Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Surgery scheduling based on large language models.

Fang Wan¹, Tao Wang¹, Kezhi Wang²

¹INSA LYON, Université Lyon2, Université Claude Bernard Lyon1, Université Jean Monnet Saint-Etienne, DISP UR4570, France.

Artificial Intelligence in Medicine

|May 11, 2025

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Vaginal microbiota and genitourinary syndrome of menopause in premenopausal breast cancer patients receiving endocrine therapy: a longitudinal cohort study protocol.

Frontiers in medicine·2026

Same author

2s-DAS: Two-Stream Diffusion with Multi-Modal Fusion for Temporal Action Segmentation.

Journal of imaging·2026

Same author

Intravenous administration of an engineered AAV9-gene-silencing vector suppresses human SOD1 and extends survival in an ALS mouse model.

Nature communications·2026

Same author

Lamellar Regulation for Fast and Reversible Zinc-Ion Transport in Water-Rich Hydrogels for Aqueous Zinc-Ion Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Electroacupuncture Ameliorates Learning and Memory Deficits in Vascular Cognitive Impairment Rats Through Activation of the Supramammillary Nucleus-Dentate Gyrus Circuit.

CNS neuroscience & therapeutics·2026

Same author

Impaired kidney function in People with HIV compared to People without HIV.

AIDS (London, England)·2026

Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026

Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026

Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026

Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026

Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026

Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026

See all related articles

Large Language Models (LLMs) enhance surgery scheduling by acting as evolutionary optimizers. LLM-NSGA significantly improves solutions and optimizes parameters, outperforming traditional methods.

Area of Science:

Artificial Intelligence
Operations Research
Computational Optimization

Background:

Traditional multi-objective optimization algorithms (e.g., NSGA-II) often require domain expertise for operator design.
Large Language Models (LLMs) show potential across various fields, including complex problem-solving.

Purpose of the Study:

To explore the application of LLMs in solving multi-objective combinatorial optimization problems, specifically surgery scheduling.
To introduce LLM-NSGA, a novel approach where LLMs function as evolutionary optimizers.

Main Methods:

LLMs were employed to perform selection, crossover, and mutation operations within an evolutionary framework (LLM-NSGA).
LLM-NSGA was compared against traditional algorithms (NSGA-II, MOEA/D) and another LLM-based method (EoH).

Keywords:

Combinatorial optimization Hyperparameter optimization Large language models Multi-objective Surgery scheduling

More Related Videos

Mixed Reality Assisted Radical Endoscopic Thyroidectomy

Mixed Reality Assisted Radical Endoscopic Thyroidectomy

Published on: January 31, 2025

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

Related Experiment Videos

Last Updated: May 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Mixed Reality Assisted Radical Endoscopic Thyroidectomy

Mixed Reality Assisted Radical Endoscopic Thyroidectomy

Published on: January 31, 2025

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

LLMs were also utilized for hyperparameter optimization, compared against Bayesian Optimization and Ant Colony Optimization (ACO).

Main Results:

LLM-NSGA generated high-quality solutions independently from prompts for 40 cases.
LLM-NSGA demonstrated superior performance over NSGA-II and MOEA/D as problem size increased, with average improvements of 5.39%, 80%, and 0.42% in three objectives.
LLMs reduced hyperparameter optimization runtime by 23.68% and yielded parameters that improved surgery scheduling solutions when validated with NSGA-II.

Conclusions:

LLMs can effectively serve as evolutionary optimizers for complex problems like surgery scheduling.
LLM-NSGA offers a promising alternative to traditional methods, achieving better results and improving resource allocation.
LLMs efficiently optimize algorithm parameters, enhancing the performance of existing optimization techniques.