Opyl clinical trial prediction tool completes COVID-19 proof-of-concept
Link copied to
Special Report: Melbourne-based artificial intelligence company Opyl’s machine learning algorithm that aims to predict the outcomes of clinical trials, potentially saving pharmaceutical companies millions of dollars, has taken a major step forward.
In a major proof-of-concept, the company has applied the prediction tool to current vaccines and therapies targeting COVID-19.
The tool forecasts that therapies in development will have a much higher probability of success than vaccines, with antibody therapy having the best probability of a successful outcome than any other program.
The tool also identified two vaccines that have a much greater probability of success than others, but for now Opyl isn’t saying which ones they are.
Opyl (ASX:OPL) says the software platform can be applied to any therapeutic area or any drug, diagnostic, vaccine or medical device.
“We see significant value in using the tool to continuously inform clinical and treatment strategies, early procurement decision making and investments,” chief executive Michelle Gallaher said.
“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 at each stage of the candidates development.”
Just 13.8 per cent of all drugs in clinical trialseventually win approval from regulators, data shows, and such unsuccessful trials are obviously costly for pharmaceutical companies.
Opyl says its sharply defined mission is to solve the two big “failure” problems for biopharma companies – recruitment and trial design.
The company also offers social media marketing and clinical trial recruitment services and the Clinical Trial Predictor Tool will mine past clinical trial data using machine learning to identify recurring patterns for success.
Opyl’s developers trained the tool using publicly published vaccine and drug clinical trial data from hundreds of thousands of past studies listed on clinicaltrials.gov.
The tool is still 18 months to two years away from being ready for market launch as an independent scalable enterprise platform, but Opyl says it is capable of generating revenue now via the company’s consulting for individual clients such as pharmaceutical companies, venture investors and governments.
The tool is designed to be used continuously thoughout the clinical development pathway of a drug, vaccine or device, re-forecasting and recalibating as data is collected and variable change in clinical trials, as they always do.
The platform’s early results are more accurate than previously published models by competitors and offer more functional features including the ability to optimise trial design.
The machine learning algorithm considers a huge range of factors – number of participants in each trial, the historic dropout rate of those trials, how long each trial will take, the end point for each trial relative to related studies, and the mode of action such as the vector or protein being employed in a program.
“Our approach is to use AI to not just predict the outcome, but to demonstrate that changing specific clinical trial variables can improve the probability of success,” Gallaher says.
“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.”
Opyl’s developers are working to further train the algorithm with more data to improve its specificity and reliability, while executives are reaching out to government and collaboration organisations that may have an interest in the findings from its COVID-19 work.
This article was developed in collaboration with Opyl, a Stockhead advertiser at the time of publishing.
This article does not constitute financial product advice. You should consider obtaining independent advice before making any financial decisions.