Pharmaceutical giants are leveraging the power of artificial intelligence (AI) to accelerate drug development and potentially save millions of dollars. Human studies, which are the most costly and time-consuming aspect of drug development, can take several years to recruit patients and trial new medicines, costing over a billion dollars from drug discovery to market launch. In recent years, pharmaceutical companies have been experimenting with AI in the hopes of discovering the next blockbuster drug. While it will take years to see the full results of these endeavors, AI is already making an impact.
Companies like Amgen, Bayer, and Novartis are training AI to analyze vast amounts of data, including public health records, prescription data, medical insurance claims, and internal data, to find suitable patients for clinical trials. By doing so, they can significantly reduce the time it takes to enroll patients and optimize the number of participants needed for testing. Deloitte estimates that approximately 80% of studies fail to meet their recruitment targets due to factors such as overestimated patient availability, high dropout rates, or non-adherence to trial protocols.
Amgen has developed an AI tool called ATOMIC, which scans extensive datasets to identify and rank clinics and doctors based on their past performance in recruiting patients for trials. This advanced system has the potential to cut the enrollment time for mid-stage trials in half, depending on the disease being studied. Amgen plans to use ATOMIC for most of its studies by 2024 and expects AI to shorten the typical drug development timeline by two years by 2030.
Novartis, too, has seen success in using AI to streamline patient enrollment in clinical trials. However, experts noted that the effectiveness of AI in this context is heavily reliant on the quality and availability of data. Currently, less than 25% of health data is publicly accessible for research purposes, limiting the scope of AI’s potential impact.
German drugmaker Bayer utilized AI to reduce the number of participants needed for a late-stage trial of its experimental drug asundexian, designed to reduce the long-term risk of strokes in adults. By linking mid-stage trial results with real-world data from millions of patients, Bayer was able to make accurate predictions about the long-term risks associated with the drug. This enabled the company to proceed with the late-stage trial with fewer participants, saving time and resources. Bayer now plans to leverage real-world patient data for a pediatric trial of asundexian, potentially eliminating the need for a placebo group.
While the use of AI in clinical trials is promising, concerns have been raised about its limitations. Regulators, including the U.S. Food and Drug Administration (FDA), emphasize that the evidentiary standards for a drug’s safety and effectiveness will remain unchanged. Additionally, some experts caution that relying solely on real-world patient data without randomization could lead to biased results and inadequate comparisons between treatment arms.
In conclusion, pharmaceutical giants are increasingly turning to AI to expedite drug development and overcome the challenges associated with patient recruitment in clinical trials. By harnessing the power of AI to analyze vast datasets, these companies aim to reduce costs and shorten the time it takes to bring new drugs to market. However, it is crucial to ensure the appropriate use of AI and maintain rigorous regulatory standards to guarantee the safety and effectiveness of these drugs.
