AutoTrial: Prompting Language Models for Clinical Trial Design
This addresses the challenge of efficient clinical trial design for drug developers, though it is incremental as it builds on existing language model techniques.
The paper tackles the problem of designing clinical trial eligibility criteria by proposing AutoTrial, a method using language models with prompting and in-context learning, which generates high-quality criteria with a 60% winning rate against GPT-3.5 baselines in human evaluations.
Clinical trials are critical for drug development. Constructing the appropriate eligibility criteria (i.e., the inclusion/exclusion criteria for patient recruitment) is essential for the trial's success. Proper design of clinical trial protocols should consider similar precedent trials and their eligibility criteria to ensure sufficient patient coverage. In this paper, we present a method named AutoTrial to aid the design of clinical eligibility criteria using language models. It allows (1) controllable generation under instructions via a hybrid of discrete and neural prompting, (2) scalable knowledge incorporation via in-context learning, and (3) explicit reasoning chains to provide rationales for understanding the outputs. Experiments on over 70K clinical trials verify that AutoTrial generates high-quality criteria texts that are fluent and coherent and with high accuracy in capturing the relevant clinical concepts to the target trial. It is noteworthy that our method, with a much smaller parameter size, gains around 60% winning rate against the GPT-3.5 baselines via human evaluations.