A research team at Florida Atlantic University (FAU)’s College of Engineering and Computer Science in the US has created a new technique to predict if a Covid-19 trial will conclude or cease.
The method leverages machine learning algorithms and ensemble learning.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalDataAccording to the research, features are available for clinical trial reports, including features to model trial management, information and design, eligibility, keywords and drugs among others.
In addition, the study demonstrated that computational techniques could provide effective models to help distinguish between completed and cessation Covid-19 trials.
These models can further predict trial status with acceptable precision, the researchers noted.
Randomised trials are conducted to gather safety and efficacy data and to understand the new and evolving SARS-CoV-2 virus.
As of 15 July 2021, approximately 6,180 Covid-19 trials have been registered via ClinicalTrials.gov, the US registry for both private and public-funded trials performed globally.
Information on which trials will be successful is considered vital.
As Covid-19 is a relatively new disease, a small number of trials have been formally terminated, and hence the FAU team considered terminated, withdrawn and suspended studies as cessation trials.
FAU department of computer and electrical engineering and computer science professor Xingquan Hill said: “The main purpose of our research was to predict whether a Covid-19 clinical trial will be completed or terminated, withdrawn or suspended.
“If we can predict the likelihood of whether a trial might be terminated or not down the road, it will help stakeholders better plan their resources and procedures.”
The research team gathered 4,441 Covid-19 trials from ClinicalTrials.gov and created statistics, keyword, drug and embedding features. A total of 693-dimensional features were designed to signify each trial.
It was observed that keyword features obtained from the medical subject heading terms of the trial reports were the most insightful to predict Covid-19 studies.
The National Science Foundation award funded the research.
