Non-invasive chronic kidney disease risk stratification tool derived from retina-based deep learning and clinical factors

Copeptin as a surrogate marker for arginine vasopressin: analytical insights, current utility, and emerging applications

Copeptin is a 39-amino-acid long glycosylated peptide with a leucine-rich core segment in the C-terminal part of pre-pro-vasopressin. It exhibits a rapid response comparable to arginine vasopressin (AVP) in response to osmotic, hemodynamic, and nonspecific stress-related stimuli. This similarity can be attributed to equimolar production of copeptin alongside AVP. However, there are markedly different decay kinetics for both peptides, with an estimated initial half-life of copeptin being approximately two times longer than that of AVP. Like AVP, copeptin correlates strongly over a wide osmolality range in healthy individuals, making it a useful alternative to AVP measurement. While copeptin does not appear to be significantly affected by food intake, small amounts of oral fluid intake may result in a significant decrease in copeptin levels. Compared to AVP, copeptin is considerably more stable in vitro. An automated immunofluorescent assay is now available and has been used in recent landmark trials. However, separate validation studies are required before copeptin thresholds from these studies are applied to other assays. The biological variation of copeptin in presumably healthy subjects has been recently reported, which could assist in defining analytical performance specifications for this measurand. An established diagnostic utility of copeptin is in the investigation of polyuria-polydipsia syndrome and copeptin-based testing protocols have been explored in recent years. A single baseline plasma copeptin >21.4 pmol/L differentiates AVP resistance (formerly known as nephrogenic diabetes insipidus) from other causes with 100% sensitivity and specificity, rendering water deprivation testing unnecessary in such cases. In a recent study among adult patients with polyuria-polydipsia syndrome, AVP deficiency (formerly known as central diabetes insipidus) was more accurately diagnosed with hypertonic saline-stimulated copeptin than with arginine-stimulated copeptin. Glucagon-stimulated copeptin has been proposed as a potentially safe and precise test in the investigation of polyuria-polydipsia syndrome. Furthermore, copeptin could reliably identify those with AVP deficiency among patients with severe hypernatremia, though its diagnostic utility is reportedly limited in the differential diagnosis of profound hyponatremia. Copeptin measurement may be a useful tool for early goal-directed management of post-operative AVP deficiency. Additionally, the potential prognostic utility of copeptin has been explored in other diseases. There is an interest in examining the role of the AVP system (with copeptin as a marker) in the pathogenesis of insulin resistance and diabetes mellitus. Copeptin has been found to be independently associated with an increased risk of incident stroke and cardiovascular disease mortality in men with diabetes mellitus. Increased levels of copeptin have been reported to be independently predictive of a decline in estimated glomerular filtration rate and a greater risk of new-onset chronic kidney disease. Furthermore, copeptin is associated with disease severity in patients with autosomal dominant polycystic kidney disease. Copeptin predicts the development of coronary artery disease and cardiovascular mortality in the older population. Moreover, the predictive value of copeptin was found to be comparable with that of N-terminal pro-brain natriuretic peptide for all-cause mortality in patients with heart failure. Whether the measurement of copeptin in these conditions alters clinical management remains to be demonstrated in future studies.

Transformative applications of oculomics-based AI approaches in the management of systemic diseases: A systematic review

BACKGROUND

Systemic diseases, such as cardiovascular and cerebrovascular conditions, pose significant global health challenges due to their high mortality rates. Early identification and intervention in systemic diseases can substantially enhance their prognosis. However, diagnosing systemic diseases often necessitates complex, expensive, and invasive tests, posing challenges in their timely detection. Therefore, simple, cost-effective, and non-invasive methods for the management (such as screening, diagnosis, and monitoring) of systemic diseases are needed to reduce associated comorbidities and mortality rates.

AIM OF THE REVIEW

This systematic review examines the application of artificial intelligence (AI) algorithms in managing systemic diseases by analyzing ophthalmic features (oculomics) obtained from convenient, affordable, and non-invasive ophthalmic imaging.

KEY SCIENTIFIC CONCEPTS OF REVIEW

Our analysis demonstrates the promising accuracy of AI in predicting systemic diseases. Subgroup analysis reveals promising capabilities of oculomics-based AI for disease staging, while caution is warranted due to the possible overestimation of AI capabilities in low-quality studies. These systems are cost-effective and safe, with high rates of acceptance among patients and clinicians. This review underscores the potential of oculomics-based AI approaches in revolutionizing the management of systemic diseases.

Validation of neuron activation patterns for artificial intelligence models in oculomics

Recent advancements in artificial intelligence (AI) have prompted researchers to expand into the field of oculomics; the association between the retina and systemic health. Unlike conventional AI models trained on well-recognized retinal features, the retinal phenotypes that most oculomics models use are more subtle. Consequently, applying conventional tools, such as saliency maps, to understand how oculomics models arrive at their inference is problematic and open to bias. We hypothesized that neuron activation patterns (NAPs) could be an alternative way to interpret oculomics models, but currently, most existing implementations focus on failure diagnosis. In this study, we designed a novel NAP framework to interpret an oculomics model. We then applied our framework to an AI model predicting systolic blood pressure from fundus images in the United Kingdom Biobank dataset. We found that the NAP generated from our framework was correlated to the clinically relevant endpoint of cardiovascular risk. Our NAP was also able to discern two biologically distinct groups among participants who were assigned the same predicted systolic blood pressure. These results demonstrate the feasibility of our proposed NAP framework for gaining deeper insights into the functioning of oculomics models. Further work is required to validate these results on external datasets.

Simultaneous detection of multiple urinary biomarkers in patients with early-stage diabetic kidney disease using Luminex liquid suspension chip technology

Background

Several urinary biomarkers have good diagnostic value for diabetic kidney disease (DKD); however, the predictive value is limited with the use of single biomarkers. We investigated the clinical value of Luminex liquid suspension chip detection of several urinary biomarkers simultaneously.

Methods

The study included 737 patients: 585 with diabetes mellitus (DM) and 152 with DKD. Propensity score matching (PSM) of demographic and medical characteristics identified a subset of 78 patients (DM = 39, DKD = 39). Two Luminex liquid suspension chips were used to detect 11 urinary biomarkers according to their molecular weight and concentration. The biomarkers, including cystatin C (CysC), nephrin, epidermal growth factor (EGF), kidney injury molecule-1 (KIM-1), retinol-binding protein4 (RBP4), α1-microglobulin (α1-MG), β2-microglobulin (β2-MG), vitamin D binding protein (VDBP), tissue inhibitor of metalloproteinases-1 (TIMP-1), tumor necrosis factor receptor-1 (TNFR-1), and tumor necrosis factor receptor-2 (TNFR-2) were compared in the DM and DKD groups. The diagnostic values of single biomarkers and various biomarker combinations for early diagnosis of DKD were assessed using receiver operating characteristic (ROC) curve analysis.

Results

Urinary levels of VDBP, RBP4, and KIM-1 were markedly higher in the DKD group than in the DM group (p < 0.05), whereas the TIMP-1, TNFR-1, TNFR-2, α1-MG, β2-MG, CysC, nephrin, and EGF levels were not significantly different between the groups. RBP4, KIM-1, TNFR-2, and VDBP reached p < 0.01 in univariate analysis and were entered into the final analysis. VDBP had the highest AUC (0.780, p < 0.01), followed by RBP4 (0.711, p < 0.01), KIM-1 (0.640, p = 0.044), and TNFR-2 (0.615, p = 0.081). However, a combination of these four urinary biomarkers had the highest AUC (0.812), with a sensitivity of 0.742 and a specificity of 0.760.

Conclusions

The urinary levels of VDBP, RBP4, KIM-1, and TNFR-2 can be detected simultaneously using Luminex liquid suspension chip technology. The combination of these biomarkers, which reflect different mechanisms of kidney damage, had the highest diagnostic value for DKD. However, this finding should be explored further to understand the synergistic effects of these biomarkers.

Prognostic potentials of AI in ophthalmology: systemic disease forecasting via retinal imaging

BACKGROUND

Artificial intelligence (AI) that utilizes deep learning (DL) has potential for systemic disease prediction using retinal imaging. The retina's unique features enable non-invasive visualization of the central nervous system and microvascular circulation, aiding early detection and personalized treatment plans for personalized care. This review explores the value of retinal assessment, AI-based retinal biomarkers, and the importance of longitudinal prediction models in personalized care.

MAIN TEXT

This narrative review extensively surveys the literature for relevant studies in PubMed and Google Scholar, investigating the application of AI-based retina biomarkers in predicting systemic diseases using retinal fundus photography. The study settings, sample sizes, utilized AI models and corresponding results were extracted and analysed. This review highlights the substantial potential of AI-based retinal biomarkers in predicting neurodegenerative, cardiovascular, and chronic kidney diseases. Notably, DL algorithms have demonstrated effectiveness in identifying retinal image features associated with cognitive decline, dementia, Parkinson's disease, and cardiovascular risk factors. Furthermore, longitudinal prediction models leveraging retinal images have shown potential in continuous disease risk assessment and early detection. AI-based retinal biomarkers are non-invasive, accurate, and efficient for disease forecasting and personalized care.

CONCLUSION

AI-based retinal imaging hold promise in transforming primary care and systemic disease management. Together, the retina's unique features and the power of AI enable early detection, risk stratification, and help revolutionizing disease management plans. However, to fully realize the potential of AI in this domain, further research and validation in real-world settings are essential.

Artificial intelligence in retinal imaging: current status and future prospects

INTRODUCTION

The steadily growing and aging world population, in conjunction with continuously increasing prevalences of vision-threatening retinal diseases, is placing an increasing burden on the global healthcare system. The main challenges within retinology involve identifying the comparatively few patients requiring therapy within the large mass, the assurance of comprehensive screening for retinal disease and individualized therapy planning. In order to sustain high-quality ophthalmic care in the future, the incorporation of artificial intelligence (AI) technologies into our clinical practice represents a potential solution.

AREAS COVERED

This review sheds light onto already realized and promising future applications of AI techniques in retinal imaging. The main attention is directed at the application in diabetic retinopathy and age-related macular degeneration. The principles of use in disease screening, grading, therapeutic planning and prediction of future developments are explained based on the currently available literature.

EXPERT OPINION

The recent accomplishments of AI in retinal imaging indicate that its implementation into our daily practice is likely to fundamentally change the ophthalmic healthcare system and bring us one step closer to the goal of individualized treatment. However, it must be emphasized that the aim is to optimally support clinicians by gradually incorporating AI approaches, rather than replacing ophthalmologists.

Applications of artificial intelligence-assisted retinal imaging in systemic diseases: A literature review

The retina is a vulnerable structure that is frequently affected by different systemic conditions. The main mechanisms of systemic retinal damage are either primary insult of neurons of the retina, alterations of the local vasculature, or both. This vulnerability makes the retina an important window that reflects the severity of the preexisting systemic disorders. Therefore, current imaging techniques aim to identify early retinal changes relevant to systemic anomalies to establish anticipated diagnosis and start adequate management. Artificial intelligence (AI) has become among the highly trending technologies in the field of medicine. Its spread continues to extend to different specialties including ophthalmology. Many studies have shown the potential of this technique in assisting the screening of retinal anomalies in the context of systemic disorders. In this review, we performed extensive literature search to identify the most important studies that support the effectiveness of AI/deep learning use for diagnosing systemic disorders through retinal imaging. The utility of these technologies in the field of retina-based diagnosis of systemic conditions is highlighted.