Preventing corneal blindness caused by keratitis using artificial intelligence.
Ontology highlight
ABSTRACT:
SUBMITTER: Li Z
PROVIDER: S-EPMC8213803 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundCorneal topography is a clinically validated examination method for keratoconus. However, there is no clear guideline regarding patient selection for corneal topography. We developed and validated a novel artificial intelligence (AI) model to identify patients who would benefit from corneal topography based on basic ophthalmologic examinations, including a survey of visual impairment, best-corrected visual acuity (BCVA) measurement, intraocular pressure (IOP) measurement, and autokeratometry.MethodsA total of five AI models (three individual models with fully connected neural network including the XGBoost, and the TabNet models, and two ensemble models with hard and soft voting methods) were trained and validated. We used three datasets collected from the records of 2,613 patients' basic ophthalmologic examinations from two institutions to train and validate the AI models. We trained the AI models using a dataset from a third medical institution to determine whether corneal topography was needed to detect keratoconus. Finally, prospective intra-validation dataset (internal test dataset) and extra-validation dataset from a different medical institution (external test dataset) were used to assess the performance of the AI models.ResultsThe ensemble model with soft voting method outperformed all other AI models in sensitivity when predicting which patients needed corneal topography (90.5% in internal test dataset and 96.4% in external test dataset). In the error analysis, most of the predicting error occurred within the range of the subclinical keratoconus and the suspicious D-score in the Belin-Ambrósio enhanced ectasia display. In the feature importance analysis, out of 18 features, IOP was the highest ranked feature when comparing the average value of the relative attributions of three individual AI models, followed by the difference in the value of mean corneal power.ConclusionAn AI model using the results of basic ophthalmologic examination has the potential to recommend corneal topography for keratoconus. In this AI algorithm, IOP and the difference between the two eyes, which may be undervalued clinical information, were important factors in the success of the AI model, and may be worth further reviewing in research and clinical practice for keratoconus screening.
| S-EPMC9386450 | biostudies-literature
Project description:BackgroundTo investigate machine-learning (ML) algorithms to differentiate corneal biomechanical properties between different topographical stages of keratoconus (KC) by dynamic Scheimpflug tonometry (CST, Corvis ST, Oculus, Wetzlar, Germany). In the following, ML models were used to predict the severity in a training and validation dataset.MethodsThree hundred and eighteen keratoconic and one hundred sixteen healthy eyes were included in this monocentric and cross-sectional pilot study. Dynamic corneal response (DCR) and corneal thickness related (pachymetric) parameters from CST were chosen by appropriated selection techniques to develop a ML algorithm. The stage of KC was determined by the topographical keratoconus classification system (TKC, Pentacam, Oculus). Patients who were classified as TKC 1, TKC 2 and TKC 3 were assigned to subgroup mild, moderate, and advanced KC. If patients were classified as TKC 1-2, TKC 2-3 or TKC 3-4, they were assigned to subgroups according to the normative range of further corneal indices (index of surface variance, keratoconus index and minimum radius). Patients classified as TKC 4 were not included in this study due to the limited amount of cases. Linear discriminant analysis (LDA) and random forest (RF) algorithms were used to develop the classification models. Data were divided into training (70% of cases) and validation (30% of cases) datasets.ResultsLDA model predicted healthy, mild, moderate, and advanced KC eyes with a sensitivity (Sn)/specificity (Sp) of 82%/97%, 73%/81%, 62%/83% and 68%/95% from a validation dataset, respectively. For the RF model, a Sn/Sp of 91%/94%, 80%/90%, 63%/87%, 72%/95% could be reached for predicting healthy, mild, moderate, and advanced KC eyes, respectively. The overall accuracy of LDA and RF was 71% and 78%, respectively. The accuracy for KC detection including all subgroups of KC severity was 93% in both models.ConclusionThe RF model showed good accuracy in predicting healthy eyes and various stages of KC. The accuracy was superior with respect to the LDA model. The clinical importance of the models is that the standalone dynamic Scheimpflug tonometry is able to predict the severity of KC without having the keratometric data.Trial registrationNCT04251143 at Clinicaltrials.gov, registered at 12 March 2018 (Retrospectively registered).
| S-EPMC8167942 | biostudies-literature
Project description:PurposeTo investigate the development of corneal neovascularization, the corneal expression of vascular endothelial growth factor (VEGF), and the antiangiogenic effects of a VEGF-inhibitory antibody during experimental keratomycosis.MethodsScarified corneas of BALB/c mice were topically inoculated with Candidaalbicans and monitored daily for corneal neovascularization. A murine gene microarray compared infected corneas to controls 1 day after inoculation. Real-time reverse transcriptase polymerase chain reaction (RT-PCR) determined levels of genes encoding VEGF-A, VEGF-B, VEGF-C, and VEGF-D and placental growth factor in infected, mock-inoculated, and normal corneas. Immunostaining localized VEGF-A in corneal sections. An anti-VEGF-A antibody that binds to murine VEGF was evaluated for effects on corneal neovascularization and fungal recovery.ResultsEyes with C. albicans keratitis manifested limbal capillary budding on the second postinoculation day, and intrastromal neovascular tufts subsequently grew at a mean rate of 250+/-80 microm/day. One day after the onset of C. albicans keratitis, VEGF-A was upregulated 12.5 fold (p=0.01) by microarray and 8.8 fold (p=0.004) by real-time RT-PCR, followed by a measured decline toward baseline over one week. VEGF-A was present in the epithelium and stroma of infected corneas. Scarification alone did not alter VEGF expression compared to the normal cornea. Anti-VEGF-A antibody significantly (p<0.01) decreased the formation of new corneal blood vessels during experimental keratomycosis without adversely affecting the fungal load of C. albicans keratitis.ConclusionsUntreated C. albicans keratitis induces VEGF-A and leads to progressive corneal neovascularization that is preventable by a VEGF-blocking antibody.
| S-EPMC2756518 | biostudies-literature
Project description:MicroRNAs (miRNAs) are small, stable non-coding RNA molecules with regulatory function and marked tissue specificity that post-transcriptionally regulate gene expression, however their role in fungal keratitis remain unknown. Our purpose was to identify the miRNAs in human cornea from fungal keratitis patients and understand their key role in regulation of pathogenesis. Corneal samples from normal cadaver (n=3) and fungal keratitis (n=5) patients were pooled separately and total RNA was extracted. Deep sequencing was done using Illumina HiSeq1000 platform to identify miRNA profile. We identified seventy five differentially expressed miRNAs in fungal keratitis corneas. Select miRNAs were validated by real-time RT-PCR (Q-PCR). We predicted their role in regulating target genes in several pathways by combining miRNA target genes and pathway analysis, and mRNA expression of select target genes were further analysed by Q-PCR. MiR-21-5p, miR-223-3p, miR-146b-5p, miR-155-5p, miR-511-5p were found to be involved in inflammatory and immune responses, regulating Toll like receptor signaling pathways, which is of particular interest. MiR-451a with an increased expression in keratitis may have a role in wound healing by targeting Macrophage Migration Inhibitory Factor (MIF). Further, we highlighted that Neurotrophin signaling pathway may play a role in wound healing process. One novel miRNA was also detected in cornea. In conclusion, several miRNAs with high expression in fungal keratitis corneas point towards their role in regulation of pathogenesis. Further insights in understanding miRNAs role in wound healing and inflammation may help design new therapeutic strategies.
2016-07-28 | GSE64843 | GEO
Project description:Plectosphaerella cucumerina is a filamentous fungus that infects plants and crops, but there are few previous reports of human infections. The current case was an 82-year-old woman who was referred to us for corneal infection in her left eye that did not improve with antibacterial and anti-inflammatory treatment. The best-corrected visual acuity (BCVA) of the eye at the first visit to us was hand motion. Slit-lamp examination revealed extensive white infiltration and ulceration in the anterior corneal stroma of the left eye. Intensive antibacterial and antiviral treatment for one month did not improve the condition of the cornea. Although initial culture testing and polymerase chain reaction (PCR) testing of corneal scraping samples did not reveal the causative microorganism, repeated culture testing identified P. cucumerina. The corneal infection eventually subsided after topical and systemic treatment with voriconazole (VRCZ). The final BCVA in the left eye was 1.3 logMAR. This was a rare case of fungal keratitis due to P. cucumerina. Our case suggests that it is important to perform repeated examinations with corneal scrapings, especially when the treatment response is poor.
| S-EPMC9437864 | biostudies-literature
Project description:Bacterial keratitis results in corneal scarring and subsequent visual impairment. The long-term evolution of corneal scars has not been well described. In this case series, we identified patients who had improvement in corneal scarring and visual acuity from a clinical trial for bacterial keratitis.We searched the records of the Steroids for Corneal Ulcers Trial (SCUT) for patients who had improvement in vision between the 3-month and 12-month visits and reviewed their clinical photographs.Of the 500 patients enrolled in SCUT, five patients with large central corneal scars due to bacterial keratitis are presented. All experienced improvement in rigid contact lens-corrected visual acuity from months 3 to 12. All patients also had marked improvement in corneal opacity during the same time period. None of the patients opted to have penetrating keratoplasty.Corneal scars may continue to improve even many months after a bacterial corneal ulcer has healed. The corneal remodeling can be accompanied by considerable improvement in visual acuity, such that corneal transplantation may not be necessary.
| S-EPMC3597874 | biostudies-literature
Project description: Not available
| S-EPMC11018329 | biostudies-literature
Project description:We propose a model of a learning agent whose interaction with the environment is governed by a simulation-based projection, which allows the agent to project itself into future situations before it takes real action. Projective simulation is based on a random walk through a network of clips, which are elementary patches of episodic memory. The network of clips changes dynamically, both due to new perceptual input and due to certain compositional principles of the simulation process. During simulation, the clips are screened for specific features which trigger factual action of the agent. The scheme is different from other, computational, notions of simulation, and it provides a new element in an embodied cognitive science approach to intelligent action and learning. Our model provides a natural route for generalization to quantum-mechanical operation and connects the fields of reinforcement learning and quantum computation.
| S-EPMC3351754 | biostudies-other
Project description:A male patient presented with complaints of redness, pain and defective vision in the left eye. The infiltrate healed completely after two weeks of topical natamycin administration. A polyphasic approach was used to identify the isolate as Aspergillus pseudotamarii, which produced aflatoxins in inducing medium.
| S-EPMC3885925 | biostudies-literature
Project description:MicroRNAs (miRNAs) are small, stable non-coding RNA molecules with regulatory function and marked tissue specificity that post-transcriptionally regulate gene expression, however their role in fungal keratitis remain unknown. Our purpose was to identify the miRNAs in human cornea from fungal keratitis patients and understand their key role in regulation of pathogenesis. Corneal samples from normal cadaver (n=3) and fungal keratitis (n=5) patients were pooled separately and total RNA was extracted. Deep sequencing was done using Illumina HiSeq1000 platform to identify miRNA profile. We identified seventy five differentially expressed miRNAs in fungal keratitis corneas. Select miRNAs were validated by real-time RT-PCR (Q-PCR). We predicted their role in regulating target genes in several pathways by combining miRNA target genes and pathway analysis, and mRNA expression of select target genes were further analysed by Q-PCR. MiR-21-5p, miR-223-3p, miR-146b-5p, miR-155-5p, miR-511-5p were found to be involved in inflammatory and immune responses, regulating Toll like receptor signaling pathways, which is of particular interest. MiR-451a with an increased expression in keratitis may have a role in wound healing by targeting Macrophage Migration Inhibitory Factor (MIF). Further, we highlighted that Neurotrophin signaling pathway may play a role in wound healing process. One novel miRNA was also detected in cornea. In conclusion, several miRNAs with high expression in fungal keratitis corneas point towards their role in regulation of pathogenesis. Further insights in understanding miRNAs role in wound healing and inflammation may help design new therapeutic strategies. Control and fungal keratitis, human corneal miRNA profiles were generated using IlluminaHiseq1000 platform
2016-07-28 | E-GEOD-64843 | biostudies-arrayexpress