Use machine learning-driven analytics to help identify promising patient subgroups, potentially preserving your investment and ensuring valuable therapies reach patients.
Many drugs being developed today focus on rare and genetic diseases, which often have very small populations, limited diagnostics, and no common treatment paths. This makes conventional recruiting methods ineffective, which can add months of even years to the recruiting process.
However, utilization of artificial intelligence and machine learning (AI/ML) can help sponsors accelerate the search process by finding undiagnosed and underdiagnosed patients with risk factors that mimic those who have been diagnosed. Combining these risk factors with effective genetic testing and counseling can help sponsors find and successfully recruit patients faster, cutting months from the trial life cycle. This paper explores how AI/ML technology and genetic testing can transform recruiting for rare disease research and give sponsors an edge in attracting participants to their trials.
The rare disease landscape Recruiting has always been one of the most difficult elements of clinical research. Even when a disease has millions of diagnosed patients and a well-established treatment path, finding patients who meet inclusion/exclusion criteria and convincing them to participate in a study is difficult. In rare disease research, that challenge is amplified. Rare diseases only affect a very small percentage of the population. The US Food and Drug Administration defines a disease as rare if less than 200,000 people in the US are affected (less than 0.06%) . The European Commission defines them as diseases that affect no more than 1 person in 2,000. Of the roughly 7000+ rare disease currently identified, it is estimated that roughly 80% are due to genetic causes; and 90% lack FDA approved treatments or therapies.
There is huge demand for treatments to address these unmet medical needs but finding study participants in order to run the trials is a constant challenge for sponsors. These diseases have small, dispersed populations with few specialists dedicated to the conditions, and most patients go years without getting an accurate diagnosis. That means study teams can go months before finding a single patient who fits the study criteria.
To solve this problem, life sciences companies need more targeted methods for finding patients, confirming diagnoses, and engaging them in conversations about the value of clinical study participation.
Use machine learning-driven analytics to help identify promising patient subgroups, potentially preserving your investment and ensuring valuable therapies reach patients.
Getting the right outcomes from your clinical trials is all about the data and insights they provide. Biostatistics in clinical trials isn’t just a necessity, it can be a real competitive advantage.
Improve the performance of your clinical trials with the power of the IQVIA CORE.
Change the model of clinical research by integrating data, expertise, analytics and technology from study design through execution to power better decisions.
Discover unrealized connections and manage your product across the entire lifecycle, from research and development, compliance to launch and commercialization.
Explore our end-to-end, full service clinical development capabilities including Therapeutics expertise, Development Planning, Phase I early clinical development, Phase IIb/III and Phase IV Trials, Regulatory Submission and Post-Launch Studies.