MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1038/s41598-023-50665-5

Медицинская библиотека · Scientific reports · 2024

Artificial intelligence enhanced ophthalmological screening in children: insights from a cohort study in Lubelskie Voivodeship.

Piotr Regulski, Robert Rejdak, Marek Niezgódka, Michał Iwański

СтатьяПеревод пока не подготовлен

Аннотация

This study aims to investigate the prevalence of visual impairments, such as myopia, hyperopia, and astigmatism, among school-age children (7-9 years) in Lubelskie Voivodeship (Republic of Poland) and apply artificial intelligence (AI) in the detection of severe ocular diseases. A total of 1049 participants (1.7% of the total child population in the region) were examined through a combination of standardized visual acuity tests, autorefraction, and assessment of fundus images by a convolutional neural network (CNN) model. The results from this artificial intelligence (AI) model were juxtaposed with assessments conducted by two experienced ophthalmologists to gauge the model's accuracy. The results demonstrated myopia, hyperopia, and astigmatism prevalences of 3.7%, 16.9%, and 7.8%, respectively, with myopia showing a significant age-related increase and hyperopia decreasing with age. The AI model performance was evaluated using the Dice coefficient, reaching 93.3%, indicating that the CNN model was highly accurate. The study underscores the utility of AI in the early detection and diagnosis of severe ocular diseases, providing a foundation for future research to improve paediatric ophthalmic screening and treatment outcomes.

Для цитирования: Piotr Regulski, Robert Rejdak, Marek Niezgódka, Michał Iwański. Artificial intelligence enhanced ophthalmological screening in children: insights from a cohort study in Lubelskie Voivodeship.. Scientific reports. 2024. DOI: 10.1038/s41598-023-50665-5.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.