TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network

TL;DR

TREEMENT is a novel interpretable machine learning model that improves patient-trial matching accuracy by leveraging personalized hierarchical representations and attention mechanisms, facilitating better adoption in clinical settings.

Contribution

Introduces TREEMENT, a personalized dynamic tree-based memory network that enhances interpretability and accuracy in patient-trial matching using hierarchical ontologies and attention.

Findings

Outperforms baseline models with 7% error reduction in criteria-level matching.

Achieves state-of-the-art results in trial-level matching.

Provides interpretable results to facilitate clinical adoption.

Abstract

Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials based on longitudinal patient electronic health records (EHR) data and eligibility criteria of clinical trials. However, they either depend on trial-specific expert rules that cannot expand to other trials or perform matching at a very general level with a black-box model where the lack of interpretability makes the model results difficult to be adopted. To provide accurate and interpretable patient trial matching, we introduce a personalized dynamic tree-based memory network model named TREEMENT. It utilizes hierarchical clinical ontologies to expand the personalized patient representation learned from sequential EHR data, and then uses an attentional beam-search query learned from eligibility criteria embedding to offer a granular level of alignment for improved performance and interpretability. We evaluated TREEMENT against existing models on real-world datasets and demonstrated that TREEMENT outperforms the best baseline by 7% in terms of error reduction in criteria-level matching and achieves state-of-the-art results in its trial-level matching ability. Furthermore, we also show TREEMENT can offer good interpretability to make the model results easier for adoption.