Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Spinal Cord: Information Processing01:10

Spinal Cord: Information Processing

4.2K
The spinal cord is an integral hub for motor and sensory information that enables the brain to communicate with the peripheral nervous system (PNS). This communication consists of relaying sensory data and transmission of motor commands.
Sensory Information Processing
Sensory information processing begins at the sensory receptors located in the skin and other tissues, which detect somatic sensory stimuli such as touch, temperature, or pain. These receptors function as catalysts, initiating...
4.2K

You might also read

Related Articles

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

Sort by
Same author

Updated 2026 Comprehensive Evidence-Based Guidelines for Facet Joint Interventions in the Management of Chronic Spinal Pain: American Society of Interventional Pain Physicians (ASIPP) Guidelines.

Pain physician·2026
Same author

The Current Scope of Pain Medicine Fellowships: A Cross-Sectional Survey Study of Trainees, Directors, and Employers on Shaping Future Leaders.

Journal of pain research·2026
Same author

Current State of Orthobiologics in Treatment of Knee Osteoarthritis-Future Directions.

International journal of molecular sciences·2026
Same author

Proposed Conditions for Pain Reprocessing Therapy Readiness: Beyond Phenotyping Neuroplastic Pain.

Current pain and headache reports·2026
Same author

Artificial Intelligence in Neuropathic Pain: From Mechanisms to Neuromodulation and Regenerative Strategies.

Current pain and headache reports·2026
Same author

Differential target multiplexed SCS (DTM SCS): a rational hypothesis.

Pain medicine (Malden, Mass.)·2026

Related Experiment Video

Updated: Mar 24, 2026

Bilateral Assessment of the Corticospinal Pathways of the Ankle Muscles Using Navigated Transcranial Magnetic Stimulation
11:06

Bilateral Assessment of the Corticospinal Pathways of the Ankle Muscles Using Navigated Transcranial Magnetic Stimulation

Published on: February 19, 2019

9.2K

Smart Processing and Intelligent Navigation for Evaluation (SPINE): Comparing Clinicians and AI Language Model

Giuliano Lo Bianco1, Alexandra Therond2, Francesco Paolo D'angelo3

  • 1Anesthesiology and Pain Department, Fondazione Istituto G. Giglio Cefalù, Palermo, Italy.

Journal of Pain Research
|March 23, 2026
PubMed
Summary

Artificial intelligence (AI) models like GPT-4 can assist in patient selection for spinal cord stimulation (SCS). However, a general-purpose GPT-4 showed lower agreement with expert teams, acting as a conservative filter for SCS candidacy.

Keywords:
artificial intelligencechronic painlarge-language modelsneuromodulationpatient selectionspinal cord stimulation

More Related Videos

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.4K
Treating Low Back Pain in Failed Back Surgery Patients with Multicolumn-lead Spinal Cord Stimulation
04:42

Treating Low Back Pain in Failed Back Surgery Patients with Multicolumn-lead Spinal Cord Stimulation

Published on: June 26, 2018

15.3K

Related Experiment Videos

Last Updated: Mar 24, 2026

Bilateral Assessment of the Corticospinal Pathways of the Ankle Muscles Using Navigated Transcranial Magnetic Stimulation
11:06

Bilateral Assessment of the Corticospinal Pathways of the Ankle Muscles Using Navigated Transcranial Magnetic Stimulation

Published on: February 19, 2019

9.2K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.4K
Treating Low Back Pain in Failed Back Surgery Patients with Multicolumn-lead Spinal Cord Stimulation
04:42

Treating Low Back Pain in Failed Back Surgery Patients with Multicolumn-lead Spinal Cord Stimulation

Published on: June 26, 2018

15.3K

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Decision Support Systems
  • Spinal Cord Stimulation

Background:

  • Advancements in AI, particularly large language models (LLMs) like GPT-4, offer potential for clinical decision support.
  • Evaluating patient candidacy for spinal cord stimulation (SCS) is a complex process where AI may assist.
  • This study compares a general-purpose LLM (GPT-4) against expert multidisciplinary teams (MDT) and an e-Health tool for SCS candidacy decisions.

Purpose of the Study:

  • To compare the decision agreement between a general-purpose LLM (GPT-4), an expert MDT, and a rule-based e-Health tool for SCS patient candidacy.
  • To assess the performance of GPT-4 in approximating MDT decision-making for SCS referrals.
  • To analyze the sensitivity and specificity of GPT-4 and the e-Health tool in SCS candidate selection.

Main Methods:

  • A retrospective cohort study of 93 adult patients referred for SCS evaluation.
  • Comparison of recommendations from an expert MDT (reference standard), a clinician-input e-Health tool, and zero-shot GPT-4 using standardized prompts.
  • Primary endpoint was weighted kappa (κ) for agreement; sensitivity/specificity analyses were performed.

Main Results:

  • The MDT recommended SCS for 91.4% of patients, while the e-Health tool recommended it for 54.8% and GPT-4 for 46.2%.
  • Agreement was moderate between MDT and e-Health (κ=0.51), and e-Health and GPT-4 (κ=0.46), but only fair between MDT and GPT-4 (κ=0.29).
  • GPT-4 exhibited a conservative decision-making profile, prioritizing specificity over sensitivity.

Conclusions:

  • A non-fine-tuned GPT-4 approximated but did not replicate MDT decisions for SCS candidacy, acting as a high-specificity, low-sensitivity filter.
  • A combined approach utilizing rule-based tools, expert oversight, and adapted LLMs may optimize SCS candidate selection.
  • Further research into tailored LLM applications is warranted for improving clinical decision support in SCS.