Emerging applications of bioinformatics and artificial intelligence in the analysis of biofluid markers involved in retinal occlusive diseases: a systematic review

Retina Fundus Photograph-Based Artificial Intelligence Algorithms in Medicine: A Systematic Review

We conducted a systematic review of research in artificial intelligence (AI) for retinal fundus photographic images. We highlighted the use of various AI algorithms, including deep learning (DL) models, for application in ophthalmic and non-ophthalmic (i.e., systemic) disorders. We found that the use of AI algorithms for the interpretation of retinal images, compared to clinical data and physician experts, represents an innovative solution with demonstrated superior accuracy in identifying many ophthalmic (e.g., diabetic retinopathy (DR), age-related macular degeneration (AMD), optic nerve disorders), and non-ophthalmic disorders (e.g., dementia, cardiovascular disease). There has been a significant amount of clinical and imaging data for this research, leading to the potential incorporation of AI and DL for automated analysis. AI has the potential to transform healthcare by improving accuracy, speed, and workflow, lowering cost, increasing access, reducing mistakes, and transforming healthcare worker education and training.

Applications of artificial intelligence and bioinformatics methodologies in the analysis of ocular biofluid markers: a scoping review

PURPOSE

This scoping review summarizes the applications of artificial intelligence (AI) and bioinformatics methodologies in analysis of ocular biofluid markers. The secondary objective was to explore supervised and unsupervised AI techniques and their predictive accuracies. We also evaluate the integration of bioinformatics with AI tools.

METHODS

This scoping review was conducted across five electronic databases including EMBASE, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics were included.

RESULTS

A total of 10,262 articles were retrieved from all databases and 177 studies met the inclusion criteria. The most commonly studied ocular diseases were diabetic eye diseases, with 50 papers (28%), while glaucoma was explored in 25 studies (14%), age-related macular degeneration in 20 (11%), dry eye disease in 10 (6%), and uveitis in 9 (5%). Supervised learning was used in 91 papers (51%), unsupervised AI in 83 (46%), and bioinformatics in 85 (48%). Ninety-eight papers (55%) used more than one class of AI (e.g. > 1 of supervised, unsupervised, bioinformatics, or statistical techniques), while 79 (45%) used only one. Supervised learning techniques were often used to predict disease status or prognosis, and demonstrated strong accuracy. Unsupervised AI algorithms were used to bolster the accuracy of other algorithms, identify molecularly distinct subgroups, or cluster cases into distinct subgroups that are useful for prediction of the disease course. Finally, bioinformatic tools were used to translate complex biomarker profiles or findings into interpretable data.

CONCLUSION

AI analysis of biofluid markers displayed diagnostic accuracy, provided insight into mechanisms of molecular etiologies, and had the ability to provide individualized targeted therapeutic treatment for patients. Given the progression of AI towards use in both research and the clinic, ophthalmologists should be broadly aware of the commonly used algorithms and their applications. Future research may be aimed at validating algorithms and integrating them in clinical practice.

Evaluating the long-term biological stability of cytokine biomarkers in ocular fluid samples

PURPOSE

The quality of biological fluid samples is vital for optimal preanalytical procedures and a requirement for effective translational biomarker research. This study aims to determine the effects of storage duration and freeze-thawing on the levels of various cytokines in the human aqueous humour and vitreous samples.

METHODS AND ANALYSIS

Human ocular aqueous humour and vitreous samples were obtained from 25 eyes and stored at -80°C for analysis. All samples were assayed for 27 cytokine biomarker concentrations (pg/mL) using a multiplex assay. Four sample storage durations following sample collection were evaluated (1 week, 3 months, 9 months and 15 months). Additionally, samples underwent up to three freeze-thaw cycles within the study period.

RESULTS

Among the 27 cytokine biomarkers, concentrations of four cytokines (Interleukin (IL)-2, IL-10, IL-12 and platelet-derived growth factor-BB) were significantly decreased by storage duration at all time points, as early as 3 months following sample collection (range of 9%-37% decline between 1 week and 15 months, p<0.001). Freeze-thawing of up to three cycles did not significantly impact the cytokine biomarker concentrations in aqueous humour or vitreous. Separability of patient-specific cytokine biomarker profiles in the principal component analysis remained relatively the same over the 15 months of storage duration.

CONCLUSION

The findings from this study suggest that several intraocular cytokine biomarkers in human aqueous humour and vitreous samples may be susceptible to degradation with long-term storage, as early as 3 months after collection. The overall patient-specific cytokine biomarker profiles are more stable than concentrations of individual cytokines. Future studies should focus on developing guidelines for optimal and standardised sample handling methods to ensure correct research findings about intraocular biomarkers are translated into clinical practice.

Variability of Replicates of Intraocular Inflammatory Biomarkers in Ocular Fluid Samples Analyzed with Multiplex Assays

Purpose

Certain factors such as instrumental and sample processing errors may contribute to variability of ocular biofluid samples when they are run as replicates with multiplex assays. There is a paucity of literature on the variability of replicates in multiplex assays. This study aims to evaluate whether there is significant variability in replicate analyses of multiplex assays.

Methods

A total of 152 human ocular biofluid samples (51 aqueous humor and 101 vitreous) were collected and assayed for 27 cytokine biomarker concentrations (pg/mL). Samples were evaluated as replicates (duplicate analysis) at four different time points. Statistical methods including paired samples t-test, 3-way ANOVA, intraclass correlation coefficient (ICC; <0.5-0.75=poor-moderate, 0.75->0.90 =good-excellent reliability), and coefficients of variation (CV) were employed to evaluate for statistical significance, with Bonferroni corrected P=0.002.

Results

Among the 4104 biomarker replicate assays for aqueous humor and vitreous, two analytes (PDGF-BB and IL-7) had a statistically significant difference between the sampled concentrations of the replicates in vitreous samples (mean (diff)=2.05, P<0.001, mean (diff)=1.56, P<0.001, respectively). Majority of the ICC values fell within the good-excellent range (86% of samples) with a minority falling in the poor-moderate range (14% of samples). More variability was noted in the vitreous humour, with five analytes (IL-2, IL-10, IL-12(p70), IL-13, IL-17) demonstrating an average ICC of less than 0.5. The CV calculated for each set of replicates suggested that 93% of replicates had an acceptable level of quantitative assay variability (CV<20%).

Conclusion

This study demonstrates that the analysis of most biomarkers in ocular fluids may not require the use of replicates. However, certain analytes such as PDGF-BB and IL-7 may require the use of replicates to ensure reliable results. Caution should be taken when applying these findings to other laboratory settings as our study was conducted by an experienced technician using a standardized protocol. In less standardized settings, replicates may be required in order to ensure accuracy of results. These findings may guide researchers with the design of their studies on ophthalmic biomarker analysis.

Research progress on diagnosing retinal vascular diseases based on artificial intelligence and fundus images

As the only blood vessels that can directly be seen in the whole body, pathological changes in retinal vessels are related to the metabolic state of the whole body and many systems, which seriously affect the vision and quality of life of patients. Timely diagnosis and treatment are key to improving vision prognosis. In recent years, with the rapid development of artificial intelligence, the application of artificial intelligence in ophthalmology has become increasingly extensive and in-depth, especially in the field of retinal vascular diseases. Research study results based on artificial intelligence and fundus images are remarkable and provides a great possibility for early diagnosis and treatment. This paper reviews the recent research progress on artificial intelligence in retinal vascular diseases (including diabetic retinopathy, hypertensive retinopathy, retinal vein occlusion, retinopathy of prematurity, and age-related macular degeneration). The limitations and challenges of the research process are also discussed.