Transforming Rare Disease Treatment: The Impact of Data Technology and Real-World Data

Rare diseases affect fewer than 200,000 people in the U.S., approximately 30 million individuals. Sadly, 3 out of 10 children with a rare disease won’t live to see their fifth birthday, yet the path to diagnosis and treatment is costly and uncertain. The uncertainty has intensified recently as funding cuts are impacting those who rely on government support for their research. 

There is good news, however; the promise of technology in the form of data intelligence platforms and high-fidelity real-world data (RWD), designed specifically for healthcare and embedded with clinical context are transforming rare disease discovery and new treatments and therapies.

Precision through data

Researching rare diseases presents unique challenges. Patient populations are small and geographically dispersed, symptoms are often non-specific, and there is little standardization in how these conditions are coded or documented. Many patients wait years for an accurate diagnosis, with treatment focused on symptoms and not disease, leading to misdiagnoses and fragmented care.

Data intelligence platforms with AI and machine learning algorithms can uncover patterns in massive, complex datasets, especially vital for rare diseases where patients may present differently with different symptoms and comorbidities. Today’s technology can identify patients, map their disease progression and care journey and also identify the physicians and other providers who care for those with rare diseases as well as those that may be at risk. 

For example, pattern recognition can identify patients with unusual diagnostic journeys and detect subtle symptom clusters which then shortens the time spent on finding a diagnosis. Ultimately, this increases the number of patients who may be eligible for clinical trials and targeted therapies. Because many rare diseases progress silently, AI and ML-powered longitudinal RWD analysis helps track patient progression based on subtle changes in lab values, medication shifts or hospitalization patterns leading to earlier and more precise interventions.

In order to take advantage of powerful AI and machine learning tools, it is critical that the data being used is both high quality and interoperable. Healthcare data is highly complex, and as a result, the quality is often inconsistent, requiring significant investments in data cleaning and preparation. Even quality validation can be inconsistent or inaccurate without correcting for missing or incomplete data.

It has long been the belief that researchers needed more data, however that is not always the case, and for rare diseases in particular, precision is key. Data that embeds clinical specificity or therapeutic context allows researchers to focus their questions more precisely. Context-rich data can power synthetic control arms or digital twins — tools that are essential in rare diseases because small patient numbers and traditional placebo groups are difficult to achieve. 

Breaking down data silos

Another significant barrier is fragmented data. The industry must work to break down data silos and combine data sources from across different health systems, electronic health records, claims, registries and biobanks. Once data can be brought together, it must be cleaned, standardized, harmonized, and mapped to common models, like OMOP, to ensure quality and comparability. Conformed and enriched data can then be linked to create unified patient journeys and uncover hidden meaning in complex data. 

True interoperability is especially critical in the world of rare diseases. By combining and linking, or bridging data, raw data is turned into high-value information that enables researchers to accelerate their clinical trial recruitment activities, uncover new discoveries and improve outcomes. 

Connecting the dots 

To overcome hurdles within the rare disease space, using data intelligence technology and context embedded RWD can offer more insights while accelerating timelines and maintaining tighter control over costs. This is especially important in an era where time and funding are limited. Technology that offers tools that conform, de-identify, link and aggregate data and data science tools like AI, machine learning and advanced analytics, can help those researching rare diseases overcome the hurdles they face in discovery and development. 

By leveraging RWD, biotech and life sciences companies can overcome the traditional challenges of patient identification, clinical trial recruitment, and regulatory approval. Integrating AI, machine learning and standardized data frameworks enables Life Sciences companies to bridge existing gaps, ensuring that more patients receive timely diagnoses and have access to life-changing therapies.

Photo: ipopba, Getty Images

Jeff McDonald, CEO and Co-Founder of Kythera Labs, is a serial entrepreneur and growth leader who successfully envisioned and developed analytical products and platform technologies to empower growth. He has more than 20 years of experience in the healthcare industry, combining his technology, innovation, and analytic product development experience with his conviction in the power of teamwork to help organizations succeed.

This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.