DOI: Google Scholar Analysis
For Authors
ijaems Issue
Using Tokenization and Random Forest Models to Predict Pandemic Trial Outcomes( Vol-11,Issue-2,March - April 2025 ) |
|
Author(s): Apeksha Mewani |
|
Keywords: |
|
|
COVID-19, clinical trials, cessation, interventions, machine learning. |
|
Abstract: |
|
|
Since the onset of the COVID-19 pandemic, thousands of clinical trials have been launched to evaluate the effectiveness of interventions aimed at preventing or treating the virus. While many of these studies reached completion, a notable proportion were prematurely cessated. Using a comprehensive XML dataset of 5,783 COVID-19 trials registered on ClinicalTrials.gov, we developed a machine learning model to predict whether a trial was likely to be completed or cessated. Our findings, supported by token frequency analysis, highlighted those specific variables, namely the type of intervention and the trial location, played a significant role in distinguishing between outcomes. Trials that included ‘hydroxychloroquine’ or ‘azithromycin’ as interventions, and those conducted in locations such as ‘France,’ were more frequently associated with early cessation, reflecting shifting scientific consensus and regulatory changes over time. |
|
| Article Info: | |
|
Received: 25 Mar 2025; Received in revised form: 21 Apr 2025; Accepted: 27 Apr 2025; Available online: 30 Apr 2025 |
|
Cite This Article: |
|
| Show All (MLA | APA | Chicago | Harvard | IEEE | Bibtex) | |
Share: |
|
DOI: 
