Yang Christopher D, Wang Jasmine, Verniani Ludovico, Ghalehei Melika, Chen Lauren E, Lin Ken Y
University of California, Irvine School of Medicine, Irvine, CA, USA.
Gavin Herbert Eye Institute, Department of Ophthalmology, UC Irvine, CA, USA.
J Ophthalmic Vis Res. 2024 Jun 21;19(2):172-182. doi: 10.18502/jovr.v19i2.13983. eCollection 2024 Apr-Jun.
To validate a convolutional neural network (CNN)-based smartphone application for the identification of glaucoma eye drop medications in patients with normal and impaired vision.
Sixty-eight patients with visual acuity (VA) of 20/70 or worse in at least one eye who presented to an academic glaucoma clinic from January 2021 through August 2022 were included. Non-English-speaking patients were excluded. Enrolled subjects participated in an activity in which they identified a predetermined and preordered set of six topical glaucoma medications, first without the CNN and then with the CNN for a total of six sequential measurements per subject. Responses to a standardized survey were collected during and after the activity. Primary quantitative outcomes were medication identification accuracy and time. Primary qualitative outcomes were subjective ratings of ease of smartphone application use.
Topical glaucoma medication identification accuracy (OR = 12.005, 0.001) and time (OR = 0.007, 0.001) both independently improved with CNN use. CNN use significantly improved medication accuracy in patients with glaucoma (OR = 4.771, = 0.036) or VA 20/70 in at least one eye (OR = 4.463, = 0.013) and medication identification time in patients with glaucoma (OR = 0.065, = 0.017). CNN use had a significant positive association with subject-reported ease of medication identification (X(1) = 66.117, 0.001).
Our CNN-based smartphone application is efficacious at improving glaucoma eye drop identification accuracy and time. This tool can be used in the outpatient setting to avert preventable vision loss by improving medication adherence in patients with glaucoma.
验证一款基于卷积神经网络（CNN）的智能手机应用程序，用于识别视力正常和受损患者的青光眼眼药水药物。
纳入2021年1月至2022年8月到学术性青光眼诊所就诊的68例至少一只眼视力（VA）为20/70或更差的患者。排除非英语患者。入选受试者参与一项活动，他们要识别一组预先确定并排序的六种局部用青光眼药物，首先在不使用CNN的情况下进行，然后使用CNN，每位受试者共进行六次连续测量。在活动期间和活动后收集对标准化调查问卷的回答。主要定量结果是药物识别准确性和时间。主要定性结果是对智能手机应用程序使用便利性的主观评分。
使用CNN后，局部用青光眼药物识别准确性（OR = 12.005，P < 0.001）和时间（OR = 0.007，P < 0.001）均独立提高。使用CNN显著提高了青光眼患者（OR = 4.771，P = 0.036）或至少一只眼VA≤20/70患者（OR = 4.463，P = 0.013）的药物识别准确性，以及青光眼患者的药物识别时间（OR = 0.065，P = 0.017）。使用CNN与受试者报告的药物识别便利性有显著正相关（X(1) = 66.117，P < 0.001）。
我们基于CNN的智能手机应用程序在提高青光眼眼药水识别准确性和时间方面是有效的。该工具可用于门诊环境，通过提高青光眼患者的用药依从性来避免可预防的视力丧失。
