Large Language Models for Epidural Stimulation Electrode Mapping in Spinal Cord Injury
8. september 2026 opdateret af: Görkem Açar, Istanbul Gelisim University
AI-Assisted Electrode Contact Configuration Mapping for Epidural Electrical Stimulation in Spinal Cord Injury: A Comparative Evaluation of Large Language Models
This observational and methodological study aims to compare the performance of large language models in generating electrode contact configuration recommendations for epidural electrical stimulation in spinal cord injury.
Five standardized synthetic spinal cord injury scenarios will be presented to four large language models: ChatGPT-4o, Claude, Grok 3, and Gemini 2.5 Pro. Each model will receive the same standardized prompt. The generated responses will be anonymized and evaluated independently by experts with experience in spinal cord injury rehabilitation and epidural electrical stimulation.
The responses will be assessed in five main areas: clinical accuracy, technical feasibility, safety awareness, consistency with current clinical guidance, and completeness of the response. Agreement between expert evaluators will also be examined.
No real patients, human participants, clinical interventions, or personal health data are included in this study. The study is designed to explore the potential and current limitations of large language models as artificial intelligence-based clinical decision-support tools in neurorehabilitation.
Studieoversigt
Status
Aktiv, ikke rekrutterende
Betingelser
Undersøgelsestype
Observationel
Tilmelding (Faktiske)
20
Kontakter og lokationer
Dette afsnit indeholder kontaktoplysninger for dem, der udfører undersøgelsen, og oplysninger om, hvor denne undersøgelse udføres.
Studiesteder
-
-
Istanbul
-
Istanbul, Istanbul, Tyrkiet (Türkiye), 34290
- Istanbul Gelisim University
-
-
Deltagelseskriterier
Forskere leder efter personer, der passer til en bestemt beskrivelse, kaldet berettigelseskriterier. Nogle eksempler på disse kriterier er en persons generelle helbredstilstand eller tidligere behandlinger.
Berettigelseskriterier
Aldre berettiget til at studere
- Barn
- Voksen
- Ældre voksen
Tager imod sunde frivillige
Ingen
Prøveudtagningsmetode
Ikke-sandsynlighedsprøve
Studiebefolkning
No human study population is included.
The analytical sample consists of five standardized synthetic spinal cord injury scenarios and the responses generated for these scenarios by ChatGPT-4o, Claude, Grok 3, and Gemini 2.5 Pro.
Each model is evaluated under the same standardized prompting conditions.
Model outputs are anonymized and independently rated by expert evaluators for clinical accuracy, technical feasibility, safety awareness, consistency with clinical guidance, and response completeness.
Beskrivelse
Inclusion Criteria:
- Responses generated for one of the five predefined standardized synthetic spinal cord injury scenarios.
- Responses generated using the identical standardized prompt specified in the study protocol.
- Responses generated by one of the four prespecified large language models.
- Complete responses available for expert evaluation.
Exclusion Criteria:
- Responses generated using prompts that differ from the standardized study prompt.
- Incomplete, interrupted, or technically corrupted model outputs.
- Duplicate responses or outputs not corresponding to a predefined synthetic scenario.
- Any response generated using real patient-identifiable or personal health information.
Studieplan
Dette afsnit indeholder detaljer om studieplanen, herunder hvordan undersøgelsen er designet, og hvad undersøgelsen måler.
Hvordan er undersøgelsen tilrettelagt?
Design detaljer
Kohorter og interventioner
Gruppe / kohorte |
Intervention / Behandling |
|---|---|
|
ChatGPT-4o
Responses generated by ChatGPT-4o for five standardized synthetic spinal cord injury scenarios using the same standardized prompt.
The responses will be evaluated for clinical accuracy, technical feasibility, safety awareness, guideline consistency, and completeness.
|
The large language model receives five standardized synthetic spinal cord injury scenarios using an identical standardized prompt and generates recommendations for epidural electrical stimulation electrode contact configuration mapping.
No intervention is administered to human participants.
|
|
Claude
Responses generated by Claude for five standardized synthetic spinal cord injury scenarios using the same standardized prompt.
The responses will be evaluated for clinical accuracy, technical feasibility, safety awareness, guideline consistency, and completeness.
|
The large language model receives five standardized synthetic spinal cord injury scenarios using an identical standardized prompt and generates recommendations for epidural electrical stimulation electrode contact configuration mapping.
No intervention is administered to human participants.
|
|
Grok 3
Responses generated by Grok 3 for five standardized synthetic spinal cord injury scenarios using the same standardized prompt.
The responses will be evaluated for clinical accuracy, technical feasibility, safety awareness, guideline consistency, and completeness.
|
The large language model receives five standardized synthetic spinal cord injury scenarios using an identical standardized prompt and generates recommendations for epidural electrical stimulation electrode contact configuration mapping.
No intervention is administered to human participants.
|
|
Gemini 2.5 Pro
Responses generated by Grok 3 for five standardized synthetic spinal cord injury scenarios using the same standardized prompt.
The responses will be evaluated for clinical accuracy, technical feasibility, safety awareness, guideline consistency, and completeness.
|
The large language model receives five standardized synthetic spinal cord injury scenarios using an identical standardized prompt and generates recommendations for epidural electrical stimulation electrode contact configuration mapping.
No intervention is administered to human participants.
|
Hvad måler undersøgelsen?
Primære resultatmål
Resultatmål |
Foranstaltningsbeskrivelse |
Tidsramme |
|---|---|---|
|
Clinical Accuracy Score of Large Language Model Responses
Tidsramme: At the time of expert evaluation, within 1 week after study initiation
|
Clinical accuracy of the epidural electrical stimulation electrode contact configuration recommendations generated by each large language model will be independently evaluated by expert reviewers using a 5-point Likert-type rating scale.
Higher scores indicate greater clinical accuracy of the generated recommendations.
|
At the time of expert evaluation, within 1 week after study initiation
|
Sekundære resultatmål
Resultatmål |
Foranstaltningsbeskrivelse |
Tidsramme |
|---|---|---|
|
Technical Feasibility Score of Large Language Model Responses
Tidsramme: At expert evaluation, within 1 week after study initiation
|
The technical feasibility of epidural electrical stimulation electrode contact configuration recommendations generated by each large language model will be independently evaluated by expert reviewers using a 5-point Likert-type rating scale.
Higher scores indicate greater technical feasibility and applicability of the generated recommendations.
|
At expert evaluation, within 1 week after study initiation
|
|
Safety Awareness Score of Large Language Model Responses
Tidsramme: At expert evaluation, within 1 week after study initiation
|
The safety awareness demonstrated in the epidural electrical stimulation electrode contact configuration recommendations generated by each large language model will be independently evaluated by expert reviewers using a 5-point Likert-type rating scale.
Higher scores indicate greater recognition and consideration of relevant safety issues.
|
At expert evaluation, within 1 week after study initiation
|
|
Clinical Guideline Consistency Score of Large Language Model Responses
Tidsramme: At expert evaluation, within 1 week after study initiation
|
The consistency of the generated epidural electrical stimulation electrode contact configuration recommendations with current clinical guidance will be independently evaluated by expert reviewers using a 5-point Likert-type rating scale.
Higher scores indicate greater consistency with current clinical guidance and relevant evidence-based recommendations.
|
At expert evaluation, within 1 week after study initiation
|
|
Response Completeness Score of Large Language Model Responses
Tidsramme: At expert evaluation, within 1 week after study initiation
|
The completeness of the epidural electrical stimulation electrode contact configuration recommendations generated by each large language model will be independently evaluated by expert reviewers using a 5-point Likert-type rating scale.
Higher scores indicate more complete and comprehensive responses.
|
At expert evaluation, within 1 week after study initiation
|
Samarbejdspartnere og efterforskere
Det er her, du vil finde personer og organisationer, der er involveret i denne undersøgelse.
Sponsor
Datoer for undersøgelser
Disse datoer sporer fremskridtene for indsendelser af undersøgelsesrekord og resumeresultater til ClinicalTrials.gov. Studieregistreringer og rapporterede resultater gennemgås af National Library of Medicine (NLM) for at sikre, at de opfylder specifikke kvalitetskontrolstandarder, før de offentliggøres på den offentlige hjemmeside.
Studer store datoer
Studiestart (Faktiske)
2. september 2026
Primær færdiggørelse (Anslået)
9. september 2026
Studieafslutning (Anslået)
9. september 2026
Datoer for studieregistrering
Først indsendt
8. september 2026
Først indsendt, der opfyldte QC-kriterier
8. september 2026
Først opslået (Faktiske)
14. september 2026
Opdateringer af undersøgelsesjournaler
Sidste opdatering sendt (Faktiske)
14. september 2026
Sidste opdatering indsendt, der opfyldte kvalitetskontrolkriterier
8. september 2026
Sidst verificeret
1. september 2026
Mere information
Begreber relateret til denne undersøgelse
Yderligere relevante MeSH-vilkår
Andre undersøgelses-id-numre
- EES-LLM-2026-01
Lægemiddel- og udstyrsoplysninger, undersøgelsesdokumenter
Studerer et amerikansk FDA-reguleret lægemiddelprodukt
Ingen
Studerer et amerikansk FDA-reguleret enhedsprodukt
Ingen
Disse oplysninger blev hentet direkte fra webstedet clinicaltrials.gov uden ændringer. Hvis du har nogen anmodninger om at ændre, fjerne eller opdatere dine undersøgelsesoplysninger, bedes du kontakte register@clinicaltrials.gov. Så snart en ændring er implementeret på clinicaltrials.gov, vil denne også blive opdateret automatisk på vores hjemmeside .