AI-Empowered Fundus Platform

Официальное название

AI-Empowered Fundus Imaging: Building an Intelligent Platform for Diagnosis, Treatment, and Early Warning of Fundus Diseases

Обзор

According to estimates by the World Health Organization, approximately half of the global adult population currently suffers from varying degrees of myopia. In urban areas of China, the myopia rate among primary school students has reached about 40%, and can exceed 80% in high school students. The proportion of patients with high myopia (refractive error greater than 600 degrees) is also increasing year by year. This group is more prone to severe visual problems, including an increased risk of complications such as cataracts, glaucoma, and macular degeneration. Pathological myopia is the main risk factor for vision loss caused by high myopia. In such patients, the elongation of the ocular axis leads to local thinning and protrusion of the posterior pole of the eyeball, forming a posterior scleral staphyloma. Posterior scleral staphyloma is the most representative pathological feature of pathological myopia. Local dilation of the choroid leads to thinning and stretching of the retina, which may ultimately cause problems such as macular retinal schisis, seriously affecting vision and even leading to blindness. This project aims to develop a multimodal intelligent screening system by combining the excellent imaging technology and advanced artificial intelligence (AI) of the Optos non-mydriatic ultra-wide-angle laser scanning ophthalmoscope, B-scan ultrasonography ophthalmic diagnostic instrument, and optical coherence tomography (OCT). The system is designed to achieve precise identification and assessment of ocular fundus diseases, especially pathological myopia, and particularly the core condition of posterior scleral staphyloma (PSS). Simultaneously, a vision prediction model will be constructed to assist doctors in formulating personalized diagnosis and treatment strategies, predicting the trend of vision deterioration, and enhancing the effectiveness of early intervention. This system is expected to significantly improve the prevention and control of pathological myopia, reduce the risk of blindness, and play a pivotal role in telemedicine services, benefiting people in remote areas and promoting public health equity and service quality.

Вмешательства

• Диагностический тест Multimodal Ocular Imaging and Biometry with Aritifical Intelligence Analysis
  The patient underwent a complete set of fundus color photography, B-scan ultrasonography, and OCT imaging during the consultation, and preoperative baseline data, including demographic information, health status, ophthalmic history, and ocular biometric parameters, were collected and recorded in detail

Первичные конечные точки

• Data collection outcome [Срок оценки: From October 2024 to April 2026 (Data collection from patients who visited the hospital before October 2024)]

Вторичные конечные точки (1)

• AI modeling Analysis [Срок оценки: From April 2026 to October 2026]

Критерии участия

Критерии включения

Patients with a diagnosis of cataract and high myopia and posterior staphyloma, who underwent comprehensive ophthalmic examinations including ultra-widefield fundus photography (Optos), B-scan ultrasonography, and optical coherence tomography (OCT). Baseline data, including demographics, health status, ophthalmic history, and ocular biometric parameters, were completely documented.

Критерии исключения

Patients with poor-quality images affecting PSS identification, severe coexisting ocular diseases including glaucoma, diabetic retinopathy that cause media opacities, or severe systemic diseases that could interfere with the study outcomes.

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

Здоровые добровольцы: Нет

Дизайн исследования

Модель наблюдения

Только случаи

Центры проведения

Китай · 1 центр

• Shanghai 10th People's Hospital — Шанхай

Идентификаторы

NCT: NCT07424755 · SHSY-LYZX-413

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗