Transformer model guides safer dose choices in early drug trials

Transformer-Based Reinforcement Learning for Phase I Dose Allocation

Machine Learning

Summary

Finding the right drug dose in early trials is tricky because giving too much can be harmful, and giving too little might not work. The authors created a computer program that learns how to pick doses by looking at past patient reactions and the number of patients tried at each dose. This program uses a special AI model called a Transformer to understand the whole trial situation and then decides whether to increase, keep, or lower the dose. The final decision on the best dose is made using another method to make sure safety is prioritized. Their tests show you can balance being safe and choosing the correct dose, though it doesn't necessarily work better than current methods.

What this means in practice

  • For clinical trial designers: Use Transformer-based reinforcement learning to adaptively select doses with a trade-off between safety and accuracy during early phase trials with varying dose levels.
  • For machine learning engineers in healthcare: Develop AI systems that summarize trial data as token sequences for making dose allocation decisions via learned policies in dose-finding studies.

Tested on simulated data.

Authors

Shijie Yuan

Abstract

Phase I dose-finding trials must learn from sparse toxicity observations while limiting exposure to overly toxic doses. We develop a single reinforcement-learning policy for trials with different numbers of ordered dose levels. Each dose is represented as a token containing its normalized position, accumulated patient count, observed dose-limiting toxicities (DLTs), and current-dose indicator. A Transformer encoder summarizes the dose tokens, trial-conditioned cross-attention produces a fixed-dimensional trial representation, and a three-action policy chooses de-escalation, staying, or escalation. The final maximum tolerated dose (MTD) decision is deliberately kept outside the learned policy: after the planned sample size, weighted isotonic regression and a prespecified safety cap select the dose closest to the target toxicity probability. In the simulations, toxicity-penalized policies reduce DLT burden while unpenalized policies improve selection accuracy at the cost of greater toxicity. These results demonstrate a controllable safety--accuracy trade-off but do not establish superiority over conventional dose-finding designs.