Learning Eligibility in Cancer Clinical Trials using Deep Neural Networks

TL;DR

This paper develops a deep neural network model trained on 6 million clinical trial statements to automatically predict eligibility criteria, aiding in more inclusive cancer trial enrollment and extracting medical knowledge from protocols.

Contribution

The study introduces a novel deep learning approach for classifying eligibility criteria and analyzing semantic representations in cancer clinical trial texts.

Findings

High accuracy in predicting eligibility from free-text statements

Ability to identify equivalent treatments for tumor types

Deep neural networks effectively extract medical knowledge from protocols

Abstract

Interventional cancer clinical trials are generally too restrictive, and some patients are often excluded on the basis of comorbidity, past or concomitant treatments, or the fact that they are over a certain age. The efficacy and safety of new treatments for patients with these characteristics are, therefore, not defined. In this work, we built a model to automatically predict whether short clinical statements were considered inclusion or exclusion criteria. We used protocols from cancer clinical trials that were available in public registries from the last 18 years to train word-embeddings, and we constructed a~dataset of 6M short free-texts labeled as eligible or not eligible. A text classifier was trained using deep neural networks, with pre-trained word-embeddings as inputs, to predict whether or not short free-text statements describing clinical information were considered eligible. We additionally analyzed the semantic reasoning of the word-embedding representations obtained and were able to identify equivalent treatments for a type of tumor analogous with the drugs used to treat other tumors. We show that representation learning using {deep} neural networks can be successfully leveraged to extract the medical knowledge from clinical trial protocols for potentially assisting practitioners when prescribing treatments.