Leveraging Machine Learning Technology to Efficiently Identify and Match Patients for Precision Oncology Clinical Trials

ASCO Annual Meeting 2021 Abstract
Authors Laura Sachse, Smriti Dasari, Marc Ackermann, Emily Patnaude, Stephanie OLeary, Hussein Al-Olimat, Alexander Grigorenko, Andrew Stewart, AnnaJane Ward, Annie Darmofal, Sowmya Ballakur, William Bennett, Amy Franzen, Sibel Blau, Abhinav Binod Chandra, Petros Nikolinakos, James Michael Orsini, Julio Antonio Peguero, Kimberly L. Blackwell, Matthew M. Cooney

Background: Pre-screening for clinical trials is becoming more challenging as inclusion/exclusion criteria becomes increasingly complex. Oncology precision medicine provides an exciting opportunity to simplify this process and quickly match patients with trials by leveraging machine learning technology. The Tempus TIME Trial site network matches patients to relevant, open, and recruiting clinical trials, personalized to each patient’s clinical and molecular biology.

Methods: Tempus screens patients at sites within the TIME TrialNetwork to find high-fidelity matches to clinical trials. The patient records include documentation submitted alongside NGS orders as well as electronic medical records (EMR) ingested through EMR Integrations. While Tempus-sequenced patients were automatically matched to trials using a Tempus-built matching application, EMR records were run through a natural language processing (NLP) data abstraction model to identify patients with an actionable gene of interest. Structured data were analyzed to filter to patients that lack a deceased date and have an encounter date within a predefined time period. Tempus abstractors manually validated the resulting unstructured records to ensure each patient was matched to a TIME Trial at a site capable of running the trial. For all high-level patient matches, a Tempus Clinical Navigator manually evaluated other clinical criteria to confirm trial matches and communicated with the site about trial options.

Results: Patient matching was accelerated by implementing NLP gene and report detection (which isolated 17% of records) and manual screening. As a result, Tempus facilitated screening of over 190,000 patients efficiently using proprietary NLP technology to match 332 patients to 21 unique interventional clinical trials since program launch. Tempus continues to optimize its NLP models to increase high-fidelity trial matching at scale.

Conclusions: The TIME Trial Network is an evolving, dynamic program that efficiently matches patients with clinical trial sites using both EMR and Tempus sequencing data. Here, we show how machine learning technology can be utilized to efficiently identify and recruit patients to clinical trials, thereby personalizing trial enrollment for each patient.