AI Model Could Flag Pancreatic Cancer Risk up to Five Years Before Diagnosis
Key Takeaways:
- Mayo Clinic researchers have developed an artificial intelligence (AI) model that uses routinely collected electronic health record data to identify people at increased risk of pancreatic cancer up to five years before the disease becomes clinically apparent.
- The model’s predictions were strongly informed by routine blood tests, particularly components of the complete blood count, alongside expected associations such as diabetes and pancreatitis, as well as patterns in seemingly unrelated healthcare interactions.
- The findings, presented at the American College of Surgeons (ACS) Clinical Congress 2026, have not yet been peer-reviewed, and further prospective validation is needed before the model could be considered for routine clinical use.
A cancer with a disproportionately high mortality burden
Pancreatic cancer is relatively uncommon, but it carries a disproportionately high mortality burden. In the United States, estimates suggest that approximately 67,530 people will receive a diagnosis in 2026, and 52,740 will die from the disease.
Although pancreatic cancer accounts for roughly 3% of all new cancer cases, it is responsible for approximately 8% of cancer deaths, underscoring its particularly high mortality burden.
Pancreatic cancer can be difficult to detect, and many cases are diagnosed only after the cancer has spread. An early diagnosis could be particularly beneficial: data show a five-year relative survival of about 44% when the cancer is still localised, compared with just 3% when it has spread to distant parts of the body.
Now, research suggests that an AI model could identify people at increased risk of pancreatic cancer as early as five years before it becomes clinically apparent, using information routinely collected in electronic health records.
The findings were presented by Mayo Clinic researchers at the ACS Clinical Congress 2026 in Washington DC. As such, it is important to note that the findings have not yet been peer-reviewed.
Early pancreatic cancer clues in routine health data
The researchers developed the model using longitudinal health information from the Mayo Clinic health system. According to the press release, this involved electronic health records for almost 40,000 patients, along with results from routine laboratory tests collected over many years.
The dataset included 6,066 people who went on to develop pancreatic cancer and 33,396 people who served as controls. Participants had between 7.5 and 19 years of clinical history available for analysis. The researchers’ aim was to determine whether patterns in routine medical data could reveal subtle signs associated with an increased future risk of pancreatic cancer.
Pancreatic cancer can develop over many years. However, the clinical signs that would prompt a doctor or a person to investigate the disease may not appear until much later.
Because pancreatic cancer is relatively uncommon in the general population, routinely screening everyone for the disease is not currently considered feasible. An approach capable of identifying people at elevated risk might therefore allow further evaluation to be focused on this group.
“The most important finding was that subtle patterns across a patient’s healthcare journey could reveal elevated pancreatic cancer risk up to five years before the diagnosis was first documented,” lead study author Chris Varghese, MBChB, surgical data analyst at Mayo Clinic, told Medical News Today.
“This creates a potential window to move detection upstream – from reacting to symptoms to proactively identifying patients who may benefit from earlier, targeted screening or further evaluation – an approach that has historically been difficult because pancreatic cancer is relatively rare and existing screening tests are not practical for broad population use.”
How accurately did the AI model identify risk?
The researchers assessed the model’s ability to distinguish between people who would later develop pancreatic cancer and those at lower risk.
Varghese informed Medical News Today that the abstract has since been updated with more data. Five years before a pancreatic cancer diagnosis, the model achieved an area under the receiver operating characteristic curve (AUROC) of 0.853 in a slightly smaller cohort of patients. The updated figures are 0.84 at one year, 0.80 at two years, and 0.76 at three years prior to diagnosis.
AUROC values range from 0.5, which indicates performance no better than chance, to 1.0, which represents perfect discrimination.
The model also achieved an area under the precision-recall curve (AUPRC) of 0.712. This measure can be particularly useful when studying relatively uncommon outcomes such as pancreatic cancer.
The researchers additionally assessed calibration – how closely the model’s predicted risk corresponded to what actually happened in the study population. The reported slope of the calibration plot was 1.08.
“An AUROC in this range means the model is reasonably good at distinguishing people who are at higher risk of pancreatic cancer from those who are at lower risk,” Varghese explained to Medical News Today. “But for clinical use, calibration – whether the risk predicted by the model actually matches the rate of pancreatic cancer we observe in practice – is also very important.”
“Given these promising results, and ongoing research that may further improve performance using more advanced AI models, the next challenge is determining what level of predicted risk should trigger additional evaluation. That threshold may differ depending on the downstream test being considered, its risks and costs, and the potential benefit of detecting cancer earlier.”
“Defining those thresholds and testing how the model performs within a real screening pathway are important next steps,” Varghese said.
In the press release, the researchers offered an example of how the predicted risk could potentially be interpreted: among people for whom the model estimated a greater than 50% risk of pancreatic cancer, 88% were diagnosed with the disease within a year.
Importantly, these results describe the model’s performance within the research dataset. They do not yet establish that using the AI system in routine clinical care will improve pancreatic cancer detection or outcomes for people living with the disease.
What signals did the model rely on?
“We found that the model’s predictions were strongly informed by routine blood tests, particularly components of the complete blood count, which are often obtained for other reasons or as part of routine care,” study co-author Cornelius Thiels, DO, MBA, surgical oncologist at Mayo Clinic, told Medical News Today.
“Expected clinical associations such as diabetes, pancreatitis, and other pancreatic conditions were also important. In addition, patterns in seemingly unrelated healthcare interactions contributed useful information. None of these signals alone would be sufficient to suggest a future diagnosis of pancreatic cancer, but the AI model was able to learn from how they appeared and changed over time across a patient’s longitudinal healthcare record.”
Could the model be used in clinical practice?
The current findings represent an early step and are not evidence that the AI model is ready for use as a pancreatic cancer screening test.
The researchers say they designed the system to rely primarily on information that is already routinely collected in healthcare settings.
The team is now moving the model beyond retrospective analysis and into prospective research at Mayo Clinic. They also plan to evaluate the model at a non-Mayo healthcare system and are investigating newer machine-learning approaches that may further improve its performance.
Prospective validation will be important, as an AI model can perform differently when applied to people outside the dataset on which it was developed. Researchers will also need to establish how the model performs across different healthcare systems and patient populations.
As risk prediction tools of this kind move closer to practice, healthcare professionals will increasingly need to understand how to interpret measures such as discrimination and calibration, and how to judge whether an AI system is safe and appropriate to use. The College of Contemporary Health’s AI Essentials for Primary Care: Tools, Ethics and Everyday Applications course is designed to support the whole primary care team in evaluating AI systems critically and explaining their role in care to the people they support.
What happens to people identified as being at higher risk?
Another important question is what should happen once someone has been identified as being at elevated risk. A prediction tool could potentially lead to additional testing or imaging, but any such follow-up would need to balance the potential benefit of earlier cancer detection against the risks, costs, and anxiety associated with false-positive results.
If further studies confirm that the model can reliably identify people who are likely to develop pancreatic cancer before symptoms or conventional clinical signs emerge, it could eventually give clinicians another tool for deciding who may benefit from closer monitoring or further evaluation.
“Identifying what should happen after someone is flagged as high risk is one of the most complex and important next steps, and we do not yet know the optimal approach,” Thiels explained to Medical News Today.
“Our hope is that by first identifying a smaller, higher-risk population, downstream screening tests – such as CT, MRI, endoscopic ultrasound, or blood-based biomarker tests – may perform better and become more practical. We and others are actively working to determine how best to combine digital risk prediction with these downstream tests and to validate those strategies prospectively before they are ready to be rolled out to patients.”
CCH insight
AI-driven risk prediction tools, such as the pancreatic cancer model developed at Mayo Clinic, are a reminder that AI is increasingly shaping how risk is identified and how care pathways may be designed. Knowing how to assess these tools – their accuracy, calibration, accountability and data protection implications – is fast becoming a core skill for healthcare professionals.
Our AI Essentials for Primary Care: Tools, Ethics and Everyday Applications course is a 3.5-hour online CPD course offering clear, NHS-aligned guidance for nurses, pharmacists, physician associates, healthcare assistants, practice managers and administrative staff. You will learn how to evaluate AI systems safely, understand accountability and data protection requirements, and gain the confidence to give patients clear answers about AI in their care.
Explore AI Essentials for Primary Care →
Source: MedicalNewsToday
Read More
AI Model Helps Clinicians Tell Epilepsy Apart from Functional Seizures Using Routine Clinical Notes
Key Takeaways:
- Researchers developed “EpiScreen”, an AI system built on fine-tuned large language models, which distinguished epilepsy from psychogenic non-epileptic seizures (PNES) using only routine clinical notes, achieving an AUC of up to 0.992 within one institution and 0.980 across institutions.
- When clinicians were given EpiScreen’s predictions and sentence-level explanations, neurology residents’ diagnostic accuracy rose from 76.3%–79.3% to 87.7%–89.0%, and senior attending physicians’ accuracy rose from 81.7% to 89.3%.
- The authors propose EpiScreen as a decision-support tool used after neurology referral and before confirmatory video-electroencephalography (vEEG), though prospective real-world trials are still needed.
An AI approach to a long-standing diagnostic challenge
In a recent study published in the journal npj Digital Medicine, researchers describe the development and validation of “EpiScreen”, a novel artificial intelligence (AI) system designed to distinguish epilepsy from psychogenic non-epileptic seizures (PNES) using clinical notes from routinely documented electronic health records (EHRs).
The retrospective, two-institution study drew on 13,633 patient records. EpiScreen outperformed comparison models, achieving an area under the receiver operating characteristic curve (AUC) of up to 0.992 in within-institution testing and 0.980 in cross-institutional testing. AUC measures a model’s ability to distinguish between the two conditions across different classification thresholds. In a retrospective case-review assessment, EpiScreen also improved clinicians’ classification accuracy.
Why telling the two conditions apart matters
Epilepsy is a chronic neurological disorder characterised by recurring, unprovoked seizures caused by sudden, abnormal electrical discharges in the brain. Approximately 50 million people live with the condition worldwide.
Diagnosis can be complicated by PNES, also termed functional or dissociative seizures. These are paroxysmal events (sudden, temporary seizure-like episodes) that resemble epileptic seizures but are not caused by epileptic electrical activity. Because the two conditions have different underlying mechanisms and management needs, accurate differentiation is critical. Misdiagnosis remains common: prior studies indicate that 20%–30% of people referred to tertiary centres for presumed drug-resistant epilepsy go on to receive a PNES diagnosis.
Prolonged inpatient video-electroencephalography (vEEG), which records synchronised brain waves alongside behavioural data, is the diagnostic gold standard. However, it often costs over US$15,000 per admission in the United States, with reported waiting times of 8 to 12 weeks that vary across healthcare systems. Diagnostic delays can also lead to unnecessary treatment and postpone appropriate care.
Routine clinical notes contain extensive diagnostic signals, but seizure semiology (the symptoms, signs and sequence of a seizure-like event) overlaps considerably across disorders, and earlier narrative-based approaches have shown limited diagnostic performance.
How EpiScreen was developed
EpiScreen was trained and evaluated using 3,451 records from the Beth Israel Deaconess Medical Center’s Medical Information Mart for Intensive Care IV (MIMIC-IV) database and 10,182 records from the University of Minnesota (UMN) Clinical Data Repository. Labels reflected clinicians’ final documented diagnoses, and notes were processed to approximate the information available before diagnosis. People with coexisting epilepsy and PNES were excluded.
The system was built by instruction fine-tuning open-source LLMs, including Qwen-2.5-32B, DeepSeek-R1-32B, Llama-3.3-70B and Med42-70B, using Quantized Low-Rank Adaptation (QLoRA), a method that reduces the memory and training demands of adapting large models. To explain its reasoning, the researchers used sentence-level Integrated Gradients (IG), a technique that highlights the sentences most influential in the model’s decisions across 11 predefined clinical feature categories.
Four medical teams, made up of six neurology residents and two senior attending physicians, then evaluated 300 MIMIC-IV test cases, with each pair reaching decisions by consensus.
Study findings
EpiScreen consistently outperformed conventional supervised baselines, including ClinicalBERT. Its Med42-based variant achieved AUCs of 0.891 on MIMIC-IV and 0.976 on UMN, while the Qwen- and DeepSeek-based variants reached 0.992 on UMN. When tested on records from institutions that had not supplied their training data, the best AUCs reached 0.875 on MIMIC-IV and 0.980 on UMN.
Working alone, EpiScreen achieved 81.0% diagnostic accuracy, compared with 81.7% for unaided senior attending physicians and 76.3%–79.3% for unaided neurology residents. These differences were not statistically significant. With access to the AI’s predictions and sentence attributions, accuracy rose to 87.7%–89.0% across the resident groups and 89.3% for the attending physicians, with the largest improvement around 12.7 percentage points.
AI assistance also reduced false negatives (missed epilepsy cases) for resident Group A from 36 to 14, while the attending pair reduced false positives from 37 to 19.
Not all diagnostic labels were vEEG-confirmed, although sensitivity analyses in confirmed cases supported the findings. Documentation bias remains possible, and other seizure mimics, including syncope and sleep disorders, were not evaluated.
What this means for clinical practice
The authors suggest EpiScreen could be used during or after neurology referral, before confirmatory vEEG, to support earlier assessment and help clinicians prioritise urgent monitoring. They propose it could reduce diagnostic delays, costs and unnecessary exposure to antiseizure medication, though these remain potential benefits rather than measured outcomes.
The study highlights how AI tools that explain their reasoning may be most valuable when working alongside clinical judgement. Clinicians looking to build confidence in evaluating and using AI in practice may find The College of Contemporary Health’s AI Essentials for Primary Care short course a useful starting point.
Future research must prioritise prospective, real-time trials to confirm how EpiScreen performs in real-world settings using minimally curated notes. The tool is intended to support clinical judgement alongside definitive testing, not replace it.
CCH insight
As AI decision-support tools like EpiScreen move closer to everyday practice, healthcare professionals need the knowledge to assess what these systems can and cannot do. Our AI Essentials for Primary Care CPD course helps clinicians understand the role of AI in healthcare and apply it safely and confidently in practice.
Explore AI Essentials for Primary Care →
Source: npj Digital Medicine
Read More
Digital Health Is Redefining Patient Expectations of Care
Key Takeaways:
- Consumers used to personalised digital experiences in banking, retail and entertainment now expect the same convenience and personalisation from healthcare, according to a 2024 Deloitte study.
- Patients are already using digital health services widely: in Spain, 72.48% of survey respondents had used online medical appointments, and older patients and caregivers valued patient portals for their convenience.
- A 2026 OECD report found that patients who have to repeat information that should already be in their health records report worse experiences of trust, quality of care and person-centred care.
The overlooked patient perspective
Professional forums are increasingly focusing on how digital health can contribute to clinical workflows, from automating administrative tasks and analysing imaging studies to segmenting patient groups. However, these discussions often overlook the role of patients themselves, and how digital health is changing their expectations and perceptions of their own healthcare needs.
The growing availability of services that combine effectiveness with patient care and convenience may also be influencing what patients expect from the healthcare system as a whole.
Convenience as a competitive advantage
A 2024 Deloitte study indicated that healthcare systems could gain a competitive advantage by ensuring that their virtual health offerings prioritise convenience and respond to consumer preferences.
According to the report, “today’s consumers, accustomed to highly personalized virtual experiences in banking, retail, and entertainment, now expect the same level of convenience and personalization in their interactions with the healthcare system.”
This shift highlights a key challenge for the healthcare sector: aligning organisational strategies with growing consumer demand for accessible digital health solutions.
For healthcare professionals looking to understand how digital and AI-driven tools are entering everyday practice, The College of Contemporary Health’s AI Essentials for Primary Care short course offers a practical starting point for building confidence in this rapidly evolving area.
Private investment in digital health
Private sector companies are also increasing their investment in digital health.
One example is the recent acquisition of Reimagine Care, a US company that provided virtual care to people with cancer outside the hospital setting, by Cureety, a French healthtech company specialising in the remote monitoring of people with cancer. In 2023, Cureety became the first company in France to receive national reimbursement for the remote monitoring of people with cancer.
Among other features, the company offered a patient interface that supported:
- simple, user-friendly symptom reporting
- secure and ongoing communication with healthcare teams
- reminders
- access to educational content selected and adapted to each person’s treatment and stage of disease
The platform also supported the digitisation and automation of care processes, the monitoring of treatment-specific toxicity, patient classification, the generation of real-world data, and the delivery of specialised educational content to both patients and healthcare professionals at the appropriate point in the care process. Taken together, these functions illustrate how digital health services are evolving.
How patients are using digital health
The question, then, is whether these new approaches to healthcare are changing what patients seek. Several studies have highlighted the value that patients place on online health platforms.
A recent article in the Journal of the American Geriatrics Society examined patient and caregiver expectations regarding the use of patient portals in geriatric care. Users considered patient portals beneficial, particularly because they were convenient and allowed them to avoid in-person care.
In Spain, data from the national survey “Supply and Demand for Users of eHealth Services in Spain”, published in the Journal of Medical Internet Research in 2023, showed that online medical appointments were the most widely used eHealth service. Overall, 72.48% of respondents had used online medical appointments at some point.
The question of trust
While convenience is one consideration, trust is another fundamental issue. Greater access to information that is readily available and easier to understand could strengthen patients’ trust in healthcare professionals and in the healthcare system more broadly.
The 2026 report Building People-Centred Digital Health Systems from the Organisation for Economic Co-operation and Development (OECD) concluded that “When patients have to repeat information that should already be available in their health records, they report significantly worse experience across key patient indicators: trust in the healthcare system, experienced quality of care, and person-centered care.”
However, the report also noted: “Truly patient-centered digital health depends not only on electronic systems but also on patient awareness of access rights, practical tools to retrieve and use data, support for health and digital literacy, and policy frameworks that prioritize patient control over the use of their own health information in line with the OECD Health Data Governance Recommendation.”
Redefining quality care
The debate, therefore, centres on whether healthcare systems need to pursue greater resolution of patients’ needs while also developing a new understanding of what constitutes quality care in a digital age.
This article was translated from El Médico Interactivo on Univadis, part of the Medscape Professional Network.
CCH insight
As patient expectations shift towards convenience, personalisation and seamless access to information, healthcare professionals have a growing role in helping digital tools work well for the people they care for. Our AI Essentials for Primary Care CPD short course helps primary care professionals build a practical understanding of AI and digital innovation in everyday practice.
Explore AI Essentials for Primary Care →
Source: Medscape
Read More
Adapting the Machine to the Medicine: New Review Shows How to Make Clinical AI Work
Key Takeaways:
- A new review in the Journal of Medical Internet Research analysed 35 recent studies and found that off-the-shelf large language models must be adapted for medical settings before they can be relied upon for diagnosis, triage and treatment planning.
- Performance depends on the clinical task: retraining the model on task-specific data suited narrow jobs such as detecting cancer in medical images, while connecting the model to live, trusted databases worked well for reasoning through complex guidelines. Hybrid systems combining both performed best of all.
- Most of the evidence to date comes from historical medical records rather than live clinical use, so prospective, real-world testing remains essential before widespread hospital adoption.
Why raw capability is not enough
Generative artificial intelligence has arrived in health care with considerable fanfare, but a new review suggests that the decisive factor is not the sheer power of the underlying model. It is what happens after the model is built. A review study published in the Journal of Medical Internet Research by JMIR Publications concludes that adapting existing language models to the clinical environment is the key to ensuring they can safely and effectively support diagnosis, patient triage and treatment planning in real-world settings.
The research team, led by Anshum Patel, MD, and Joseph Y Cheung, MD, MS, analysed 35 recent studies to understand how different customisation methods affect AI performance. Their conclusion was that standard large language models (LLMs) are undoubtedly capable, but capability alone does not translate into clinical reliability. To be trusted in a consulting room or on a ward, a model has to be tailored specifically for the medical environment in which it will be used.
What adaptation actually looks like
The review examined the two broad routes clinicians and developers can take. The first is retraining, in which a general-purpose model is further trained on specific clinical data or guidelines so that it internalises the patterns and standards of a particular task. The second is connection, in which the model is linked directly to trusted medical databases and draws on that source material at the point of use rather than relying solely on what it absorbed during training.
Both approaches produced meaningful gains. When models were connected directly to trusted medical databases or retrained on specific clinical guidelines, accuracy greatly improved, with some systems matching the diagnostic performance of human doctors. That is a striking benchmark, and it underlines the central argument of the review: the adaptation step is not a technical afterthought but the point at which a general tool becomes a clinical one.
The right method depends on the task
The most successful approach was found to depend heavily on the specific medical task at hand, and this is arguably the review’s most practical finding for anyone evaluating these tools.
For narrow, focused tasks such as detecting cancer in medical images, retraining the AI on specific data worked best. Where the job is well defined and the data are consistent, teaching the model directly on that material produces the sharpest results.
For tasks that require reasoning through complex guidelines, linking the AI to live databases was highly effective. Clinical guidance changes, and a model that consults an authoritative, current source is far better placed than one working from a fixed snapshot of its training data.
However, the researchers determined that the best performance came from hybrid systems, which combine both methods to manage complicated workflows such as stroke triage and oncology cases. These are precisely the situations in which speed, protocol adherence and nuanced judgement all matter at once, and where people presenting with time-critical or complex conditions stand to gain the most from well-designed decision support.
“There is no single best way to adapt AI for health care. The right approach depends on the clinical task, and the next step is making sure these systems are safe, reliable, and useful in real-world patient care,” says Anshum Patel.
Implications for clinical teams
For healthcare professionals, the message is not that they need to become engineers. It is that the questions worth asking about any AI tool offered to a service are increasingly practical ones: what was this model adapted for, what source material informs its outputs, how current is that material, and has it been tested on a population and a workflow resembling ours?
That kind of informed scrutiny is becoming part of everyday clinical literacy, and it is one reason structured professional development in this area has grown in demand. The College of Contemporary Health’s AI Essentials for Primary Care short course is designed for exactly this purpose, helping clinicians understand how these systems are built, where their limitations lie, and how to appraise them responsibly within their own practice.
The evidence gap that still needs closing
While these findings are promising, the researchers note that the vast majority of studies on these AI systems are based on past medical records rather than live patient testing. Retrospective analysis can demonstrate that a system performs well against a tidy historical dataset; it cannot show how that system behaves when confronted with incomplete notes, atypical presentations, or the ordinary time pressures of a busy department.
Before these advanced tools are widely adopted in hospitals, additional prospective, real-world testing is needed to guarantee patient safety and ensure the technology works reliably across different clinical environments. Until that evidence accumulates, the sensible position is one of informed optimism – recognising the genuine potential of adapted clinical AI while insisting that it earns its place through testing in the settings where people actually receive care.
CCH insight
Artificial intelligence is moving quickly from conference agendas into everyday clinical workflows, and the professionals best placed to use it well are those who understand both its strengths and its blind spots. AI Essentials for Primary Care is a CPD-accredited short course from The College of Contemporary Health, built for clinicians who want a clear, practical grounding in how AI tools work, how to evaluate them critically, and how to apply them safely in patient-facing practice.
Explore AI Essentials for Primary Care →
Source: Journal of Medical Internet Research
Read More
Fungal Disease Is Rising and Underdiagnosed – Can AI Help Close the Gap?
Key Takeaways:
- Fungal diseases affect more than 300 million people each year and are linked to over 3.75 million deaths annually, yet they remain historically underrecognised, difficult to diagnose and poorly tracked compared with viral and bacterial infections.
- A World Health Organization (WHO) blueprint released in June 2026 sets out a framework for countries to raise awareness, build laboratory and surveillance networks, stimulate research and improve access to diagnosis and treatment.
- Australian researchers are finalising an automated surveillance platform that uses AI to extract evidence of fungal disease from electronic medical records, with the biggest obstacle being the standardisation of clinical annotations rather than the technology itself.
A threat that has grown in the shadows
Fungal disease and antifungal resistance are growing global threats that have long sat at the margins of public health planning. They are difficult to detect, difficult to track and, until recently, have attracted comparatively little policy attention. That is beginning to shift, driven by two parallel developments: a new international policy framework and a set of digital health initiatives designed to make fungal infection visible in routine clinical data.
The scale of the problem is substantial. More than 300 million people are affected by fungal diseases every year, and over 3.75 million people die annually. Among patients who are immunocompromised, invasive fungal infections are the “leading cause of mortality and morbidity”, according to a 2025 WHO report.
In recent years, the number of new infections, and especially antifungal-resistant infections, has doubled. Two environmental drivers are implicated. As the climate warms, fungi are adapting to survive at higher temperatures, narrowing the thermal barrier that has historically protected humans from many environmental fungi. Increased flooding events have also contributed to mould growth, which in turn leads to disease spread. A third driver sits outside the clinical environment altogether: the use of fungicides on agricultural crops is a major cause of antifungal resistance encountered in healthcare settings, because agricultural compounds and clinical antifungals share overlapping mechanisms of action.
Despite rising prevalence, fungal infections are still not as common as viral infections, so far fewer diagnostic tools have been developed to test for them. With relatively fewer resources allocated to fungal disease research, surveillance and response, fungal diseases also lag behind bacterial infections in terms of treatment options. Recent policy developments and digital health initiatives are working to change this.
Why fungal diseases are difficult to diagnose and treat
One of the biggest challenges to fungal disease preparedness is underdiagnosis, which makes research, surveillance and response considerably more difficult. Without a diagnosis, there is no case to count, and without counted cases there is no evidence base to justify investment.
“If we don’t have good diagnostic tests, these diseases don’t exist because we don’t know who has them,” said Tom Chiller, MD, former chief of the Mycotic Diseases Branch at the Centers for Disease Control and Prevention.
Chiller adds that diagnosing fungal disease is inherently difficult because fungal cells look similar to human cells, making it challenging to develop a diagnostic test sensitive enough to tell the difference. Fungi are also everywhere around us, in their billions. Exposure is “near universal”, and it is hard to distinguish the colonies that are causing disease from those that are entirely harmless. A positive result, in other words, does not automatically indicate infection.
That same cellular similarity creates a second problem at the point of treatment. Because fungal cells so closely resemble human cells, it remains very challenging to kill one type of cell without also damaging the other, which makes treatment toxicity a major issue for the patients who most need therapy.
There is also the matter of range. Only three major classes of antifungal drugs are available – azoles, echinocandins and polyenes – so resistance carries disproportionate consequences. When a fungal pathogen becomes resistant, there are simply fewer tools left in the toolbox.
New antifungal agents in development
Encouragingly, several new antifungal drugs are at various stages of development and investigation, and may help to address resistance. Oteseconazole and rezafungin have received US Food and Drug Administration approval in recent years, building on the existing antifungal classes and expanding the available arsenal. Two newer treatments, olorofim and fosmanogepix, represent entirely new classes and will hopefully be approved in the coming years. New classes matter more than new agents within existing classes, because they offer options where cross-resistance is less likely.
A blueprint for improving antifungal care
While millions of fungi exist, only a few hundred can cause disease in humans. Some of the most common and well-known fungal diseases include ringworm, vaginal yeast infections, athlete’s foot, skin infections such as sporotrichosis, and mould infections such as aspergillosis, as well as invasive infections including cryptococcal meningitis and candidiasis.
The most dangerous fungal disease is multidrug-resistant Candida auris, which was first identified in a Japanese hospital in 2009 and has been found fatal in 29% to 62% of cases.
Without surveying when these conditions are diagnosed and treated, there can be no accurate picture of which diseases are most prevalent, or of when they become resistant to available antifungal treatments. Stewardship programmes designed to protect against resistance also remain weak and limited in scope, particularly in underresourced countries.
Recognising this gap, the WHO released a new blueprint in June 2026 to help countries begin to create uniform tools to respond to the growing public health threat of fungal disease and antifungal resistance. The report provides a framework with recommendations to guide implementation across four areas: increasing awareness and strengthening public health initiatives; building laboratory networks and surveillance systems; stimulating research and improving access to diagnosis and treatment; and addressing the factors that contribute to disease and resistance.
It also aims to support countries in their disease response and to make more fungal diseases reportable to public health officials. Across the United States, for example, reporting priorities vary between states, and the only fungal diseases prioritised as legally reportable nationally are coccidioidomycosis (Valley fever) and Candida auris – a small fraction of those that can affect human health.
Chiller said he hopes the report will draw more attention to both the prevalence and the morbidity of these infections in order to improve available funding. Increased resources would be particularly useful for investing in new treatments to stave off antifungal resistance.
A digital platform for fungal disease and antifungal resistance surveillance
Alongside the policy work, Australian researchers are in the final stages of launching an automated fungal infection surveillance platform that will digitally survey fungal disease across the continent.
The digital platform, called the Design Thinking Framework, was built from a review of multiple sources of clinical information across a wide array of healthcare settings in Melbourne. It extracts information from electronic medical records (EMRs) using AI trained to detect episodes of fungal disease even when the diagnosis is not explicitly recorded. The tool will also provide a web-based platform accessible to physicians so that they can properly report future episodes of fungal disease and resistance.
Vlada Rozova, PhD, a senior lecturer in AI in Health at Monash University, who originally led the project at the University of Melbourne, said the Design Thinking Framework will be helpful in monitoring what is being prescribed for fungal diseases across a range of hospitals, in order to understand when prescribing leads to resistance and what can be done to reduce it, while also identifying which treatments are most effective for patients.
“It will help clinicians to better evaluate the therapies that they’re providing their patients to know what’s necessary and in what particular types of patients certain antifungal agents are most effective,” said Rozova.
Why the hardest problem is human, not technical
The biggest challenge for Rozova and her colleagues has not been the algorithm. It has been standardising clinical annotations to ensure that reports are consistent across the platform. Getting clinicians to agree on which notes within EMRs indicate fungal disease, and which indicate resistance, has been and will continue to be a complex task, because humans, unlike machines, are not standardised.
“If we can’t get humans to agree on what a fungal disease is, we can’t train a machine to look for it,” said Rozova.
This is a familiar theme across clinical AI. Tools that read free-text records depend on consistent human documentation and shared definitions, which is why clinicians increasingly need a working understanding of how these systems are built, what they can reasonably infer and where they are likely to fail. Practitioners looking to develop that grounding often begin with structured CPD, such as the College of Contemporary Health’s AI Essentials for Primary Care short course, which introduces how AI-driven tools are being applied in clinical practice and how to appraise them critically.
Looking ahead
Increased awareness will hopefully bring increased agreement. With guidance from global bodies such as the WHO, and with new digital surveillance platforms of the kind being finalised in Australia, the global response to fungal infections and antifungal resistance stands to be meaningfully strengthened – provided the diagnostic, documentation and funding gaps are addressed in parallel.
CCH insight
Digital surveillance tools are only as reliable as the clinical documentation that feeds them, and clinicians are increasingly being asked to work alongside AI systems rather than simply receive their outputs. Our CPD-accredited short course AI Essentials for Primary Care is designed for healthcare professionals who want a practical, jargon-free grounding in how these technologies work and how to evaluate them in day-to-day practice.
Explore AI Essentials for Primary Care →
Source: JMIR Publications
Read More
When the Diagnosis Arrives by App: Why Most Patients Still Want a Human Voice
Key Takeaways:
- In a UT Southwestern survey of more than 2,400 people diagnosed with cancer, 75% said they would prefer to receive the news directly from their physician – in person or by telemedicine – rather than through an electronic patient portal.
- More than half of those who first learned of their diagnosis via the portal were alone at the time, often without support from a clinician or family member.
- Researchers are calling for a more personalised approach, including better portal notification settings, tiered or delayed release of sensitive findings, and plain-language summaries of radiology and pathology reports.
A digital convenience with an emotional cost
Electronic patient portals have transformed how quickly people can see their own test results. For routine bloodwork or a clear scan, near-instant access is a welcome convenience. But the same speed raises a difficult question for clinicians: how should a new cancer diagnosis be communicated when a patient can open the result on a phone before anyone has had the chance to talk it through?
That tension has grown sharper since 2021, when a provision of the 21st Century Cures Act came into force in the United States. The regulation requires that patients have timely, unrestricted access to their electronic health information – which, in practice, means a growing number of people are discovering a new or recurrent cancer diagnosis through their portal, sometimes with no clinician present to interpret it or answer the questions that immediately follow.
What the UT Southwestern survey found
A new survey carried out at UT Southwestern Medical Center suggests that, for most people facing a cancer diagnosis, faster is not better. The findings, published in JAMA Network Open, show that 75% of respondents would prefer to learn about a cancer diagnosis directly from their physician, whether in person or through a telemedicine appointment.
The 2025 survey gathered responses from more than 2,400 people who were diagnosed with cancer at the Harold C. Simmons Comprehensive Cancer Center between 2019 and 2023, giving the researchers a substantial real-world picture of how patients want sensitive results delivered.
According to the study’s lead author, Sheena Bhalla, M.D., Assistant Professor of Internal Medicine in the Division of Hematology and Oncology and a medical oncologist at the Simmons Cancer Center, the broad enthusiasm for digital access does not extend neatly to oncology. “While most patients in the general population appreciate rapid electronic access to test results, the situation for patients with cancer is much more nuanced,” she said. “Learning about a cancer diagnosis without the ability to immediately ask questions or discuss next steps with a trusted clinician can add to the significant stress, uncertainty, and fear that patients experience.”
Preferences are not one-size-fits-all
The survey also revealed that there is no single right way to share a result. Preferences varied according to people’s prior experiences, how frequently they used their portal, and their demographic characteristics. Men, for instance, were more likely than women to prefer learning of a diagnosis through the portal.
For senior author David Gerber, M.D., Professor of Internal Medicine in the Division of Hematology and Oncology and of Epidemiology in the Peter O’Donnell Jr. School of Public Health, and co-Director of the Simmons Cancer Center Office of Education and Training, that variation is precisely the point. “These findings highlight the need for a more personalized, tailored approach to communicating sensitive and life-changing results,” he said. “Moving beyond a one-size-fits-all approach can help clinicians provide a more thoughtful, compassionate patient experience.”
The hidden consequence: facing the news alone
Perhaps the most striking insight concerns the circumstances in which people are receiving these results. Among those who learned of their diagnosis through the portal, more than half reported that they were alone when they read it.
Dr Bhalla described this as one of the most troubling side effects of real-time access. “That’s one of the most unintended consequences of real-time access,” she said. “Patients are often alone without support from their physician or family at one of their most vulnerable moments.”
Possible solutions for clinicians and health systems
The researchers are clear that the answer is not to roll back access, but to design around it more thoughtfully. They point to several potential measures, including raising awareness among both clinicians and patients of the portal notification settings already available; developing tiered or delayed-release approaches for particularly sensitive findings; and integrating supportive digital tools such as plain-language summaries for radiology and pathology reports.
Policy is beginning to catch up. Since the Cures Act took effect, three states – including Texas – have enacted laws permitting the delayed portal release of cancer-related and other sensitive results, giving care teams a window to reach out before a patient is left to interpret difficult news on their own.
Looking ahead
For the study’s authors, the work is a starting point rather than a conclusion. “Further study and increased interdisciplinary collaboration among oncology clinicians, health services researchers, and digital health experts can help us better understand how patients receive and react to cancer diagnoses,” Dr Bhalla said. “Our goal is to increase awareness of this issue and help drive innovative approaches to patient-centered communication.”
Source: UT Southwestern Medical Center
Read More