System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Research Support, Non-U.S. Gov't Epublish 1 citation

PubMed: 39652380 DOI: 10.2196/55827

Evaluation of RMES, an Automated Software Tool Utilizing AI, for Literature Screening with Reference to Published Systematic Reviews as Case-Studies: Development and Usability Study.

JMIR Form Res 8:e55827

Authors: Ayaka Sugiura, Satoshi Saegusa, Yingzi Jin, Riki Yoshimoto, Nicholas D Smith, Koji Dohi, Tadashi Higuchi, Tomotake Kozu

Affiliations

  • Deloitte Analytics, Deloitte Tohmatsu Risk Advisory LLC, Tokyo, Japan.
  • Evidence Generation ＆ Communication Division, EMC K.K. Tokyo, Japan.

Abstract

BACKGROUND

Systematic reviews and meta-analyses are important to evidence-based medicine, but the information retrieval and literature screening procedures are burdensome tasks. Rapid Medical Evidence Synthesis (RMES; Deloitte Tohmatsu Risk Advisory LLC) is a software designed to support information retrieval, literature screening, and data extraction for evidence-based medicine.

OBJECTIVE

This study aimed to evaluate the accuracy of RMES for literature screening with reference to published systematic reviews.

METHODS

We used RMES to automatically screen the titles and abstracts of PubMed-indexed articles included in 12 systematic reviews across 6 medical fields, by applying 4 filters: (1) study type; (2) study type + disease; (3) study type + intervention; and (4) study type + disease + intervention. We determined the numbers of articles correctly included by each filter relative to those included by the authors of each systematic review. Only PubMed-indexed articles were assessed.

RESULTS

Across the 12 reviews, the number of articles analyzed by RMES ranged from 46 to 5612. The number of PubMed-cited articles included in the reviews ranged from 4 to 47. The median (range) percentage of articles correctly labeled by RMES using filters 1-4 were: 80.9% (57.1%-100%), 65.2% (34.1%-81.8%), 70.5% (0%-100%), and 58.6% (0%-81.8%), respectively.

CONCLUSIONS

This study demonstrated good performance and accuracy of RMES for the initial screening of the titles and abstracts of articles for use in systematic reviews. RMES has the potential to reduce the workload involved in the initial screening of published studies.

MeSH

Natural Language Processing, Software, Artificial Intelligence, Evidence-Based Medicine