Unlocking the Power of EMR Data for Earlier Gastric Cancer Diagnosis and Risk Prediction
By Léon Van Wouwe, Clinical Innovation Director, Volv Global Gastric (stomach) cancer remains a formidable global health challenge, ranking as the fifth most common cancer and a leading cause of cancer-related mortality. [1] Alarmingly, its incidence is rising in patients under 50 years old, alongside other gastrointestinal malignancies. In 2022 alone, nearly one million new cases were diagnosed, leading to approximately 660,000 deaths worldwide. One particularly aggressive form, gastroesophageal junction (GEJ) cancer, spans the critical connection between the esophagus and the stomach, further complicating detection and treatment. As with all cancers, early diagnosis is critical for optimizing treatment outcomes. Yet, gastric cancer often remains undetected until later stages, limiting therapeutic options and survival rates. Could primary care electronic medical records (EMR) data hold the key to shifting this paradigm? The Power of EMR Data in Earlier Cancer Detection Our recent research on gastroenteropancreatic neuroendocrine tumours (GEP-NETs), a rare type of gut cancer, demonstrates how EMR-driven analytics can uncover hidden diagnostic delays. Leveraging UK primary care data, we identified that undiagnosed patients are, on average, 5 to 7 years younger than those already diagnosed—highlighting a significant opportunity to intervene earlier. [2] Addressing Gastric Cancer Recurrence and Outcome Prediction For gastric cancer, the stakes are even higher. Despite curative surgery and neoadjuvant/adjuvant chemotherapy, recurrence is common. One in four patients experiences disease recurrence within a year post-surgery, and survival beyond two years remains a challenge. The five-year survival rate remains dismally low, with fewer than half of patients alive at this milestone. [3, 4, 5] Beyond early detection, advanced risk prediction models leveraging EMR data could refine patient stratification and enhance personalized treatment decisions. By integrating EMR-driven insights, we can better predict recurrence risk and tailor therapeutic regimens accordingly. Notably, Imfinzi-based regimens have already demonstrated statistically significant and clinically meaningful improvements in event-free survival for resectable early-stage gastric and GEJ cancers, underscoring the potential of precision medicine approaches. [6] A Call to Action: Innovating in Gastric Cancer Drug Development The integration of EMR data into drug development and commercialization strategies presents an immense opportunity to revolutionize gastric cancer management. Pharmaceutical innovators and executives, are you ready to explore how real-world data can drive earlier diagnosis, improve risk modelling, and ultimately enhance patient outcomes? Let’s connect to discuss how advanced analytics and AI-driven EMR insights can shape the future of gastric cancer therapeutics. Looking forward to your thoughts in the comments or via direct conversation. This article was originally published on LinkedIn: Unlocking the Power of EMR Data for Earlier Gastric Cancer Diagnosis and Risk Prediction About the author Léon van Wouwe has 20+ years’ global experience in clinical development and operations, uniting data science with pharma and research. He drives cross-functional collaboration to advance innovative treatments. References World Health Organization . International Agency for Research on Cancer. Stomach Fact Sheet. Available at: https://gco.iarc.who.int/media/globocan/factsheets/cancers/7-stomach-fact-sheet.pdf. Accessed March 2025. Volv Global SA , project results. For information contact www.volv.global Li Y, et al. Postoperative recurrence of gastric cancer depends on whether the chemotherapy cycle was more than 9 cycles. Medicine. 2022;101(5):e28620. Ilic M, Ilic I. Epidemiology of stomach cancer. World J Gastroenterol. 2022;28(12):1187-1203. Al-Batran SE, et al. Perioperative chemotherapy with fluorouracil plus leucovorin, oxaliplatin, and docetaxel versus fluorouracil or capecitabine plus cisplatin and epirubicin for locally advanced, resectable gastric or gastro-oesophageal junction adenocarcinoma (FLOT4): a randomised, phase 2/3 trial. Lancet. 2019;393(10184):1948-1957. AstraZeneca : Imfinzi-based regimen demonstrated statistically significant and clinically meaningful improvement in event-free survival in resectable early-stage gastric and gastroesophageal junction cancers Header photo by mohamad azaam on Unsplash
Press Release: Volv Global Expands Office Footprint to Power Next-Generation AI Innovation in Healthcare
ÉPALINGES, Switzerland, March 5, 2025 /PRNewswire-PRWeb/ Volv Global has more than doubled its office space for the fourth year in a row Expansion driven by accelerating demand for its proprietary AI-driven healthcare insights. New space fosters collaboration, innovation, and impact—driving precision in difficult-to-diagnose diseases. Volv Global, a leader in AI-powered healthcare intelligence, has expanded its global office footprint for the fourth year in a row, more than doubling its space again to accommodate the company’s rapid growth. This strategic expansion underscores Volv’s commitment to accelerating innovation and delivering breakthrough insights that transform disease detection, diagnosis, and treatment pathways. “Our growth is a reflection of our mission—to provide new knowledge at speed, enabling us to do more with less,” said Christopher Rudolf, CEO of Volv Global. “As we scale, our new space will serve as a hub for collaboration, where our multidisciplinary teams can push the boundaries of AI-driven discovery in healthcare.” Over the past year, Volv Global has significantly expanded its team, attracting top talent across data science, machine learning, and healthcare. This move not only meets the immediate need for additional space but also strengthens the company’s ability to drive impact—enhancing pharmaceutical R&D strategies, optimizing clinical pathways, and personalizing patient care. Innovation at the Intersection of AI and Human Health Volv Global’s expansion reflects its position as a category thought leader, distinguishing itself from competitors through its unique approach to machine learning. Unlike conventional AI solutions, Volv’s proprietary inTrigue technology enables: Earlier detection of difficult-to-diagnose diseases. More precise patient stratification to enhance clinical development and drug repurposing. Actionable, real-world insights that drive healthcare efficiencies and reduce costs. By creating an environment that fosters deep collaboration and critical thinking, Volv is reinforcing its “where technology meets human” philosophy—bridging the gap between cutting-edge AI and real-world healthcare challenges. The Future of AI-Driven Healthcare With a multinational team spanning Europe and the U.S., Volv Global remains focused on its core mission: to speed science, reduce the cost of healthcare, close the diagnostic gap, and improve outcomes for people living with disease. The expanded office space enables the company to advance this vision—supporting pharmaceutical partners with unparalleled data intelligence and transforming the future of patient care. About Volv Global Volv Global is a pioneering AI-driven healthcare intelligence company, delivering unprecedented insights into rare and difficult-to-diagnose diseases. By leveraging population-scale data, Volv helps clinicians and pharmaceutical innovators recognize undiagnosed patients, detect diseases earlier, predict outcomes, and optimize healthcare pathways. Unlike traditional approaches, Volv’s machine learning methodologies overcome data bias, fragmentation, and standard AI limitations, offering universally adaptable solutions that work across diseases, healthcare systems, and clinical coding environments. With inTrigue, Volv’s proprietary AI technology, the company enables a paradigm shift in disease detection—bringing precision, personalization, and efficiency to healthcare. Volv Global does not hold patient data by design, ensuring privacy-first solutions powered by trusted data processors worldwide. Volv Global website: www.volv.global Internal link: News Article: Volv Global Tracks Nearly Undetectable Diseases External links: Volv Global Expands Office Footprint to Power Next-Generation AI Innovation in Healthcare – Biopôle Volv Global set on expansion course – Startupticker.ch Volv Global Expands Offices to Fuel AI-Driven Healthcare Breakthroughs – Company Glance
A Rare Disease Day Message from Dr. Al Freedman
On the occasion of international Rare Disease Day 2025, we are beyond thrilled to host the voice of patient advocate Dr. Albert Freedman. He tells the story of his son, Jack, below. On Rare Disease Day, it is most important to honor the experiences of patients and families around the world who are affected by rare diseases. For rare disease patients and their families, rare disease day is every day. As a practicing psychologist specializing in supporting the needs of patients and families affected by rare disease, I see and hear the challenges our families experience every single day. As the father of an adult son who lived to the age of 26 with Spinal Muscular Atrophy (SMA), I experienced these challenges myself every single day for 26 years. Living with a rare disease is hard. It’s hard to live with uncertainty – rare disease patients and their families are often riddled with anxiety because they do not know what the future will hold for them. It’s hard to maintain friendships – rare disease patients often feel isolated because they can’t do things the same way others can and their friends don’t stick with them as time passes. It’s hard to navigate the health care system – rare disease patients often feel misunderstood, unheard, and frustrated by the lack of knowledge of their condition by health care professionals. It’s hard to manage financially – rare disease patients are often challenged by the combination of the high costs of their medical care and limited ability to earn an income because of their condition. It’s hard to find partners – rare disease patients often feel sad because they are alone. Living with a rare disease is hard. Remarkably, despite all of these challenges, the majority of rare disease patients and their families – following a period of psychological reorientation upon receiving the news of a rare disease diagnosis – move forward with their lives with extraordinary grace and dignity. Remarkably, despite so many challenges, so many rare disease patients and their families demonstrate strength, courage, and resilience, and a sense of perspective about what is truly important. No one ever chooses a rare disease. We are all in a club none of us choose to join. But we do the best we can, with the support of others – like my friends at Volv Global – to move forward with our lives and to live our lives to the fullest. So as we pause to acknowledge Rare Disease Day, let us do whatever we can do to provide meaningful, authentic, and substantive support – not only today but every day we possibly can – to the patients and families who need help. Dr. Al Freedman Psychologist, Consultant, Keynote Speaker & Father Dr. Al Freedman Psychologist/Consultant | rarecounseling.com I am a psychologist and rare disease dad, and I’ve been living and working with individuals and families affected by rare disease for over two decades. I’m uniquely prepared to support families affected by disability and complex medical conditions and the professionals who serve them. My son, Jack, lived with Spinal Muscular Atrophy for 26 years. I am grateful to have learned a great deal from Jack and everyone who supported my family over the years. I use what Jack taught me, my professional training as a psychologist, and my early experience as an educator to provide counseling and consultation to families, advocacy organizations, pharmaceutical companies, healthcare organizations, and schools.
Where technology meets Human: Volv Global at the World Orphan Drug Congress USA 2025
Volv Global sits at the crucial intersection between technology and human beings, i.e., patients and physicians, supporting favourable patient journeys and outcomes. Meet us at the World Orphan Drug Congress USA 2025 in Boston, 22nd-25th April, to find out more: 🟥 Our booth: #413 🟥 Our Panel Discussion at 11.05 a.m., on Wednesday, 23rd April, in the AI & Digital Health Track, in Theater 3. Where technology meets Human: Redefining Patient Personalisation will discuss how technology may bring incredible benefits for health and healthcare, but how can the way be eased for the healthcare ecosystem – incl. patients, physicians, HCOs, health authorities and payers – to be able to fully embrace new advances? And, if adopted, what work is needed to ensure these innovations are sustained and continue? We are very pleased to have leading lights of the industry on this panel with us: 🟥 Albert Freedman, Counseling Psychologist/ Rare Dad, RareCounseling.com, 🟥 Faisal Riaz, MD, Medical Director PDT, RAID/ Neuroimmunology, Takeda Pharmaceuticals, 🟥 Rachel Smith, Executive Director and Global Head, Rare Disease Center of Excellence, Parexel, 🟥 Joern-Peter Halle, Advisor and Venture Partner, BGV, will join 🟥 Christopher Rudolf, Founder and Chief Executive Officer, Volv Global 🟥 Our Talk at 11.10 a.m., on Thursday, 24th April in the Global Market and Patient Access track, in Theater 4 – Room 050. Where technology meets Human: Healthcare. Numbers. Money. People. How can we in the healthcare ecosystem avoid technology pitfalls and bring the human being back into focus? Volv Global CEO Christopher Rudolf will touch on lessons in successful collaboration for international projects, with a focus on “Value and Access 2.0.” Looking forward to having great discussions with you there! Please Contact Us to book a meeting!
News Article: Volv Global Tracks Nearly Undetectable Diseases
This article is also available in French and originally published 24 Heures. Read the original article Based in Épalinges, the small company has developed an innovative AI model to improve diagnostics. A company profile. In Brief: A British Accent, Whippets, and Secret Algorithms A touch of a British accent, three whippets to remember before opening the door, and closely guarded algorithms … The offices of Volv Global, located at the Biopôle in Épalinges, are a world of mystery. This is partly because the company collaborates with the largest pharmaceutical multinationals, and partly because its AI algorithms have learned to identify not only rare diseases but also conditions that are difficult to diagnose. The ultimate goal: to reduce healthcare costs through early detection of these illnesses. To achieve this, Volv Global has taken an unconventional route. Instead of relying on public healthcare funding, the company started by selling its services to pharmaceutical companies. Initially working for pharmaceutical and tech firms, Volv Global decided to tackle the challenge of identifying patients with a disease affecting only one in a million people. Lipodystrophy affects the body’s ability to manage fat. “These people are very thin, and their condition is often mistaken for diabetes. They can suffer for years from misdiagnoses,” explains Christopher Rudolf, Volv Global’s CEO. This situation doesn’t help patients and burdens the healthcare system unnecessarily. Moreover, for pharmaceutical companies, it represents patients who miss out on potentially beneficial treatments. The Search for Rare Patients Volv Global began its work by finding patients on behalf of pharmaceutical companies. But how do you identify someone at risk of a rare and difficult-to-diagnose disease? The answer lies in the company’s mathematical model, which has been developed over the past seven years. Developers of AI-based models agree that high-quality data is essential for training algorithms. However, medical data quality varies significantly from one country to another. “Electronic health records are disparate, messy, and scattered, and it’s impossible to clean them up,” explains Christopher Rudolf. Searching the Unknown The challenge is to create a model capable of detecting signs of a disease within anonymized and heterogeneous data, even when the disease itself is not explicitly listed. “We’ve developed a methodology that allows AI to learn without labels—that is, without the disease being mentioned in the data.” This explanation seems almost mystical, like consulting a crystal ball. “On the contrary,” responds Rudolf, “our method is highly scientific and has allowed us to study many rare and less rare diseases. We know we can detect a wide range of them.” The investments made by Volv Global’s multinational clients suggest the solution is effective. While Rudolf keeps client names confidential, he is proud to announce their first contract with a Swiss company: Novartis. Reducing Healthcare Costs Christopher Rudolf’s vision extends beyond pharmaceutical collaborations. He hopes that the algorithms will ultimately benefit the healthcare system. Imagine these algorithms being integrated into hospital IT systems, flagging potential risks of rare diseases based solely on a patient’s data. “Finding what hasn’t yet been diagnosed is our biggest added value. The continuous rise in healthcare costs is unsustainable, and we hope to contribute by enabling the early detection of patients,” says Rudolf. Without early detection, patients might undergo numerous consultations and years of ineffective treatments due to misdiagnoses. However, Rudolf acknowledges that healthcare systems are not yet ready to implement such technology, even though it is already available. “We find patients for pharmaceutical companies, but they must remain anonymous. Physicians must handle the rest. That’s why, in Europe, we provide our algorithms free of charge to doctors.” Rapid Growth Without Funding While waiting for attitudes to change, Volv Global continues its projects and is growing at a remarkable pace without ever having raised external funds. “Over the past three years, we’ve doubled in size annually,” says Rudolf. However, he remains cautious. The field of data science in healthcare faces two opposing forces: the drive to achieve more while introducing stricter legislation to protect personal information. Link: Press Release: Volv Global Expands Office Footprint to Power Next-Generation AI Innovation in Healthcare
Poster: Alpha-1 Antitrypsin Deficiency: Why millions remain undiagnosed
Alpha-1 antitrypsin deficiency (AATD), a rare genetic condition, can cause lung disease in adults with symptoms similar to chronic obstructive pulmonary diseases. AATD is largely underdiagnosed, with an estimated prevalence of 100,000 individuals with AATD in the United States (US); however, fewer than 10,000 individuals are diagnosed with the disorder. Previously, AATD was thought to affect only White individuals of European descent. Recent studies have shown that people of different races and ethnicities have genotypes consistent with those with moderate-to-severe AATD-related lung disease. We developed a prediction model to identify symptomatic patients of different races and ethnicities with likely risk of AATD using claims data from a large US database. This poster was developed together with Takeda and presented at the American Thoracic Society International Conference 2024.
Case Study: Detecting signs of Fabry and Pompe disease in UK clinical data
Volv, supported by Sanofi, and working with Optimum Patient Care, and collaborating with a specialist Consultant Clinician, is performing research to build algorithms in the UK which are aimed at finding ways to better identify people living with Fabry or Pompe disease. This novel and innovative methodology, inTrigue, is highlighting ways in which we can be much more precise in detecting people living with either disease much earlier. Are you a Fabry or Pompe specialist in the UK and want to know more, or collaborate? Please contact us. inTrigue: helping people living with disease get better outcomes In the sections below you will find an overview of how we create models to help predict which people might be at risk of disease, some of the current performance metrics, and also some background information on both Fabry and Pompe disease. By using the inTrigue methodology in collaboration with Optimum Patient Care (OPC) in the UK and the OPC Research Database and supported by Sanofi, we are learning novel patterns of disease, we do this because using published medical criteria does not help find the patients that remain undiagnosed and in fact highlights many more patients that do not in fact have disease (false positives). The inTrigue approach looks for people that cannot be found using those methods. inTrigue is designed to help clinicians detect the people who are living with a rare or difficult-to-diagnose disease and help uncover those people who are therefore otherwise unlikely to get a diagnosis. Importantly, this is a research project that focusses on a limited population at first works with a population of clinicians that have signed up for the OPC quality improvement (QI) programme to improve the quality of care for patients in general practice aims to use the feedback from clinicians to improve the approach This is a completely different level of performance that promises to reduce the time to a diagnosis, and also importantly, uncover the undiagnosed patients. OPC quality improvement (QI) programme: (https://www.primescholars.com/articles/strategies-that-promote-sustainability-in-quality-improvement-activities-for-chronic-disease-management-in-healthcare-se-100520.html) Volv, Sanofi and OPC: collaborating for people living with disease Volv, supported by Sanofi, and leveraging the data from OPC in the UK, is creating a unique collaboration that does not stop here. Introduction The first phase of this project was to collaborate to build new types of models for two rare diseases: Fabry and Pompe. To do this, we focussed on primary health care records, i.e. the records that general practitioners use. Both diseases are difficult to diagnose for primary care clinicians, and as a result, remain underdiagnosed. For Pompe disease in the UK, it is estimated that 50% of people with the disease are not being diagnosed, leading to a longer delay until they eventually do get diagnosed. This data is managed by Optimum Patient Care, which provides de-identified data, of around 8.5 million patient records, for research purposes. Data security and protection are paramount. This means that the data remains anonymous and secure during the disease model development process. The data complies with: GDPR/ DPA 2018 compliant Secured EHR data extraction Data is de-identified (no PID) Data is pseudonymised SHA256 Secure data encryption AES256 Secure data transfer via HSCN NHS DSP Toolkit (ref: 8HR5) Non-identifiable data is contributed to OPCCRD for ethically approved research NHS IHRA REC (ref: 20/EM/0148) Phase 1: Learn an algorithm/model for the diseases and validate with expert clinicians The first phase of the inTrigue methodology involved an iterative process of finding a way to determine what makes patients with Fabry and Pompe disease stand out from all other patients. We used a combination of data science (or AI) approaches to get to a list of patients that plausibly have a disease. Within this phase, crucially and differentiatingly, we also needed to validate whether the approach has worked by checking the inTrigue results with an expert clinician. We did this with a consultant in a specialist Fabry and Pompe department in a UK teaching hospital. The results of this evaluation can be seen in the results section. Once the clinician’s validation was complete, we then take those inputs and optimise the algorithm, which will again boost the performance. Once this is done, we are ready to move to Phase 2. Phase 2: Clinical follow-up on plausible patients, more accurately and earlier In this second phase, the algorithm is applied to the data, and clinicians are asked if they want to participate in the model deployment programme. The clinicians need to give their consent to be part of this quality improvement programme. Several QI programmes are already in place and if they agree, they can then check to see if any of the patients in their practice are at risk of these diseases. This is done through the remote installation of reports in the GP system. We can then monitor to see if there is an improvement in terms of quality of clinical care. More results on this aspect of the deployment of the models will be published at a later stage, but the optimisation steps post clinician validation shows significant improvement on these results presented here. Later phases After this programme, consideration is being given to deploying the models more widely by embedding them into GP systems nationwide. Initial metrics on model performance Model performance: Fabry disease in UK Task Use model learned via Algorithm SLSL to find undiagnosed FD patients in OPCRD EHR database GP-EHR-DB-UK (18M patients). Evaluation procedure Request that FD specialist practicing in UK review EHRs of top 50 candidate patients (candidates have predicted probabilities exceeding FD threshold FD). Evaluation outcome Results are very promising showing that out of 50 patients the top 25 have a precision of 88%, and when the total 50 patients are considered the precision remains high at 76% using the precision@k metric. Model performance: Pompe disease in UK Task Use model learned via Algorithm SLSL to find undiagnosed PD patients in OPCRD EHR database GP-EHR-DB-UK (18M patients). Evaluation procedure Request that PD specialist practicing in UK review
White Paper: The Path to Rare Disease Clinical Trial Innovation
By Volv Global SA and WODC EU contributors Executive Summary For decades, the pharmaceutical industry has faced the same recurring problems with clinical development: the struggle to fully recruit and retain enough patients, meet target timelines, and have trials conclude on time. Certainly, the industry does overestimate its ability to recruit, but a bigger issue is that study designs and protocol development seemingly fail to truly reflect patients’ lives, or account for the reality in the clinic. In fact, data shows the probability of success for any clinical development effort is 6.2% for orphan drug trials, compared with 13.8% overall, which translates to a 93.8% failure rate for orphan drug development efforts. Given the often progressive and irreversible nature of rare diseases, there is a need to increase efforts to find those undiagnosed patients, diagnose them earlier, and bring them into the frame when developing new treatment options. To achieve this, collectively as an industry, we must do more research into the rare disease patient population to characterise and better understand both the already diagnosed and the undiagnosed. We need this deeper understanding before deciding on the best clinical development strategy, finalising clinical trial design, and starting the enrolment of the patient population in a clinical study. To do that, clinical researchers and drug developers need to include much more knowledge and understanding of those people who are unknowingly living with the disease in the design of clinical development plans and study protocols. To find those people, there is a need to consult more extensively on the design of protocols, not just with the key opinion leaders, but also with physicians that are typically seeing and treating larger numbers of patients. One crucial factor with rare diseases is that the diagnostic journey is arduous and lengthy, often with many patients not being correctly diagnosed. As an example, a study found that 58% of Ehlers-Danlos syndrome (EDS) patients consulted more than five doctors, and 20% consulted more than 20[i]. So, when designing and recruiting for clinical trials, drug developers must first learn where the “as yet undiagnosed patients” are “hidden” – in other words, where they may be in the healthcare system, and which specialists they are seeing. It is those specialisms that need to be brought along in the diagnostic journey, so they can learn to identify rare disease patients within their practice. This is very well illustrated in the case of acute hepatic porphyria (AHP), where the view is that patients reside in the gastroenterology world, but, in fact, an even larger group is residing in other specialties. Another example is cited in Chapter 2. With novel approaches, such as the use of Machine Learning (ML), we can now highlight people who are not yet diagnosed as patients but are likely to be living with a disease, for their clinicians’ attention. Subtle indicators are derived from health care records by using ML, which would be difficult or nigh impossible for a doctor to recognise amidst the wealth of data already in front of them. Conducting thorough natural history studies of patients living with disease, but also including those wider populations of people suspected of living with disease but currently undiagnosed, can help to uncover sentinel events or detectable physiologic changes that are key predictors of disease progression or that are clinically important. These can provide an understanding of which subgroups of people living with the disease might benefit from a drug in development and should therefore be targeted for inclusion in the clinical trial. And, importantly, clinical researchers need to scrutinise the data and adopt insights gained by using ML models which will enable better clinical development strategy, design, and patient stratification. First, though, we need to understand the barriers and misconceptions about the art of the possible and address those directly. This paper explores the changing expectations of the regulators, the challenges the health industry continues to face, and the ways in which we can rethink the entire clinical development process – from development strategy to protocol design, to patient identification and recruitment – to achieve real breakthroughs in rare disease research and development. Chapter 2: Misconceptions and industry challenges The path to rare disease innovation begins with a better understanding of the complexity of each disease – a point well understood by the health authorities. As the US Federal Food and Drug Administration (FDA) has identified in its guidance on natural history studies, rare diseases can have substantial genotypic and/or phenotypic heterogeneity. As such, the natural history of each subtype, if it exists at all, may be poorly understood or inadequately characterised. Above all, a typical natural history study certainly does not include those people living with the disease that – in rare – often remain undiagnosed. There are two levels of undiagnosed patients: those who have had no diagnosis at all and have therefore not been matched with a disease, and those who have had a partial diagnosis but whose symptoms are not well characterised and therefore do not belong in a defined subgroup. As researchers learn more about rare diseases, they are starting to understand that different phenotypes may present with the involvement of different organ systems, with varying degrees of severity or rate of deterioration. As noted earlier, ML can help to elicit subtle indicators from electronic health records or claims data. However, during panel debates at recent orphan drug conferences, there seemed a strong bias towards the use of registries for research and patient characterisation, and there were clear misconceptions from both industry and regulators about the usability of primary care electronic medical records (or electronic claims data) for the purpose of early disease detection, be it in a traditional manner, or ML assisted. The limitations of registries While disease registries have a clear purpose, they are constrained by the fact that they tend only to contain data on patients that are known to have a given disease. By focusing only on rare disease data that already exists in patient registries, research