AI Could Cut 10 Weeks From Cancer Trials. Drugmakers Could Save Millions.

Artificial intelligence could dramatically cut the time and cost of cancer clinical trials, potentially saving drug developers millions of dollars and accelerating treatments through one of the most expensive stages of pharmaceutical development.

According to a new analysis from the Tufts Center for the Study of Drug Development, AI agents could accelerate the clinical development of cancer medicine by approximately 10 weeks while reducing direct operating costs by as much as $5.6 million in late-stage trials, according to Axios, which first reported the findings on Wednesday.

The potential financial impact becomes substantially larger when researchers account for drugs being studied across multiple types of cancer. According to the analysis, an experimental treatment with as many as 50 active uses, or indications, could generate net benefits reaching $565 million.

AI-powered systems are increasingly being explored for some of the labor-intensive work involved in running clinical trials, including patient recruitment and enrollment, monitoring, data management and analysis.

Tufts CSDD has been studying the use of artificial intelligence and machine learning in clinical research for years. The center lists the use and impact of AI and machine learning in clinical research among its research areas and says it conducted an extensive collection of AI and machine-learning use cases in drug development and their impact on performance in 2025.

For the latest analysis, Tufts applied a clinical monitoring agent developed by Medable, a technology company that provides a platform supporting clinical trials, to an unspecified oncology drug development program involving Phase 2 and Phase 3 studies.

Ken Getz, executive director of Tufts CSDD, said the use of the agent produced efficiencies including fewer on-site monitoring visits, faster patient enrollment and quicker database lock, an important milestone that occurs when trial data is finalized and ready for analysis.

"To our knowledge, this is the first time that [predictive] modeling based on actual use and benchmark data has been applied to quantify the net financial impact of an agentic AI solution in a drug development program," Getz said, according to Axios.

The potential savings are particularly significant in oncology, where trials can be highly complex and monitoring budgets substantial. Cutting weeks from development timelines could allow pharmaceutical companies to redirect money and personnel toward additional studies while potentially getting successful treatments through the development process faster.

Medable officials believe AI agents could become standard features in some clinical trials within three to five years. The technology could eventually function somewhat like a self-driving system for clinical research, handling repetitive monitoring and record-keeping tasks while allowing researchers to concentrate on more strategic decisions.

AI systems could also help researchers monitor the demographic diversity of trial participants and identify safety or effectiveness signals earlier in the process. Diversity remains an important issue in clinical research because trial populations need to adequately represent the patients who may ultimately receive a treatment.

Still, AI cannot guarantee that an experimental drug will work, nor can it solve every challenge involved in identifying eligible patients, obtaining informed consent, or manufacturing and distributing experimental treatments. Human researchers would also still need to review and verify work performed by AI agents, potentially reducing some of the projected time savings.