Tohà-Dalmau Ariadna, Rosinés-Fonoll Josep, Romero Enrique, Mazzanti Ferran, Martin-Pinardel Ruben, Marias-Perez Sonia, Bernal-Morales Carolina, Castro-Dominguez Rafael, Mendez Andrea, Ortega Emilio, Vinagre Irene, Gimenez Marga, Vellido Alfredo, Zarranz-Ventura Javier
Department of Computer Science, Universitat Politècnica de Catalunya (UPC), Barcelona, Spain.
Institut Clínic d'Oftalmología (ICOF), Hospital Clínic de Barcelona, Barcelona, Spain.
Ophthalmol Sci. 2025 Jul 4;5(6):100874. doi: 10.1016/j.xops.2025.100874. eCollection 2025 Nov-Dec.
To develop a machine learning (ML) algorithm capable of determining cardiovascular (CV) risk in multimodal retinal images from patients with type 1 diabetes mellitus (T1DM), distinguishing between moderate, high, and very high-risk levels.
Cross-sectional analysis of a retinal image data set from a previous prospective OCT angiography (OCTA) study (ClinicalTrials.gov NCT03422965).
Patients with T1DM included in the progenitor study.
Radiomic features were extracted from color fundus photographs (CFPs), OCT, and OCTA images, and ML models were trained using these features either individually or combined with clinical data (demographics and systemic data, OCT + OCTA commercial software metrics, ocular data, blood data). Different data combinations were tested to determine the CV risk stages, defined according to international classifications.
Area under the receiver operating characteristic curve mean and standard deviation for each ML model and each data combination.
A data set of 597 eyes (359 individuals) was analyzed. Models trained only with the radiomic features achieved area under the curve (AUC) values of (0.79 ± 0.03) to identify moderate risk cases from high and very high-risk cases, and (0.73 ± 0.07) for distinguishing between high and very high-risk cases. The addition of clinical variables improved all AUC values, obtaining (0.99 ± 0.01) for identifying moderate cases, and (0.95 ± 0.02) for differentiating between high and very high-risk cases. For very high CV risk, radiomics combined with OCT + OCTA metrics and ocular data achieved an AUC of (0.89 ± 0.02) without systemic data input. The performance of the models was similar in unilateral and bilateral eye image data sets.
Radiomic features obtained from retinal images are helpful to discriminate and classify CV risk labels, differentiating risk categories. The addition of demographics and systemic data combined with ocular data differentiate high from very high CV risk cases, and interestingly OCT + OCTA metrics with ocular data identify very high CV risk cases without systemic data input. These results reflect the potential of this oculomics approach for CV risk assessment.
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
开发一种机器学习（ML）算法，该算法能够根据1型糖尿病（T1DM）患者的多模态视网膜图像确定心血管（CV）风险，区分中度、高度和极高风险水平。
对先前一项前瞻性光学相干断层扫描血管造影（OCTA）研究（ClinicalTrials.gov NCT03422965）中的视网膜图像数据集进行横断面分析。
纳入原始研究的T1DM患者。
从彩色眼底照片（CFP）、OCT和OCTA图像中提取放射组学特征，并使用这些特征单独或与临床数据（人口统计学和全身数据、OCT + OCTA商业软件指标、眼部数据、血液数据）相结合来训练ML模型。测试不同的数据组合以确定根据国际分类定义的CV风险阶段。
每个ML模型和每个数据组合的受试者操作特征曲线下面积的均值和标准差。
分析了一个包含597只眼（359名个体）的数据集。仅使用放射组学特征训练的模型在从高风险和极高风险病例中识别中度风险病例时，曲线下面积（AUC）值为（0.79±0.03），在区分高风险和极高风险病例时为（0.73±0.07）。添加临床变量提高了所有AUC值，在识别中度病例时为（0.99±0.01），在区分高风险和极高风险病例时为（0.95±0.02）。对于极高的CV风险，在没有全身数据输入的情况下，放射组学与OCT + OCTA指标和眼部数据相结合的AUC为（0.89±0.02）。模型在单眼和双眼图像数据集中的表现相似。
从视网膜图像中获得的放射组学特征有助于区分和分类CV风险标签，区分风险类别。添加人口统计学和全身数据并结合眼部数据可区分高CV风险和极高CV风险病例，有趣的是，OCT + OCTA指标与眼部数据相结合在没有全身数据输入的情况下可识别极高CV风险病例。这些结果反映了这种眼组学方法在CV风险评估中的潜力。
在本文末尾的脚注和披露中可能会找到专有或商业披露信息。
