CASE STUDY
How Telisina used AI to identify
ideal clinical trial sites.
This case study illustrates how artificial intelligence and machine learning can help drive site identification and activation in clinical trials for a rare genetic disease. It also underscores how fundamental data strategy is in enabling a data-driven, evidence-based approach to clinical trial site identification, leading to improved efficiency, risk mitigation, and success rates.
CATEGORY
Advanced Analytics/AI
Clinical Trials
CLIENT TYPE
BioPharma
IMPACT
20+
Clinical Trial Sites
Defined and Identified
IMPACT
45+
Principal Investigator
Candidates
THE STORY
Accelerating rare disease clinical trial site selection
A BioPharma company wanted to speed up and reduce the cost of clinical trial site selection amid the COVID-19 pandemic. They turned to data and AI to automate and streamline their site selection process.
Our client was close to a breakthrough with a potential gene therapy for a rare genetic disease. However, they faced a major challenge: the difficult process of activating sites for clinical trials, especially during the early stages of the COVID-19 pandemic. Because the disease was rare and the pandemic was ongoing, there were few patients available, and finding suitable trial sites was like finding a needle in a haystack. Traditional strategies weren’t enough to handle these complexities, so we needed a new, innovative solution.
THE GOAL
Identify the top 20 clinical sites locations
This project aimed to define and implement a data-centric and analytic approach to clinical trial site selection.
THE SOLUTION
Integrating AI and data strategy for enhanced results
Custom AI/ML algorithms transform clinical trial site activation. AI-driven profiling and predictive modeling revolutionize decision-making.
This was the perfect opportunity to integrate a data-centric strategy. Recognizing the potential of data analytics and AI, we took on this project with the goal of revolutionizing the site identification process for clinical trials in rare genetic diseases.
We started by collecting data on patient populations, clinical trial sites, and the COVID-19 pandemic. We then used this data to develop a predictive model that could identify potential trial sites. This model was able to identify sites that were more likely to have patients who were eligible for the trial and that were less likely to be affected by the pandemic.
Using this model, we were able to identify a network of trial sites in a fraction of the time it would have taken using traditional methods. This allowed our client to begin their clinical trials much sooner than they would have been able to otherwise.
THE RESULTS
Transformed Clinical Trial Process with Data-Driven Insights.
The data-driven approach resulted in significant improvements in the clinical trial process. It not only streamlined the site selection processes but also provided valuable insights for future trials.
- Over 20 ideal clinical trial site locations were identified. These locations were selected based on a number of factors, including the number of patients with the disease, the availability of healthcare providers, and their affiliated institutions
- Over 45 high-value investigator candidates were mapped and identified. These candidates were selected based on their expertise in the rare disease, their experience in clinical trials, and existing patients with the disease state.
- Results were provided in less than 6 weeks. The process of identifying ideal clinical trial site locations and mapping and identifying high-value investigator candidates was completed in less than 6 weeks.
20+
Ideal Clinical Trial
Site Locations Identified
6
Number of Weeks to
Deliver Results
45+
High-value Investigator
Candidates Identified