Predicting Clinical Trial Results by Implicit Evidence Integration

TL;DR

This paper introduces a new task for predicting clinical trial outcomes using unstructured medical literature, leveraging implicit evidence to improve prediction accuracy and reduce reliance on costly structured data.

Contribution

The study proposes a novel CTRP task and a model that predicts trial results from unstructured evidence, outperforming existing baselines on multiple datasets.

Findings

Model achieves 10.7% relative gain over BioBERT in macro-F1.

Pre-training on implicit evidence enhances prediction accuracy.

Performance validated on COVID-19 related clinical trial data.

Abstract

Clinical trials provide essential guidance for practicing Evidence-Based Medicine, though often accompanying with unendurable costs and risks. To optimize the design of clinical trials, we introduce a novel Clinical Trial Result Prediction (CTRP) task. In the CTRP framework, a model takes a PICO-formatted clinical trial proposal with its background as input and predicts the result, i.e. how the Intervention group compares with the Comparison group in terms of the measured Outcome in the studied Population. While structured clinical evidence is prohibitively expensive for manual collection, we exploit large-scale unstructured sentences from medical literature that implicitly contain PICOs and results as evidence. Specifically, we pre-train a model to predict the disentangled results from such implicit evidence and fine-tune the model with limited data on the downstream datasets. Experiments on the benchmark Evidence Integration dataset show that the proposed model outperforms the baselines by large margins, e.g., with a 10.7% relative gain over BioBERT in macro-F1. Moreover, the performance improvement is also validated on another dataset composed of clinical trials related to COVID-19.