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

Related Concept Videos

Local Anesthetics: Differential Sensitivity of Nerve Fibers

Local Anesthetics: Differential Sensitivity of Nerve Fibers

Local anesthetics (LAs) block the sodium channels of nerve trunks, sensory nerve endings, and neuromuscular junctions. Although LAs can block all kinds of nerves, the sensitivity of nerve fibers differs according to nerve types and structures. LAs are known to block myelinated fibers faster than unmyelinated ones. Also, they block pain or sensory neurons at low concentrations without affecting the motor neurons involved in muscle contractions. This helps relieve labor pain without affecting the...

You might also read

Related Articles

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

Sort by

Same author

On-premises open-source large language models for privacy-preserving multimodal depression screening.

International journal of medical informatics·2026

Same author

Allergic Diseases and Risk of Incident Autoimmune Diseases: Phenotype-Specific Patterns and Multimorbidity Effects in a Nationwide Cohort.

Clinical and experimental allergy : journal of the British Society for Allergy and Clinical Immunology·2026

Same author

Impact of acute kidney injury labeling strategies in hospitalized patients: suggestion for a dual-alert clinical decision support system.

Kidney research and clinical practice·2026

Same author

Noncombustible Nicotine or Tobacco Product Use after Smoking Cessation and Major Vision-Impairing Diseases: A Nationwide Cohort Study.

American journal of ophthalmology·2026

Same author

Week-ahead prediction of depressive episodes using wearable-derived circadian biomarkers: A multicenter deep learning study with risk-based operating thresholds.

Journal of affective disorders·2026

Same author

Protist community sites and structure under two barn management systems at a commercial dairy.

Frontiers in microbiomes·2026

Same journal

Characterizing Combined Central and Peripheral Demyelination-Insights From a Multimodal Comparison With Chronic Inflammatory Demyelinating Polyneuropathy and Multiple Sclerosis.

Muscle & nerve·2026

Same journal

Electrical Modalities in the Rehabilitation of Peripheral Nerve Injuries: State of the Literature and Current Clinical Applications.

Muscle & nerve·2026

Same journal

Reply to "Sural/Radial Amplitude Ratio in Non-Length-Dependent Neuropathy (NLDN): A Call for More Standardized Methodology and Further Evaluation of Distal NLDN".

Muscle & nerve·2026

Same journal

Late-Onset Myasthenia Gravis: An Increasingly Frequent Clinical Entity With Distinctive Challenges.

Muscle & nerve·2026

Same journal

Clinical Characteristics and Treatment Management of Seronegative Myasthenia Gravis: A Systematic Review of the Literature.

Muscle & nerve·2026

Same journal

Muscle-Specific Kinase Signaling and Its Therapeutic Potential.

Muscle & nerve·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 15, 2026

Use of In Vivo Single-fiber Recording and Intact Dorsal Root Ganglion with Attached Sciatic Nerve to Examine the Mechanism of Conduction Failure

Use of In Vivo Single-fiber Recording and Intact Dorsal Root Ganglion with Attached Sciatic Nerve to Examine the Mechanism of Conduction Failure

Published on: August 27, 2019

Dual Component Framework Approach for Automated Nerve Conduction Study Interpretation: Rule-Based Coding and

Hojin Yoon^1,2, Yihyun Kim², Yeongmin Kim²

¹Department of Neurology, Korea University Anam Hospital, Seoul, Republic of Korea.

|April 14, 2026

Summary

This summary is machine-generated.

Automated nerve conduction study (NCS) interpretation using a dual framework achieved accuracy comparable to junior neurophysiologists, significantly speeding up reporting and enhancing diagnostic capabilities for neurological conditions.

Keywords:

electrophysiology fine‐tuning large language models nerve conduction study neurology

More Related Videos

In Vivo Electrophysiological Measurements on Mouse Sciatic Nerves

In Vivo Electrophysiological Measurements on Mouse Sciatic Nerves

Published on: April 13, 2014

In Vivo Electrophysiological Measurement of the Rat Ulnar Nerve with Axonal Excitability Testing

In Vivo Electrophysiological Measurement of the Rat Ulnar Nerve with Axonal Excitability Testing

Published on: February 6, 2018

Related Experiment Videos

Last Updated: Apr 15, 2026

Use of In Vivo Single-fiber Recording and Intact Dorsal Root Ganglion with Attached Sciatic Nerve to Examine the Mechanism of Conduction Failure

Use of In Vivo Single-fiber Recording and Intact Dorsal Root Ganglion with Attached Sciatic Nerve to Examine the Mechanism of Conduction Failure

Published on: August 27, 2019

In Vivo Electrophysiological Measurements on Mouse Sciatic Nerves

In Vivo Electrophysiological Measurements on Mouse Sciatic Nerves

Published on: April 13, 2014

In Vivo Electrophysiological Measurement of the Rat Ulnar Nerve with Axonal Excitability Testing

In Vivo Electrophysiological Measurement of the Rat Ulnar Nerve with Axonal Excitability Testing

Published on: February 6, 2018

Area of Science:

Neurology
Artificial Intelligence
Medical Informatics

Background:

Nerve conduction study (NCS) interpretation is a time-consuming process in clinical neurology.
Automation of NCS reporting can potentially improve workflow efficiency and diagnostic accuracy.

Purpose of the Study:

To develop and evaluate a dual framework combining rule-based coding and fine-tuned language models for NCS interpretation.
To standardize NCS reporting and enhance diagnostic accuracy.

Main Methods:

A dual framework was developed, integrating rule-based coding for data conversion and GPT-4o fine-tuning with structured NCS reports.
The model was trained on 1335 cases across 18 diagnostic categories.
Performance was evaluated on 66 test cases, comparing diagnostic accuracy and clinical rationale quality against foundation large language models and physicians.

Main Results:

The fine-tuned model achieved diagnostic accuracy comparable to junior neurophysiologists (4.40/5).
It outperformed zero-shot GPT-4o (3.56/5) with a macro F1 of 0.77 and micro F1 of 0.8.
Conclusion generation was 16 times faster than the best physician (2.88s vs. 46.34s per case), with high clinical rationale quality (4.34/5).

Conclusions:

The developed dual framework shows comparable performance to junior neurophysiologists in NCS interpretation.
It effectively streamlines parameter calculations and generates diagnostic reports with clinical rationales.
Future work should focus on multicenter and external validation of the framework.