inTrigue
Volv's methodology for finding patients with difficult to diagnose and rare diseases

inTrigue is a new way of building computational models using machine learning to detect undiagnosed rare and orphan disease patients in population-scale databases such as electronic health records.

Volv has a number of products and services that together with the core predictive modelling make up the inTrigue methodology. They enrich the insights and learnings derived from the core predictive orphan disease modelling delivering further value to healthcare providers, patients, and payers alike.

inTrigue: Be ready for truly personalised medicine

Using robust proprietary technology that learns digital biomarkers for any human disease, we focus on difficult-to-diagnose conditions, where there is significant unmet need.

With inTrigue, it is possible to transform disease management and treatment at the individual patient level. Significantly earlier patient diagnosis and more accurate targeting enables innovative medical practice.

inTrigue is different

It is built using novel data science, developed over the last fifteen years, which has been designed to find very rare 'events' in complex systems. It is ideally suited for finding difficult-to-diagnose patients scarcely represented in electronic medical record systems.
It learns a model of the disease from published medical literature and does not rely on expert input or incorporate expert bias.
It builds patient finding models that comprise over 10,000 features compared to traditional AI search-based models with 10s of features.
In contrast to traditional machine learning approaches requiring 1,000s of example target disease patients to build an accurate prediction model, inTrigue does not require rare disease patients labelled with the disease to learn a patient finding model.
It builds accurate, tailored algorithms for individual country’s based on unique medical data structures and clinical diagnosis procedures to the disease in that country.
It is therefore capable of delivering powerful results globally

What inTrigue does very well

inTrigue learns robust prediction models that find undiagnosed and misdiagnosed patient cohorts for difficult to diagnose diseases with a very high accuracy.

As individual country systems and data are different, inTrigue learns the model in each country, adapting to differences in

clinical thinking
language
data structures
population variance

Unlocking how to find patients accurately in any language and in almost any available data set

How is inTrigue different?

inTrigue does not look at diagnosed patients and create simple similarity searches. It does not seek to combine existing data sets to create symptom lists or genome mutation libraries. None of these approaches work effectively, and all produce poor results with many false positives. Precision is low, when we need precision to be high.

It does not search by genotype. For many rare diseases we have worked on, we have found that gene mutations have insufficient predictive power to indicate symptom onset or severity.

inTrigue does not do simple search by collections of phenotypes. For many diseases, this approach fails to account for the differences in the way in which patients are managed in different healthcare systems, and it does not work. Stated differently, simple algorithms learnt like this in one country cannot be ported unchanged to another country.

It does not need any positive class patients (with disease) to build the disease models. Looking for undiagnosed patients is a discovery process and using other methods will not discover the hidden patients.

inTrigue does not seek to remove features that are sparse, as it can manage sparsity in the data set.

That's amazing, and it is the way to better results.

What else does inTrigue deliver?

Unrivaled Accuracy

inTrigue’s current performance has an area under curve (AUC) of 97.5%. What does that mean? It means there are almost no false positives.

This accuracy enables reliable, clear insights in the following areas:

Disease Learning

inTrigue uses a new way to learn about your disease thereby driving new insights in:

- Symptom prioritisation;
- Patient journeys;
- The reasons for current misdiagnoses;
- Understanding variability in clinical decision making, for example, between different doctors and hospitals.

InTrigue prediction models improve via machine learning on new data.

Patient Cohort Finding

InTrigue excels at cohort identification enabling precision case-finding. Start putting your real-world evidence to work and derive full value from your clinical trials. InTrigue identifies the patients that fit the cohort profile.

Prevalence Insight

Stop guessing about prevalence. InTrigue brings evidence to support your prevalence claim, and introduces confidence into payer discussions about your treatment.
Based on analysis of electronic health records in each country and finding new undetected patients, true numbers of patients in a country are uncovered, which payers want to know.

Risk Mitigation

Payers are focused today on correctly assessing the value and costs of individual medicines as a way of reducing their overall financial risk. Gaining agreement from payers is necessary, not only for unit pricing, but also to identify eligible treatment populations. Having accurate, evidence-based prevalence facilitates agreement on both points, and ensures that your payer customers derive the maximum value from their investment. This in turn builds trust in your medicines.

inTrigue enables World Class Market Access Planning

Use our precision and reliability to achieve your market access planning more effectively. Clinician adoption means improving clinical practice by helping physicians identify and treat the right patients. InTrigue high-performance prediction models are transformable into simpler models which, while still accurate, are readily-interpretable by non-experts.

Uptake with physicians shows that for companies focusing on rare diseases, the specialist diagnosing physicians become the medicine advocates, owing to the accuracy of the clinical toolsets that they can work with (and the identification of undiagnosed patients). This combination accelerates diagnosis and can reduce cost of sales significantly.

Patient satisfaction is increased as early diagnosis reduces patient frustration and increases quality of life.

inTrigue Impact on your rare disease business

By understanding more about your markets with empirical evidence derived from real-world data, inTrigue has a ripple of significant benefits through your organisation.

inTrigue Business Case

By finding more patients and finding them earlier and with greater accuracy, inTrigue helps more patients to be treated for longer. The greater accuracy also ensures that you remove risk of inappropriate treatment.

inTrigue Components

Volv inTrigue methodology, for difficult to diagnose and rare disease modelling. inTrigue is a completely new way to discover the patients that typically cannot be found.

inTrigue Volv's methodology for finding patients with difficult to diagnose and rare diseases