Press Release
Épalinges, Switzerland, June 1st, 2026
Machine Learning Maps and Discovers Clinical Endpoints in Pompe Disease Using Real-World Data
In the largest machine learning study of Pompe disease to date, Volv Global demonstrates that clinician-defined endpoints can be tracked and novel disease features discovered in US claims data across 3,549 patients
In brief
- Real-world claims data can serve as a reliable evidence foundation for Pompe disease, with literature-based symptoms confirmed as both identifiable and measurable within routine healthcare data.
- Clinician-defined clinical trial endpoints can be mapped to and monitored within routine claims data, strengthening the real-world evidence base for regulatory and HTA purposes.
- Machine learning can discover clinically meaningful disease features in Pompe disease that no pre-specified framework had defined, informing the design of future studies and trials.
New research presented at ISPOR Global 2026 in Philadelphia demonstrates that machine learning can map clinician-defined endpoints to real-world claims data in Pompe disease and surface disease manifestations beyond pre-specified frameworks. The study, conducted by Volv Global in collaboration with Sanofi, was conducted in a US administrative claims database.
Pompe disease is a rare, chronically debilitating metabolic disorder in which enzyme replacement therapy has now extended patient survival, bringing new long-term manifestations not captured by endpoints established earlier in its treatment history. Many clinically meaningful endpoints do not map to routine healthcare codes, leaving a gap between what patients experience and what the evidence base reflects – with consequences for disease monitoring, HTA submissions, and trial design.
The research addresses that gap through three sequenced methodological contributions:
- The prevalence of literature-based disease symptoms was compared between the Pompe patient cohort and a matched control population without Pompe disease, confirming that the correct patients are represented in the claims data and that these symptoms are reliably measurable within it – a foundational validation step underpinning all subsequent analyses.
- Machine learning models mapped 46 of 67 pre-specified clinical endpoints to diagnosis, procedure, and treatment codes in claims data, demonstrating that endpoints designed for clinical trials can be reliably tracked in routine healthcare data.
- An unsupervised discovery analysis identified novel cardiovascular, respiratory, and systemic features highly prevalent in the Pompe cohort but absent from any pre-specified framework, confirmed against the same control population and offering candidates for endpoint design in future natural history studies and trials.
Volv Global’s proprietary machine learning methodology was applied across all three components, providing a reproducible framework applicable across rare diseases where treatment advances have outpaced existing evidence frameworks.
“Rare disease evidence frameworks are often frozen at the moment of first approval,” said Christopher Rudolf, CEO and Founder of Volv Global. “This research demonstrates that machine learning can systematically close that gap – confirming what clinicians know, independently discovering what the data reveals, and making this a tractable problem for any team building an evidence strategy in a disease where treatment has changed the clinical picture. This is precisely the work Volv Global exists to do.”
Note to editors
Patients were identified in a US administrative claims database using confirmed diagnosis and/or treatment records. The control population comprised patients with mimic disease codes and no Pompe disease history in the preceding seven years. Of 67 pre-specified clinical endpoints, 46 were successfully mapped to claims codes; the 21 unmapped endpoints reflect the limits of administrative claims data coding, and are themselves informative for teams assessing the feasibility of claims-based real-world evidence strategies. All findings are based on retrospective analysis; prospective validation has not been conducted and is not claimed. Research conducted in collaboration with Sanofi.
Links
- Release on PRWeb.
- Find the full abstract, here.
- Download the poster: Real-World Endpoint Mapping and Identification of Evolving Phenotypes of Pompe Disease using Machine
- Case Study: Detecting signs of Fabry and Pompe disease in UK clinical data
- Biopôle
- Swiss Biotech – Volv Global Featured in Swiss Biotech News
- Samedan
- Rareatives
About Volv Global
Volv Global is a healthcare AI company founded in 2017 and headquartered in Épalinges, Switzerland. Its mission is to generate new knowledge at speed, close the diagnostic gap, as well as other gaps in the care pathway, to improve patient outcomes. Volv Global works across conditions where patients are difficult to identify, where the window for effective treatment is narrow, and where understanding which patients will progress or need therapy beyond standard care can meaningfully change outcomes. It is a trusted partner to leading pharmaceutical organisations across the USA and Europe, with capabilities deployed in live clinical programmes.
Applying a proprietary machine learning methodology to population-scale real-world data – accessed through trusted data partners covering more than 400 million patients – Volv Global generates disease intelligence that enables pharmaceutical teams to de-risk clinical programmes, identify and stratify patient populations with greater precision, and build stronger real-world evidence. For clinicians, Volv Global’s insights are designed to surface actionable signals within existing care pathways. For patients, they translate into earlier diagnosis, better-informed treatment decisions, and a faster path through a diagnostic system that too often leaves difficult-to-diagnose diseases unrecognised for years.
Volv Global’s solutions each address a distinct clinical question across the patient journey, and are configured to the client’s specific research question, disease area, and healthcare setting. Volv Global does not hold patient data; all work is conducted within the governed environments operating under applicable privacy and regulatory frameworks.
Key Questions About Volv’s Pompe Disease Research
What is the significance of the results achieved by Volv?
The research does a few things that haven’t been done together before in rare disease. It starts by confirming that what clinicians expect in Pompe patients – the recognised symptoms from the literature – actually shows up in routine claims data. If you can’t find the disease in the data, nothing else holds, so that’s the foundation.
From there, we mapped 46 of 67 established clinical trial endpoints onto codes available in claims data. That matters because it means outcomes designed for controlled trials can be monitored in routine healthcare data years after approval – which has real implications for real-world evidence and HTAs.
The more interesting part, to my mind, is what came next. We ran a data-driven, unsupervised discovery pass – no pre-specified hypotheses – and found novel cardiovascular, respiratory, and systemic features that were highly prevalent in the Pompe cohort but absent from any existing endpoint framework. The field hadn’t defined them, let alone measured them. When we validated them against a matched control population, they held up.
Together, that gives you something you rarely see: a complete, repeatable framework that both validates what you know and finds what you don’t – directly relevant to natural history studies, HTA submissions, and the next generation of trial design.
Do the results demonstrate Volv Global’s capabilities in the field of rare diseases?
Pompe involves a small patient population, limited natural history data, and real diagnostic complexity. The fact that we confirmed a cohort of 3,549 patients – the largest study of its kind – and ran a full analytical pipeline from cohort validation through to open-ended phenotype and clinical trial endpoint discovery says something about what’s possible at this scale.
It’s not the first time we’ve taken this approach. We’ve applied comparable methods in Alpha-1 antitrypsin deficiency, hypertrophic cardiomyopathy, Fabry disease, and others, across healthcare systems in the US and Europe. The goal is the same in each case: generate disease intelligence that pharmaceutical teams can act on – for patient identification, endpoint design, real-world evidence, and trial planning.
Will the endpoints discovered and mapped be used to detect and treat Pompe disease? If yes, how many people around the world suffer from it?
To be precise: the endpoints we’ve mapped and the features we’ve discovered aren’t diagnostic tools or treatments. They are evidence building blocks.
The mapped endpoints show which clinical trial outcomes can be tracked in routine healthcare data after approval – useful for strengthening the real-world evidence base with regulators and payers. The newly discovered features are candidates for future natural history studies and trial designs; they could change how the next round of Pompe research measures outcomes and treatment response.
More importantly, because enzyme replacement therapy (ERT) extends survival, patients are now living long enough to develop complications that earlier cohorts never reached. These emerging unmet needs can be captured in real-world data and used to develop new clinical trial endpoints.
On prevalence: Pompe affects roughly 1 in 40,000 people – around 5,000–10,000 patients in the US and somewhere between 150,000 and 250,000 globally, though estimates vary by source. As with most rare diseases, the diagnosed population is almost certainly smaller than the actual one. Closing that gap is part of what this kind of research is designed to do.
Will the data be sold to pharmaceutical companies, research centres, or hospitals?
We don’t hold patient data, and we don’t sell it. All our research is conducted within the governed environments of our data partners – in this case, the Komodo Health US administrative claims database – under applicable privacy frameworks, including GDPR and HIPAA.
What we produce is disease intelligence: the models, endpoint frameworks, phenotype profiles, and real-world evidence outputs derived from the analysis. These are developed with each partner, tailored to their disease, their data environment, and what they’re trying to answer. The underlying patient records never leave the governed environment. That’s not a constraint we work around – it’s how we’ve built the business from the start.
For more information, please contact:
Le Vin Chin
Marketing & Communications Director
[email protected]
Volv Global SA
Route de la Corniche 3B, 1066 Épalinges, Switzerland
