Luong Amanda, Cheung Jesse, McMurtry Shyla, Nelson Christina, Najac Tyler, Ortiz Philippe, Aronoff Stephen, Henderer Jeffrey, Zhang Yi
Lewis Katz School of Medicine at Temple University, Philadelphia, Pennsylvania.
Department of Internal Medicine at University of Kentucky HealthCare, Lexington, Kentucky.
Ophthalmol Sci. 2024 Aug 3;5(1):100592. doi: 10.1016/j.xops.2024.100592. eCollection 2025 Jan-Feb.
To develop an easily applicable predictor of patients at low risk for diabetic retinopathy (DR).
An experimental study on the development and validation of machine learning models (MLMs) and a novel retinopathy risk score (RRS) to detect patients at low risk for DR.
All individuals aged ≥18 years of age who participated in the telemedicine retinal screening initiative through Temple University Health Systems from October 1, 2016 through December 31, 2020. The subjects must have documented evidence of their diabetes mellitus (DM) diagnosis as well as a documented glycosylated hemoglobin (HbA1c) recorded in their chart within 6 months of the retinal screening photograph.
The charts of 1930 subjects (1590 evaluable) undergoing telemedicine screening for DR were reviewed, and 30 demographic and clinical parameters were collected. Diabetic retinopathy is a dichotomous variable where low risk is defined as no or mild retinopathy using the International Clinical Diabetic Retinopathy severity score. Five MLMs were trained to predict patients at low risk for DR using 1050 subjects and further underwent 10-fold cross validation to maximize its performance indicated by the area under the receiver operator characteristic curve (AUC). Additionally, a novel RRS is defined as the product of HbA1c closest to screening and years with DM. Retinopathy risk score was also applied to generate a predictive model.
The performance of the trained MLMs and the RRS model was compared using DeLong's test. The models were further validated using a separate unseen test set of 540 subjects. The performance of the validation models were compared using DeLong's test and chi-square tests.
Using the test set, the AUC for the RRS was not statistically different from 4 out of 5 MLM. The error rate for predicting low-risk patients using the RRS was significantly lower than the naive rate (0.097 vs. 0.19; < 0.0001), and it was comparable to the error rates of the MLMs.
This novel RRS is a potentially useful and easily deployable predictor of patients at low risk for DR.
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
开发一种易于应用的糖尿病视网膜病变（DR）低风险患者预测指标。
一项关于机器学习模型（MLMs）和新型视网膜病变风险评分（RRS）的开发与验证的实验性研究，以检测DR低风险患者。
2016年10月1日至2020年12月31日期间通过天普大学健康系统参与远程医疗视网膜筛查计划的所有年龄≥18岁的个体。研究对象必须有糖尿病（DM）诊断的记录证据，以及在视网膜筛查照片拍摄后6个月内其病历中记录的糖化血红蛋白（HbA1c）。
回顾了1930名接受DR远程医疗筛查的受试者（1590名可评估）的病历，并收集了30个人口统计学和临床参数。糖尿病视网膜病变是一个二分变量，使用国际临床糖尿病视网膜病变严重程度评分，低风险定义为无或轻度视网膜病变。使用1050名受试者训练了5个MLMs来预测DR低风险患者，并进一步进行10倍交叉验证，以最大化其由受试者操作特征曲线下面积（AUC）表示的性能。此外，一种新型RRS被定义为最接近筛查时的HbA1c与患糖尿病年数的乘积。视网膜病变风险评分也被用于生成一个预测模型。
使用德龙检验比较训练后的MLMs和RRS模型的性能。使用一个由540名受试者组成的单独的未见过的测试集对模型进行进一步验证。使用德龙检验和卡方检验比较验证模型的性能。
使用测试集，RRS的AUC与5个MLMs中的4个在统计学上无差异。使用RRS预测低风险患者的错误率显著低于朴素率（0.097对0.19；<0.0001），并且与MLMs的错误率相当。
这种新型RRS是一种潜在有用且易于应用的DR低风险患者预测指标。
本文末尾的脚注和披露中可能会有专有或商业披露信息。
