Screening Automation in Systematic Reviews: Analysis of Tools and Their Machine Learning Capabilities.
Stud Health Technol Inform
; 313: 179-185, 2024 Apr 26.
Article
em En
| MEDLINE
| ID: mdl-38682527
ABSTRACT
Systematic reviews provide robust evidence but require significant human labor, a challenge that can be mitigated with digital tools. This paper focuses on machine learning (ML) support for the title and abstract screening phase, the most time-intensive aspect of the systematic review process. The existing literature was systematically reviewed and five promising tools were analyzed, focusing on their ability to reduce human workload and their application of ML. This paper details the current state of automation capabilities and highlights significant research findings that point towards further improvements in the field. Directions for future research in this evolving field are outlined, with an emphasis on the need for a cautious application of existing systems.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Aprendizado de Máquina
/
Revisões Sistemáticas como Assunto
Limite:
Humans
Idioma:
En
Revista:
Stud Health Technol Inform
Ano de publicação:
2024
Tipo de documento:
Article