Receive our newsletter – data, insights and analysis delivered to you
  1. News
July 22, 2021

FAU team develops new method to forecast Covid-19 trial outcome

The study showed that computational techniques could help distinguish between finished and stopped Covid-19 trials.

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.

According 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.

Content from our partners
Africa’s last mile: Building viable vaccine supply chains
Why this global life sciences COO believes relocation to Charleston, SC, was key to achieving next-level success
Patient-centric pharma logistics: How CRYOPDP delivers hope worldwide

As of 15 July 2021, approximately 6,180 Covid-19 trials have been registered via, 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new disease, a small number of trials have been formally terminated, and hence the FAU team considered terminated, withdrawn and suspended studies as cessation trials.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“The main purpose of our research was to predict whether a Covid-19 clinical trial will be completed or terminated, withdrawn or suspended.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 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.


Related Companies

Topics in this article:
NEWSLETTER Sign up Tick the boxes of the newsletters you would like to receive. Key drug pipeline and competitive landscape changes based on the latest clinical activity, sent every Tuesday. Curated analysis and data-driven insights on clinical trials strategy and operations, sent every Thursday. The pharmaceutical industry's most comprehensive news and information delivered every month.
I consent to GlobalData UK Limited collecting my details provided via this form in accordance with the Privacy Policy