Traditional screening for systemic diseases often relies on laboratory tests, imaging evaluations, and specialist consultations, wntial value in applications related to cardiovascular diseases, diabetes and metabolic abnormalities, kidney diseases, hepatobiliary system diseases, neurodegenerative diseases, and certain autoimmune diseases. Extensive research demonstrates that deep learning models perform exceptionally well in these tasks, with multiple studies reporting an Area Under the Curve (AUC) exceeding 0.90. However, the field still faces challenges, such as significant data heterogeneity, insufficient external validation, limihich are frequently associated with high costs, invasiveness, and limited accessibility in primary care settings. The eye is one of the few organs in the human body that allows for the non-invasive, direct observation of microvessels, neural tissues, and the microstructures of semi-transparent tissues, offering a unique advantage in reflecting systemic health status.In recent years, with the development of deep learning technology and high-resolution ocular imaging, the scope of eye image analysis has gradually expanded from traditional ophthalmic diseases to the screening, risk prediction, and long-term monitoring of systemic diseases. The primary ocular imaging modalities currently available for systemic disease research include color fundus photography (CFP), optical coherence tomography (OCT), optical coherence tomography angiography (OCTA), corneal confocal microscopy (CCM/IVCM), and anterior segment imaging.Existing studies indicate that multimodal ocular imaging holds poteted interpretability, low levels of research design, and difficulties in real-world clinical translation.This review focuses on the theoretical basis, methodological framework of deep learning, major disease applications, current challenges, and future directions for identifying systemic diseases using multimodal ocular imaging, with the aim of providing a reference for subsequent research design and clinical translation.

Yixing Li, Jiali Hu, Mincong Zhou, Wei Wang. Advances in Artificial Intelligence-Based Ocular Imaging for the Detection of Systemic Diseases. Academic Journal of Medicine & Health Sciences (2026), Vol. 7, Issue 4: 51-68. https://doi.org/10.25236/AJMHS.2026.070407.

[1] Shah R, Amador C, Tormanen K, et al. Systemic diseases and the cornea[J]. Experimental eye research, 2021, 204: 108455.

[2] Zhang, Y., Ma, M., Tian, C., et al.: Current status and dilemmas of osteoporosis screening tools: a narrative review[J]. Clinical Nutrition ESPEN, (2024).

[3] Grossniklaus H E, Geisert E E, Nickerson J M. Introduction to the Retina[J]. Progress in molecularbiology and translational science, 2015, 134: 383-396.

[4] London A, Benhar I, Schwartz M. The retina as a window to the brain—from eye research to CNSdisorders[J].Nature Reviews Neurology, 2013, 9(1): 44-53.

[5] Gunn R. Ophthalmoscopic evidence of (1) arterial changes associated with chronic renal disease, and(2) of increased arterial tension. Transactions of the Ophthalmological Society of the United Kingdom. 1892;12:124–125.

[6] Wagner S K, Fu D J, Faes L, et al. Insights into systemic disease through retinal imaging-based oculomics[J]. Translational vision science & technology, 2020, 9(2): 6.

[7] Hamet P, Tremblay J. Artificial intelligence in medicine[J]. metabolism, 2017, 69: S36-S40.

[8]Panayides A S, Amini A, Filipovic N D, et al. AI in medical imaging informatics: current challenges and future directions[J]. IEEE journal of biomedical and health informatics, 2020, 24(7): 1837-1857.

[9] Tan Y, Sun X. Ocular images-based artificial intelligence on systemic diseases. Biomed Eng Online. 2023 May 19;22(1):49. doi: 10.1186/s12938-023-01110-1. PMID: 37208715; PMCID: PMC10197476.

[10] Iao, W.C.; Zhang, W.; Wang, X.; Wu, Y.; Lin, D.; Lin, H. Deep Learning Algorithms for Screeningand Diagnosis of Systemic Diseases Based on Ophthalmic Manifestations: A Systematic Review. Diagnostics 2023, 13, 900. https://doi.org/10.3390/diagnostics13050900

[11] Li X. Multimodal deep learning and its application prospects in ophthalmic artificial intelligence [J]. Medical Journal of Peking Union Medical College, 2021, 12(5): 602-607.

[12] Aumann S, Donner S, Fischer J, et al. Optical coherence tomography (OCT): principle and technicalrealization[J]. High resolution imaging in microscopy and ophthalmology: new frontiers in biomedical optics, 2019: 59-85.

[13] De Carlo T E, Romano A, Waheed N K, et al. A review of optical coherence tomography angiography (OCTA)[J]. International journal of retina and vitreous, 2015, 1(1): 5.

[14] Sperlich K, Bohn S, Worsch F, et al. In vivo corneal microscopy: from image to insight–where are we going?[J]. Zeitschrift für Medizinische Physik, 2025.

[15] Cui Y, Zhu Y, Wang J C, et al. Comparison of widefield swept-source optical coherence tomography angiography with ultra-widefield colour fundus photography and fluorescein angiography for detection of lesions in diabetic retinopathy[J]. British Journal of Ophthalmology, 2021, 105(4): 577-581.

[16] Besenczi R, Tóth J, Hajdu A. A review on automatic analysis techniques for color fundus photographs[J]. Computational and structural biotechnology journal, 2016, 14: 371-384.

[17] Panwar N, Huang P, Lee J, et al. Fundus Photography in the 21st Century—A Review of Recent Technological Advances and Their Implications for Worldwide Healthcare. Telemedicine and e-Health. 2016;22(3):198-208. doi:10.1089/tmj.2015.0068

[18] Poplin R, Varadarajan A V, Blumer K, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning[J]. Nature biomedical engineering, 2018, 2(3): 158-164.

[19] Konstantopoulos A, Hossain P, Anderson D F. Recent advances in ophthalmic anterior segment imaging: a new era for ophthalmic diagnosis?[J]. British journal of ophthalmology, 2007, 91(4): 551-557.

[20] Sapkota R, Roumeliotis K I, Karkee M. Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges[J]. Information Fusion, 2025: 103599.

[21] Armstrong G W, Lorch A C. A (eye): a review of current applications of artificial intelligence and machine learning in ophthalmology[J]. International ophthalmology clinics, 2020, 60(1): 57-71.

[22] Akil M, Elloumi Y, Kachouri R. Detection of retinal abnormalities in fundus image using CNN deep learning networks[M]//State of the Art in Neural Networks and their Applications. Academic Press, 2021: 19-61.

[23] Nabel E G. Cardiovascular disease[J]. New England Journal of Medicine, 2003, 349(1): 60-72.

[24] Chikumba S, Hu Y, Luo J. Deep learning-based fundus image analysis for cardiovascular disease: review[J]. Therapeutic Advances in Chronic Disease, 2023, 14: 20406223231209895.

[25] Abdollahi M, Jafarizadeh A, Ghafouri‐Asbagh A, et al. Artificial intelligence in assessing cardiovascular diseases and risk factors via retinal fundus images: A review of the last decade[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2024, 14(6): e1560.

[26] Li L Y, Isaksen A A, Lebiecka-Johansen B, et al. Prediction of cardiovascular markers and diseasesusing retinal fundus images and deep learning: a systematic scoping review[J]. European Heart Journal-Digital Health, 2024, 5(6): 660-669.

[27] Poplin R, Varadarajan A V, Blumer K, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning[J]. Nature biomedical engineering, 2018, 2(3): 158-164.

[28] Chang J, Ko A, Park S M, et al. Association of cardiovascular mortality and deep learning-funduscopic atherosclerosis score derived from retinal fundus images[J]. American journal of ophthalmology, 2020, 217: 121-130.

[29] Rim T H, Lee C J, Tham Y C, et al. Deep-learning-based cardiovascular risk stratification using coronary artery calcium scores predicted from retinal photographs[J]. The Lancet Digital Health,2021, 3(5): e306-e316.

[30] Tseng R M W W, Rim T H, Shantsila E, et al. Validation of a deep-learning-based retinal biomarker (Reti-CVD) in the prediction of cardiovascular disease: data from UK Biobank[J]. BMC medicine, 2023, 21(1): 28.

[31] Diaz-Pinto A, Ravikumar N, Attar R, et al. Predicting myocardial infarction through retinal scans and minimal personal information[J]. Nature Machine Intelligence, 2022, 4(1): 55-61.

[32] Lee Y C, Cha J, Shim I, et al. Multimodal deep learning of fundus abnormalities and traditional risk factors for cardiovascular risk prediction[J]. NPJ digital medicine, 2023, 6(1): 14.

[33] Zhou Y, Chia M A, Wagner S K, et al. A foundation model for generalizable disease detection from retinal images[J]. Nature, 2023, 622(7981): 156-163.

[34] Cheung CY, Xu D, Cheng CY, Sabanayagam C, Tham YC, Yu M, et al. A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre. Nat Biomed Eng. 2021;5(6):498–508.

[35] Rudnicka A R, Welikala R, Barman S, et al. Artificial intelligence-enabled retinal vasculometry for prediction of circulatory mortality, myocardial infarction and stroke[J]. British Journal of Ophthalmology, 2022, 106(12): 1722-1729.

[36] Al-Absi H R H, Islam M T, Refaee M A, et al. Cardiovascular disease diagnosis from DXA scan and retinal images using deep learning[J]. Sensors, 2022, 22(12): 4310.

[37] Yi J K, Rim T H, Park S, et al. Cardiovascular disease risk assessment using a deep-learning-based retinal biomarker: a comparison with existing risk scores[J]. European Heart Journal-Digital Health, 2023, 4(3): 236-244.

[38] Muthupalaniaptiaa M N, Suganthi P. Cardiovascular Disease Detection Using Retinal Fundus Images[C]//2025 IEEE 4th International Conference on Data, Decision and Systems (ICDDS). IEEE, 2025: 78-83.

[39] Seo H, Park S J, Song M. Diabetic retinopathy (DR): mechanisms, current therapies, and emerging strategies[J]. Cells, 2025, 14(5): 376.

[40] Zhang L, Yuan M, An Z, et al. Prediction of hypertension, hyperglycemia and dyslipidemia from retinal fundus photographs via deep learning: A cross-sectional study of chronic diseases in central China[J]. PloS one, 2020, 15(5): e0233166.

[41] Choi J H, Kang S, Kim S K, et al. Bridging evidence and practice: a consensus statement from the Korean Diabetes Association on diabetes screening, pharmacological treatment and severe diabetes[J]. Diabetes & Metabolism Journal, 2025, 49(6): 1155-1177.

[42] Ballester Dolz P, Ålander K, Smedberg P, et al. Eye diseases in chronic kidney disease: A nationwide longitudinal case–control study in Sweden[J]. Clinical & Experimental Ophthalmology, 2025, 53(2): 209-217.

[43] Kanbay M, Guldan M, Ozbek L, et al. Unveiling the intricacies of chronic kidney disease: From ocular manifestations to therapeutic frontiers[J]. European Journal of Clinical Investigation, 2025, 55(1): e14324.

[44] Mukherjee S, Nazm N, Ghosh M K, et al. Ophthalmic Manifestations of Chronic Kidney Disease[J]. Journal of Contemporary Clinical Practice, 2025, 11: 575-580.

[45] Wong T Y, Xu D, Ting D, et al. Artificial intelligence deep learning system for predicting chronic kidney disease from retinal images[J]. Investigative Ophthalmology & Visual Science, 2019, 60(9): 1468-1468.

[46] Sabanayagam C, Xu D, Ting D S W, et al. A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations[J]. The Lancet Digital Health, 2020, 2(6): e295-e302.

[47] Betzler B K, Chee E Y L, He F, et al. Deep learning algorithms to detect diabetic kidney disease from retinal photographs in multiethnic populations with diabetes[J]. Journal of the American Medical Informatics Association, 2023, 30(12): 1904-1914.

[48] Kang E Y C, Hsieh Y T, Li C H, et al. Deep learning–based detection of early renal function impairment using retinal fundus images: model development and validation[J]. JMIR medical informatics, 2020, 8(11): e23472.

[49] Zhang K, Liu X, Xu J, et al. Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images[J]. Nature biomedical engineering, 2021, 5(6): 533-545.

[50] Joo Y S, Rim T H, Koh H B, et al. Non-invasive chronic kidney disease risk stratification tool derived from retina-based deep learning and clinical factors[J]. NPJ Digital Medicine, 2023, 6(1): 114.

[51] Shi S, Gao L, Zhang J, et al. The automatic detection of diabetic kidney disease from retinal vascular parameters combined with clinical variables using artificial intelligence in type-2 diabetes patients[J]. BMC Medical Informatics and Decision Making, 2023, 23(1): 241.

[52] Xie X, Wang W, Wang H, et al. Artificial intelligence–assisted perfusion density as biomarker for screening diabetic nephropathy[J]. Translational Vision Science & Technology, 2024, 13(10): 19.

[53] Wilson G N. Wilson disease[M]//Rosenberg's Molecular and Genetic Basis of Neurological and Psychiatric Disease. Academic Press, 2025: 745-755.

[54] Song W, Xin L, Wang J. A grading method for Kayser Fleischer ring images based on ResNet[J]. Heliyon, 2023, 9(5).

[55] Xiao W, Huang X, Wang J H, et al. Screening and identifying hepatobiliary diseases through deep learning using ocular images: a prospective, multicentre study[J]. The Lancet Digital Health, 2021, 3(2): e88-e97.

[56] Babenko B, Traynis I, Chen C, et al. A deep learning model for novel systemic biomarkers in photographs of the external eye: a retrospective study[J]. The Lancet Digital Health, 2023, 5(5): e257-e264.

[57] Mariakakis A, Banks M A, Phillipi L, et al. Biliscreen: smartphone-based scleral jaundice monitoring for liver and pancreatic disorders[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2017, 1(2): 1-26.

[58] Kovacs G G. Concepts and classification of neurodegenerative diseases[M]//Handbook of clinical neurology. Elsevier, 2018, 145: 301-307.

[59] Toader C, Dobrin N, Brehar F M, et al. From recognition to remedy: The significance of biomarkers in neurodegenerative disease pathology[J]. International journal of molecular sciences, 2023, 24(22): 16119.

[60] Vij R, Arora S. A systematic survey of advances in retinal imaging modalities for Alzheimer’s disease diagnosis[J]. Metabolic Brain Disease, 2022, 37(7): 2213-2243.

[61] Cheung C Y, Ran A R, Wang S, et al. A deep learning model for detection of Alzheimer's disease based on retinal photographs: a retrospective, multicentre case-control study[J]. The Lancet Digital Health, 2022, 4(11): e806-e815.

[62] Wang X, Wang Y, Liu H, et al. Macular microvascular density as a diagnostic biomarker for Alzheimer’s disease[J]. Journal of Alzheimer’s Disease, 2022, 90(1): 139-149.

[63] Huang Y J, Kuo C F, Huang Y H, et al. Detecting Subtle Changes in Fundoscopic Retinal Images in Patients with Axial Spondyloarthritis with Deep Learning[J]. Arthritis & rheumatology (Hoboken, NJ), 2020, 72.

[64] Wisely C E, Wang D, Henao R, et al. Convolutional neural network to identify symptomatic Alzheimer’s disease using multimodal retinal imaging[J]. British Journal of Ophthalmology, 2022, 106(3): 388-395.

[65] Slootweg, I. R., Thach, M., Curro-Tafili, K. R., et al.: Generative artificial intelligence in ophthalmology: multimodal retinal images for the diagnosis of Alzheimer’s disease with convolutional neural networks[J]. arXiv preprint arXiv:2406.18247, (2024).

[66] Wagner S K, Hughes F, Cortina-Borja M, et al. AlzEye: longitudinal record-level linkage of ophthalmic imaging and hospital admissions of 353 157 patients in London, UK[J]. BMJ open, 2022, 12(3): e058552.

[67] Hu W, Wang W, Wang Y, et al. Retinal age gap as a predictive biomarker of future risk of Parkinson’s disease[J]. Age and Ageing, 2022, 51(3): afac062.

[68] Tran C, Shen K, Liu K, et al. Deep learning predicts prevalent and incident Parkinson’s disease from UK Biobank fundus imaging[J]. Scientific Reports, 2024, 14(1): 3637.

[69] Richardson A, Kundu A, Henao R, et al. Multimodal retinal imaging classification for Parkinson's disease using a convolutional neural network[J]. Translational Vision Science & Technology, 2024, 13(8): 23.

[70] Lau A Y, Mok V, Lee J, et al. Retinal image analytics detects white matter hyperintensities in healthy adults[J]. Annals of clinical and translational neurology, 2019, 6(1): 98-105.

[71] Ritchlin C, Adamopoulos I E. Axial spondyloarthritis: new advances in diagnosis and management[J]. bmj, 2021, 372.

[72] Vieth J T, Lane D R. Anemia[J]. Emergency Medicine Clinics, 2014, 32(3): 613-628.

[73] Margulies L J. Ocular manifestations of cardiovascular and hematologic disorders[J]. Current Opinion in Ophthalmology, 1994, 5(6): 99-104.

[74] Mitani A, Huang A, Venugopalan S, et al. Detection of anaemia from retinal fundus images via deep learning[J]. Nature biomedical engineering, 2020, 4(1): 18-27.

[75] Wei H, Shen H, Li J, et al. AneNet: A lightweight network for the real-time anemia screening fromretinal vessel optical coherence tomography images[J]. Optics & Laser Technology, 2021, 136: 106773.