Introduction
A recent study conducted by the School of Biomedical Informatics at the University of Texas in collaboration with Melax Tech has shown that it is possible to use AI-based approaches that employ deep learning Natural Language Processing (NLP) methods along with knowledge graph (KG) technology to create advanced search, retrieval, and visualization capabilities to search for COVID-19 clinical trials.
Methods
Due to the urgency of finding safe and effective treatments for COVID-19, clinical trials have become an indispensable tool for the clinical research community. However, the rapid growth in the number of clinical trials has made it difficult for patients to join them or for clinicians to register patients. For instance, from the onset of the pandemic in late 2019 until October 2020, 3,392 COVID-19 clinical trials were registered in ClinicalTrials.gov. By November 21, 2021, the number had increased to 7,031, with 3,085 actively recruiting participants.
Our novel approach for searching this material is constructing a knowledge graph of information from registered clinical trials on ClinicalTrials.gov that includes structured information about the trial and inclusion of information extracted from the study protocol and eligibility criteria. Inclusion/exclusion criteria and protocol are represented as free, unstructured text, with deep learning-based NLP used to extract named entities and clinical concepts. Both structured and unstructured are then normalized and used as nodes in a KG, allowing sophisticated user queries to be constructed and visualize the results.
During the evaluation, our methods demonstrated high precision and recall scores in retrieving relevant trials from ClinicalTrials.gov based on queries of both the eligibility criteria and searches involving the structured information from the trial. Melax Tech’s AI-based NLP system, CLAMP, was used during this project's development and NLP work.
This method allows for diverse search queries and provides graph-based visualization of COVID-19 clinical trials. For example, the following are some of the use cases that we evaluated the system on:
Case query 1: Retrieve all COVID-19 clinical trials that target “remdesivir” as the intervention.
Case query 2: Retrieve all COVID-19 clinical trials that target “remdesivir” as the intervention but exclude pregnant women [OMOP ID: 4299535] from participating.
Case query 3: Retrieve all COVID-19 clinical trials that target “hydroxychloroquine” as the intervention and allow patients with shortness of breath [OMOP ID: 312437] to participate.
Case query 4: Retrieve all COVID-19 clinical trials in the United States that target “hydroxychloroquine” as the intervention and allow patients with diabetes to participate.
Note that our high-dimensional graph embedding vectors benefit many downstream applications, such as trial-end recruitment status prediction and trial similarity comparison. This methodology generalizes to clinical trials in other areas, such as oncology.
Conclusion
The School of Biomedical Informatics at the University of Texas and Melax Tech have developed an innovative solution to simplify the search and retrieval process for COVID-19 clinical trials. By utilizing advanced AI-driven technologies, this powerful tool creates new opportunities for insights and discoveries in clinical research. Request a demo today to learn more!
A full description of our methodology and results is given in “COVID-19 trial graph: a linked graph for COVID-19 clinical trials.” Jingcheng Du, Qing Wang, Jingqi Wang, Prerana Ramesh, Yang Xiang, Xiaoqian Jiang, Cui Tao. Journal of the American Medical Informatics Association, Volume 28, Issue 9, September 2021, Pages 1964–1969, PMCID: PMC8135317, https://doi.org/10.1093/jamia/ocab078