NCT07485465

Brief Summary

A domain-specific, custom-trained large language model for the differential diagnosis and treatment planning of lymphedema, lipedema, and venous insufficiency.

Trial Health

43
At Risk

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Trial has exceeded expected completion date
Enrollment
25

participants targeted

Target at below P25 for all trials

Timeline
Completed

Started Mar 2026

Shorter than P25 for all trials

Geographic Reach
1 country

1 active site

Status
not yet recruiting

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

First Submitted

Initial submission to the registry

March 4, 2026

Completed
11 days until next milestone

Study Start

First participant enrolled

March 15, 2026

Completed
5 days until next milestone

First Posted

Study publicly available on registry

March 20, 2026

Completed
12 days until next milestone

Primary Completion

Last participant's last visit for primary outcome

April 1, 2026

Completed
Same day until next milestone

Study Completion

Last participant's last visit for all outcomes

April 1, 2026

Completed
Last Updated

March 20, 2026

Status Verified

March 1, 2026

Enrollment Period

17 days

First QC Date

March 4, 2026

Last Update Submit

March 17, 2026

Conditions

LymphedemaArtificial Intelligence (AI)

Keywords

lymphedemachat gptartificial intelligence

Outcome Measures

Primary Outcomes (3)

  • Diagnostic accuracy rate

    Percentage of cases where the primary diagnosis (most likely diagnosis) was correctly determined. The maximum percentage for each case was 100, and the minimum percentage was 0. Higher percentages mean a better outcome.

    1 hour

  • Treatment adequacy rate

    Percentage of treatment recommendations consistent with current guidelines. The maximum percentage for each case was 100, and the minimum percentage was 0. Higher percentages mean a better outcome.

    1 hour

  • Average criterion score

    Average Likert score of two evaluators for each criterion. The maximum score for each case was 40, and the minimum score was 8. higher scores mean a better outcome.

    1 hour

Secondary Outcomes (1)

  • Overall performance score

    1 hour

Interventions

a domain-specific, custom-trained large language model for the differential diagnosis and treatment planning of lymphedema, lipedema, and venous insufficiencyOTHER

LymphedemaGPT was designed to analyze structured patient data to extract clinical summaries, present possible diagnoses with percentage probabilities, create differential diagnosis tables, suggest additional diagnostic tests, and generate evidence-based treatment plans.

Eligibility Criteria

Age18 Years+
Sexall
Healthy VolunteersNo
Age GroupsAdult (18-64), Older Adult (65+)
Sampling MethodProbability Sample
Study Population

secondary lymphedema cases (post-pelvic surgery, post-breast cancer), primary lymphedema cases, lipedema cases (different types and stages), chronic venous insufficiency cases, mixed edema cases, and atypical presentations with diagnostic difficulties

You may qualify if:

  • Patients over the age of 18
  • Clinical diagnosis of lymphoedema
  • Clinical diagnosis of lipoedema
  • Clinical diagnosis of venous insufficiency

You may not qualify if:

  • Lack of medical history
  • Lack of demographic data
  • Lack of clinical data and
  • Lack of imaging methods

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (1)

Istanbul Fatih Sultan Mehmet Training and Research Hospital

Istanbul, Istanbul, 34704, Turkey (Türkiye)

Location

Related Publications (4)

  • Leypold T, Lingens LF, Beier JP, Boos AM. Integrating AI in Lipedema Management: Assessing the Efficacy of GPT-4 as a Consultation Assistant. Life (Basel). 2024 May 20;14(5):646. doi: 10.3390/life14050646.

    PMID: 38792666BACKGROUND

  • Eldaly AS, Avila FR, Torres-Guzman RA, Maita K, Garcia JP, Serrano LP, Forte AJ. Artificial intelligence and lymphedema: State of the art. J Clin Transl Res. 2022 Jun 1;8(3):234-242. eCollection 2022 Jun 29.

    PMID: 35813896BACKGROUND

  • Wojcik S, Rulkiewicz A, Pruszczyk P, Lisik W, Pobozy M, Domienik-Karlowicz J. Beyond ChatGPT: What does GPT-4 add to healthcare? The dawn of a new era. Cardiol J. 2023;30(6):1018-1025. doi: 10.5603/cj.97515. Epub 2023 Oct 13.

    PMID: 37830256BACKGROUND

  • Mesko B. The Impact of Multimodal Large Language Models on Health Care's Future. J Med Internet Res. 2023 Nov 2;25:e52865. doi: 10.2196/52865.

    PMID: 37917126BACKGROUND

MeSH Terms

Conditions

Lymphedema

Condition Hierarchy (Ancestors)

Lymphatic DiseasesHemic and Lymphatic Diseases

Study Officials

  • Yunus Emre Doğan, MD

    Istanbul Fatih Sultan Mehmet Training and Research Hospital

    PRINCIPAL INVESTIGATOR

  • Feyza Akan Begoğlu, MD

    Istanbul Fatih Sultan Mehmet Training and Research Hospital

    STUDY CHAIR

  • Mesut Canlı, MD

    Istanbul Fatih Sultan Mehmet Training and Research Hospital

    STUDY CHAIR

  • İlknur Aktaş, MD, Prof.

    Istanbul Fatih Sultan Mehmet Training and Research Hospital

    STUDY CHAIR

  • Feyza Ünlü Özkan, MD, Prof.

    Istanbul Fatih Sultan Mehmet Training and Research Hospital

    STUDY CHAIR

Central Study Contacts

Yunus Emre Doğan, MD

CONTACT

+90 506 051 25 00ynsemredgn91@gmail.com

Study Design

Study Type
observational
Observational Model
CASE ONLY
Time Perspective
CROSS SECTIONAL
Target Duration
1 Day
Sponsor Type
OTHER
Responsible Party
SPONSOR

Study Record Dates

First Submitted

March 4, 2026

First Posted

March 20, 2026

Study Start

March 15, 2026

Primary Completion

April 1, 2026

Study Completion

April 1, 2026

Last Updated

March 20, 2026

Record last verified: 2026-03

Data Sharing

IPD Sharing
Will not share

Locations

TU(1)