An International Multicenter Clinical Study on Application of UroMed AI Doctor Based on Large Language Models

Официальное название

AN INTERNATIONAL MULTICENTER CLINICAL STUDY ON APPLICATION OF UROMED AI DOCTOR BASED ON LARGE LANGUAGE MODELS

Обзор

This study evaluates our team's urology-specific AI (UroMed AI Doctor) for its safety, professionalism, knowledge and Q\&A ability, and tests its effectiveness against traditional manual urology care, to confirm if it can be a safe auxiliary tool and improve patients' preoperative experience. Before the study, we will test the AI with urology questions, compare it to international AI models (DeepSeek, ChatGPT, Google Gemini), and have two senior chief physicians evaluate it. In the clinical trial, patients at The First Affiliated Hospital of Guangxi Medical University will be randomly split into two groups: AI-assisted care or traditional care by a specialist. Two senior specialists will evaluate both groups blindly; each group will get preoperative education (AI or physician), with anxiety and satisfaction surveyed. Subsequently, a multi-center validation will be conducted with 11 domestic and international hospitals.

Подробное описание

Prior to the clinical study, the knowledge base, Q\&A capability, professionalism, and safety of the urology UroMed AI Doctor independently developed by our team will be evaluated. The evaluation method involves using the UroMed AI Doctor for public science Q\&A and answering standard urology examination questions (multiple-choice and case analysis questions). Comparisons will be made with internationally recognized large language models such as DeepSeek, ChatGPT, and Google Gemini. Two senior chief physicians will conduct the evaluation based on a scoring rubric. In the clinical study phase, trial cases will first be recruited at the lead institution, The First Affiliated Hospital of Guangxi Medical University. Enrolled patients will be randomly assigned to either the UroMed AI Doctor-assisted diagnosis and treatment group or the traditional manual diagnosis and treatment group. The scope of UroMed AI Doctor assistance includes providing auxiliary diagnosis and treatment plans based on the admission records of urology inpatients. The traditional manual group will have these tasks completed by one specialist attending physician. The evaluation will be independently conducted by two senior chief specialists using a blinded method. Furthermore, the UroMed AI Doctor and the attending physician will respectively provide preoperative science education to patients within their groups. The post-education anxiety reduction and satisfaction levels of patients in both groups will be compared using survey scales. Subsequently, a multi-center clinical validation was conducted in collaboration with 11 clinical research centers both domestically and internationally, including Guilin People's Hospital, Yulin Red Cross Hospital, Liuzhou Hospital of Traditional Chinese Medicine, Guigang People's Hospital, Nanning Second People's Hospital, Affiliated Hospital of Youjiang Medical University for Nationalities, Beihai People's Hospital, as well as Binh Duong General Hospital, Hue Central Hospital, Viet Duc Hospital, and the University of Medicine and Pharmacy at Ho Chi Minh City in Vietnam.

Вмешательства

• Другое UroMed AI Doctor-assisted Urological Diagnosis, Treatment and Preoperative Health Education
  This urological intervention uses the independently developed UroMed AI Doctor, a urology-specialized large language model system distinct from generic medical AI tools. Trained \*\*exclusively\*\* on the latest international urology guidelines and high-quality literature, it has a built-in data cleaning system blocking non-standard knowledge sources, eliminating factual deviations and guideline misalignment common in general LLMs. It provides two core AI-assisted services for kidney stone, BPH
• Другое Physician-led Urological Diagnosis, Treatment & Preoperative Education
  This intervention consists of standard, physician-led urological care without any artificial intelligence support. Qualified urologists independently diagnose and create personalized treatment plans for inpatients with kidney stones, BPH, or bladder cancer, following official clinical guidelines and consensus. One-on-one preoperative education, including disease information, treatment procedures, and postoperative care, is provided directly by attending physicians. This arm represents routine cl

Первичные конечные точки

• Comprehension of Medical Cases [Срок оценки: Baseline Day 1]
• Adherence to Medical Guidelines and Consensus [Срок оценки: Baseline Day 1]
• Clinical Reasoning [Срок оценки: Baseline Day 1]
• Relevance of Differential Diagnoses [Срок оценки: Baseline Day 1]
• Diagnostic Acceptability [Срок оценки: Baseline Day 1]
• Presence of Unrealistic Content [Срок оценки: Baseline Day 1]
• Bias and Unfairness [Срок оценки: Baseline Day 1]
• Potential Harm [Срок оценки: Baseline Day 1]

Вторичные конечные точки (3)

• Science Education Text Score [Срок оценки: Immediately after the formulation of preoperative science education content for each enrolled patient]
• Inpatient Preoperative Anxiety Score (HADS-A) [Срок оценки: Perioperative/Periprocedural]
• Patient Satisfaction Score with Health Education [Срок оценки: Baseline Day 1]

Критерии участия

Критерии включения

• Diagnosed with kidney stones, benign prostatic hyperplasia, or bladder cancer in line with the Chinese Guidelines for the Diagnosis and Treatment of Urological and Andrological Diseases (2022 Edition) and requiring hospitalization for surgery.

Aged 18 to 60 years with good communication skills. Voluntarily agrees to participate in the clinical study and has signed the informed consent form.

Критерии исключения

• Suffers from psychiatric disorders. Refuses to participate in medical activities involving the use of artificial intelligence systems.

Unable to engage in effective communication with the research team. Has multiple underlying diseases with unstable clinical conditions.

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

Здоровые добровольцы: Нет

Дизайн исследования

Распределение

Рандомизированное

Модель

Параллельные группы

Маскирование

Простое слепое

Основная цель

Диагностика

Центры проведения

Вьетнам · 4 центра

• Binh Duong General Hospital — Thu Dau Mot
• Viet Duc University Hospital — Hanoi
• Faculty of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City — Ho Chi Minh City
• Hue Central Hospital — Huế

Китай · 1 центр

• The First Affiliated Hospital of Guangxi Medical University — Nanning

Идентификаторы

NCT: NCT07555756 · 2026-K0059 · guikeFN2504240032

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗