Machine learning-assisted screening increases efficiency of systematic review

PICO Portal (PP) prioritizes articles for review using natural language processing and active learning to monitor user decisions on eligibility during title/abstract screening. To predict eligibility, PP uses several algorithms including both decision tree (e.g., SVM, Random Forest Naïve Bayes) and deep learning (e.g., Bidirectional Encoder Representations (BERT)) models. We…

0 Comments

PICO Portal Plus+: A Global Talent Connection Service for Project Support and Professional Growth

PICO Portal Plus+ is an innovative service that connects talented individuals from around the world, including clinicians, young researchers, and methodologists, with institutions in need of resources to complete their projects. The service particularly focuses on individuals who come from economically disadvantaged countries, offering them a chance to utilize their…

0 Comments

Workshops to Support EPA’s Development of Human Health Assessments: Artificial Intelligence

Workshops to Support EPA's Development of Human Health Assessments: Artificial Intelligence and Open Data Practices in Chemical Hazard Assessment Practical application of systematic review (SR) methods to the peer-reviewed literature and other data sources for chemical hazard identification is labor-intensive and costly. Advances in artificial intelligence hold promise to ease those…

0 Comments