Platform forecasts COVID-19 trial outcomes
Australia-based Opyl has unveiled software that uses artificial intelligence (AI) to generate a ‘probability of success’ prediction of the likelihood of a drug, diagnostic, vaccine or medical device succeeding in a clinical trial. According to the company, the platform is suitable for any therapeutic area, or any drug, test, vaccine or medical device.
Applying the technology to current vaccines and therapies targeting the virus in a proof-of-concept study, the company reportedly determined:
- therapies show a much higher probability of success in studies than vaccines
- which two vaccines are most likely to succeed their current phases
- an antibody therapy has the best probability of success of getting a positive Phase III outcome over all other programs
According to Opyl CEO Michelle Gallaher, the platform has the potential to inform clinical and treatment strategies, early procurement decision making and investments.
“The early outcome of this software trial, investigating the 475 registered COVID-19 clinical trials related to vaccines or treatments, has delivered results that give us an indication of the power of the predictive platform in identifying the COVID-19 trials, or any drug or device trial, with the greatest chance of success,” she said.
Previous studies reportedly demonstrated that, on average, only 13.8% of all drugs in Phase I clinical trials eventually win approval from regulators and enter the market. Further, vaccines typically enjoy a higher success rate (33.4%) than most other drugs, and cancer drugs have a far lower rate of success (3%).
The aim of the Opyl software platform is to work with drug and device development companies to refine their clinical trial approaches and improve study outcomes of their clinical studies, reducing costs and accelerating the timeline to get new treatments to patients.
The company reports the trial predictor platform has delivered confident early results that turn out to be more accurate than previously published models, with more functional features including the potential to optimize trial design.
“Our approach is to use AI to not just predict the outcome, but to demonstrate that changing specific clinical trials variables can improve the probability of success,” Gallaher commented. “Our goal is to improve the efficiency, improve the application of research funding and ultimately the return on investment for scientists, clinicians, health technology developers and investors.”
The platform uses current and historical global data and considers everything from the numbers of participants in each trial; the dropout rate from those trials; how long each trial will take; the end point for each trial relative to related studies, through to the mode of action such as type of protein or vector being employed in a program.
The company reports the next stage for development of the platform will involve increasing the data pool from additional clinical data sources, then expanding the variables to further train the algorithm and refine the specificity and reliability. And, Gallaher added, the company plans on expanding to other therapeutic areas.
“Although looking at the current pipeline of COVID-19 programs is an initial application of the AI platform, we are not limiting ourselves to just COVID-19 trials,” Gallaher stated. “The AI platform can be applied to all drugs, diagnostics, vaccines and medical devices about to begin or in clinical trials, and our goals is to improve the clinical trial process which will in turn save money, time and ensure patients can access treatment options sooner.”
