Contrary to what the name may imply, “rare diseases” impact millions of people. The Orphan Drug Act (ODA) defines rare or “orphan” diseases as conditions that affect fewer than 200,000 people in the United States (keeping in mind that the actual footprint for a specific condition may be far larger than the numbers reveal, as it takes an average of 4.8 years for rare disease patients to receive an accurate diagnosis).
While individual conditions may be comparatively rare, the total number of those affected by this category of maladies is far from inconsequential. According to the National Institutes of Health, around 1 in 10 Americans are affected by a rare disease, 85% to 90% of which are considered “serious or life-threatening.” Although the industry has made tremendous progress in creating new drugs for rare diseases, thanks in large part to measures like the ODA, which incentivizes orphan drug development, 95% of rare afflictions still do not have an approved treatment option.
Developing new drugs of any kind is a long and expensive process. However, orphan drugs come with an additional set of challenges. These diseases are often biologically complex and include many variations or subtypes resulting in different clinical manifestations and disease progressions. To complicate things further, data surrounding rare diseases is limited and spans the drug development lifecycle, from grants and conferences and research papers in the initial stages to patents and clinical trials and patents in the latter stages.
The good news is that a new breed of AI-powered data analytics platforms built for the pharmaceutical industry, such as Signals Analytics, efficiently connect researchers with data-driven insights culled from numerous external sources, which can optimize decision-making, mitigate the risk of research investments and hasten the development of new rare drug treatments.
Due to the high cost and long development cycles of drug development, pharmaceutical companies must be extremely deliberate in how they invest their resources — this is true even under the best of circumstances, but particularly apt when it comes to orphan drug research, which on average takes 2.3 years longer to develop than other medicines.
At the most fundamental level, this means taking a data-driven approach to prioritize areas of focus by identifying promising development opportunities (e.g., pinpointing ascendant molecular targets and modalities, or new academic research) and uncovering competitive strategies (e.g., identifying threats and comparing pipeline performance against competitors).
This is no simple task considering the sprawling expanse of external data sources including research papers, grants, clinical trials, patents, conferences and more. This is where AI-powered analytics can make a huge difference.
Using Natural Language Processing (NLP), these platforms are able to connect data from a wide variety of sources and automatically classify them with data taxonomies built by subject matter experts to the specificity of each unique industry and category. Machine Learning (ML) can identify patterns and extract the context which pharmaceutical companies can then leverage to make strategic decisions across the drug development lifecycle. These advanced analytics platforms allow companies to easily arrive at actionable insights without making a huge investment in a massive in-house analytics function.
These forms of AI-powered insights can be invaluable in focusing research efforts for rare diseases. Case in point: fallopian tube cancer (also known as “tubal cancer”) is a rare form of cancer that affects only a few hundred patients in the US. A few clicks in the Signals Analytics’ platform, recently enhanced with expanded coverage of rare diseases, and you can detect early signals of innovation, such as:
An increased volume in early R&D areas for fallopian tube cancer
A YoY 115% growth in research paper activity in the last year
Steady increasing trends in IP activity across large Pharma
(You can download more specific insights regarding tubular cancer research by clicking here.)
Readily available insights like these make it easy for pharmaceutical companies to identify where academic innovation is occurring, surface early signals of innovation across the rare disease space, identify new and promising areas to invest in with less risk, and benchmark their rare disease assets against others in its class.
Want to learn more about how Signals Analytics can provide you with data-driven insights and accelerate your drug development activities? Schedule a meeting with one of our Solutions Consultants.