SciScribe: Automating and contextualizing literature reviews in cardiac surgery
The Journal of Thoracic and Cardiovascular Surgery · 2025
DOI: 10.1016/j.jtcvs.2024.09.014 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Thoracic and Cardiovascular Surgery, 2025. Verfasst von Rashed Mahboubi und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thoracic and Cardiovascular Surgery, Heart and Vascular Institute, Cleveland Clinic, Cleveland, Ohio. Hauptthemen laut MEDLINE: Cardiac Surgical Procedures, Review Literature as Topic, Information Storage and Retrieval, Data Mining. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 9 Literaturangaben. Gefördert von: International Business Machines Corporation, Cleveland Clinic.
Abstract (Originalsprache)
BACKGROUND: The task of writing structured content reviews and guidelines has grown stronger and more complex. We propose to go beyond search tools and toward curation tools by automating time-consuming and repetitive steps of extracting and organizing information. METHODS: SciScribe is built as an extension of IBM's Deep Search platform, which provides document processing and search capabilities. This platform was used to ingest and search full-content publications from PubMed Central (PMC) and official, structured records from the ClinicalTrials and OpenPayments databases. Author names and NCT numbers, mentioned within the publications, were used to link publications to these official records as context. Search strategies involve traditional keyword-based search as well as natural language question and answering via large language models (LLMs). RESULTS: SciScribe is a web-based tool that helps accelerate literature reviews through key features: (1) accumulating a personal collection from publication sources, such as PMC or other sources; (2) incorporating contextual information from external databases into the presented papers, promoting a more informed assessment by readers; (3) semantic questioning and answering of documents to quickly assess relevance and hierarchical organization; and (4) semantic question answering for each document within a collection, collated into tables. CONCLUSIONS: Emergent language processing techniques are opening new avenues to accelerate and enhance the literature review process, for which we have demonstrated a use case implementation in cardiac surgery. SciScribe automates and accelerates this process, mitigates errors associated with repetition and fatigue, and contextualizes results by linking relevant external data sources instantaneously.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Thoracic and Cardiovascular Surgery, Heart and Vascular Institute, Cleveland Clinic, Cleveland, Ohio.
- IBM Research, Zürich, Switzerland.
- Syracuse University, Syracuse, NY.
- Department of Thoracic and Cardiovascular Surgery, Heart and Vascular Institute, Cleveland Clinic, Cleveland, Ohio. Electronic address: karamlt@ccf.org.
Förderung
- International Business Machines Corporation
- Cleveland Clinic
Zitieren
APA
Mahboubi, R., Dinkla, K., Weiss, A., Acierto, A., Staar, P., Robinson, J., Hammoud, M. S., & Karamlou, T. (2025). SciScribe: Automating and contextualizing literature reviews in cardiac surgery. The Journal of Thoracic and Cardiovascular Surgery. https://doi.org/10.1016/j.jtcvs.2024.09.014
Vancouver
Mahboubi R, Dinkla K, Weiss A, Acierto A, Staar P, Robinson J, et al. SciScribe: Automating and contextualizing literature reviews in cardiac surgery. The Journal of Thoracic and Cardiovascular Surgery. 2025. doi:10.1016/j.jtcvs.2024.09.014
BibTeX
@article{Mahboubi2025,
author = {Mahboubi, Rashed and Dinkla, Kasper and Weiss, Aaron and Acierto, Anthony and Staar, Peter and Robinson, Justin and Hammoud, Miza Salim and Karamlou, Tara},
title = {SciScribe: Automating and contextualizing literature reviews in cardiac surgery},
journal = {The Journal of Thoracic and Cardiovascular Surgery},
year = {2025},
doi = {10.1016/j.jtcvs.2024.09.014}
}
EUVIMED