The traditional drug-centric trial model is failing. The next evolution is trials designed to validate the *decision-making process* itself, using platforms to assign the best therapy to heterogeneous patient groups, rather than testing one drug on a narrow population.

Our ability to generate and test therapeutic hypotheses in silico is rapidly outpacing the slow, expensive conventional clinical trial system. Without regulatory reform, the pipeline of promising drugs will remain stuck, preventing breakthroughs from reaching patients. The science is solvable; the system is not.

With over 5,000 oncology drugs in development and a 9-out-of-10 failure rate, the current model of running large, sequential clinical trials is not viable. New diagnostic platforms are essential to select drugs and patient populations more intelligently and much earlier in the process.

While AI for novel drug discovery has lofty goals, its most practical value lies in accelerating development. This includes applying AI to de-risked assets for new indications, improving delivery methods, and designing faster, more effective clinical trials, which is where the real bottleneck lies.

Acadia's R&D process starts by considering what will ultimately matter to patients, physicians, and payers. This "end in mind" approach ensures clinical trials are designed to demonstrate meaningful, commercially relevant benefits. It forces realism about a drug's potential impact early in development, avoiding wasted resources on therapies that won't be adopted.

Despite major scientific advances, the key metrics of drug R&D—a ~13-year timeline, 90-95% clinical failure rate, and billion-dollar costs—have remained unchanged for two decades. This profound lack of productivity improvement creates the urgent need for a systematic, AI-driven overhaul.

With clinical development cycles lasting 7-10 years, junior team members rarely see a project to completion. Their career incentive becomes pushing a drug to the next stage to demonstrate progress, rather than ensuring its ultimate success. This pathology leads to deferred problems and siloed knowledge.

Despite the appeal of stopping treatment, a key insight from clinical practice is that patients' most critical question remains which therapy offers the longest period of remission, often overriding factors like treatment duration and oral-only options.

The GLORA-IV trial is designed with a dual endpoint, evaluating both patient response rate and overall survival. This structure creates an alternative pathway for regulatory approval based on response rates, which can be assessed faster than survival, strategically de-risking the lengthy and expensive trial process.