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 23, 2026

Ultra-Fast Amplicon-Based Next-Generation Sequencing in Non-Squamous Non-Small Cell Lung Cancer

Ultra-Fast Amplicon-Based Next-Generation Sequencing in Non-Squamous Non-Small Cell Lung Cancer

Published on: September 8, 2023

Few-Shot Lung Cancer Classification via Electronic Nose Using Large Language Models: A Multicentre Prospective Study.

Meng-Rui Lee^1,2, Chien-Chi Huang³, Joyce Yue Sun⁴

¹Department of Internal Medicine, National Taiwan University Hospital, Taipei, Taiwan.

Respirology (Carlton, Vic.)

|May 21, 2026

Summary

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

Response to comments on "Effectiveness of amivantamab compared with real-world therapies in patients with non-small cell lung cancer with EGFR exon 20 insertion mutations post platinum-based chemotherapy".

Journal of the Formosan Medical Association = Taiwan yi zhi·2026

Same author

Safety and Immunogenicity of 1 or 2 Additional Doses of the Adjuvanted Recombinant Zoster Vaccine Administered 5-6 Years After Primary Vaccination in Adults ≥50 Years.

Open forum infectious diseases·2026

Same author

Point-of-care ultrasound training using near-peer training and remote Supervision: A pilot randomized controlled trial.

The ultrasound journal·2026

Same author

Epigenetic reprogramming of T cell metabolism restores function and enhances anti-tumor immunity in lung cancer.

Nature immunology·2026

Same author

Using drawings to examine the interactions between parents with advanced lung cancer and their children/adolescents.

Journal of psychosocial oncology·2026

Same author

Correction: Real-World Outcomes of Sequential Afatinib and Osimertinib Versus Afatinib and Chemotherapy in EGFR-Mutant NSCLC: Taiwan Multicenter GIANT Study.

Targeted oncology·2026

Same journal

Early Intervention With Biologics for Asthma Remission: Promising or Premature?

Respirology (Carlton, Vic.)·2026

Same journal

Clinical and Inflammatory Phenotypes During Exacerbations Predict In-Hospital Adverse Outcomes in Asthma-COPD Overlap.

Respirology (Carlton, Vic.)·2026

Same journal

Diagnostic Yield of EBUS Mediastinal Cryobiopsy Versus TBNA in Suspected Lymphoproliferative Disorders: A Prospective Multicentre Study.

Respirology (Carlton, Vic.)·2026

Same journal

Association of Airway Mucus Plugs and Physical Activity, Exercise Tolerance, Sarcopenia, and Frailty in Patients With COPD and Pre-COPD.

Respirology (Carlton, Vic.)·2026

Same journal

An Age-Friendly Approach to Caring for Chronic Lung Disease in the Ambulatory Setting.

Respirology (Carlton, Vic.)·2026

Same journal

Supplemental Oxygen Therapy in Advanced Lung Disease-New Evidence Raises New Questions.

Respirology (Carlton, Vic.)·2026

See all related articles

This summary is machine-generated.

This study shows that large language models (LLMs) can effectively classify lung cancer using electronic nose (eNose) breathprints with minimal data. This approach offers a promising, non-invasive diagnostic tool that requires fewer training samples.

Area of Science:

Biomedical Engineering
Artificial Intelligence in Medicine
Respiratory Medicine

Background:

Electronic Nose (eNose) breathprints show potential for non-invasive lung cancer diagnosis.
Cross-site validation and adaptation are key challenges for clinical use of eNose technology.
The efficacy of large language models (LLMs) for few-shot, site-specific lung cancer classification using eNose data is unexplored.

Purpose of the Study:

To investigate if a natural language processing-pretrained LLM can enable few-shot, site-specific classification of lung cancer from eNose breathprints.
To compare the performance of an LLM against traditional Convolutional Neural Networks (CNNs) in this task.

Main Methods:

Collected 432 eNose breathprints from lung cancer and non-lung cancer patients across two medical centers in Taiwan.

Keywords:

breathprint diagnosis electronic nose large language model lung cancer

Related Experiment Videos

Last Updated: May 23, 2026

Ultra-Fast Amplicon-Based Next-Generation Sequencing in Non-Squamous Non-Small Cell Lung Cancer

Ultra-Fast Amplicon-Based Next-Generation Sequencing in Non-Squamous Non-Small Cell Lung Cancer

Published on: September 8, 2023

Utilized a GPT-2-backbone LLM with parameter-efficient adaptation.

Compared LLM performance with CNNs trained from scratch or pretrained on CIFAR-100, using few-shot (2-6 samples/class) and full-data protocols.

Main Results:

With 6 shots, the LLM achieved an AUC of 0.79 on Site 1 and 0.76 on Site 2.
The LLM significantly outperformed both scratch CNNs and CIFAR-100 pretrained CNNs on both sites (p < 0.05).
Transfer learning to a new site did not improve performance for either LLM or CNN models, with LLM performance even slightly decreasing.

Conclusions:

Pretrained LLMs demonstrate potential for few-shot lung cancer classification using eNose breathprints in mixed clinical settings.
This approach can reduce the need for extensive training datasets in developing non-invasive lung cancer diagnostics.
Further research is needed to address cross-site adaptation challenges for robust clinical deployment.