Pharma Giants Turn To AI To Streamline Clinical Trials: Report

Major pharmaceutical companies are increasingly turning to artificial intelligence (AI) to streamline patient selection for clinical trials and reduce the number of participants needed, consequently expediting drug development and potentially saving substantial financial resources. Human studies constitute the most expensive and time-consuming aspect of drug development, requiring years to recruit patients and test new medications. This process can cost over a billion dollars from drug discovery to completion.

For years, pharmaceutical firms have been experimenting with AI, envisioning it as a tool to discover groundbreaking drugs. Some compounds identified through AI are now in the development phase, although these ventures will require years to materialise.

Insights gained from Reuters interviews with numerous pharmaceutical company executives, drug regulators, public health experts, and AI companies indicate that AI technology is increasingly playing a significant role in human drug trials.

Companies like Amgen, Bayer, and Novartis are leveraging AI to analyse vast troves of public health records, prescription data, medical insurance claims, and internal data to identify potential trial patients. In some cases, this approach has halved the time required for patient enrollment.

Jeffrey Morgan, managing director at Deloitte, noted that AI’s integration is beyond the experimental stage, although it hasn’t yet permeated every aspect of drug development.

The US Food and Drug Administration (FDA) reported receiving around 300 applications integrating AI or machine learning in drug development from 2016 to 2022. Over 90 per cent of these applications were submitted in the last two years, mostly concerning AI usage during the clinical development stage.

Before utilising AI, pharmaceutical companies like Amgen would spend months sending surveys to doctors globally to determine suitable clinics or hospitals for trials based on relevant clinical and demographic criteria. However, AI tools like Amgen’s ATOMIC are now able to identify and rank clinics and doctors based on past performance in patient recruitment, significantly speeding up the process.

German drugmaker Bayer, for instance, used AI to drastically reduce the number of participants needed for a late-stage trial for asundexian, an experimental drug designed to reduce the long-term risk of strokes in adults. AI-enabled Bayer to link mid-stage trial results to real-world data, providing a predictive assessment of long-term risks in a similar population to the trial.

Overall, AI’s growing role in drug development is anticipated to reshape timelines and create substantial cost efficiencies for pharmaceutical giants. However, ensuring data accuracy and addressing potential biases remain ongoing concerns to maintain the credibility and safety of AI-driven approaches in drug development.