Volv Global Poster: Early prediction of ARDS in community-acquired pneumonia patients using machine learning
Presenting new research on whether a machine learning model can flag which patients with CAP are most likely to progr...
Many patients show no signs a clinician would currently recognise, even as a disease develops. By the time symptoms appear or a diagnosis is confirmed, the disease may already be established and the window for changing its course narrower. This gap is wider for some conditions than others, particularly those that develop silently or fall outside routine screening.
inAdvance moves that point earlier. By surfacing who is likely to see their condition progress or need intervention sooner, it widens the window in which treatment can change the course of a disease.
Why early detection matters
Diagnosis usually follows symptoms, which usually follow disease progression, so treatment often starts only once a disease is established and harder to change. Patients diagnosed early tend to have better outcomes, fewer complications and a higher quality of life; those diagnosed late carry a cost that rarely shows up as a missed diagnosis, because clinicians can only act on what they can see.
Clinicians and health systems want to find every patient while treatment can still change a disease's course, wherever they enter care. inAdvance's approach has been shown to flag one rare neuroendocrine condition five to seven years earlier than usual diagnosis.
Market access and HTA teams want every avoided complication and year of stable health reflected in the price and funding a treatment secures. inAdvance predicts each patient's trajectory. One example, validated across more than 340,000 patients, gave a patient-level basis to credit the burden it avoids.
Trial teams and regulators want predictive models that hold up under independent scrutiny before they change enrolment or submission decisions. inAdvance's model flags predicted clinical outcomes with accuracy to clinicians. This has been confirmed across two independent patient cohorts.
Where inAdvance creates value
Detecting candidates earlier, before conventional treatment begins, so recruitment starts on a real population and de-risks the trial ahead.
Surfacing the early-stage population from real-world data, building an evidenced case for earlier diagnosis.
Delivering an earlier, evidence-based signal that connects detection to the outcomes clinicians aim to improve.
Finding patients before conventional symptoms appear, helping plan where earlier intervention will matter most.
How inAdvance works
inAdvance applies Volv Global’s proprietary machine learning to population-scale real-world data, including electronic health records, claims data and other clinical sources, detecting subtle patterns that signal a disease developing before conventional symptoms appear.
Drawing on structured and unstructured records to build a fuller picture of a person’s health, it flags indicators that conventional diagnostics can miss, surfacing the signal while the decision stays with the clinician.
What people ask
A: inAdvance applies Volv Global's proprietary machine learning to population-scale real-world data, including biomarkers, electronic health records and other clinical data. It surfaces subtle patterns that signal a disease developing before conventional symptoms appear, so intervention can begin sooner.
A: Earlier detection gives clinicians and patients more time to act. Treatment started before a disease is established can change its course, and clinical trials that recruit from an earlier-stage population can test whether intervention works before symptoms take hold.
A: inAdvance supports clinical development teams estimating the scale of an early-stage population, HEOR and market access teams building the case for earlier diagnosis, medical affairs teams connecting earlier detection to outcomes, and commercial teams pinpointing where earlier intervention delivers the most value, often alongside inCare to find patients who are already eligible for treatment.
A: Accuracy depends on the disease and the data available. Our prognostic models are held to that same bar: one, validated across more than 340,000 patients, held up under independent clinician review across two separate patient cohorts.
A: Volv Global does not hold patient data. All work is conducted through trusted data partners operating under the privacy and regulatory frameworks that apply in each market. inAdvance surfaces and prioritises patients for clinical attention; it does not diagnose, prescribe, or replace clinical judgement.
Shaping the future today
Presenting new research on whether a machine learning model can flag which patients with CAP are most likely to progr...
Volv Global at ERS Congress 2026, presenting new research in collaboration with CSL Behring: Can We Catch ARDS Before...
AI Innovation in Real-World Evidence & Data Analytics Volv Global has been selected as a finalist in the 2026 Fie...
Volv Global applied machine learning to 24M UK primary care records, surfacing ~1,200 undiagnosed GEP-NET patients, 5...
GEP-NETs are among the most diagnostically elusive tumours in oncology. This case study shows how machine learning ap...
ASCO 2026 produced landmark oncology data. The question no one asked from the podium: can clinical infrastructure get...
Drive For Change white paper: three paradigm shifts to unlock orphan drug development
Approximately 95% of rare diseases have no approved treatment. Drive For Change identifies three structural paradigms...
Machine learning applied to 3,549 confirmed Pompe disease patients – the largest machine learning study of the diseas...
New research demonstrates that machine learning can map clinician-defined endpoints to real-world claims data in Pomp...
Explore Volv Global’s ISPOR 2026 research with Sanofi on Pompe disease, based on use of machine learning-driven endpo...
In Inflammatory Bowel Disease (IBD), steroids are considered a routine treatment, but repeated steroid exposure is a ...