Accelerating Clinical Trial Enrollment – Vyasa at HETT 2022
According to industry research, 85% of clinical trials end with less than expected enrollment, while 19% are terminated or fail to meet accrual goals at all. Considering the millions of dollars and significant time invested into these trials, the ability to identify and enroll viable candidates is key to successful trial completion and driving innovation around cutting-edge therapeutics.
Clinical Trials’ Data Problem
One of the major challenges associated with clinical trial enrollment is the vast amounts of data required to identify relevant candidates. This data is stored across multiple silos and formats making it difficult to quickly access and analyze. In fact, over half of eligibility criteria for clinical trials is unstructured, and that’s not considering the other critical data points that help influence candidate identification such as patient records, clinician notes, genomics files, images and more.
Traditionally, trial sponsors have relied on manual processes to identify appropriate candidates – searching through massive databases and multiple resources before gleaning out potentially relevant participants. These processes are time and labor-intensive; in many cases, only a fraction of potential leads are found.
Tackling Your Data with Deep Learning
Deep learning is revolutionizing how the healthcare and life sciences industries can search and access data. Known as transformer-based deep learning, these advanced models use a novel approach called self-attention to train on large sets of data. Unlike traditional deep learning models that process each term separately and without context, self-attention allows transformers to build rich representations of the data to understand the relevance of the location of a term, the relation of one term to the next (even if far away from each other) and more. When trained on larger datasets, these models reach remarkable accuracy and recall for understanding the context within unstructured data like large documents of natural language text.
At Vyasa, we leverage this novel approach to deep learning as part of our Layar intelligent data fabric. By applying deep learning to disparate data sources, Layar is able to make the contents of those sources searchable and accessible in a single platform, or data fabric. We then take this a step further by providing a suite of low code application interfaces to help users simultaneously explore and gain access to key insights in their data regardless of its format or location it’s stored in.
Successful Candidate Identification with Vyasa
While data fabrics provide benefits across healthcare and life science, they hold significant power when applied to research tasks including clinical trial design and candidate recruitment.
For example, healthcare organizations are turning to Vyasa to enhance their understanding of their patient population and improve clinical trial enrollment as a whole. By connecting their data silos into a single data fabric they can have all of the relevant information they need in a single platform without having to collect, move or replicate data. The addition of deep learning on top of this data enables them to uncover new insights with peak accuracy and speed. As a result, these organizations can leverage Vyasa Layar to create a unified data platform to search and identify relationships between clinical trials and their patient population to improve trial enrollment and viability.
Working with Dell Technologies, we can provide this solution on innovative compute and storage hardware, allowing organizations to access and operate these capabilities in a familiar server environment.
Smarter Trial Analysis – HETT 2022
Vyasa will be presenting our Layar intelligent data fabric and clinical trial analysis capabilities at Dell Technologies stand #E30 from September 27-28 at HETT 2022.
Interested in meeting? Contact us here.
Access a 7-day free trial of Vyasa Layar here.