Volv Global Blog

Executive Summary

To acknowledge Rare Disease Day and the struggles facing patients with rare diseases, the World Orphan Drug Congress hosted a webinar titled, “How can AI impact industry?” The session, which explores the role of real-world evidence (RWE) to improve orphan drug development and access, brought together leaders in their field with deep knowledge of rare diseases and the importance of RWE in helping to identify the right solutions for the right patient.

During the discussion, several important and often overlooked themes were brought to the fore. The purpose of this paper is to explore these in greater depth and share the unique insights from the panel. These include the integral role of the patient in owning, managing, and deciding when, how and where to share their data. Certainly, a patient-focused approach that safeguards the individual’s privacy and ensures consent, is paramount if researchers and drug developers are to make full use of RWE to find therapeutic approaches and cures for rare diseases. In addition, the industry will need to address data sharing issues and legislative barriers and ensure they fully engage the regulators to bring therapies to patients in need. The paper provides a thoughtful and balanced discussion of these topics and aims to seed further insights as drug developers, clinical research experts, regulators, artificial intelligence specialists and, crucially, patients and their carers, seek to leverage tools such as RWE to help the millions of rare disease patients in need worldwide.

 

The journey from first symptoms to diagnosis is a long one for most patients with rare diseases. According to a survey from EURODIS, 25 per cent of patients with among the most common rare diseases waited between 5 and 30 years for a diagnosis and 40 per cent were misdiagnosed during that time.

There are many reasons why diagnosis is so challenging. One is that most physicians have limited knowledge about rare or ultra-rare diseases. Another is that as many as 60% of rare diseases present with significant heterogeneity of symptoms, making it extremely difficult to diagnose patients early enough in their disease progression.

A third barrier to diagnosis can often be attributed to the complexity of the diagnostic test currently available. For some rare conditions, deep muscle biopsies are still used for diagnosis and for some rare heart conditions, stents are often the only commercial diagnostic tool available to accurately identify a condition.

It might be said that picking out patterns to identify patients with rare diseases is a bit like distinguishing thousands of constellations of stars. Neither is within the scope of the human eye and both require extremely advanced technologies to even begin to decipher and separate patterns. Yet finding the 50 percent of undiagnosed patients with one of the approximately 7,000 rare diseases is a medical and clinical imperative.

Typically, the way clinicians diagnose patients is by taking what the broader healthcare industry knows about a disease – generally as described by key opinion leaders (KOL) – and correlating a patient’s symptoms to those definitions. The problem with this approach when it comes to rare and ultra-rare diseases is that it is subject to experiential bias. If the KOL has not observed a pattern of symptoms or the order in which those symptoms emerge differs significantly, the patient will likely remain undiagnosed.

There is so much we don’t know about rare disease, but what we do know is that there is enormous heterogeneity of symptoms – so much so that as many as 60% of rare diseases present with significant heterogeneity, according to genomics experts. Understanding this 60% variation in symptoms with rare diseases is undoubtedly the greatest challenge facing both healthcare professionals as well as the companies seeking to find and develop new treatment options. Even for those rare diseases where there are already treatments, the difficulty can be diagnosing patients early enough to limit the worst effects of the disease. For example, some symptoms may not be flagged as significant from a clinical perspective, despite the challenges they present to the patient on their journey to diagnosis, and by the time the patient’s symptoms escalate to correlate with recognised patterns, it’s often much later in the disease’s progression, on average, six years from the onset of symptoms.

At Volv we provide the insights on our approaches and methodology 

Quantifying Predictive Power of Features in Electronic Health Record Models – the Volv inTrigue way

When we work on complex prediction models with our inTrigue methodology, we are often asked to help clinicians and others to interpret these models by listing the patient features (attributes) which are used by the model to form its predictions. And indeed, generating a list of predictors ranked by their ‘importance’ in a model can translate to improved interpretability and clinical impact. However, there is some work that needs to be carefully considered in order to produce tooling that is derived from complex models that can provide real benefit in a clinical situation. So Rich Colbaugh and I decided to discuss this for you, our audience.

as a challenge for customers and is discussed at many conferences. As it is important to deliver real world results, we discuss here what Volv does to create interpretable models of true utility. The journey from complex modelling to interpretable models is however not necessarily simple when dealing with real-world solutions involving highly dimensional messy data.

The Case Study Problem

This case study derives from an ongoing Volv engagement, which started in July 2017. A pharmaceutical company approached Volv Global to develop a prediction model to identify additional patients suffering from the rare disease treatable by its specialist medicine.

This pharmaceutical company faced four difficulties: the disease prevalence was one in a million of population; specialist clinicians were able to diagnose the disease with no more than 76% accuracy; only one in four patients were ever identified; and those that were identified, were done so generally after six years of misdiagnoses. To compound these four difficulties, the pharmaceutical company was unable to provide medical records for any already diagnosed patients.