Automating Systematic Reviews: API-Powered Bibliographic Data Retrieval Module for NeutrinoReview

Systematic reviews are the gold standard for synthesiz-ing research evidence but are highly time- and resource-intensive, often requiring months or even years to complete.While existing review management systems provide sup-port for the screening phase, early steps such as literatureretrieval typically require external execution, creating in-efficiencies and potential for error. This paper presents aproof-of-concept implementation of an automated data re-trieval and deduplication module integrated into the Neutri-noReview platform. The module supports multi-databasequerying, metadata normalization, and duplicate resolutionthrough a similarity-based algorithm. To assess its perfor-mance, a controlled user study compared task completiontimes with Rayyan, a widely used review tool. Seven noviceparticipants performed retrieval and deduplication work-flows for four medical reviews using both systems. Resultsshowed that NeutrinoReview reduced completion time byan average of 75%. These findings highlight the potential ofautomation to significantly reduce human workload in theearly stages of systematic reviews. While NeutrinoReviewserves as a proof of concept, the demonstrated efficiencygains underscore the value of integrating robust retrievaland deduplication modules into current and next-generationreview management tools to enhance timeliness, consistency,and reliability in evidence synthesis.