EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Identifying symptom etiologies using syntactic patterns and large language models

Hillel Taub-Tabib, Yosi Shamay, Micah Shlain, Menny Pinhasov, Mark Polak, Aryeh Tiktinsky, Sigal Rahamimov, Dan Bareket, Ben Eyal, Moriya Kassis, Yoav Goldberg, Tal Kaminski Rosenberg und 2 weitere

Scientific Reports · 2024

DOI: 10.1038/s41598-024-65645-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Reports, 2024. Verfasst von Hillel Taub-Tabib und 13 weiteren Autor:innen. Beteiligte Einrichtung: Allen Institute for AI, Seattle, USA. Hauptthemen laut MEDLINE: Natural Language Processing. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Israeli Science Foundation, H2020 European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Differential diagnosis is a crucial aspect of medical practice, as it guides clinicians to accurate diagnoses and effective treatment plans. Traditional resources, such as medical books and services like UpToDate, are constrained by manual curation, potentially missing out on novel or less common findings. This paper introduces and analyzes two novel methods to mine etiologies from scientific literature. The first method employs a traditional Natural Language Processing (NLP) approach based on syntactic patterns. By using a novel application of human-guided pattern bootstrapping patterns are derived quickly, and symptom etiologies are extracted with significant coverage. The second method utilizes generative models, specifically GPT-4, coupled with a fact verification pipeline, marking a pioneering application of generative techniques in etiology extraction. Analyzing this second method shows that while it is highly precise, it offers lesser coverage compared to the syntactic approach. Importantly, combining both methodologies yields synergistic outcomes, enhancing the depth and reliability of etiology mining.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingHumansData MiningDiagnosis, DifferentialAlgorithms

Autor:innen und Institutionen

  • Allen Institute for AI, Seattle, USA.
  • Faculty of Biomedical Engineering, Technion, Haifa, Israel.
  • Computer Science Department, Bar Ilan University, Ramat Gan, Israel.
  • Technion Faculty of Medicine Library and Rambam Health Campus Library, Haifa, Israel.
  • Institute for Pain Medicine, Rambam Health Campus, Haifa, Israel.
  • Institute for Pain Medicine, Rambam Health Campus, Haifa, Israel. maayanbensasson@gmail.com.

Förderung

  • Israeli Science Foundation
  • H2020 European Research Council

Zitieren

APA

Taub-Tabib, H., Shamay, Y., Shlain, M., Pinhasov, M., Polak, M., Tiktinsky, A., Rahamimov, S., Bareket, D., Eyal, B., Kassis, M., Goldberg, Y., Kaminski Rosenberg, T., Vulfsons, S., & Ben Sasson, M. (2024). Identifying symptom etiologies using syntactic patterns and large language models. Scientific Reports. https://doi.org/10.1038/s41598-024-65645-6

Vancouver

Taub-Tabib H, Shamay Y, Shlain M, Pinhasov M, Polak M, Tiktinsky A, et al. Identifying symptom etiologies using syntactic patterns and large language models. Scientific Reports. 2024. doi:10.1038/s41598-024-65645-6

BibTeX
@article{TaubTabib2024,
  author = {Taub-Tabib, Hillel and Shamay, Yosi and Shlain, Micah and Pinhasov, Menny and Polak, Mark and Tiktinsky, Aryeh and Rahamimov, Sigal and Bareket, Dan and Eyal, Ben and Kassis, Moriya and Goldberg, Yoav and Kaminski Rosenberg, Tal and Vulfsons, Simon and Ben Sasson, Maayan},
  title = {Identifying symptom etiologies using syntactic patterns and large language models},
  journal = {Scientific Reports},
  year = {2024},
  doi = {10.1038/s41598-024-65645-6}
}
Kostenlos starten →