Journal of refractive surgery (Thorofare, N.J. : 1995) · 2026
Optical Character Recognition-based Biometry Scanner for Easy and Efficient Biometry Calculations.
СтатьяВалидационное исследованиеНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
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.
Levy Issac, Dick H Burkhard, Israeli Arbel, Schendel Amit, Nanavaty Mayank A
Аннотация
PURPOSE: To describe the development and validation of an optical character recognition (OCR)-based mobile application (Biometry Scanner, Version 1.0; Ocumetric Innovations Ltd) designed to automate biometric data entry into the European Society of Cataract and Refractive Surgeons (ESCRS) intraocular lens (IOL) calculator, thereby reducing transcription errors and improving workflow efficiency in cataract surgery planning.
METHODS: A cross-platform mobile application integrating artificial intelligence-powered OCR technology (Google Gemini 2.5) was developed for iOS and Android. The app processes biometry printouts from any device, extracts numerical data, and automatically populates the ESCRS IOL calculator. Validation comprised two components: a user experience survey of 21 ophthalmologists using 5-point Likert scales after 4 weeks of clinical use, and a prospective time-and-motion study comparing manual versus app-based data entry across five biometry calculations performed by 10 ophthalmologists. Paired t-tests were used for statistical comparison.
RESULTS: Twelve ophthalmologists completed the survey, with 50% reporting more than 11 uses and 30% more than 21 uses. Mean Likert scores were 4.5 ± 0.67 for OCR accuracy, 4.5 ± 0.8 for ease of use, and 4.67 ± 0.65 for recommendation to colleagues. The time-motion analysis demonstrated significantly faster app-based entry (91.72 ± 5.59 seconds) than manual entry (179.42 ± 22.12 seconds), resulting in a 48.9% time reduction (P < .001). Time savings were consistent across all five biometry calculations (43.1% to 52.7% reduction).
CONCLUSIONS: The Biometry Scanner provides a streamlined, accurate, and user-friendly solution for automating IOL power calculations. By eliminating manual transcription, it enhances accuracy, saves time, and promotes safer, more efficient preoperative cataract surgery planning.
METHODS: A cross-platform mobile application integrating artificial intelligence-powered OCR technology (Google Gemini 2.5) was developed for iOS and Android. The app processes biometry printouts from any device, extracts numerical data, and automatically populates the ESCRS IOL calculator. Validation comprised two components: a user experience survey of 21 ophthalmologists using 5-point Likert scales after 4 weeks of clinical use, and a prospective time-and-motion study comparing manual versus app-based data entry across five biometry calculations performed by 10 ophthalmologists. Paired t-tests were used for statistical comparison.
RESULTS: Twelve ophthalmologists completed the survey, with 50% reporting more than 11 uses and 30% more than 21 uses. Mean Likert scores were 4.5 ± 0.67 for OCR accuracy, 4.5 ± 0.8 for ease of use, and 4.67 ± 0.65 for recommendation to colleagues. The time-motion analysis demonstrated significantly faster app-based entry (91.72 ± 5.59 seconds) than manual entry (179.42 ± 22.12 seconds), resulting in a 48.9% time reduction (P < .001). Time savings were consistent across all five biometry calculations (43.1% to 52.7% reduction).
CONCLUSIONS: The Biometry Scanner provides a streamlined, accurate, and user-friendly solution for automating IOL power calculations. By eliminating manual transcription, it enhances accuracy, saves time, and promotes safer, more efficient preoperative cataract surgery planning.