To fight rare diseases, win the data battle first

Innovation is the key to evolution. In the pharmaceutical space, brilliant advancements have occurred with drugs with large population pools. Those successes have given pharma companies the building blocks needed to focus more on rare diseases and orphan drugs – treatments that, by definition, do not have a large community of potential users. Here is where artificial intelligence (AI) can help in the rare disease race.

The numbers are sobering

This focus on rare diseases does not come a moment too soon; the US Food and Drug Administration (FDA) says there are more than 7,000 rare diseases affecting people in the United States right now, and most do not have treatments.¹ Worldwide, the number is a staggering 400,000,000.² Researchers say just 5% of the rare diseases in the US have a drug approved by the FDA.³

The success of a drug provides the resources to support others. However, a rare treatment works very differently than the regular drug development process. They often carry significant production costs and, most importantly, there is a precious window of time to make that drug commercially viable.

Post-trial pain

The pain points that drugs face during the trial phase are already known: finding the suitable patients to accept and those to exclude. This can be more challenging with the smaller patient populations in rare diseases. But the struggle doesn’t end when the trial does. Instead, the focus is on what comes next: the drug has just hit the market, and the goal is to keep it viable. This looks to be one of the most significant focal points for pharma companies in 2024. 

Data is the key to rare treatment success

The key to earning this type of success in rare diseases is data. There must be clear information showing that the drug is working. Consider this: traditional drugs with a large patient pool will carry a relatively lower cost as the expense is spread out. It’s the opposite with rare diseases; these drugs have a high cost and a low patient pool. It is imperative to adopt a data-first approach to close that critical time gap in finding new prescriptions. This takes on renewed importance as we see more “miracle drugs” in the current pharma development pipeline.

So, what will this data-first approach look like? Well, if looking for patients, what they’re looking for in a treatment needs to be known. First, those suffering from the ailment be recruited and then their adherence to the treatment closely monitored. Again, with such a small window of opportunity, every data point becomes more valuable. The continued viability of the drug requires discipline with data quality, cleansing, standardisation, and visualisation. 

From a practical standpoint, gathering data on one drug can help pave the way for future efforts, a promising thought for those suffering from lifelong diseases for which there is no cure. As Janet Mifsud and Noel Cranswick put it in a 2022 report, “Such mechanistic studies can lead to better and more robust models of disease and, eventually, successful approaches to treatment at a clinical level.”²

Finding the right practitioners, too

However, there is a second consideration in this time-sensitive task. A pharma company must also find physicians who will prescribe these medications and add their patients to the new brand. Due to the high expense of marketing and promotion through different channels, getting physicians to accept a brand may be cost-prohibitive. Adopting a data-first mindset here can help. Accurate and timely information on prescribers’ preferences for interaction must be kept, especially when dealing with new-to-market offerings.

Trust and security, always

And, of course, this wealth of data needs to be secured and restricted to its proper use. All regulations must be adhered to. Rules are changed or added consistently. There must be a data management system in play that not only ingests, collates, and serves that information, but is linked to the regulations in the industry – ensuring compliance, trust, and transparency.

The takeaway

Data takes on a special urgency when working with rare diseases and orphan drugs. Making sure these rare treatments remain commercially viable isn’t just an effort made by the manufacturers; it’s one that’s made so the people suffering with these debilitating conditions can continue to have an option for relief. Data may be at the heart of everything, but the goal will always be to create better patient outcomes.