News

... Biostatisticians have enthusiastically welcomed new draft guidance from the US Food and Drug Administration (FDA) on using Bayesian methodology in clinical trials for new drugs. “Bayesian methodologies help address two of the biggest problems of drug development: high costs and long timelines,” said FDA Commissioner Marty Makary, announcing the draft guidance (tinyurl.com/28mrznwf). “Providing clarity around modern statistical methods will help sponsors bring more cures and meaningful treatments to patients faster and more affordably.” The development marks “a major modernizing shift” in the clinical trial landscape, according to Juan Ji, professor of biostatistics at the University of Chicago, whose research is cited in the guidance document. “This shift isn't happening in a vacuum; it's a direct response to the evolving challenges of modern drug development.” “Key points in the guidance include: permission to incorporate prior information (data from previous research and external sources) before the trial begins; the importance of running simulations in trial planning and in submissions; the move away from p-values (notorious for their misinterpretation) and toward simple, direct statements of the chances a clinical effect exceeds a specific level; and the need for transparency – the FDA expects enough detail, including on software, code, and seed numbers, to allow verification and reproducibility.