Maura Grossman, a member of the Merlin Legal Open Source Foundation, and her colleague at the University of Waterloo, Gordon Cormack, have been tapped by the Canadian Health Authorities to use their groundbreaking Continuous Active Learning® algorithm, originally designed to make legal search and review more efficient, to find medical research documents that may speed up Coronavirus vaccine research.
Continuous Active Learning is a technique pioneered in parallel by Catalyst Repository Systems, Inc. and the subject of CEO John Tredennick’s widely-read book: TAR (Technology Assisted Review) for Smart People. “We have used our CAL engine in hundreds of cases finding in every case that the machine learning algorithm saved our clients substantially on document review.” Tredennick noted. We are in the process of integrating this amazing information retrieval technology into our platform right now.
Here is a report from the University of Waterloo,
A new artificial intelligence tool is being used to help medical researchers at a Toronto-area hospital to shave months off the time they need to identify clinical studies available to help physicians treat COVID-19 patients.
In building the AI-driven search tool, researchers at the University of Waterloo used a machine-learning approach originally developed to expedite the review of documents in high-stakes litigation, to help the researchers mine through thousands of new studies on COVID-19 quickly.
“Searching and finding studies for systematic reviews has traditionally been a time-consuming and laborious process that uses keyword search,” said Maura Grossman, computer science research professor at the University of Waterloo. “It’s a long process that involves the manual screening of abstracts, and finally full papers.” Grossman worked with the primary developer of the tool, fellow computer science professor at the University of Waterloo, Gordon Cormack. The tool is being deployed in conjunction with the knowledge synthesis team at St. Michael’s Hospital on behalf of Health Canada, which commissioned the systematic review.
“We are training the machine-learning algorithm to perform the initial steps of the review. We use the trained algorithm to search multiple, massive medical and scientific databases, in different languages, in real-time, as they are updated. We then send to the research team at St. Michael’s the studies they need to consider for inclusion in their systematic reviews. Our goal is to find as many as we can, as quickly as we can, so that researchers, clinicians, and public health officials can quickly draw sound conclusions about the treatments and other procedures that are likely to be the most promising, and to dismiss those that are not,” said Grossman.
Systematic reviews use formal explicit methods — in other words, pre-specifications — that set forth precisely what question is to be answered, how evidence is to be searched for and assessed, and how the information will be synthesized to reach a conclusion. Conducting a systematic review involves multiple processes typically requiring many tedious steps and numerous hours of expert labour. An average systematic review can take a team of researchers a year or more to produce.
“Our continuous active learning tool identifies for screening the abstracts or studies most likely to meet the specific inclusion criteria, based on studies that have previously been identified and meet the inclusion criteria,” Cormack said. “We’re thrilled that our technology can help during the pandemic.”
Maura R. Grossman is a Research Professor and Director of Women in Computer Science in the David R. Cheriton School of Computer Science at the University of Waterloo. Gordon V. Cormack is a professor in the David R. Cheriton School of Computer Science at the University of Waterloo and co-inventor of Dynamic Markov Compression.