Keratoconus-susceptibility gene identification by corneal thickness genome-wide association study and artificial intelligence IBM Watson

Role of artificial intelligence, machine learning and deep learning models in corneal disorders - A narrative review

In the last decade, artificial intelligence (AI) has significantly impacted ophthalmology, particularly in managing corneal diseases, a major reversible cause of blindness. This review explores AI's transformative role in the corneal subspecialty, which has adopted advanced technology for superior clinical judgment, early diagnosis, and personalized therapy. While AI's role in anterior segment diseases is less documented compared to glaucoma and retinal pathologies, this review highlights its integration into corneal diagnostics through imaging techniques like slit-lamp biomicroscopy, anterior segment optical coherence tomography (AS-OCT), and in vivo confocal biomicroscopy. AI has been pivotal in refining decision-making and prognosis for conditions such as keratoconus, infectious keratitis, and dystrophies. Multi-disease deep learning neural networks (MDDNs) have shown diagnostic ability in classifying corneal diseases using AS-OCT images, achieving notable metrics like an AUC of 0.910. AI's progress over two decades has significantly improved the accuracy of diagnosing conditions like keratoconus and microbial keratitis. For instance, AI has achieved a 90.7% accuracy rate in classifying bacterial and fungal keratitis and an AUC of 0.910 in differentiating various corneal diseases. Convolutional neural networks (CNNs) have enhanced the analysis of color-coded corneal maps, yielding up to 99.3% diagnostic accuracy for keratoconus. Deep learning algorithms have also shown robust performance in detecting fungal hyphae on in vivo confocal microscopy, with precise quantification of hyphal density. AI models combining tomography scans and visual acuity have demonstrated up to 97% accuracy in keratoconus staging according to the Amsler-Krumeich classification. However, the review acknowledges the limitations of current AI models, including their reliance on binary classification, which may not capture the complexity of real-world clinical presentations with multiple coexisting disorders. Challenges also include dependency on data quality, diverse imaging protocols, and integrating multimodal images for a generalized AI diagnosis. The need for interpretability in AI models is emphasized to foster trust and applicability in clinical settings. Looking ahead, AI has the potential to unravel the intricate mechanisms behind corneal pathologies, reduce healthcare's carbon footprint, and revolutionize diagnostic and management paradigms. Ethical and regulatory considerations will accompany AI's clinical adoption, marking an era where AI not only assists but augments ophthalmic care.

Identification of Keratoconus-Related Phenotypes in Three Ppip5k2 Mouse Models

Purpose

It is necessary to establish a mouse model of keratoconus (KC) for research and therapy. We aimed to determine corneal phenotypes in 3 Ppip5k2 mouse models.

Methods

Central corneal thickness (CCT) was determined using spectral domain optical coherence tomography (SD-OCT) in Ppip5k2+/K^ (n = 41 eyes), Ppip5k2K^/K^ (n = 17 eyes) and 2 knock-in mice, Ppip5k2S419A/+ (n = 54 eyes) and Ppip5k2S419A/S419A (n = 18 eyes), and Ppip5k2D843S/+ (n = 42 eyes) and Ppip5k2D843S/D843S (n = 44 eyes) at 3 and 6 months. Pachymetry maps were generated using the Mouse Corneal Analysis Program (MCAP) to process OCT images. Slit lamp biomicroscopy was used to determine any corneal abnormalities, and, last, hematoxylin and eosin (H&E) staining using corneal sections from these animals was used to examine morphological changes.

Results

CCT significantly decreased from 3 to 6 months in the Ppip5k2+/K^ and Ppip5k2K^/K^ mice compared to their littermate controls. OCT-based pachymetry maps revealed abnormally localized thinning in all three models compared to their wild-type (WT) controls. Slit lamp examinations revealed corneal abnormalities in the form of bullous keratopathy, stromal edema, stromal scarring, deep corneal neovascularization, and opacities in the heterozygous/homozygous mice of the three models in comparison with their controls. Corneal histological abnormalities, such as epithelial thickening and stromal layer damage, were observed in the heterozygous/homozygous mice of the three models in comparison with the WT controls.

Conclusions

We have identified phenotypic and histological changes in the corneas of three mouse lines that could be relevant in the development of animal models of KC.

Utility of artificial intelligence in the diagnosis and management of keratoconus: a systematic review

Introduction

The application of artificial intelligence (AI) systems in ophthalmology is rapidly expanding. Early detection and management of keratoconus is important for preventing disease progression and the need for corneal transplant. We review studies regarding the utility of AI in the diagnosis and management of keratoconus and other corneal ectasias.

Methods

We conducted a systematic search for relevant original, English-language research studies in the PubMed, Web of Science, Embase, and Cochrane databases from inception to October 31, 2023, using a combination of the following keywords: artificial intelligence, deep learning, machine learning, keratoconus, and corneal ectasia. Case reports, literature reviews, conference proceedings, and editorials were excluded. We extracted the following data from each eligible study: type of AI, input used for training, output, ground truth or reference, dataset size, availability of algorithm/model, availability of dataset, and major study findings.

Results

Ninety-three original research studies were included in this review, with the date of publication ranging from 1994 to 2023. The majority of studies were regarding the use of AI in detecting keratoconus or subclinical keratoconus (n=61). Among studies regarding keratoconus diagnosis, the most common inputs were corneal topography, Scheimpflug-based corneal tomography, and anterior segment-optical coherence tomography. This review also summarized 16 original research studies regarding AI-based assessment of severity and clinical features, 7 studies regarding the prediction of disease progression, and 6 studies regarding the characterization of treatment response. There were only three studies regarding the use of AI in identifying susceptibility genes involved in the etiology and pathogenesis of keratoconus.

Discussion

Algorithms trained on Scheimpflug-based tomography seem promising tools for the early diagnosis of keratoconus that can be particularly applied in low-resource communities. Future studies could investigate the application of AI models trained on multimodal patient information for staging keratoconus severity and tracking disease progression.

Association of Novel Loci With Keratoconus Susceptibility in a Chinese Genome-Wide Association Study

Purpose

Keratoconus (KC) is a progressive corneal disease that can lead to corneal blindness if not properly managed. The purpose of this study was to identify genetic associations with KC in China and to investigate whether these genetic variants are associated with corneal thickness and corneal curvature in KC cases.

Methods

A genome-wide association study was conducted on 853 patients with KC and 6248 controls. The KC cases were genotyped with the Illumina Infinium Human Asian Screening Array BeadChip, and the controls were genotyped with the Illumina Infinium Human Global Screening Array BeadChip. Genetic associations with KC, as well as correlations between the positive variants and corneal parameters including central corneal thickness (CCT) and mean keratometry (Km), were compared using PLINK version 1.90.

Results

Our present study identified four single-nucleotide polymorphisms (SNPs) within four risk loci (PTGER3: rs2300163, EYA1: rs1077435, ASS1: rs141365191, and CHTF8: rs3743680) associated with KC in Chinese patients that reached genome-wide significance. Among the identified SNPs with P < 1.00 × 10-4, seven SNPs (FOSL2-PLB1: rs12622211, RXRA-COL5A1: rs3118515, rs3132306, rs1536482, rs3118520, KAT6B: rs192187772, RAP2A-IPO5: rs41361245) were observed to be associated with CCT, and one SNP (USP13: rs6767552) was found to be associated with Km.

Conclusions

In the first genome-wide association study of KC with a relatively large study population in China, we identified four SNPs in four risk loci associated with the disease. The findings enriched the understanding of genetic susceptibility to KC and provided new insights into the genetic etiology of the disease.

Keratoconus: exploring fundamentals and future perspectives - a comprehensive systematic review

Background

New developments in artificial intelligence, particularly with promising results in early detection and management of keratoconus, have favorably altered the natural history of the disease over the last few decades. Features of artificial intelligence in different machine such as anterior segment optical coherence tomography, and femtosecond laser technique have improved safety, precision, effectiveness, and predictability of treatment modalities of keratoconus (from contact lenses to keratoplasty techniques). These options ingrained in artificial intelligence are already underway and allow ophthalmologist to approach disease in the most non-invasive way.

Objectives

This study comprehensively describes all of the treatment modalities of keratoconus considering machine learning strategies.

Design

A multidimensional comprehensive systematic narrative review.

Data sources and methods

A comprehensive search was done in the five main electronic databases (PubMed, Scopus, Web of Science, Embase, and Cochrane), without language and time or type of study restrictions. Afterward, eligible articles were selected by screening the titles and abstracts based on main mesh keywords. For potentially eligible articles, the full text was also reviewed.

Results

Artificial intelligence demonstrates promise in keratoconus diagnosis and clinical management, spanning early detection (especially in subclinical cases), preoperative screening, postoperative ectasia prediction after keratorefractive surgery, and guiding surgical decisions. The majority of studies employed a solitary machine learning algorithm, whereas minor studies assessed multiple algorithms that evaluated the association of various keratoconus staging and management strategies. Last but not least, AI has proven effective in guiding the implantation of intracorneal ring segments in keratoconus corneas and predicting surgical outcomes.

Conclusion

The efficient and widespread clinical translation of machine learning models in keratoconus management is a crucial goal of potential future approaches to better visual performance in keratoconus patients.

Trial registration

The article has been registered through PROSPERO, an international database of prospectively registered systematic reviews, with the ID: CRD42022319338.

Bioinformatics analysis of key candidate genes and pathways in Chinese patients with keratoconus

Keratoconus (KC) is a multifactorial disease in which genetic factors played important roles in its pathogenesis. The purpose of the current study was to identify the key candidate genes and pathways in Chinese patients with KC through bioinformatics analysis. Totally, we identified 71 candidate genes by analyzing the results of whole exome sequencing on 51 Chinese patients with KC, combining with previous reports on differential expression at transcription and protein levels in KC. Gene enrichment analysis with GeneCodis demonstrated that two significantly enriched terms including 21 genes in biological process (BP) were detected, and six significantly enriched terms containing 14 genes in Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway were discovered. The STRING was utilized to construct the protein-protein interaction (PPI) network of identified genes. The result showed that a PPI network consisted of 14 nodes with 14 edges was constructed, and two gene modules were obtained. Eight hub genes (LAMB3, LAMA3, LAMA1, ITGA6, ITGA3, COL6A3, COL6A2, and COL6A1) were identified as key candidate genes for KC by cytoHubba in Cytoscape. Functional enrichment analysis with ClueGO and CluePedia indicated that the ECM-receptor interaction was the key pathway accounted for KC. The findings might provide novel insights on the genetic basis of KC.

Trio-based exome sequencing broaden the genetic spectrum in keratoconus

Keratoconus (KC) is a complex corneal disorder with genetic factors involving in its pathogenesis. The genetic etiology of KC has not been fully elucidated. In this study, we aimed to expand the genetic spectrum in KC by trio-based exome sequencing. Trio-based exome sequencing was conducted in 20 patients with KC and their unaffected parents to broaden the genetic spectrum of the disease. With a series of filtering criteria, de novo, recessive homozygous, and compound heterozygous variants in candidate genes were identified, and the candidate genes were classified for further analysis. Finally, we identified 60 variants in 32 candidate genes through trio-based exome sequencing. Among the candidate genes, 10 genes (ARHGEF10, ARHGEF17, ASPM, FLNA, NDRG1, NEB, PLS3, STARD8, SYNE1, TTN) were classified as cytoskeleton-related genes, 4 genes (COL28A1, SDK1, STAB1, TENM2) were classified as cell adhesion-related genes, and 18 genes (APLP2, BCORL1, CCNB3, FOXN1, FUT8, GALNT10, HEPH, HHIP, HMGB3, HS6ST2, JADE3, KIAA0040, MCF2L, MYOF, QRICH2, RPS6KA6, SMARCA1, TNRC6A) were classified into other genes group. Additionally, the candidate rare deleterious variants in TTN were highly repeated in 25% trios. In conclusion, the study provided new insights into the genetic spectrum of KC which might underlie the genetic etiology for the disease. The findings would improve our understanding of pathogenesis in KC and provide critical clues to future functional validation.

Artificial intelligence-assisted diagnosis of ocular surface diseases

With the rapid development of computer technology, the application of artificial intelligence (AI) in ophthalmology research has gained prominence in modern medicine. Artificial intelligence-related research in ophthalmology previously focused on the screening and diagnosis of fundus diseases, particularly diabetic retinopathy, age-related macular degeneration, and glaucoma. Since fundus images are relatively fixed, their standards are easy to unify. Artificial intelligence research related to ocular surface diseases has also increased. The main issue with research on ocular surface diseases is that the images involved are complex, with many modalities. Therefore, this review aims to summarize current artificial intelligence research and technologies used to diagnose ocular surface diseases such as pterygium, keratoconus, infectious keratitis, and dry eye to identify mature artificial intelligence models that are suitable for research of ocular surface diseases and potential algorithms that may be used in the future.

Family-based exome sequencing identifies candidate genes related to keratoconus in Chinese families

Background: Keratoconus (KC) is a complex corneal disorder with a strong genetic component. The present study aimed to identify candidate genes related to KC in Chinese families.

Methods: Family-based exome sequencing was performed in ten patients suffering from KC who belong to five families with two affected members in each. The candidate rare variants were identified with multi-step bioinformatics analysis. The STRING website was used to perform the protein interaction of the identified genes.

Results: Our analyses identified 32 candidate rare variants in 13 genes by family-based exome sequencing. The molecular analyses of identified genes showed that EPCAM directly interacted with CTNNB1 of the Hippo signaling pathway and focal adhesion pathway, and directly interacted with CTNNB1, CDH1 of the WNT signaling pathway. SHROOM3 directly interacted with ROCK2, ROCK1 of the focal adhesion pathway. SYNE1 directly interacted with MUSK of the extracellular matrix organization pathway. TEK directly interacted with VEGFA, SHC1, PIK3R1, GRB2 of the focal adhesion pathway. TTN directly interacted with CAPN3 of the extracellular matrix organization pathway.

Conclusion: The EPCAM, SHROOM3, SYNE1, TEK, and TTN genes were potential high-risk candidate pathogenic genes of familial KC. The findings might significantly improve our understanding of the genetic etiology of the disease, providing novel insights on KC pathogenesis.

Heritability of Corneal Parameters in Nuclear Families With Keratoconus

Purpose

This study aimed to investigate the heritability of corneal parameters obtained by Pentacam in nuclear families with keratoconus (KC).

Methods

A total of 82 patients with KC and their biological parents (n = 164) were recruited in the current study. All subjects underwent corneal tomography with Pentacam. Family units were analyzed to calculate the heritability of corneal parameters by linear mixed effects model using the R statistical software.

Results

The pachymetry at apex, pupil, and thinnest point were all significantly heritable at 43.26%, 42.63%, and 43.09%, respectively. The heritability of flat meridian keratometry, steep meridian keratometry, and mean keratometry in the anterior surface were 10.36%, 9.05%, and 10.21%, respectively, and that of flat meridian keratometry, steep meridian keratometry, and mean keratometry in the posterior surface were 8.44%, 9.67%, and 9.06%, respectively. The posterior radius of curvature had higher heritability in comparison with anterior radius of curvature (19.16% vs. 14.37%). Moreover, among combined topometric indices, the heritability of index of vertical asymmetry was the highest (19.49%), and that of central keratoconus index was the lowest (6.64%).

Conclusions

The present study demonstrated a substantial heritability of corneal parameters in nuclear families with KC. The pachymetric indices are heritable and may be suitable as KC endophenotypes, suggesting a necessity to discover the genes associated with corneal thickness in KC.

Translational Relevance

The pachymetric indices are heritable and may be suitable as KC endophenotypes, indicating that the pachymetric indices might be a corneal characteristic to predict the occurrence of KC.

Novel Mutations Identified in the Chinese Han Population with Keratoconus by Next-Generation Sequencing

Aim. To identify novel mutations in keratoconus (KC) susceptibility genes in the Chinese Han population. Methods. A total of fifty-two patients with primary KC were recruited. Blood samples were collected, and genomic DNA was isolated from peripheral blood leukocytes. The entire coding region, intron-exon junctions, and promoter regions of sixteen known KC susceptibility genes were screened with next-generation sequencing technology. All identified variants were further confirmed using the Sanger sequencing technology. The Sorting Intolerant from Tolerant (SIFT), MutationTaster, and PolyPhen 2 programs were used to predict the effect of amino acid substitution on protein. Results. After removing twelve known SNPs (single nucleotide polymorphisms) and three variants predicted to be harmless, nine novel mutations were identified in eight of the fifty-two patients, including c.455C > T:p.P152L in FNDC3B; c.3636_3637del:p.R1212fs in COL4A4; c.5015G > T:p.R1672L, c.3798dupA:p.P1267fs, and c.28G > A:p.A10T in MPDZ; c.1940C > T:p.P647L in DOCK9; c.127_128insGGC:p.Q43delinsRQ in POLG; c.3019G > A:p.V1007I in IPO5; and c.624 + 7− > A in TGFBI. All nine mutations in the patients with KC were heterozygote. Conclusion. This study enlarged the gene profile of KC and should be further confirmed by well-powered, genome-wide association studies (GWAS) of Han Chinese patients.

Systematically Displaying the Pathogenesis of Keratoconus via Multi-Level Related Gene Enrichment-Based Review

Keratoconus (KC) is an etiologically heterogeneous corneal ectatic disorder. To systematically display the pathogenesis of keratoconus (KC), this study reviewed all the reported genes involved in KC, and performed an enrichment analysis of genes identified at the genome, transcription, and protein levels respectively. Combined analysis of multi-level results revealed their shared genes, gene ontology (GO), and pathway terms, to explore the possible pathogenesis of KC. After an initial search, 80 candidate genes, 2,933 transcriptional differential genes, and 947 differential proteins were collected. The candidate genes were significantly enriched in extracellular matrix (ECM) related terms, Wnt signaling pathway and cytokine activities. The enriched GO/pathway terms of transcription and protein levels highlight the importance of ECM, cell adhesion, and inflammatory once again. Combined analysis of multi-levels identified 13 genes, 43 GOs, and 12 pathways. The pathogenic relationships among these overlapping factors maybe as follows. The gene mutations/variants caused insufficient protein dosage or abnormal function, together with environmental stimulation, leading to the related functions and pathways changes in the corneal cells. These included response to the glucocorticoid and reactive oxygen species; regulation of various signaling (P13K-AKT, MAPK and NF-kappaB), apoptosis and aging; upregulation of cytokines and collagen-related enzymes; and downregulation of collagen and other ECM-related proteins. These undoubtedly lead to a reduction of extracellular components and induction of cell apoptosis, resulting in the loosening and thinning of corneal tissue structure. This study, in addition to providing information about the genes involved, also provides an integrated insight into the gene-based etiology and pathogenesis of KC.

Regulatory-approved deep learning/machine learning-based medical devices in Japan as of 2020: A systematic review

Machine learning (ML) and deep learning (DL) are changing the world and reshaping the medical field. Thus, we conducted a systematic review to determine the status of regulatory-approved ML/DL-based medical devices in Japan, a leading stakeholder in international regulatory harmonization. Information about the medical devices were obtained from the Japan Association for the Advancement of Medical Equipment search service. The usage of ML/DL methodology in the medical devices was confirmed using public announcements or by contacting the marketing authorization holders via e-mail when the public announcements were insufficient for confirmation. Among the 114,150 medical devices found, 11 were regulatory-approved ML/DL-based Software as a Medical Device, with 6 products (54.5%) related to radiology and 5 products (45.5%) related to gastroenterology. The domestic ML/DL-based Software as a Medical Device were mostly related to health check-ups, which are common in Japan. Our review can help understanding the global overview that can foster international competitiveness and further tailored advancements.

Common ALDH3A1 Gene Variant Associated with Keratoconus Risk in the Polish Population

Background: ALDH3A1 protein is important in maintaining corneal physiology and protecting the eye from UV damage. However, none of the genome-wide association studies has indicated that the ALDH3A1 locus is associated with keratoconus. In this study, we examined the potential role of ALDH3A1 variants as risk factors for keratoconus incidence and severity in a large group of Polish keratoconus patients. Methods: In the first stage we analyzed the coding region sequence of the ALDH3A1 in a subgroup of keratoconus. Then, we genotyped three selected ALDH3A1 variants in a larger KC group of patients (n = 261) and healthy controls (n = 317). Results: We found that the rs1042183 minor allele A is a risk factor for keratoconus in the dominant model (OR = 2.06, 95%CI = 1.42–2.98, p = 0.00013). The rs2228100 variant genotypes appear to be associated with an earlier age of KC diagnosis in the Polish population (p = 0.055 for comparison of three genotypes and p = 0.022 for the dominant inheritance model). Conclusions: The rs1042183 variant in ALDH3A1 is associated with keratoconus risk in the Polish population. The differences in the allele frequency between both populations could be partially responsible for the difference in the disease prevalence.

Potential underlying genetic associations between keratoconus and diabetes mellitus

Background Keratoconus (KC) is the most common ectatic corneal disease, characterized by significantly localized thinning of the corneal stroma. Genetic, environmental, hormonal, and metabolic factors contribute to the pathogenesis of KC. Additionally, multiple comorbidities, such as diabetes mellitus, may affect the risk of KC. Main Body Patients with diabetes mellitus (DM) have been reported to have lower risk of developing KC by way of increased endogenous collagen crosslinking in response to chronic hyperglycemia. However, this remains a debated topic as other studies have suggested either a positive association or no association between DM and KC. To gain further insight into the underlying genetic components of these two diseases, we reviewed candidate genes associated with KC and central corneal thickness in the literature. We then explored how these genes may be regulated similarly or differentially under hyperglycemic conditions and the role they play in the systemic complications associated with DM. Conclusion Our comprehensive review of potential genetic factors underlying KC and DM provides a direction for future studies to further determine the genetic etiology of KC and how it is influenced by systemic diseases such as diabetes.

Artificial Intelligence in Cornea, Refractive Surgery, and Cataract: Basic Principles, Clinical Applications, and Future Directions

ABSTRACT

Corneal diseases, uncorrected refractive errors, and cataract represent the major causes of blindness globally. The number of refractive surgeries, either cornea- or lens-based, is also on the rise as the demand for perfect vision continues to increase. With the recent advancement and potential promises of artificial intelligence (AI) technologies demonstrated in the realm of ophthalmology, particularly retinal diseases and glaucoma, AI researchers and clinicians are now channeling their focus toward the less explored ophthalmic areas related to the anterior segment of the eye. Conditions that rely on anterior segment imaging modalities, including slit-lamp photography, anterior segment optical coherence tomography, corneal tomography, in vivo confocal microscopy and/or optical biometers, are the most commonly explored areas. These include infectious keratitis, keratoconus, corneal grafts, ocular surface pathologies, preoperative screening before refractive surgery, intraocular lens calculation, and automated refraction, among others. In this review, we aimed to provide a comprehensive update on the utilization of AI in anterior segment diseases, with particular emphasis on the recent advancement in the past few years. In addition, we demystify some of the basic principles and terminologies related to AI, particularly machine learning and deep learning, to help improve the understanding, research and clinical implementation of these AI technologies among the ophthalmologists and vision scientists. As we march toward the era of digital health, guidelines such as CONSORT-AI, SPIRIT-AI, and STARD-AI will play crucial roles in guiding and standardizing the conduct and reporting of AI-related trials, ultimately promoting their potential for clinical translation.

IL1A and IL1B gene polymorphisms and keratoconus susceptibility: evidence from an updated meta-analysis

Background: Several single-nucleotide polymorphisms (SNPs) in IL1B genes have been associated with KTCN. However, the results of these studies were not conclusive. This meta-analysis association study is aimed to quantitatively estimate the association of IL1B rs16944 (g.4490T>C) and rs1143627 (g.4970C>T), and IL1A rs2071376 (c.615 + 169C>A) polymorphisms with KTCN susceptibility.Materials and Methods: Systematic literature search was performed in Web of Science, MEDLINE, PubMed, Scopus, and Google Scholar databases. The odds ratios (ORs) and 95% confidence intervals (CI) were calculated assuming different contrasted genetic models.Results: The reference T allele of IL1B (g.4490T>C) polymorphism was significantly associated with decreased KTCN risk under all assessed genetic models. Regarding the reference C allele of IL1B (g.4970C>T) polymorphism, decreased risk of KTCN was found. The reference C allele of IL1A (c.615 + 169C>A) polymorphism conferred a decreased risk of KTCN under heterozygous codominant (AC vs. AA), homozygous codominant (CC vs. AA), and dominant (AC+CC vs. AA) genetic models. The pooling estimates showed that the T C haplotype was associated with a significant increase in KTCN risk. In contrast, the T T haplotype was correlated with a decreased risk of KTCN. With the assumption of a prior probability of 0.25, the false-positive report probability (FPRP) values were less than 0.2, indicating the observed significant associations were notable.Conclusion: These findings propose that the studied IL1B polymorphisms and the IL1A variation have opposite effects on KTCN susceptibility. More large-scale replication studies are warranted to illuminate the precise role of these SNPs on the etiology of eye disorders.

Evaluating the association between single nucleotide polymorphisms in the stonin 2 (STON2) gene and keratoconus in a Han Chinese population

Background

A recent genome-wide association study (GWAS) identified a significant association between the single nucleotide polymorphism (SNP) rs2371597 in the stonin 2 gene (STON2) and keratoconus (KCTN) susceptibility. The current study further explored the association between STON2 and KCTN susceptibility in an independent Han Chinese population.

Methods

Three SNPs (rs2371597, rs8004137, and rs8008602) located in the STON2 gene were examined in 164 Han Chinese patients with KCTN and 239 age- and gender-matched healthy subjects. The TaqMan SNP genotyping assays were performed, and the LDlink, RegulomeDB, and PLINK package were applied for data analyses. The gene expression levels of STON2 were investigated in various murine organ tissues using quantitative real-time polymerase chain reaction (qRT-PCR).

Results

The SNP rs2371597 was significantly associated with KCTN risk in this Han Chinese population. The frequency of the C allele in KCTN patients was significantly higher than that in healthy subjects [34.8% vs. 26.6%; odds ratio (OR) =1.47; 95% confidence interval (CI): 1.08 to 2.02; P=0.01409]. The genotype distribution of the SNP rs2371597 was also significantly different between KCTN patients and controls. The other two genotyped SNPs allele and genotypic frequencies were not remarkably different between the KCTN group and the control group. However, the haplotype CAT formed by the three SNPs was substantially associated with the risk of KCTN (P=0.04101). Also, gene expression pattern analysis showed a relatively higher expression of STON2 in the cornea in comparison to other tissues.

Conclusions

The current study demonstrated that SNPs in the STON2 gene were associated with an increased risk of developing KCTN in this Han Chinese population, suggesting that the STON2 gene may play an important role in the etiology of KCTN.

Application of Artificial Intelligence in the Diagnosis and Management of Corneal Diseases

Diagnosis and treatment planning in ophthalmology heavily depend on clinical examination and advanced imaging modalities, which can be time-consuming and carry the risk of human error. Artificial intelligence (AI) and deep learning (DL) are being used in different fields of ophthalmology and in particular, when running diagnostics and predicting outcomes of anterior segment surgeries. This review will evaluate the recent developments in AI for diagnostics, surgical interventions, and prognosis of corneal diseases. It also provides a brief overview of the newer AI dependent modalities in corneal diseases.

Cascade of interactions between candidate genes reveals convergent mechanisms in keratoconus disease pathogenesis

Keratoconus is a progressive thinning, steepening and distortion of the cornea which can lead to loss of vision if left untreated. Keratoconus has a complex multifactorial etiology, with genetic and environmental components contributing to the disease pathophysiology. Studies have observed high concordance between monozygotic twins, discordance between dizygotic twins, and high familial segregation indicating the presence of a very strong genetic component in the pathogenesis of keratoconus. The use of genome-wide linkage studies on families and twins, genome-wide association studies (GWAS) on case-controls, next-generation sequencing (NGS)-based genomic screens on both familial and non-familial cohorts have led to the identification of keratoconus candidate genes with much greater success and increased resproducibility of genetic findings. This review focuses on candidate genes identified till date and attempts to understand their role in biological processes underlying keratoconus pathogenesis. In addition, using these genes I propose molecular pathways that could contribute to keratoconus pathogenesis. The pathways identified the presence of direct cross-talk between known candidate genes of keratoconus and remarkably, 28 known candidate genes have a direct relationship among themselves that involves direct protein-protein binding, regulatory activities such as activation and inhibition, chaperone, transcriptional activation/co-activation, and enzyme catalysis. This review attempts to describe these relationships and cross-talks in the context of keratoconus pathogenesis.

Update on the genetics of keratoconus

In the past few years we have seen a great acceleration of discoveries in the field of keratoconus including new treatments, diagnostic tools, genomic and molecular determinants of disease risk. Recent genome-wide association studies (GWAS) of keratoconus cases and population wide studies of variation in central corneal thickness and in corneal biomechanical properties confirmed already identified genes and found many new susceptibility variants and biological pathways. Recent findings in genetic determinants of familial keratoconus revealed functionally important variants and established first mouse model of keratoconus. Latest transcriptomic and expression studies started assessing novel non-coding RNA targets in addition to identifying tissue specific effects of coding genes. First genomic insights into better prediction of treatment outcomes are bringing the advent of genomic medicine into keratoconus clinical practice.