Machine Learning Prediction of Cardiovascular Risk in Type 1 Diabetes Mellitus Using Radiomics Features from Multimodal Retinal Images

2025-04-01

AI Summary

This study addresses the need for noninvasive, tiered cardiovascular risk stratification—low/intermediate, high, and very high risk—in patients with type 1 diabetes mellitus (T1DM). Method: We propose “oculomics”—a novel paradigm integrating radiomic features extracted from multimodal retinal imaging (color fundus photography, optical coherence tomography [OCT], and OCT angiography [OCTA]) with clinical variables. Machine learning models (XGBoost and SVM) were trained to classify risk tiers. Contribution/Results: Using imaging features alone, the model achieved AUCs of 0.79 (intermediate vs. high/very-high risk) and 0.73 (high vs. very-high risk); incorporating clinical variables improved performance to 0.99 and 0.95, respectively. Notably, a purely oculomic feature set (OCT + OCTA + ocular biometrics) yielded an AUC of 0.89 for identifying very-high-risk patients. Critically, this framework requires no blood tests or whole-body imaging, offering a highly accurate, scalable, and noninvasive tool for early cardiovascular risk screening in T1DM.

Technology Category

Computer Vision: Multi-modal VisionMachine Learning: Feature Construction/ReformulationData Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

Security and Privacy: Data transparency and provenanceUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and rankingEconomics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

This study aimed to develop a machine learning (ML) algorithm capable of determining cardiovascular risk in multimodal retinal images from patients with type 1 diabetes mellitus, distinguishing between moderate, high, and very high-risk levels. Radiomic features were extracted from fundus retinography, optical coherence tomography (OCT), and OCT angiography (OCTA) images. ML models were trained using these features either individually or combined with clinical data. A dataset of 597 eyes (359 individuals) was analyzed, and models trained only with radiomic features achieved AUC values of (0.79 $pm$ 0.03) for identifying moderate risk cases from high and very high-risk cases, and (0.73 $pm$ 0.07) for distinguishing between high and very high-risk cases. The addition of clinical variables improved all AUC values, reaching (0.99 $pm$ 0.01) for identifying moderate risk cases and (0.95 $pm$ 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 $pm$ 0.02) without systemic data input. These results demonstrate that radiomic features obtained from multimodal retinal images are useful for discriminating and classifying CV risk labels, highlighting the potential of this oculomics approach for CV risk assessment.

Problem

• Predict cardiovascular risk in type 1 diabetes using retinal images
• Classify risk levels (moderate, high, very high) via machine learning
• Combine radiomics and clinical data for improved risk assessment

Innovation

• Machine learning predicts CV risk from retinal images
• Radiomics features extracted from multimodal retinal scans
• Combined radiomics and clinical data enhance AUC accuracy