文献速递眼底病与葡萄膜炎

基于超广角视网膜图像的自动化机器学习预测糖尿病视网膜病变进展

Automated Machine Learning for Predicting Diabetic Retinopathy Progression From Ultra-Widefield Retinal Images.
PubMed 文献 · JAMA Ophthalmol · 2024-01-01

本研究利用1179张轻度或中度非增殖性糖尿病视网膜病变(NPDR)的超广角视网膜图像开发自动化机器学习模型,预测糖尿病视网膜病变(DR)进展。验证集显示,轻度NPDR的AUPRC为0.717,中度NPDR为0.863;模型对1年内进展2步及以上的识别率较高,轻度NPDR为75%,中度NPDR为85%。

要点

  • 自动化机器学习模型预测轻度NPDR进展的AUPRC为0.717,中度NPDR为0.863。
  • 验证集中,模型识别出75%的轻度NPDR和85%的中度NPDR在1年内进展2步及以上。
  • 所有4只轻度NPDR眼在6个月和1年内进展均被识别,中度NPDR识别率分别为89%和85%。

核心结论

  • 研究表明自动化机器学习模型利用超广角图像识别DR进展具有准确性和可行性,尤其对预测1年内进展2步及以上效果较好。
  • 作者认为,机器学习算法可能有助于细化疾病进展风险并识别短期最高风险者,从而降低成本并改善视力相关结局。

研究设计与样本

  • 使用来自三级糖尿病专科医疗中心视网膜图像数据集的去标识化超广角图像,开发自动化机器学习模型预测DR进展。
  • 图像纳入标准为轻度或中度NPDR,且具有3年纵向随访视网膜成像或3年内有进展证据。
  • 数据收集时间为2022年7月至9月。
  • 基线视网膜图像根据临床早期治疗糖尿病视网膜病变研究严重程度量表由中心阅读中心评估标注进展。
  • 图像按8:1:1分割用于训练、优化和测试,以检测1步及以上DR进展;验证使用来自同一患者人群的328张图像集。

主要发现

  • 共纳入1179张去标识化超广角图像,其中轻度NPDR 380张(32.2%),中度NPDR 799张(67.8%)。
  • 训练集中DR进展存在于一半图像(590/1179,50.0%)。
  • 模型AUPRC对基线轻度NPDR为0.717,对中度NPDR为0.863。
  • 验证集中,轻度NPDR眼灵敏度为0.72(95%CI 0.57-0.83),特异度为0.63(95%CI 0.57-0.69),患病率为0.15(95%CI 0.12-0.20),准确率为64.3%;中度NPDR眼灵敏度为0.80(95%CI 0.70-0.87),特异度为0.72(95%CI 0.66-0.76),患病率为0.22(95%CI 0.19-0.27),准确率为73.8%。
  • 验证集中,进展2步及以上的轻度NPDR眼识别出6/9(75%),中度NPDR眼识别出35/41(85%);6个月和1年内进展的轻度NPDR眼4/4均被识别,中度NPDR眼分别识别出8/9(89%)和17/20(85%)。

关键数值与推荐

  • 模型预测轻度NPDR进展的AUPRC为0.717,中度NPDR为0.863。
  • 验证集轻度NPDR灵敏度0.72(95%CI 0.57-0.83),特异度0.63(95%CI 0.57-0.69),准确率64.3%。
  • 验证集中度NPDR灵敏度0.80(95%CI 0.70-0.87),特异度0.72(95%CI 0.66-0.76),准确率73.8%。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

IMPORTANCE: Machine learning (ML) algorithms have the potential to identify eyes with early diabetic retinopathy (DR) at increased risk for disease progression. OBJECTIVE: To create and validate automated ML models (autoML) for DR progression from ultra-widefield (UWF) retinal images. DESIGN, SETTING AND PARTICIPANTS: Deidentified UWF images with mild or moderate nonproliferative DR (NPDR) with 3 years of longitudinal follow-up retinal imaging or evidence of progression within 3 years were used to develop automated ML models for predicting DR progression in UWF images. All images were collected from a tertiary diabetes-specific medical center retinal image dataset. Data were collected from July to September 2022. EXPOSURE: Automated ML models were generated from baseline on-axis 200° UWF retinal images. Baseline retinal images were labeled for progression based on centralized reading center evaluation of baseline and follow-up images according to the clinical Early Treatment Diabetic Retinopathy Study severity scale. Images for model development were split 8-1-1 for training, optimization, and testing to detect 1 or more steps of DR progression. Validation was performed using a 328-image set from the same patient population not used in model development. MAIN OUTCOMES AND MEASURES: Area under the precision-recall curve (AUPRC), sensitivity, specificity, and accuracy. RESULTS: A total of 1179 deidentified UWF images with mild (380 [32.2%]) or moderate (799 [67.8%]) NPDR were included. DR progression was present in half of the training set (590 of 1179 [50.0%]). The model's AUPRC was 0.717 for baseline mild NPDR and 0.863 for moderate NPDR. On the validation set for eyes with mild NPDR, sensitivity was 0.72 (95% CI, 0.57-0.83), specificity was 0.63 (95% CI, 0.57-0.69), prevalence was 0.15 (95% CI, 0.12-0.20), and accuracy was 64.3%; for eyes with moderate NPDR, sensitivity was 0.80 (95% CI, 0.70-0.87), specificity was 0.72 (95% CI, 0.66-0.76), prevalence was 0.22 (95% CI, 0.19-0.27), and accuracy was 73.8%. In the validation set, 6 of 9 eyes (75%) with mild NPDR and 35 of 41 eyes (85%) with moderate NPDR progressed 2 steps or more were identified. All 4 eyes with mild NPDR that progressed within 6 months and 1 year were identified, and 8 of 9 (89%) and 17 of 20 (85%) with moderate NPDR that progressed within 6 months and 1 year, respectively, were identified. CONCLUSIONS AND RELEVANCE: This study demonstrates the accuracy and feasibility of automated ML models for identifying DR progression developed using UWF images, especially for prediction of 2-step or greater DR progression within 1 year. Potentially, the use of ML algorithms may refine the risk of disease progression and identify those at highest short-term risk, thus reducing costs and improving vision-related outcomes.

来源:JAMA Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Silva PS, Zhang D, Jacoba CMP, et al. Automated Machine Learning for Predicting Diabetic Retinopathy Progression From Ultra-Widefield Retinal Images. JAMA Ophthalmol. 2024. PMID: 38329765. doi:10.1001/jamaophthalmol.2023.6318

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。