可解释多模态OCT与OCTA分析揭示不同种族轻度青光眼的结构与血管特征
本研究开发并外部验证了整合OCT与OCTA的可解释人工智能模型,用于轻度原发性开角型青光眼分类。亚洲队列(n=621)用于模型开发与测试,独立白人队列(n=131)用于外部验证。多模态模型内部测试AUC=0.975,外部测试AUC=0.884,SHAP分析识别下方视盘周围视网膜神经纤维层厚度和视盘周围灌注密度为关键贡献特征。
要点
- 多模态OCT/OCTA模型在外部验证中AUC=0.884,优于单独OCT(AUC=0.801)和单独OCTA(AUC=0.792)。
- OCTA血管指标可为结构OCT提供互补信息,尤其在外部验证队列中。
- SHAP识别下方视盘周围RNFL厚度和视盘周围灌注密度为关键分类特征。
核心结论
- 可解释多模态OCT/OCTA分析在不同种族队列中识别出轻度青光眼一致的结构和血管特征。
- OCTA衍生的血管指标为结构OCT提供互补信息,尤其在外部验证队列中。
研究设计与样本
- 横断面、多中心诊断研究,纳入轻度POAG(视野平均偏差≥-6 dB)和正常对照。
- 亚洲队列(n=621;429例青光眼,192例对照)用于模型开发与测试。
- 独立白人队列(n=131;62例青光眼,69例对照)用于外部验证。
- 提取视盘和黄斑的定量结构OCT与血管OCTA特征,比较随机森林模型(仅OCT、仅OCTA、联合OCT/OCTA)。
- 使用SHAP评估特征贡献。
主要发现
- 共752名参与者(平均年龄60岁;50%男性)。
- 内部测试集:多模态模型AUC=0.975,与仅OCT模型(AUC=0.965;P=0.248)相当,优于仅OCTA模型(AUC=0.870;P<0.001)。
- 外部测试集:多模态模型AUC=0.884,优于仅OCT(AUC=0.801;P<0.001)和仅OCTA(AUC=0.792;P=0.005)模型。
- SHAP分析识别下方视盘周围视网膜神经纤维层厚度和视盘周围灌注密度为关键贡献特征。
关键数值与推荐
- 轻度POAG定义:视野平均偏差≥-6 dB。
- 内部测试集多模态模型AUC=0.975,仅OCT模型AUC=0.965(P=0.248),仅OCTA模型AUC=0.870(P<0.001)。
- 外部测试集多模态模型AUC=0.884,仅OCT模型AUC=0.801(P<0.001),仅OCTA模型AUC=0.792(P=0.005)。
临床怎么用
- 多模态OCT/OCTA联合分析可用于轻度青光眼分类,尤其在不同种族人群中具有较好泛化性能。
- OCTA血管指标可补充结构OCT信息,支持联合使用。
- SHAP可解释性有助于理解模型依赖的关键结构和血管特征。
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
PURPOSE: To develop and externally validate an explainable artificial intelligence model integrating optical coherence tomography (OCT) and OCT angiography (OCTA) for mild primary open-angle glaucoma (POAG) and to determine the structural and vascular features contributing to classification across ethnically distinct cohorts. METHODS: This cross-sectional, multicenter diagnostic study included participants with mild POAG (visual field mean deviation ≥ -6 dB) and normal controls. Quantitative structural OCT and vascular OCTA features from the optic disc and macula were extracted. An Asian cohort (n = 621; 429 glaucoma, 192 controls) was used for model development and testing, and an independent Caucasian cohort (n = 131; 62 glaucoma, 69 controls) was used for external validation. Random Forest models using OCT-only, OCTA-only, and combined OCT/OCTA features were compared using area under the receiver operating characteristic (AUC) curve, sensitivity, and specificity. Feature contributions were assessed using SHapley Additive exPlanations (SHAP). RESULTS: Among 752 participants (mean age, 60 years; 50% male), the multimodal model achieved high discrimination in the internal test set (AUC = 0.975) and comparable performance to OCT-only model (AUC = 0.965; P = 0.248) but outperformed the OCTA-only model (AUC = 0.870; P < 0.001). In the external test set, the multimodal model achieved an AUC of 0.884, outperforming both OCT-only (AUC = 0.801; P < 0.001) and OCTA-only (AUC = 0.792; P = 0.005) models. SHAP analysis identified inferior peripapillary retinal nerve fiber layer thickness and peripapillary perfusion density as key contributors. CONCLUSIONS: Explainable multimodal OCT/OCTA analysis identified consistent structural and vascular features of mild glaucoma across ethnically distinct cohorts. OCTA-derived vascular metrics provided complementary information to structural OCT, particularly in the external validation cohort.
引用
- Chua J, Shi Z, Kumar EJ, et al. Explainable Multimodal OCT and OCTA Analysis Reveals Structural and Vascular Features of Mild Glaucoma Across Ethnicities. Invest Ophthalmol Vis Sci. 2026. PMID: 42747257. doi:10.1167/iovs.67.11.32
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。