Bhambhwani Vishaal, Whitestone Noelle, Patnaik Jennifer L, Ojeda Alonso, Scali James, Cherwek David H
Ophthalmology, Northern Ontario School of Medicine University, Thunder Bay, Ontario, Canada.
Ophthalmology, Thunder Bay Regional Health Sciences Centre, Thunder Bay, Ontario, Canada.
Ophthalmic Epidemiol. 2025 Oct;32(5):518-524. doi: 10.1080/09286586.2024.2434738. Epub 2024 Dec 18.
To assess the feasibility, implementation, and patient experience of autonomous artificial intelligence-based diabetic retinopathy detection models.
This was a prospective cohort study where consenting adult participants previously diagnosed with diabetes were screened for diabetic retinopathy using retinal imaging with autonomous artificial intelligence (AI) interpretation at their routine primary care appointment from December 2022 through October 2023 in Thunder Bay, Ontario. Demographic (age, sex, race) and clinical (type and duration of diabetes, last reported eye exam) data were collected using a data collection form. A 5-point Likert scale questionnaire was completed by participants to assess patient experience following the AI exam.
Among the 202 participants (38.6% women) with a mean age of 70.8 ± 11.7 years included in the study and screened by AI, the exam was successfully completed by 93.6% ( = 189), with only 1.5% ( = 3) requiring dilating eyedrops. The most common reason for an unsuccessful exam was small pupils with patient refusal for dilating eyedrops ( = 4). Among the participants with successful eye exams, 22.2% ( = 42) had referable diabetic retinopathy detected and were referred to see an ophthalmologist; 32/42 (76.0%) of these attended their ophthalmologist appointment. A total of 184 participants completed the satisfaction questionnaire; the mean score (out of 5) for satisfaction with the addition of an eye exam to their primary care visit was 4.8 ± 0.6.
Screening for diabetic retinopathy using autonomous artificial intelligence in a primary care setting is feasible and acceptable. This approach has significant advantages for both physicians and patients while achieving very high patient satisfaction.
评估基于人工智能的自主糖尿病视网膜病变检测模型的可行性、实施情况及患者体验。
这是一项前瞻性队列研究，在安大略省桑德贝，从2022年12月至2023年10月，对之前被诊断患有糖尿病且同意参与的成年参与者在其常规初级保健预约时使用视网膜成像及自主人工智能（AI）解读进行糖尿病视网膜病变筛查。使用数据收集表收集人口统计学（年龄、性别、种族）和临床（糖尿病类型和病程、上次报告的眼科检查）数据。参与者完成一份5级李克特量表问卷，以评估AI检查后的患者体验。
在研究纳入并经AI筛查的202名参与者（38.6%为女性）中，平均年龄为70.8±11.7岁，93.6%（n = 189）成功完成检查，仅1.5%（n = 3）需要使用散瞳眼药水。检查未成功的最常见原因是瞳孔小且患者拒绝使用散瞳眼药水（n = 4）。在眼科检查成功的参与者中，22.2%（n = 42）检测出有可转诊的糖尿病视网膜病变，并被转诊去看眼科医生；其中32/42（76.0%）前往就诊。共有184名参与者完成了满意度问卷；对在初级保健就诊时增加眼科检查的满意度平均得分（满分5分）为4.8±0.6。
在初级保健环境中使用自主人工智能筛查糖尿病视网膜病变是可行且可接受的。这种方法对医生和患者都有显著优势，同时能实现很高的患者满意度。
