inTrigue
Real world evidence combined with artificial intelligence.
Learning from patients to help other patients to be diagnosed and treated sooner
inTrigue
Real world evidence combined with artificial intelligence.
Learning from patients to help other patients to be diagnosed and treated sooner
AI & Data Science
Volv’s approach is unique and provides state of the art, performance-defining cohorts more accurately.
Volv's data science team are specialists at using real world data, both structured and unstructured, to build robust predictive models for better patient outcomes
Model external medical knowledge
Volv models the semantics of target rare diseases and their symptoms and comorbidities via representation learning with large medical corpora to render a highly dimensional computational model.
Build robust predictive models with no labels
Volv uses combinations of unsupervised and lightly supervised machine learning methods in a highly dimensional feature space, which would ordinarily require 1,000s of labels to deliver the same level of accuracy. Volv can do this with no labels at all.
Validated prevalence
Throughout the inTrigue process we maintain the ability to get external validation of our results and methods. Specialist clinicians are involved in the assessment of the patients being flagged as at risk. This delivers empirical and validated prevalence results.
Novel Biomarker Discovery
inTrigue learns new things about the disease including new symptoms, comorbidities, natural history. It creates new predictive biomarkers that can be cognitive, digital and physical.
Clinically Interpretable Models
Volv's machine learning algorithms, with thousands of features, are impossible for humans to understand. It is desirable to construct different prediction models which are both accurate and human interpretable, so that clinicians can understand the basis for the recommendations of decision-support systems.
Transfer learn and deploy models in diverse healthcare systems
Volv has developed transfer learning techniques, which adapts the models in different data sets so that they can be deployed and maintained in multiple, heterogenous settings.
