EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyse

Large language models in neurosurgery: a systematic review and meta-analysis

Advait Patil, Paul Serrato, Nathan Chisvo, Omar Arnaout, Pokmeng Alfred See, Kevin T Huang

Acta Neurochirurgica · 23.11.2024 · 166 (1)

DOI: 10.1007/s00701-024-06372-9 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Acta Neurochirurgica, online erschienen am 23.11.2024. Verfasst von Advait Patil und 5 weiteren Autor:innen. Beteiligte Einrichtung: Harvard Medical School, Harvard University, Boston, MA, 02115, USA. advaitpatil@hms.harvard.edu. Hauptthemen laut MEDLINE: Neurosurgery, Neurosurgical Procedures. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 72 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Large Language Models (LLMs) have garnered increasing attention in neurosurgery and possess significant potential to improve the field. However, the breadth and performance of LLMs across diverse neurosurgical tasks have not been systematically examined, and LLMs come with their own challenges and unique terminology. We seek to identify key models, establish reporting guidelines for replicability, and highlight progress in key application areas of LLM use in the neurosurgical literature. METHODS: We searched PubMed and Google Scholar using terms related to LLMs and neurosurgery ("large language model" OR "LLM" OR "ChatGPT" OR "GPT-3" OR "GPT3" OR "GPT-3.5" OR "GPT3.5" OR "GPT-4" OR "GPT4" OR "LLAMA" OR "MISTRAL" OR "BARD") AND "neurosurgery". The final set of articles was reviewed for publication year, application area, specific LLM(s) used, control/comparison groups used to evaluate LLM performance, whether the article reported specific LLM prompts, prompting strategy types used, whether the LLM query could be reproduced in its entirety (including both the prompt used and any adjoining data), measures of hallucination, and reported performance measures. RESULTS: Fifty-one articles met inclusion criteria, and were categorized into six application areas, with the most common being Generation of Text for Direct Clinical Use (n = 14, 27.5%), Answering Standardized Exam Questions (n = 12, 23.5%), and Clinical Judgement and Decision-Making Support (n = 11, 21.6%). The most frequently used LLMs were GPT-3.5 (n = 30, 58.8%), GPT-4 (n = 20, 39.2%), Bard (n = 9, 17.6%), and Bing (n = 6, 11.8%). Most studies (n = 43, 84.3%) used LLMs directly out-of-the-box, while 8 studies (15.7%) conducted advanced pre-training or fine-tuning. CONCLUSIONS: Large language models show advanced capabilities in complex tasks and hold potential to transform neurosurgery. However, research typically addresses basic applications and overlooks enhancing LLM performance, facing reproducibility issues. Standardizing detailed reporting, considering LLM stochasticity, and using advanced methods beyond basic validation are essential for progress.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeurosurgeryNeurosurgical ProceduresHumansLanguage

Stichwörter der Autor:innen

Artificial intelliegenceLarge language modelsNeurosurgery

Autor:innen und Institutionen

  • Harvard Medical School, Harvard University, Boston, MA, 02115, USA. advaitpatil@hms.harvard.edu.
  • Computational Neuroscience Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA. advaitpatil@hms.harvard.edu.
  • Department of Neurosurgery, Brigham and Women's Hospital, 60 Fenwood Road, Hale Building, 4th Floor, Boston, MA, 02115, USA. advaitpatil@hms.harvard.edu.
  • Department of Neurosurgery, Boston Children's Hospital, 02115, Boston, MA, USA. advaitpatil@hms.harvard.edu.
  • Yale School of Medicine, Yale University, New Haven, CT, 06510, USA.
  • Harvard T.H. Chan School of Public Health, Harvard University, Boston, CT, 02115, USA.

Zitieren

APA

Patil, A., Serrato, P., Chisvo, N., Arnaout, O., See, P. A., & Huang, K. T. (2024). Large language models in neurosurgery: a systematic review and meta-analysis. Acta Neurochirurgica, 166(1). https://doi.org/10.1007/s00701-024-06372-9

Vancouver

Patil A, Serrato P, Chisvo N, Arnaout O, See PA, Huang KT. Large language models in neurosurgery: a systematic review and meta-analysis. Acta Neurochirurgica. 2024;166(1). doi:10.1007/s00701-024-06372-9

BibTeX
@article{Patil2024,
  author = {Patil, Advait and Serrato, Paul and Chisvo, Nathan and Arnaout, Omar and See, Pokmeng Alfred and Huang, Kevin T},
  title = {Large language models in neurosurgery: a systematic review and meta-analysis},
  journal = {Acta Neurochirurgica},
  year = {2024},
  volume = {166},
  number = {1},
  doi = {10.1007/s00701-024-06372-9}
}
Kostenlos starten →