Clinical Trial Recommendations Using Semantics-Based Inductive Inference and Knowledge Graph Embeddings

TL;DR

This paper introduces a novel recommendation system for clinical trial design leveraging knowledge graph embeddings and inductive inference, trained on clinical trial data to improve decision-making accuracy.

Contribution

It presents a new methodology using neural embeddings on a knowledge graph for clinical trials, including design, effectiveness of embedding methods, and inductive inference for recommendations.

Findings

Relevance scores of 70%-83% in recommendations

Most relevant recommendations appear near the top of the list

Potential improvements in training KGE with node semantics

Abstract

Designing a new clinical trial entails many decisions, such as defining a cohort and setting the study objectives to name a few, and therefore can benefit from recommendations based on exhaustive mining of past clinical trial records. Here, we propose a novel recommendation methodology, based on neural embeddings trained on a first-of-a-kind knowledge graph of clinical trials. We addressed several important research questions in this context, including designing a knowledge graph (KG) for clinical trial data, effectiveness of various KG embedding (KGE) methods for it, a novel inductive inference using KGE, and its use in generating recommendations for clinical trial design. We used publicly available data from clinicaltrials.gov for the study. Results show that our recommendations approach achieves relevance scores of 70%-83%, measured as the text similarity to actual clinical trial elements, and the most relevant recommendation can be found near the top of list. Our study also suggests potential improvement in training KGE using node semantics.