AI Models in Clinical Pathology Diagnosis: A Multicenter RCT

Официальное название

Performance of AI Models in the Clinical Pathology Diagnostic Workflow: A Multicenter, Prospective, Randomized Controlled Trial

Обзор

The investigators plan to conduct a multicenter, prospective, randomized controlled trial to systematically evaluate the incremental value of pathology-based artificial intelligence (AI) models in a pan-disease diagnostic workflow. The study will primarily compare interpretation using an AI-assisted platform with conventional independent slide reading in terms of diagnostic accuracy (e.g., AUC), reading efficiency (e.g., diagnostic time), diagnostic report quality, diagnostic confidence (Likert scale), and pathologists' satisfaction with the AI model. Investigators will also assess superiority among less experienced (junior) pathologists and non-inferiority among more experienced (senior) pathologists. Successful completion of this project will provide high-level prospective evidence to support standardized deployment, quality control, and broader implementation of pathology AI in clinical practice. This trial may also evaluate the potential benefits and risks of using AI tools in medical research.

Подробное описание

In this study, investigators plan to enroll 60 pathologists with varying levels of experience and 2,000 patients requiring pathological diagnosis, with whole-slide images (WSIs) collected.

Вмешательства

• Другое AI model
  Doctors in this group are required to use the AI model to assist their diagnoses. The AI pathology model will provide a predicted result for each case.
• Другое Control
  Pathologists will independently diagnose each case based on their own clinical experience, and will record both their time to diagnosis and their diagnostic confidence.

Первичные конечные точки

• Area under ROC curve (AUC) [Срок оценки: Assessments will be conducted within one week after the pathologists' diagnoses]

Вторичные конечные точки (2)

• Diagnostic time per case [Срок оценки: Measured immediately after the pathologists' diagnosis]
• Pathologists' diagnostic confidence [Срок оценки: At the time of diagnosis for each case.]

Критерии участия

Pathologists:

Критерии включения

• Voluntarily provide written informed consent.
• Age ≥ 20 years.
• Have completed at least 1 year of training in pathological diagnosis.

Критерии исключения

• Individuals with reading difficulties or a reading disorder.
• Unwilling to participate in this study.

Patients:

Критерии включения

• Voluntarily provide written informed consent.
• Age ≥ 18 years.
• Have available digital pathology images and relevant clinical information.

Критерии исключения

• Missing data or data quality not meeting the requirements for analysis.
• Deemed unsuitable for participation by the investigator.
• Unwilling to participate in this study.

Критерии приведены из реестра в оригинале (на английском). Окончательную оценку соответствия проводит исследовательский центр.

Здоровые добровольцы: Да

Дизайн исследования

Распределение

Рандомизированное

Модель

Перекрёстный дизайн

Маскирование

Простое слепое

Основная цель

Другое

Центры проведения

Китай · 3 центра

• The First Hospital Affiliated to AMU SOUTHWEST HOSPITAL — Чунцин
• Nanfang Hospital, Southern Medical University — Гуанчжоу
• The First Affiliated Hospital of Zhengzhou University — Чжэнчжоу

Идентификаторы

NCT: NCT07408167 · NFEC-2026-059

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗