inVerse - learning from aggregate data to improve outcomes
Volv has developed a way of deriving fine-grained insights and learnings from aggregate data such as summary clinical trial results. This singular ability to "unbake the cake" into its components has been productised as Volv inVerse.
Precision medicine tailors the treatment for different groups and ultimately for individuals, often using genetic or molecular profiling.
The benefits of precision medicine in terms of superior healthcare outcomes are increasingly clear. There are, however, challenges to the equitable and widespread dissemination of the tools, technologies and solutions required for precision medicine, and unfortunately, more than half of the world’s population has no access to these.
We know from host genome work that some people are much more likely to suffer severe symptoms, even in the absence of underlying health conditions. Being able to find these people through, for example, a knowledge of simple phenotypic signals that clinicians can look for or through simple testing would enable them to be treated properly at the first signs of illness.
The analysis of many types of data from many different sources is required to understand the biology linking genes to observable traits, which is a necessary first step in creating a precision medicine.
Volv has partnerships with key data partners such as Clinerion and others, to provide the reach necessary to perform analysis work across disparate data sources in a secure and compliant way.
Clinical trials are reported in aggregate
For clinical trials, reporting is done at the aggregate level for reasons of maintaining patient data security.
The detail of how each individual was present in the clinical trial is unavailable when the results are reported as aggregates, for example in grouping by sex and by age.
Volv is able to reverse this process to derive fine-grained data from the aggregate data
Volv's inVerse product take aggregate data and resolves it back to the individual patient level. It "unbakes the cake" and presents the original ingredients for inspection. Patient-level results do not identify specific individuals, as their personal data is redacted.
This powerful ability to drive individual-level learning across different aggregate data sets can deliver the necessary insights to create effective personalised treatments.
inVerse can derive understandings from research that was non-optimally conducted, which was seen originally to have failed. For example, inVerse can be used to identify characteristics of patient responders and non-responders from both successful as well as failed clinical trials. In this way, it represents a profound value-creation opportunity for pharmaceutical companies.
Future patients can potentially be triaged and managed better in a care setting without complexity. There is value for both patients and payers to stem disease progression early and effectively. Patients gain many more life years and payers can reduce the healthcare cost burden that is in continuous growth worldwide.
inVerse - Multiple Sclerosis as a case study
Volv shows how data mining clinical trials can improve outcomes for Multiple sclerosis (MS) patients, (MS is a progressive, immune-mediated disorder), by reducing disease progression through predictive models based on patient phenotypes, which can be utilised by clinicians.
