Development of oculomics artificial intelligence for cardiovascular risk factors: A case study in fundus oculomics for HbA1c assessment and clinically relevant considerations for clinicians

Abstract

Artificial Intelligence (AI) is transforming healthcare, notably in ophthalmology, where its ability to interpret images and data can significantly enhance disease diagnosis and patient care. Recent developments in oculomics, the integration of ophthalmic features to develop biomarkers for systemic diseases, have demonstrated the potential for providing rapid, non-invasive methods of screening leading to enhance in early detection and improve healthcare quality, particularly in underserved areas. However, the widespread adoption of such AI-based technologies faces challenges primarily related to the trustworthiness of the system. We demonstrate the potential and considerations needed to develop trustworthy AI in oculomics through a pilot study for HbA1c assessment using an AI-based approach. We then discuss various challenges, considerations, and solutions that have been developed for powerful AI technologies in the past in healthcare and subsequently apply these considerations to the oculomics pilot study. Building upon the observations in the study we highlight the challenges and opportunities for advancing trustworthy AI in oculomics. Ultimately, oculomics presents as a powerful and emerging technology in ophthalmology and understanding how to optimize transparency prior to clinical adoption is of utmost importance.

Keywords: Artificial intelligence; Machine learning; Oculomics; Ophthalmology; Reliability; Trustworthy.

Fig. 1.

Male to female ratio of patients in cohort for pilot study.

Fig. 2.

HbA1c level distributions for male and female patients.

Fig. 3.

Age distribution of patients in pilot study cohort.

Fig. 4.

Mean and standard deviation of HbA1c level by age group.

Fig. 5.

Confusion matrix for output of VGG 19 model.

Fig. 6.

Three-stage diabetes triage process architecture based on Ensemble Model.

Fig. 7.

Ensemble model ROC curve.

Fig. 8.

Ensemble model confusion matrix.

Fig. 9.

Confusion matrix of predictions when model is trained on senior and youth groups, respectively.

Fig. 10.

Confusion matrix of model predictions of sex based on fundus images.

Fig. 11.

Sample of results comparing Grad-CAM output for classifying male vs female.

Fig. 12.

Comparison of Grad-CAM output on different classes.