- Staff workload pressures – Clinicians were already under heavy demand, making engagement with selection and integration processes difficult.
- Technological integration – Many NHS hospitals operate on ageing or varied IT systems, which created barriers for embedding the new AI tools.
- Governance processes – Local approvals and oversight requirements delayed progress.
- Lack of understanding and scepticism – Many staff expressed uncertainty or caution about the reliability and usefulness of AI in clinical care.
The study found that trusts that employed dedicated project managers were more successful at managing implementation, underscoring the importance of structured leadership in rolling out new technology.
Lessons for the future
The authors of the study cautioned that although AI tools hold promise for enhancing diagnostic services, they may not resolve workforce and system pressures as easily or quickly as policymakers might hope. As they wrote:
“AI tools may offer valuable support for diagnostic services, they may not address current healthcare service pressures as straightforwardly as policymakers may hope.”
The researchers recommended that:
- NHS staff should receive training on how AI can be used safely and effectively.
- Dedicated project management should be built into large-scale AI implementation programmes.
- Timelines for introducing AI should realistically reflect the complexity of NHS structures and systems.
Professor Naomi Fulop, senior author and professor of health care organisation and management at UCL, emphasised the complexity of the task:
“The NHS is made up of hundreds of organisations with different clinical requirements and different IT systems and introducing any diagnostic tools that suit multiple hospitals is highly complex.”
Funding and next steps
The research was funded by the National Institute for Health and Care Research and conducted collaboratively by teams from UCL, the Nuffield Trust and the University of Cambridge. The group is now conducting further studies on how AI tools perform once they are more firmly embedded in NHS practice.The findings are expected to offer valuable insights for the government’s 10-year health plan, published on 3 July 2025, which identified AI as a central element in modernising and improving NHS services.
Read More
Mayo Clinic Launches AI-Powered Nurse Virtual Assistant to Support Frontline Care
Key Takeaways:
- Mayo Clinic nurses have led the design and development of an in-house, AI-powered Nurse Virtual Assistant to streamline access to clinical information.
- The tool consolidates patient summaries, evidence-based guidelines, and clinical policies into one tab within the electronic health record, reducing administrative burden.
- More than 9,600 nurses across Mayo Clinic’s inpatient and emergency departments are now using the system, with ongoing feedback ensuring it continues to evolve with nursing practice.
Streamlining access to critical information
High-quality care depends on timely access to electronic health records, clinical policies, and evidence-based practice guidelines. However, navigating multiple systems to retrieve this information can be time-consuming for nurses, detracting from direct patient care.
To solve this challenge, Mayo Clinic’s Department of Nursing led a multidisciplinary initiative to create Nurse Virtual Assistant – a generative artificial intelligence (AI) tool developed entirely in-house by nurses for nurses. Integrated into Mayo Clinic’s electronic health record (EHR) system, the tool presents essential information within a single tab, making it easier to retrieve and act upon.
Nurses can view a curated, nurse-specific patient summary and access direct links to key evidence-based resources, including Lippincott procedures, IV administration guidelines, and Mayo Clinic’s clinical policy library – all in one place.
This streamlined interface allows nurses to spend less time searching and more time focusing on what matters most: the person receiving care.
Augmenting – not replacing – human connection
Mayo Clinic emphasises that Nurse Virtual Assistant is designed to support, rather than replace, the expertise and human presence that nurses bring to clinical practice.
“It is an amazing tool,” says Nick Flynn, a registered nurse in the Emergency Department at Mayo Clinic Hospital in Arizona. Flynn highlights the value of consolidated patient data from inpatient stays, outpatient visits, and phone calls:
“You have easy access to a history of their illness, and that is available just moments after they arrive.”
Nurse-driven innovation from concept to rollout
The project began in 2024 as part of Mayo Clinic’s strategy to ease administrative pressures in a rapidly digitising healthcare environment. Crucially, nurses were involved at every stage – from conceptualisation to design and testing – ensuring the tool meets real-world clinical needs.
Early-access users played an active role in shaping the system’s features, providing feedback that directly informed improvements.
Brendon Bloomfield, a registered nurse in Psychiatric Acute Care at Mayo Clinic Hospital – Rochester, explains:
“To see a concept I was passionate about, AI-enhanced communication, actually get built – and to be invited to help shape it – reinforces that frontline nurses’ voices matter and that we have the power to influence the future of care.”
The solution underwent a research study approved by an Institutional Review Board before scaling to more than 9,600 nurses across inpatient and emergency department units.
Evolving with nursing practice
Nurse Virtual Assistant has been released as a Minimum Lovable Product – a version that not only solves an immediate problem but is designed to be engaging and impactful for end users. Nurses can submit feedback directly through the tool, allowing the solution to continuously evolve with frontline input.
Enhancements already implemented include improved search result accuracy, refined content layouts, and new functionality based on user suggestions.
Privacy, security, and compliance at the core
Built to the highest standards of data privacy, the Nurse Virtual Assistant is a patent-pending solution developed in full compliance with HIPAA regulations and other applicable requirements. This ensures that patient information remains secure while enabling timely and efficient access for clinical teams.
Shaping the future of nursing care
Mayo Clinic’s Chief Nursing Officer, Ryannon Frederick, sees the innovation as a milestone in supporting nursing practice:
“Nurse Virtual Assistant is an example of how Mayo Clinic nurses are driving innovation and shaping the future of care. By reducing administrative burden, we allow nurses to focus on the most important part of their work: caring for patients with skill, compassion and presence.”
Read More
Vanderbilt Researchers Use AI to Address Gaps in Long-Term Obesity Care
Key Takeaways:
- A $1 million Eli Lilly grant will fund a two-year Vanderbilt University Medical Center (VUMC) project using artificial intelligence (AI) to address gaps in obesity care.
- The initiative will analyse electronic health records (EHRs), survey patients and clinicians, and build a multi-agent AI system to develop evidence-based strategies for improving long-term engagement.
- A patient-facing mobile application will be designed and piloted in VUMC obesity clinics to support shared decision-making and sustained weight management.
Major investment in addressing gaps in care
Vanderbilt University Medical Center (VUMC) has secured a $1 million grant from Eli Lilly and Company to fund a two-year research project aimed at improving continuity of care for people living with obesity. The initiative seeks to understand why many individuals discontinue treatment and to create scalable solutions to help them stay engaged in long-term care.
“Obesity is a chronic, relapsing condition that requires ongoing management, yet too often it is treated episodically because of barriers like delayed medication access,” explained You Chen, PhD, Associate Professor of Biomedical Informatics and the project’s Principal Investigator for informatics and technology. “We’re combining data-driven insights, stakeholder input and multi-agent AI to understand where continuity breaks down and to design evidence-based interventions that keep patients engaged.”
Data-driven insights and stakeholder engagement
In its first year, the research team will analyse VUMC’s electronic health records to identify patterns distinguishing people who remain in continuous follow-up from those who disengage. Patient and clinician surveys will be conducted to capture real-world barriers to care, including logistical, financial and psychological challenges.
The findings will be integrated into a multi-agent AI system, featuring simulated physician, nurse and dietitian agents. This system will generate and prioritise strategies for maintaining engagement, which will then be reviewed by panels of clinicians, informaticians and patient representatives.
Patient-facing app to support engagement
The second year of the project will focus on designing and piloting a mobile application to be used in VUMC obesity clinics. This app is intended to help patients view and interpret their own health data, complete pre-visit tasks, and communicate more effectively with their care teams.
“By helping patients view and interpret their own data, complete previsit tasks, and communicate more effectively with care teams, the app will aim to strengthen shared decision-making and sustain engagement over time,” said Chen.
Clinical leadership and broader impact
The project’s clinical lead is Gitanjali Srivastava, MD, Professor of Medicine in the Division of Diabetes, Endocrinology and Metabolism.
“Medicine has evolved, and we need to adapt to new technological advances while catering to patient needs,” Srivastava stated. “It’s about designing practical tools and processes that fit naturally into patients’ lives and clinicians’ workflows, ultimately supporting healthier weight management over time.”
Chen emphasised that the project is intended to be scalable across health systems. The researchers believe that the human–AI collaborative approach developed through this project could serve as a reproducible framework for improving continuity of care for other chronic conditions that require long-term management.
Read More
AI Model Forecasts Risk of More Than 1,000 Diseases Decades in Advance
Key Takeaways:
- Delphi-2M, a generative AI model, can predict susceptibility to over 1,000 diseases using anonymised medical records.
- The system has been tested successfully across large-scale UK and Danish datasets, showing remarkable accuracy and transferability.
- Experts say the model could transform population health forecasting within years and may eventually be adapted for personalised clinical use.
European scientists build AI model to predict long-term disease risk
European researchers have unveiled a powerful new artificial intelligence model that can predict a person’s susceptibility to more than 1,000 diseases decades before symptoms arise.
The system, known as Delphi-2M, was developed by scientists at the European Molecular Biology Laboratory (EMBL) in Cambridge. “Delphi uses a similar architecture to large language models but with key innovations to work with healthcare data,” explained Tom Fitzgerald of EMBL.
Delphi was trained on anonymised health records from 400,000 participants in the UK Biobank, a major long-term biomedical study. The researchers then validated its performance using records from 1.9 million patients in the Danish National Patient Registry.
Matching and exceeding existing prediction tools
The predictions made by Delphi-2M spanned more than 1,000 diseases and were generally comparable in accuracy to existing clinical tools that focus on specific conditions, such as the QRisk score used for cardiovascular disease risk. Results from the study were published in Nature on Wednesday.
“Our model is a proof of concept, showing that it’s possible for AI to learn many of our long-term health patterns and use this information to generate meaningful predictions,” said Ewan Birney, EMBL’s interim executive director. “We were surprised at how well the model transferred from the UK to Denmark though it had never seen a single bit of Danish data.”
Birney emphasised that turning Delphi into a clinically deployable forecasting tool could take five to ten years, but he noted that it could be used much sooner to inform public health strategies.
Population-level insights and healthcare planning
While Delphi generates predictions at the level of individual patients, its most immediate value may be in population health planning. “Although it makes predictions for each individual, it can be very useful at the population level to forecast collective healthcare needs, how many people will suffer from particular diseases such heart attacks, cancers or diabetes and what sort of treatment they need,” said Moritz Gerstung, head of AI at the German Cancer Research Center in Heidelberg and a member of the Delphi team.
The model performed best for diseases with well-understood and consistent progression patterns, such as cardiovascular disease, diabetes and sepsis (blood poisoning). It was less effective for conditions triggered by unpredictable environmental factors or for very rare congenital disorders.
Expanding to genomics and biological data
Researchers are now working to enhance Delphi by incorporating biological information, such as genomic and proteomic data. Despite this, Birney said they were “very pleasantly surprised” at how well the model performed using healthcare records alone, achieving results comparable to or better than some models that rely on genetic and protein-level data.
“I want to stress the power of the straightforward medical record,” Birney added.
The team has patented key aspects of Delphi’s approach to predicting disease risk and timing. “We are exploring whether there are commercialisation possibilities and how to do that with our respective institutions,” Birney confirmed.
Towards ethical and scalable predictive medicine
Independent experts have praised the work as an important step forward for responsible AI in medicine. “This research looks to be a significant step towards scalable, interpretable, and — most importantly — ethically responsible form of predictive modelling in medicine,” said Gustavo Sudre, professor of genomic neuroimaging and AI at King’s College London, who was not involved in the study.
He added that while the current model relies solely on anonymised health records, its architecture has been designed to handle richer data types in the future, including biomarkers, imaging and genomics.
Read More
New AI Tool Pinpoints Genes and Drug Combinations That Restore Health in Diseased Cells
Key Takeaways:
- Harvard researchers have developed PDGrapher, an AI tool that identifies genes and drug combinations most likely to restore diseased cells to a healthy state.
- The model uses graph neural networks to map cellular relationships and predict effective single or combined drug targets, significantly reducing the need for exhaustive drug screening.
- PDGrapher demonstrated high accuracy and speed across multiple cancer datasets, offering promise for personalised medicine and drug discovery in complex diseases such as cancer, Parkinson’s, and Alzheimer’s.
Introduction: A new era in drug discovery
Researchers at Harvard Medical School (HMS) have unveiled a powerful artificial intelligence (AI) model capable of identifying therapies that can reverse disease at the cellular level. This innovation, published in Nature Biomedical Engineering on 9 September, could reshape how new drugs are discovered, designed, and personalised for patients.
Unlike traditional approaches that examine one protein target or drug candidate at a time, this new model — named PDGrapher and freely available to researchers — analyses multiple cellular drivers of disease. It identifies the genes most likely to return diseased cells to normal function and pinpoints the most promising single or combined drug targets to correct the underlying cellular dysfunction.
“Traditional drug discovery resembles tasting hundreds of prepared dishes to find one that happens to taste perfect,” explained senior study author Marinka Zitnik, Associate Professor of Biomedical Informatics at HMS’s Blavatnik Institute. “PDGrapher works like a master chef who understands what they want the dish to be and exactly how to combine ingredients to achieve the desired flavour.”
Limitations of traditional drug discovery
Historically, drug discovery has focused on activating or inhibiting a single protein target. This approach has produced successful therapies such as kinase inhibitors, which block proteins that drive cancer cell growth. However, Zitnik emphasised that such strategies often fall short for diseases driven by multiple interacting pathways and genes.
She noted that many recent therapeutic breakthroughs — including immune checkpoint inhibitors and CAR T-cell therapies — work by targeting broader disease processes rather than single molecules. PDGrapher aims to expand this concept by identifying drug targets that can reverse signs of disease, even when the precise molecular mechanisms are not yet fully understood.
How PDGrapher works: Mapping complex cellular networks
PDGrapher is based on a graph neural network — a form of AI that analyses not only individual data points but also the relationships and interactions between them. In biological research, this means mapping how genes, proteins, and signalling pathways influence one another inside a cell.
Instead of screening thousands of compounds blindly, PDGrapher simulates what would happen if certain genes or pathways were switched off, dialled down, or targeted with a drug. It then predicts whether these interventions would shift a diseased cell towards a healthier state.
“Instead of testing every possible recipe, PDGrapher asks: ‘Which mix of ingredients will turn this bland or overly salty dish into a perfectly balanced meal?’” said Zitnik.
Testing and validation: Proving its predictive power
To train the model, researchers fed PDGrapher a dataset of diseased cells both before and after treatment, allowing it to learn which gene changes led to recovery.
They then evaluated the tool using 19 independent datasets across 11 cancer types, combining both genetic and drug-based experiments. PDGrapher was asked to propose treatment options for samples and cancer types it had never seen before.
The model accurately predicted known drug targets that had been deliberately excluded during training and identified new candidates supported by emerging evidence. Notably, it highlighted KDR (VEGFR2) as a target for non-small cell lung cancer, consistent with clinical findings, and identified TOP2A, an enzyme already targeted by chemotherapy, as a promising target for preventing metastasis in certain tumours.
PDGrapher consistently outperformed comparable AI models — ranking correct therapeutic targets up to 35 percent higher and producing results up to 25 times faster.
Implications for future drug discovery
By focusing on targets that directly reverse disease traits, PDGrapher streamlines the drug discovery process. This allows researchers to prioritise fewer, more promising interventions and to design experiments that are faster and more cost-effective.
This capability is particularly valuable for complex diseases such as cancer, where tumours often evade therapies that strike only one target. Because PDGrapher identifies multiple disease drivers, it offers a way to design combination treatments that could prevent drug resistance.
In the future, with further validation, PDGrapher could be applied to individual patients’ cellular profiles to create personalised treatment strategies.
Broader applications and ongoing research
Beyond cancer, the research team is using PDGrapher to investigate neurological conditions such as Parkinson’s disease and Alzheimer’s disease, aiming to identify genetic drivers that could restore neuronal health.
They are also collaborating with Massachusetts General Hospital’s Center for X-linked Dystonia-Parkinsonism (XDP) to map potential drug targets for this rare, inherited neurodegenerative disorder.
“Our ultimate goal is to create a clear road map of possible ways to reverse disease at the cellular level,” Zitnik stated.
Read More