Turning Records into Foresight: Machine Learning to Anticipate Need in Cancer Survivorship Care
Key Takeaways:
- Sylvester researchers used machine learning on records and patient-reported data from over 25,000 people who have survived cancer to predict who is most at risk.
- Adding patients’ own reports nearly doubled the models’ accuracy, with the top 10 per cent of risk capturing about half of later events.
- The work signals a shift towards proactive, personalised survivorship care, though it is not yet meant to change practice.
A new phase of care
For a growing number of people who have survived cancer, ringing the bell at the end of primary treatment marks the start of a complex new phase of care – one that is often less structured and far harder to predict. Even once therapy has concluded, people may continue to experience lingering physical symptoms, emotional distress or other unexpected medical needs. These can lead to visits to the emergency department or urgent care, to hospital admissions, and to a worsening burden of symptoms over time.
A new study from Sylvester Comprehensive Cancer Center, part of the University of Miami Miller School of Medicine, suggests that the key to anticipating these outcomes may lie in examining electronic health records and patient-reported data systematically, using novel artificial intelligence (AI) technologies.
Published in JCO – Clinical Cancer Informatics, the study demonstrates how machine learning models, when applied to clinical data and patient-reported outcomes (PROs), can help identify survivors at increased risk of unplanned healthcare use and of an elevated symptom burden during survivorship. By transforming medical records and patient-reported data into predictive signals, the research offers a potential route towards more proactive, personalised survivorship care.
Cancer survivorship care is a dynamic, ongoing process rather than a single phase of care, explained Frank J. Penedo, Ph.D., Sylvester associate director for population sciences, director of Sylvester’s Survivorship and Supportive Care Institute and the study’s senior author.
“For many patients, new or evolving challenges arise after treatment ends, just as routine clinical contact often tapers off, raising a critical question. How can we identify those at higher risk earlier, before these concerns intensify and become harder to address?” Dr Penedo said.
Listening to people’s own experiences
Patient-reported outcomes capture experiences that traditional clinical data often miss or assess only infrequently. These include emotional well-being, fatigue, functional limitations and other practical needs that may interfere with adequate survivorship care. Over the past decade, PROs have become an increasingly important component of cancer care. Yet translating large volumes of patient-reported data, and integrating them with vast amounts of medical record data to produce actionable insights – particularly across whole populations of survivors – has remained a persistent challenge.
Led by Akina Natori, M.D., M.S.P.H., a Sylvester oncologist and assistant professor in the Division of Medical Oncology at the Miller School, the study reframed PROs. Rather than treating them as retrospective descriptions of what a person has already experienced, the team used them as prospective indicators of future need.
“PROs tell us how patients are actually feeling and functioning,” said Dr Natori, first author of the study. “We wanted to know whether those self-reported experiences, in combination with clinical data such as cancer and treatment type, could help us identify which survivors might be at higher risk for significant symptom burden or unplanned health care use down the line.”
Unplanned healthcare use can include emergency department visits or hospital admissions that arise outside scheduled follow-up. Such events often signal unmet needs or gaps in survivorship and supportive care. Being able to forecast that risk could allow care teams to step in earlier, with targeted symptom management, psychosocial support or closer monitoring.
Applying machine learning to survivorship data
To explore that possibility, the research team analysed data from more than 25,000 people who have survived cancer, followed over three years, using machine learning to detect patterns that traditional statistical methods can miss. The advantage of these approaches is their ability to weigh many factors at once – clinical history, treatments, symptoms, emotional well-being and patterns of healthcare use – and to find the subtle interactions that signal which people are heading towards trouble.
The answers turned out to depend on what was being predicted. For acute events such as emergency room visits and hospital admissions, recent clinical activity was the strongest signal: what was happening with a person over the last few months mattered more than where they had started. For symptom burden, longer-term trends told a clearer story. Crucially, adding patient-reported outcomes nearly doubled how well the models performed compared with clinical data alone. When the researchers flagged the highest-risk 10 per cent of people, that group accounted for roughly half of all subsequent healthcare events and elevated symptom episodes.
Building models that clinicians can trust
“This type of risk stratification problem is well-suited for machine learning,” said Jerry R. Bonnell, Ph.D., a postdoctoral associate at the University of Miami’s Frost Institute for Data Science and Computing. “The challenge is developing models that are not only accurate, but also interpretable and meaningful for clinicians making real-world decisions.”
That emphasis on interpretability shaped the study’s design. Rather than treating the models as opaque, “black box” systems, the team built them to show their reasoning. This surfaced which factors were driving a given person’s risk score, and how those factors shifted over time. The goal is a tool that gives clinicians not just a number, but a starting point for conversation: about who needs closer follow-up, what they may need, and when to step in before a problem escalates.
An interdisciplinary approach
The project drew together expertise from clinical oncology, psychosocial oncology, population sciences and data science, reflecting the multifaceted nature of survivorship care. Contributors included Vasileios Stathias, Ph.D., assistant director for data science at Sylvester, alongside collaborators across the University of Miami.
“Survivorship sits at the intersection of biology, behavior and health systems,” Dr Stathias said. “By combining patient-reported and clinical data with advanced analytics, we can begin to see patterns that might otherwise remain invisible and that can inform more proactive care strategies.”
Additional authors included:
- Sara Fleszar Pavlovic, Ph.D., a Miller School research assistant professor of medical oncology
- Mitsunori Ogihara, Ph.D., programme director of UM’s Big Data Analytics and Data Mining program
- Andrew Wang, A.B.
- Ravi Vadapalli, Ph.D., director of advanced computing for the Frost Institute for Data Science and Computing
- Blanca Silvia Noriega Esquives, M.D., Ph.D., a Sylvester postdoctoral associate
- Tracy Crane, Ph.D., RDN, co-leader of the Cancer Control Program and director of lifestyle medicine, prevention and digital health at Sylvester
Implications for cancer survivorship care
While the authors emphasised that the findings are not intended to change clinical practice immediately, they highlighted the broader implications of the work. As populations of people living beyond cancer continue to grow, health systems face mounting pressure to deliver long-term care that is precise, proactive and sustainable.
“This is about shifting from reactive to proactive survivorship care,” Dr Penedo said. “If we can identify patients who are more likely to struggle, we can begin to align supportive resources earlier and more effectively.”
The team also noted the potential impact of predictive models that combine clinical and PRO-based data on healthcare access. Because PROs reflect patient voices directly, they may help surface unmet needs that are less likely to be captured through routine clinical encounters alone.
Looking ahead
Future research will focus on continuing to refine and validate these models across broader populations of survivors, and on exploring how risk stratification driven by electronic health record and PRO data could be integrated into survivorship standards of care.
“The expertise of our multidisciplinary team provides a unique opportunity to create a data ecosystem that facilitates the implementation of AI-powered analytics to guide proactive and precision care to reduce the burden of cancer on patients and health systems. This study is among several initiatives that are working towards this goal,” said Dr Penedo.
“Our long-term goal is to ensure that survivorship care keeps pace with advances in treatment,” said Dr Natori. “That means using data not only to describe outcomes, but to anticipate them, so we can more proactively support patients in the years after cancer.”
Source: University of Miami Miller School of Medicine
Read More
Obesity Identified as Key Driver of Rising Cancer Rates in Younger Adults
Key Takeaways:
- A major new study has found that overweight and obesity are likely to be significant contributors to rising cancer rates among younger adults in England.
- Researchers found that many traditional behavioural cancer risk factors – including smoking, alcohol consumption and physical inactivity – have remained stable or improved over the past two decades, making them unlikely to fully explain the increase in early-onset cancers.
- Although excess weight appears to play an important role, researchers say it cannot entirely account for the rise in cancers such as bowel cancer, suggesting that additional biological, environmental and early-life factors may also be involved.
Study highlights growing concern over early-onset cancer
Being overweight or living with obesity may be a key driver behind rising cancer rates in younger adults in England, according to a major new study led by researchers at The Institute of Cancer Research, London, and Imperial College London.
The analysis, published in BMJ Oncology, examined trends in cancer incidence alongside changes in known behavioural cancer risk factors over nearly two decades. Researchers found that while rates of several cancers among younger adults have continued to increase, many established lifestyle-related risk factors have either improved or remained stable during the same period.
These findings led researchers to conclude that obesity is likely to be one of the most important contributors to the increase in cancer incidence among younger generations in England.
At the same time, the researchers stressed that rising body mass index (BMI) alone does not fully explain the growing number of cancer cases, indicating that additional factors may also be contributing to the trend.
Researchers analysed cancer trends across England
The research team used national cancer registry data from England covering the years 2001 to 2019. The study was conducted by scientists from the Cancer Epidemiology and Prevention Research Unit (CEPRU) at both The Institute of Cancer Research (ICR) and Imperial College London.
Researchers examined incidence trends across:
- 22 cancer types in women
- 21 cancer types in men
From this analysis, they identified 11 cancers that are increasing among adults aged between 20 and 49 years and are associated with known behavioural risk factors.
All of the cancers identified – except oral cancer – are recognised as being linked to excess weight.
For most cancer types, increases seen in younger adults mirrored trends observed in adults aged over 50, where the overall disease burden remains considerably higher. However, bowel cancer and ovarian cancer stood out as notable exceptions because rates were increasing only among younger age groups.
Most traditional risk factors have improved
The study examined trends in several well-established behavioural cancer risk factors, including:
- Smoking
- Alcohol use
- Overweight and obesity
- Physical inactivity
- Red and processed meat consumption
- Low fibre intake
Together, these risk factors accounted for an estimated 40–50 per cent of bowel, endometrial, oral and liver cancer cases in 2019.
However, researchers found that trends for most of these risk factors have either remained stable or improved over time, making them unlikely to substantially explain the recent rise in cancer incidence among younger adults.
According to the analysis:
- Smoking among younger adults has fallen by approximately two per cent annually over the past two decades.
- Alcohol consumption has largely stabilised or declined.
- Physical inactivity has decreased.
- Consumption of red and processed meat has reduced.
- Fibre intake, while still below recommended levels, has gradually improved.
In contrast, rates of overweight and obesity have steadily increased since 1995.
The largest increases in obesity were observed among younger women, where obesity prevalence rose by approximately 2.6 per cent relative increase per year.
Obesity linked to rising bowel cancer rates
The researchers found evidence linking rising BMI to increasing bowel cancer rates among younger adults.
Among younger women, bowel cancer rates associated with BMI rose from 0.9 to 1.6 cases per 100,000 people. In comparison, bowel cancer rates not attributable to BMI increased from 6.4 to 9.6 cases per 100,000 people.
Similar patterns were also observed in men.
However, the authors emphasised that the total number of BMI-linked bowel cancer cases remained lower than the number of cases not linked to BMI. This suggests that although obesity is an important contributor, it cannot fully explain the scale of the increase in bowel cancer among younger adults.
Additional causes may be contributing
The study points to the likelihood that multiple interacting factors are contributing to rising cancer rates in younger generations.
Several suspected contributors have previously been proposed, including:
- Ultra-processed foods
- Antibiotic use
- Air pollution
However, researchers noted that many of these exposures have also shown relatively stable or declining trends in the UK, complicating efforts to identify the main drivers of early-onset cancers.
The authors also highlighted emerging evidence suggesting that obesity-related mechanisms not fully captured by BMI may influence cancer risk. These include:
- Metabolic dysfunction
- Chronic inflammation
- Alterations in the gut microbiome
Further research is needed to determine whether these mechanisms directly contribute to the development of bowel cancer and other cancers in younger adults.
Experts say more research is urgently needed
The researchers called for large-scale, long-term studies capable of tracking exposures across the entire life course in order to better understand what is driving rising rates of early-onset cancers.
Professor Marc Gunter, Co-Director of the Cancer Epidemiology and Prevention Research Unit at Imperial College London, said:
“The changes we’re seeing in cancer incidence, particularly the rates of some cancers in younger adults, don’t have a single cause or a simple answer. They reflect a complex mix of generational effects, gaps in long-term exposure data, and shifts in diagnosis and detection, and show how much more scientists still need to understand about when and how cancer develops across the life course. While rising rates in younger adults are concerning, it remains crucial not to lose sight of cancer trends in older adults, where the absolute burden of disease is still far greater.”
Professor Montserrat García-Closas, Co-Director of the Cancer Epidemiology and Prevention Research Unit and Group Leader in Integrative Cancer Epidemiology at The Institute of Cancer Research, London, said the findings indicate that behavioural changes alone cannot explain current trends.
She said:
“Our findings show that while cancer rates are rising in younger adults, the trends are unlikely to be explained by changes in most known behavioural risk factors. Smoking, alcohol and other behaviours have been stable or improving for two decades, yet early-onset cancers continue to increase – particularly bowel cancer.
“Excess weight is an important contributor, although it cannot fully account for the scale of the rise in bowel and other cancers. This tells us that multiple factors – including early-life exposures – may be acting together. Understanding these patterns is essential for identifying what is truly driving cancer risk in today’s generations. We now need deeper research, better measurement and continued surveillance to uncover the causes behind these worrying trends.
“However, we cannot wait to act. Tackling obesity across all ages, particularly in children and young people, through stronger public health policies and wider access to effective interventions, could slow the rise in cancer and prevent many cancers – and must become a national priority.”
Calls for stronger prevention and public health action
The findings have prompted renewed calls for stronger public health measures aimed at preventing obesity and improving cancer prevention strategies across all age groups.
Professor Kristian Helin, CEO of The Institute of Cancer Research, London, said the study highlights an urgent public health challenge requiring coordinated action across research, prevention and policy.
He said:
“This work highlights a growing public health challenge and the need for urgent action across research, prevention and policy. Although rising cancer rates in younger adults are concerning, the burden remains overwhelmingly higher in older people, which means prevention efforts must span all ages.
“This study makes clear that traditional lifestyle risks alone cannot explain current trends – pointing to the importance of investigating other exposures such as the potential role of the microbiome, while strengthening strategies to address obesity and other established risks. To protect future generations, we must invest in understanding the causes of cancer at all ages and ensure that early diagnosis, screening and prevention strategies keep pace with a changing population.”
CCH insights:
The outcomes of this study are concerning but not entirely surprising, given that obesity rates in children and young people are still rising and obesity is a significant risk factor for many cancers. It adds further support for the call to treat obesity at the earliest opportunity, regardless of the age of the individual. The longer obesity goes untreated the greater the risk of individuals developing serious chronic diseases such as cancer, type 2 diabetes and heart disease.
Automated Weight Loss Programme Shows Promise for People Living with Cancer in Landmark Trial
Key Takeaways:
- A fully automated, web-based programme delivered clinically meaningful weight loss in people living with and beyond cancer, without any in-person support
- More than 43 percent of participants achieved at least 3 percent weight loss, with nearly one in three reaching 5 percent or more
- The intervention also improved a range of health outcomes, including diet quality, physical functioning, and cardiometabolic markers
A new model for post-cancer care
A large national randomised clinical trial has demonstrated that a fully automated, web-based weight loss intervention can deliver substantial health benefits for people living with and beyond cancer. The programme, developed by researchers at the University of Alabama at Birmingham, represents a significant shift in how post-cancer care may be delivered in the future.
Published in the Journal of the National Comprehensive Cancer Network, the study reported the highest level of weight loss ever achieved through a fully automated intervention in this population. The programme, known as the AMPLIFY Diet (AiM, PLan and act on LIFestYles), was designed to provide structured, evidence-based lifestyle support without requiring direct clinician involvement.
Addressing a major unmet need
A substantial proportion of people living with and beyond cancer are also living with overweight or obesity. In the United States, this figure is estimated to be around 70 percent. This places individuals at increased risk of cardiovascular disease, type 2 diabetes, functional decline, cancer recurrence, and the development of second primary cancers.
Despite this, access to specialist oncology dietitians remains limited. Traditional weight management programmes often rely on in-person consultations or regular coaching, which can be difficult to scale and may not be accessible to all patients.
The AMPLIFY Diet intervention was developed specifically to address these barriers by delivering personalised nutrition and behavioural support entirely online.
A fully automated intervention
The programme operates without live coaching, counselling calls, or face-to-face appointments. Instead, it uses a structured digital platform that includes weekly interactive sessions, goal-setting tools, progress monitoring, and automated personalised feedback.
Participants engage with the system independently, receiving guidance that is grounded in established behavioural and nutritional science. This approach allows for scalability while maintaining a consistent standard of care.
“This is a game changer for cancer survivorship care,” said Wendy Demark-Wahnefried, Ph.D., R.D., senior author and professor at UAB’s School of Health Professions and O’Neal Comprehensive Cancer Center. “We showed that a completely automated online program grounded in decades of behavioral and nutrition science can safely and effectively help cancer survivors lose weight and improve their health at scale.”
Study design and participant profile
Between 2020 and 2024, the study enrolled 349 participants aged between 50 and 82 years from 31 states across the United States. All participants were living with and beyond cancers associated with obesity.
The cohort included individuals with a range of cancer types, including breast, colorectal, prostate, endometrial, ovarian, thyroid, renal, and haematologic cancers. Participants were randomly assigned to either the AMPLIFY Diet programme or a control group receiving standard survivorship information.
Clinically meaningful weight loss outcomes
After six months, the results showed clear differences between the intervention and control groups.
More than 43 percent of participants in the AMPLIFY Diet group achieved weight loss of at least 3 percent of their body weight. In comparison, only 13 percent of those receiving usual care reached this threshold.
In addition, nearly one in three participants in the intervention group lost at least 5 percent of their body weight. This level of weight loss is widely associated with reductions in cardiovascular risk and improvements in cancer-related outcomes.
On average, weight loss in the intervention group was nearly five times greater than that observed in the control group.
Broader health improvements
The benefits of the programme extended beyond weight loss alone. Participants in the AMPLIFY Diet group experienced improvements across multiple domains of health and wellbeing.
These included reductions in waist circumference and overall caloric intake, as well as improvements in diet quality. Biochemical markers also shifted in a favourable direction, with lower circulating levels of leptin, a hormone associated with cancer progression and cardiometabolic disease.
Further gains were observed in blood pressure, physical functioning, and cognitive performance. Participants also reported improvements in depression and their ability to engage in social roles, suggesting a broader impact on quality of life.
Strong engagement without human support
One notable finding from the study was the level of participant engagement. Individuals completed an average of 60 percent of the weekly sessions, which is considerably higher than engagement rates typically reported in other digital lifestyle interventions.
This suggests that a well-designed automated system can maintain user engagement even in the absence of direct human interaction.
Implications for scalable care
Unlike many conventional weight management programmes, the AMPLIFY Diet intervention does not require ongoing staff involvement. This makes it particularly well suited for integration into healthcare systems, cancer centres, and community-based services.
The ability to deliver consistent, evidence-based care at scale may help address longstanding gaps in survivorship support, particularly in settings where specialist resources are limited.
The role of behavioural and nutritional care
The researchers emphasise that lifestyle-based interventions remain a cornerstone of care for people living with and beyond cancer, particularly as pharmacological approaches continue to evolve.
“Behavioral and nutritional interventions are essential,” Demark-Wahnefried said. “Diet quality, muscle preservation, cognition, and long-term sustainability of a healthful lifestyle and body weight are critical for cancer survivors, and even if weight loss medications eventually receive broadscale endorsement, they alone do not address all of these needs.”
Future directions
The research team is now focusing on expanding the reach of the AMPLIFY Diet programme across both clinical and non-clinical settings. The aim is to improve access to effective survivorship care while also contributing to broader cancer prevention efforts.
The study was funded by the National Institutes of Health and the American Cancer Society.
Read More
Larger Organs, More Cells – New Study Clarifies How Obesity May Increase Cancer Risk
Key Takeaways:
- A new study suggests that larger organ size in people living with obesity increases cancer risk due to a higher number of cells
- Organ growth appears to be driven largely by an increase in cell number rather than simply larger cells
- Findings indicate that organ size may be a more precise predictor of cancer risk than BMI alone
A longstanding question in obesity and cancer
For many years, researchers have recognised a clear association between obesity and an increased risk of cancer, particularly in organs such as the liver, kidneys and pancreas. However, the biological mechanism underpinning this relationship has remained uncertain.
A research team from City of Hope and its Translational Genomics Research Institute, known as TGen, has now provided a clearer explanation. Their findings suggest that the relationship may be explained by a straightforward principle – larger bodies tend to have larger organs, and larger organs contain more cells.
This increase in cell number creates more opportunities for mutations and, consequently, cancer development.
Study design and key findings
The study, presented in Cancer Research, analysed data from 747 adults across a broad spectrum of body mass index (BMI), ranging from underweight at 18.5 kg/m² to severe obesity above 40 kg/m².
Researchers examined the pancreas, kidneys and liver, identifying a consistent pattern: as body weight increased, organ size increased proportionally.
For every 5-point rise in BMI:
- The liver increased in size by 12%
- The kidneys increased by 9%
- The pancreas increased by 7%
These findings demonstrate a measurable and progressive relationship between BMI and organ enlargement.
More cells, not just bigger cells
To better understand how organs grow, the research team analysed kidney tissue from autopsies and biopsy samples from living individuals. This allowed them to distinguish between two biological processes:
- Hypertrophy – where existing cells grow larger
- Hyperplasia – where the number of cells increases
First author Sophie Pénisson, PhD, explained the importance of this distinction:
“When an organ increases in size, the question is to know whether it’s because the cells in it become bigger or whether there are more of them [that are] the same size,” Pénisson said. “And the first case is we call hypertrophy, with bigger cells, and hyperplasia is when we have more cells.”
The results showed that approximately 60% of kidney growth was due to hyperplasia, meaning an increase in the number of cells, while the remainder was due to hypertrophy.
A simple but powerful explanation for cancer risk
These findings support the idea that a greater number of cells increases the likelihood of cancer simply by increasing the number of opportunities for mutations to occur.
Senior author Cristian Tomasetti, PhD, illustrated this concept with a simple analogy:
“Think of playing the lottery: The more tickets you buy, the greater your chances of winning,” Tomasetti said. “Similarly, the more cells in an organ, the more mutations and the greater the risk of one cell going awry during division and becoming cancerous.”
Importantly, this mechanism does not replace existing explanations such as inflammation or hormonal disruption. Instead, it works alongside them.
Pénisson elaborated on this interaction:
“If more cells is like having more raffle tickets, she said, ‘if on top of that, there is inflammation – it means you play more often. With greater frequency, again, you increase your risk of developing cancer.’”
Rethinking BMI as a predictor of risk
The study also raises important questions about the use of BMI as a measure of cancer risk.
Although BMI is widely used in clinical practice, the researchers observed considerable variation in organ size among individuals with similar BMI values. Some individuals within a “healthy” BMI range had organ sizes typically seen in severe obesity, while others with higher BMI did not.
The authors wrote:
“We…observe substantial interindividual variation in organ size among people with similar BMI: For example, some individuals in the healthy BMI range have organ sizes expected only in severe obesity, and vice versa. This large variability suggests that organ size itself may be a better predictor of cancer risk than BMI, a possibility we believe warrants further investigation.”
They further concluded:
“Taken together, these findings establish organ hyperplasia as a previously unrecognized contributor to obesity-related kidney, liver, and pancreatic cancer risk, complementing known mechanisms including inflammation, hormonal changes, and metabolic dysfunction.”
Pénisson reinforced this point:
“When an organ doubles in size, it is expected to roughly double its risk of developing cancer,” Pénisson said, noting that BMI does not distinguish between fat mass and lean tissue. “Our work suggests that, at least for some organs, their dimensions may predict cancer risk better than BMI.”
Can weight loss reverse the risk?
An important question arising from these findings is whether reducing body weight can reverse organ enlargement and lower cancer risk.
Tomasetti indicated that this is an active area of research:
“It’s actually something we are working on right now,” Tomasetti said. “But yes, preliminary data seem to indicate that essentially, you are reverting back according to the same process” that caused the weight gain.
He also referenced emerging evidence presented at the American Society of Clinical Oncology, suggesting a link between GLP-1 receptor agonists and reduced cancer risk, although further research is needed to confirm this relationship.
Implications for treatment and prevention
Given the global scale of obesity, affecting more than 2 billion people, these findings may have important implications for prevention strategies and treatment approaches.
Tomasetti suggested that therapies such as GLP-1 receptor agonists could play a broader role:
GLP-1 RAs “are something that should be given to people as a treatment option to reduce the cancer risk, among other things,” including heart disease.
While further research is needed, this study provides a clearer mechanistic link between obesity and cancer risk and highlights the potential importance of organ size as a clinical marker.
Read More
GLP-1 Receptor Agonists Unlikely to Meaningfully Influence Obesity-Related Cancer Risk, Review Suggests
Key Takeaways:
- Evidence from randomised trials suggests GLP-1 receptor agonists are unlikely to meaningfully increase or reduce the risk of most obesity-related cancers.
- For several cancer types, including colorectal, liver and endometrial cancer, the certainty of evidence remains low due to limited follow-up.
- Researchers emphasise the need for longer-term studies with cancer-specific outcomes to fully understand potential risks or protective effects.
A comprehensive systematic review published online on 8 December in Annals of Internal Medicine suggests that glucagon-like peptide-1 receptor agonists, commonly known as GLP-1 RAs, have little or no effect on the risk of developing cancers associated with obesity.
The review was led by Albert Ko, MD, of the Harvard T.H. Chan School of Public Health in Boston, and examined data from randomised, placebo-controlled trials involving people treated with GLP-1 RAs for type 2 diabetes or overweight and obesity. While these medications have transformed metabolic care in recent years, concerns have persisted about their long-term safety, including potential cancer risk.
Scope and purpose of the review
GLP-1 receptor agonists are widely prescribed for glycaemic control and weight management, yet their association with cancer has remained uncertain. To address this gap, the researchers conducted a systematic review and meta-analysis to assess whether treatment with GLP-1 RAs is associated with an increased or reduced risk of obesity-related cancers.
The review focused on cancers known to have strong links with excess adiposity, including thyroid, pancreatic, colorectal, gastric, oesophageal, liver, gallbladder, breast, ovarian, endometrial and kidney cancers. It also included multiple myeloma and meningioma.
Data sources and study selection
The authors searched PubMed, Embase, Web of Science, Scopus and the Cochrane Central Register of Controlled Trials from database inception through to August 2025. Only randomised, placebo-controlled trials reporting at least one of the specified cancer outcomes were eligible for inclusion.
In total, 48 trials met the inclusion criteria, encompassing 94,245 participants. None of the trials had been specifically designed to evaluate cancer outcomes, and follow-up durations were generally short.
Methods and quality assessment
Risk of bias across the included trials was assessed using the Cochrane Risk of Bias 2 tool. The certainty of evidence for each outcome was evaluated using the GRADE framework, which considers factors such as study limitations, consistency of results and precision of estimates.
Pooled odds ratios were calculated using random-effects meta-analysis to account for variation between studies.
Main findings by cancer type
The analysis found that GLP-1 receptor agonists probably have little or no effect on the risk of several common obesity-related cancers, based on evidence of moderate certainty.
Specifically:
- Thyroid cancer showed no clear association with GLP-1 RA use, with an odds ratio of 1.37 (95% CI, 0.82 to 2.31), corresponding to between one fewer and nine more cases per 10,000 people treated.
- Pancreatic cancer risk was similarly unaffected, with an odds ratio of 0.84 (95% CI, 0.53 to 1.35), equating to nine fewer to six more cases per 10,000 people.
- Breast cancer showed an odds ratio of 0.95 (95% CI, 0.60 to 1.49), indicating no meaningful difference in risk.
- Kidney cancer also demonstrated no significant association, with an odds ratio of 1.12 (95% CI, 0.78 to 1.60).
For other cancers, including colorectal, oesophageal, liver, gallbladder, ovarian and endometrial cancer, as well as multiple myeloma and meningioma, the evidence suggested little or no effect. However, the certainty of this evidence was rated as low.
For gastric cancer, the findings were described as very uncertain, reflecting sparse data and wide confidence intervals.
Consistency across analyses
The results remained consistent across multiple sensitivity and subgroup analyses. These included analyses restricted to trials with a low risk of bias, studies involving newer agents such as semaglutide or tirzepatide, and comparisons across different follow-up durations, populations, GLP-1 RA classes, doses, weight-loss profiles and durations of action.
This consistency strengthens confidence that the observed lack of association is not driven by a specific drug, dose or patient group.
Limitations of the evidence
The authors highlight important limitations that temper the conclusions. Most notably, the included trials were not designed to detect cancer outcomes and generally had relatively short follow-up periods. As a result, rare cancers or effects that emerge only after prolonged exposure may not have been captured.
Implications and next steps
Summarising the findings, the authors conclude that GLP-1 receptor agonists “may have little or no effect on risk for obesity-related cancers,” while emphasising the need for further research. As they write, “These findings offer important insights into the safety of GLP-1 RAs but highlight the need for longer-term studies with cancer-specific end points to clarify potential risks or protective effects.”
For clinicians and people considering or already using GLP-1 receptor agonists, the review provides a degree of reassurance regarding cancer risk in the short to medium term. However, ongoing surveillance and dedicated long-term studies will be essential as use of these medications continues to expand globally.
Read More
Obesity-Linked Lipids Drive Aggressive Breast Cancer Growth in Mouse Models
Key Takeaways:
- New research from the University of Utah reveals that lipids – fat molecules elevated in people living with obesity – can accelerate tumour growth in aggressive forms of breast cancer.
- The findings suggest that lipid-lowering therapies may slow cancer progression and that high-fat diets such as ketogenic regimens may worsen outcomes in some patients.
- Researchers caution that weight loss without addressing lipid levels is insufficient protection against obesity-associated cancers like triple-negative breast cancer.
Lipids identified as key driver in obesity-related breast cancer
A new study from the University of Utah’s Huntsman Cancer Institute (HCI) has found that lipids, a hallmark of obesity, play a significant role in fuelling tumour growth in an aggressive form of breast cancer. The research, funded by the National Cancer Institute and conducted using preclinical mouse models, highlights how lipid metabolism may be a crucial therapeutic target for individuals living with obesity who have or have survived breast cancer.
The findings suggest that breast cancer patients and survivors with obesity could benefit from therapies that lower lipid levels. Conversely, high-fat dietary approaches, such as the ketogenic diet, may have unintended adverse effects by increasing lipid availability to cancer cells.
“The key here is that people have underestimated the importance of fats and lipids in the all-encompassing term that is obesity,” explained Dr Keren Hilgendorf, assistant professor of biochemistry and investigator at HCI. “But our study shows that breast cancer cells are really addicted to lipids, and the abundance of lipids in patients with obesity is one of the reasons that breast cancer is more prevalent and more aggressive in these patients.”
Focus on triple-negative breast cancer
The study focused on triple-negative breast cancer (TNBC) – a fast-growing and difficult-to-treat subtype that lacks receptors for oestrogen, progesterone, and HER2. TNBC is more common in women under 40 and in Black women, and it accounts for approximately 10 to 15 per cent of all breast cancer cases. This form of cancer is particularly prone to recurrence and metastasis.
A high level of lipids in the blood, known as hyperlipidaemia, is a frequent feature of obesity. Dr Hilgendorf and her colleagues, Dr Amandine Chaix and Dr Greg Ducker, both from HCI, examined how lipid levels influence tumour growth using specialised mouse models.
Lipid levels alone drive tumour growth
The researchers used two sets of models: one group of mice was fed high-fat diets, while another was genetically engineered to develop hyperlipidaemia without other typical markers of obesity, such as elevated blood glucose or insulin levels. In both cases, tumours grew faster when lipid levels were high.
“The idea is that lipids, which form the surface membrane of the cell, are like building blocks,” explained Dr Chaix, assistant professor of nutrition and integrative physiology. “If a cell receives the signal to proliferate and more building blocks are available, the tumour is going to grow more easily. We see that a high amount of lipids enables this proliferation.”
Importantly, when lipid levels were lowered – even in the presence of high glucose and insulin – breast cancer cell growth slowed down.
Potential implications for treatment and prevention
While the research was conducted in mice, the results point to potential therapeutic strategies for people with obesity and breast cancer.
“We think this has therapeutic implications, because if you could just lower the lipids – which we already know how to do in patients, for example, with lipid-lowering medication – that could be a way to decelerate breast cancer growth,” said Dr Hilgendorf. “If we can target these high levels of fat in the blood, the cancer sufferers, because the lipids are no longer feeding the cancer. But while our results in mice were striking, there are clear limitations in directly projecting these findings onto human patients. More research using human samples and patients will be necessary to confirm our hypotheses.”
Rethinking weight management in cancer care
These findings may also influence how clinicians guide people with obesity and breast cancer in managing their weight. While weight loss is commonly recommended to reduce recurrence risk, there is limited guidance on the best dietary approaches.
Some individuals turn to ketogenic diets, which are high in fat and low in carbohydrates, to induce ketosis – a state where the body uses fat rather than carbohydrates for energy. However, the new findings raise concerns about such diets in this patient group.
“For patients who are diagnosed with breast cancer and have an elevated BMI [body mass index], we would advise them to consult their physician and develop a weight-loss plan as part of their treatment,” said Dr Ducker, assistant professor of biochemistry. “If you have high cholesterol levels to start with, think about a weight-loss plan or potential pharmaceuticals that could lower your lipid levels. As our study shows, diets like keto that are very high in fat can have serious unintended side effects – even causing the tumour to grow.”
Beyond breast cancer: Broader implications
The research team believes that lipid-driven tumour growth may not be limited to breast cancer alone. Elevated lipid levels could also contribute to tumour progression in other cancers linked to obesity, such as ovarian or colorectal cancers.
The next stage of the research will investigate how anti-lipid drugs could improve the effectiveness of chemotherapy and explore the mechanisms through which lipids feed cancer cells.
Dr Chaix, Dr Ducker and Dr Hilgendorf emphasised that their results apply specifically to triple-negative breast cancer, and that ketogenic diets might still hold benefits for other forms of cancer. Nevertheless, their findings underscore the need for careful, evidence-based dietary guidance for people with obesity affected by cancer.
Read More
Digital Health Programme Boosts Lung Cancer Screening Uptake in High-Risk Individuals
Key Takeaways:
- A digital health intervention (mPATH-Lung) increased lung cancer screening rates by over 40% compared with usual care.
- The programme helped people overcome common barriers to screening, including lack of awareness and limited clinical consultation time.
- Findings demonstrate the potential of direct-to-patient digital tools to improve early cancer detection and preventive care.
Digital tools for early detection
A new study led by researchers at Wake Forest University School of Medicine, in collaboration with the University of North Carolina at Chapel Hill and MD Anderson Cancer Center, has shown that a direct-to-patient digital health programme can significantly increase lung cancer screening rates among people at high risk.
The findings were published in JAMA and mark an important step towards using digital health to support early cancer detection.
Lung cancer remains the leading cause of cancer-related death worldwide. However, early detection through low-dose computed tomography (CT) screening can dramatically improve outcomes and survival rates. Despite this, fewer than 20% of eligible individuals in the United States currently undergo lung cancer screening each year.
Common barriers include a lack of awareness, confusion over screening eligibility guidelines, and limited opportunities for shared decision-making within standard clinical appointments.
“Our goal was to address these barriers by testing a digital programme that reaches patients directly, outside of traditional clinical encounters,” said David P. Miller, M.D., Professor of Implementation Science in the Division of Public Health Sciences at Wake Forest University School of Medicine and corresponding author of the study.
How the study worked
The randomised clinical trial was conducted across two major academic health systems in North Carolina. More than 26,000 individuals with a history of smoking were invited to take part. Those who met the screening eligibility criteria were randomly assigned to one of two groups: the mPATH-Lung digital health programme or enhanced usual care.
The enhanced usual care group received a message informing them that they were eligible for lung cancer screening and were encouraged to speak with their primary care clinician. They also viewed a short educational video on lung health. Although this provided more support than standard practice, it did not include access to the mPATH-Lung platform.
By contrast, participants in the mPATH-Lung group received access to a fully digital intervention comprising:
- A brief educational video,
- A structured decision aid outlining the benefits and risks of screening, and
- An option to request a screening appointment directly online.
This approach allowed participants to learn at their own pace and make informed decisions without needing an in-person consultation.
The main outcome measured was the completion of a low-dose CT scan for lung cancer screening within 16 weeks of enrolment.
Results and key findings
The results demonstrated a clear improvement in screening uptake.
- 24.5% of participants who used the mPATH-Lung programme completed a screening CT scan, compared with 17% of those in the enhanced usual care group.
- The increase in screening rates was consistent across demographic and socioeconomic groups, suggesting that the digital approach may help reduce health disparities.
- There were no reported complications from screening-related procedures in either group.
“Our study shows that reaching patients directly with digital tools can help overcome barriers to lung cancer screening and potentially save lives,” said Miller. “By empowering individuals with information and easy access to screening, we can make a real difference in early detection of lung cancer.”
Implications for preventive health
According to Miller, the findings highlight that digital health interventions can modestly but meaningfully improve screening uptake, even among populations that have historically faced barriers to preventive care. Early detection is crucial, as individuals diagnosed at an early stage of lung cancer have significantly higher survival rates.
The research team believes that the mPATH-Lung approach could be adapted to other preventive health services, enabling more people to benefit from life-saving interventions such as cancer screenings, vaccinations, and chronic disease management programmes.
Next steps and future research
The researchers emphasised that further studies are needed to evaluate digital lung cancer screening initiatives across a broader range of healthcare settings and populations. They also plan to explore strategies for maintaining patient engagement with digital health tools over time.
To extend the impact of their work, Miller and Ajay Dharod, M.D., Associate Professor of Internal Medicine at Wake Forest University School of Medicine, have co-founded mPATH Health – a startup designed to make the programme widely available. The venture aims to expand access to lung cancer screening and other forms of preventive care, aligning with Advocate Health’s academic learning health system model, which focuses on translating research into real-world, scalable solutions.
Miller, Dharod, and Wake Forest University Health Sciences hold ownership interests in the mPATH technology used in the research.
Funding and acknowledgements
This research was supported by the National Cancer Institute under grant R01CA237240. The project utilised the Data and Design Services of the Wake Forest Clinical and Translational Science Institute, supported by the National Center for Advancing Translational Sciences (NCATS) through award UM1TR004929. Additional funding was provided by the University Cancer Research Fund of the University of North Carolina at Chapel Hill Lineberger Comprehensive Cancer Center.
The project also benefited from services provided by the North Carolina Translational and Clinical Sciences Institute, funded by NCATS through award UM1TR004406.
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