Multi-Disciplinary Treatment on the Anthropomorphism of Large Language Models

Sponsor
North Sichuan Medical College
Study ID
NCT06627985
Status
Not Yet Recruiting

Notify me when recruiting opens

Save your spot on the interest list for this study. We'll keep your details with this study so our team can follow up when recruiting opens.

Not yet recruiting

Add your contact details and location so we can keep your interest tied to this study.

Conditions

  • Cancer
  • Disease
  • Heart Diseases
  • Infections
  • Pneumonia
  • Respiratory Failure

Eligibility Criteria

Sex
ALL
Age
N/A - N/A
Healthy Volunteers
Not accepted

Interventions

  • GPT-4o — DIAGNOSTIC_TEST
    Input all patient medical records, including text, examination reports, and imaging data, into GPT-4o. Use pre-tested prompts to establish department roles, enabling it to provide diagnostic and treatment recommendations pertinent to the respective department.
  • GPT-4o mini — DIAGNOSTIC_TEST
    Input all patient medical records, including text, examination reports, and imaging data, into GPT-4o mini. Use pre-tested prompts to establish department roles, enabling it to provide diagnostic and treatment recommendations pertinent to the respective department.
  • MedicalGPT — DIAGNOSTIC_TEST
    Input all patient medical records, including text, examination reports, and imaging data, into MedicalGPT. Use pre-tested prompts to establish department roles, enabling it to provide diagnostic and treatment recommendations pertinent to the respective department.
  • Claude-3.5 Sonnet — DIAGNOSTIC_TEST
    Input all patient medical records, including text, examination reports, and imaging data, into Claude-3.5 Sonnet. Use pre-tested prompts to establish department roles, enabling it to provide diagnostic and treatment recommendations pertinent to the respective department.
  • Claude 3 Haiku — DIAGNOSTIC_TEST
    Input all patient medical records, including text, examination reports, and imaging data, into Claude 3 Haiku. Use pre-tested prompts to establish department roles, enabling it to provide diagnostic and treatment recommendations pertinent to the respective department.
  • Real Doctors — DIAGNOSTIC_TEST
    Retrospectively collect the diagnostic and treatment recommendations from the corresponding departments involved in the multidisciplinary treatment of past patients, as well as the overall recommendations.

Study Details

This retrospective clinical trial aims to better explore the potential of large language models in medicine by comparing the effectiveness of MDT consultations conducted by human doctors with those conducted by large language models. The main questions to be addressed are: Does using large language models to conduct anthropomorphic MDT consultations yield better results than using non-anthropomorphic processes? Is there a significant performance gap between MDT consultations conducted by large language models and those conducted by humans? How much greater is the economic benefit of MDT consultations from large language models compared to those conducted by humans? Retrospectively collect MDT consultation records from the past 20 years in northern Sichuan in China, as well as anonymized patient medical records. Group 1: Different large language models are assigned to act as doctors from different departments and as MDT secretaries to summarize consultations. Group 2: The large language model directly outputs diagnostic and treatment recommendations for patients. Compare the outputs of groups 1 and 2 with human performance retrospectively, score them, and select the best model from each department for a re-evaluation through anthropomorphic MDT consultations, once again comparing them to human results.

Key Dates

First listed
Oct 4, 2024
Start date
Oct 1, 2024
Status verified
Oct 2024
Primary completion
Nov 1, 2024
Completion
Nov 1, 2024

Study Design

Enrollment
300 participants (estimated)

Arms

  • Arm: Anthropomorphized Process Large Language Model Multidisciplinary Treatment Group
    Using a locally deployed MedicalGPT, the commercially available online GPT-4o, Claude-3.5 Sonnet, GPT-4o mini, and Claude 3 Haiku, will each sequentially play the role of physicians from different departments involved in the Multi-Disciplinary Treatment Process. They will then sequentially take on the role of a summarizer to compile their recommendations into a final suggestion or treatment plan.
  • Arm: Non-anthropomorphized Process Large Language Model Multidisciplinary Treatment Group
    Using a locally deployed MedicalGPT, the commercial online GPT-4o, Claude-3.5 Sonnet, GPT-4o mini, and Claude 3 Haiku to output multidisciplinary consultation results in a single instance, without separately assuming roles for each department and then compiling the results.
  • Arm: Real Doctors Multi-Disciplinary Treatment Group
    In traditional multidisciplinary treatments, the results are documented in the consultation records of the patients involved, including the recommendations from doctors of various departments who participated in the consultation and the final summary by the secretary.
  • Arm: Best Large Language Model Multidisciplinary Treatment Group
    After scoring the results of the Anthropomorphized Process Large Language Model Multidisciplinary Treatment Group against the outcomes of the Real Doctors' Multi-Disciplinary Treatment Group on a department-by-department basis, the best substitute models and the best summary models for each department were selected. These top models are set to assume roles in a Multi-Disciplinary Treatment consultation.

Primary Outcome Measure

Consultation Cost ($) [ Time Frame: From Multi-Disciplinary Treatment Process to Multi-Disciplinary Treatment Process until all json fields are output, the time taken by human doctors to record the time using His system generally does not exceed 12 hours. ]

Central Contacts

Related Studies