Effects of rare kidney diseases on kidney failure: a longitudinal analysis of the UK National Registry of Rare Kidney Diseases (RaDaR) cohort.

BACKGROUND: Individuals with rare kidney diseases account for 5-10% of people with chronic kidney disease, but constitute more than 25% of patients receiving kidney replacement therapy. The National Registry of Rare Kidney Diseases (RaDaR) gathers longitudinal data from patients with these conditions, which we used to study disease progression and outcomes of death and kidney failure. METHODS: People aged 0-96 years living with 28 types of rare kidney diseases were recruited from 108 UK renal care facilities. The primary outcomes were cumulative incidence of mortality and kidney failure in individuals with rare kidney diseases, which were calculated and compared with that of unselected patients with chronic kidney disease. Cumulative incidence and Kaplan-Meier survival estimates were calculated for the following outcomes: median age at kidney failure; median age at death; time from start of dialysis to death; and time from diagnosis to estimated glomerular filtration rate (eGFR) thresholds, allowing calculation of time from last eGFR of 75 mL/min per 1·73 m2 or more to first eGFR of less than 30 mL/min per 1·73 m2 (the therapeutic trial window). FINDINGS: Between Jan 18, 2010, and July 25, 2022, 27 285 participants were recruited to RaDaR. Median follow-up time from diagnosis was 9·6 years (IQR 5·9-16·7). RaDaR participants had significantly higher 5-year cumulative incidence of kidney failure than 2·81 million UK patients with all-cause chronic kidney disease (28% vs 1%; p<0·0001), but better survival rates (standardised mortality ratio 0·42 [95% CI 0·32-0·52]; p<0·0001). Median age at kidney failure, median age at death, time from start of dialysis to death, time from diagnosis to eGFR thresholds, and therapeutic trial window all varied substantially between rare diseases. INTERPRETATION: Patients with rare kidney diseases differ from the general population of individuals with chronic kidney disease: they have higher 5-year rates of kidney failure but higher survival than other patients with chronic kidney disease stages 3-5, and so are over-represented in the cohort of patients requiring kidney replacement therapy. Addressing unmet therapeutic need for patients with rare kidney diseases could have a large beneficial effect on long-term kidney replacement therapy demand. FUNDING: RaDaR is funded by the Medical Research Council, Kidney Research UK, Kidney Care UK, and the Polycystic Kidney Disease Charity.

Proactive Decision Support for Glaucoma Treatment: Predicting Surgical Interventions with Clinically Available Data.

A longitudinal ophthalmic dataset was used to investigate multi-modal machine learning (ML) models incorporating patient demographics and history, clinical measurements, optical coherence tomography (OCT), and visual field (VF) testing in predicting glaucoma surgical interventions. The cohort included 369 patients who underwent glaucoma surgery and 592 patients who did not undergo surgery. The data types used for prediction included patient demographics, history of systemic conditions, medication history, ophthalmic measurements, 24-2 VF results, and thickness measurements from OCT imaging. The ML models were trained to predict surgical interventions and evaluated on independent data collected at a separate study site. The models were evaluated based on their ability to predict surgeries at varying lengths of time prior to surgical intervention. The highest performing predictions achieved an AUC of 0.93, 0.92, and 0.93 in predicting surgical intervention at 1 year, 2 years, and 3 years, respectively. The models were also able to achieve high sensitivity (0.89, 0.77, 0.86 at 1, 2, and 3 years, respectively) and specificity (0.85, 0.90, and 0.91 at 1, 2, and 3 years, respectively) at an 0.80 level of precision. The multi-modal models trained on a combination of data types predicted surgical interventions with high accuracy up to three years prior to surgery and could provide an important tool to predict the need for glaucoma intervention.

Zebrafish models of candidate human epilepsy-associated genes provide evidence of hyperexcitability.

Hundreds of novel candidate human epilepsy-associated genes have been identified thanks to advancements in next-generation sequencing and large genome-wide association studies, but establishing genetic etiology requires functional validation. We generated a list of >2200 candidate epilepsy-associated genes, of which 81 were determined suitable for the generation of loss-of-function zebrafish models via CRISPR/Cas9 gene editing. Of those 81 crispants, 48 were successfully established as stable mutant lines and assessed for seizure-like swim patterns in a primary F2 screen. Evidence of seizure-like behavior was present in 5 (arfgef1, kcnd2, kcnv1, ubr5, wnt8b) of the 48 mutant lines assessed. Further characterization of those 5 lines provided evidence for epileptiform activity via electrophysiology in kcnd2 and wnt8b mutants. Additionally, arfgef1 and wnt8b mutants showed a decrease in the number of inhibitory interneurons in the optic tectum of larval animals. Furthermore, RNAseq revealed convergent transcriptional abnormalities between mutant lines, consistent with their developmental defects and hyperexcitable phenotypes. These zebrafish models provide strongest experimental evidence supporting the role of ARFGEF1, KCND2, and WNT8B in human epilepsy and further demonstrate the utility of this model system for evaluating candidate human epilepsy genes.

Establishing vitreous glucose and beta-hydroxybutyrate thresholds to assist in the diagnosis of hypothermia.

The post-mortem diagnosis of hypothermia is challenging to establish due to the lack of pathognomonic findings and the confounding problem that any comorbidity may account for death. A 4-year retrospective case-control study was performed to compare the vitreous glucose and beta-hydroxybutyrate (BHB) concentrations between hypothermia deaths and controls. Over the study period 34 cases of hypothermia and 39 controls were analyzed. Hypothermia deaths versus controls had higher mean vitreous glucose (2.93 mmol/L vs. 1.14 mmol/L; p < 0.0001), BHB (1.89 mmol/L vs. 1.35 mmol/L; p = 0.01), and combined glucose+BHB (4.83 mmol/L vs. 2.46 mmol/L; p < 0.0001). Receiver operating characteristic (ROC) curves showed that the best model for predicting hypothermia in all cases was a combined vitreous glucose+BHB threshold of 2.03 mmol/L (sensitivity 88.2 %; specificity 56.4 %). A sub-group analysis broken down by detectable levels of blood ethanol showed that cases of hypothermia with and without ethanol maintained higher median vitreous glucose relative to the controls (2.05 vs. 0.35 mmol/L and 2.70 vs. 0.65 mmol/L; p = 0.02), however median BHB was only significantly elevated when ethanol was absent (1.88 vs. 1.42 mmol/L; p < 0.0001). Subsequent ROC curve analysis demonstrated that a better model for predicting hypothermia was in cases when blood ethanol was absent. In those deaths vitreous BHB alone had the best area under the curve, with an optimum threshold of 1.83 mmol/L (sensitivity 83.3 %; specificity 96.3 %). This study shows that post-mortem vitreous glucose and BHB are useful ancillary studies to assist in the diagnosis of hypothermia. Ethanol however is a confounder and can alter the utility of vitreous BHB when diagnosing hypothermia in those who have consumed alcohol prior to death.

Homozygous SMAD6 variants in two unrelated patients with craniosynostosis and radioulnar synostosis.

BACKGROUND: SMAD6 encodes an intracellular inhibitor of the bone morphogenetic protein (BMP) signalling pathway. Until now, rare heterozygous loss-of-function variants in SMAD6 were demonstrated to increase the risk of disparate clinical disorders including cardiovascular disease, craniosynostosis and radioulnar synostosis. Only two unrelated patients harbouring biallelic SMAD6 variants presenting a complex cardiovascular phenotype and facial dysmorphism have been described. CASES: Here, we present the first two patients with craniosynostosis harbouring homozygous SMAD6 variants. The male probands, both born to healthy consanguineous parents, were diagnosed with metopic synostosis and bilateral or unilateral radioulnar synostosis. Additionally, one proband had global developmental delay. Echocardiographic evaluation did not reveal cardiac or outflow tract abnormalities. MOLECULAR ANALYSES: The novel missense (c.[584T>G];[584T>G], p.[(Val195Gly)];[(Val195Gly)]) and missense/splice-site variant (c.[817G>A];[817G>A], r.[(817g>a,817delins[a;817+2_817+228])];[(817g>a,817delins[a;817+2_817+228])], p.[(Glu273Lys,Glu273Serfs*72)];[(Glu273Lys,Glu273Serfs*72)]) both locate in the functional MH1 domain of the protein and have not been reported in gnomAD database. Functional analyses of the variants showed reduced inhibition of BMP signalling or abnormal splicing, respectively, consistent with a hypomorphic mechanism of action. CONCLUSION: Our data expand the spectrum of variants and phenotypic spectrum associated with homozygous variants of SMAD6 to include craniosynostosis.

Deep Learning Identifies High-Quality Fundus Photographs and Increases Accuracy in Automated Primary Open Angle Glaucoma Detection.

Purpose: To develop and evaluate a deep learning (DL) model to assess fundus photograph quality, and quantitatively measure its impact on automated POAG detection in independent study populations. Methods: Image quality ground truth was determined by manual review of 2815 fundus photographs of healthy and POAG eyes from the Diagnostic Innovations in Glaucoma Study and African Descent and Glaucoma Evaluation Study (DIGS/ADAGES), as well as 11,350 from the Ocular Hypertension Treatment Study (OHTS). Human experts assessed a photograph as high quality if of sufficient quality to determine POAG status and poor quality if not. A DL quality model was trained on photographs from DIGS/ADAGES and tested on OHTS. The effect of DL quality assessment on DL POAG detection was measured using area under the receiver operating characteristic (AUROC). Results: The DL quality model yielded an AUROC of 0.97 for differentiating between high- and low-quality photographs; qualitative human review affirmed high model performance. Diagnostic accuracy of the DL POAG model was significantly greater (P < 0.001) in good (AUROC, 0.87; 95% CI, 0.80-0.92) compared with poor quality photographs (AUROC, 0.77; 95% CI, 0.67-0.88). Conclusions: The DL quality model was able to accurately assess fundus photograph quality. Using automated quality assessment to filter out low-quality photographs increased the accuracy of a DL POAG detection model. Translational Relevance: Incorporating DL quality assessment into automated review of fundus photographs can help to decrease the burden of manual review and improve accuracy for automated DL POAG detection.

Central visual field damage in glaucoma eyes with choroidal microvasculature dropout with and without high axial myopia.

PURPOSE: To characterise the relationship between a deep-layer microvasculature dropout (MvD) and central visual field (VF) damage in primary open-angle glaucoma (POAG) patients with and without high axial myopia. DESIGN: Cross-sectional study. METHODS: Seventy-one eyes (49 patients) with high axial myopia and POAG and 125 non-highly myopic POAG eyes (97 patients) were enrolled. Presence, area and angular circumference of juxtapapillary MvD were evaluated on optical coherence tomography angiography B-scans and en-face choroidal images. RESULTS: Juxtapapillary MvD was detected more often in the highly myopic POAG eyes (43 eyes, 86%) than in the non-highly myopic eyes (73 eyes, 61.9%; p=0.002). In eyes with MvD, MvD area and angular circumference (95% CI) were significantly larger in the highly myopic eyes compared with the non-highly myopic eyes (area: (0.69 (0.40, 0.98) mm2 vs 0.31 (0.19, 0.42) mm2, p=0.011) and (angular circumference: 84.3 (62.9, 105.8) vs 74.5 (58.3, 90.9) degrees, p<0.001), respectively. 24-2 VF mean deviation (MD) was significantly worse in eyes with MvD compared with eyes without MvD in both groups (p<0.001). After adjusting for 24-2 MD VF, central VF defects were more frequently found in eyes with MvD compared with eyes without MvD (82.7% vs 60.9%, p<0.001). In multivariable analysis, higher intraocular pressure, worse 24-2 VF MD, longer axial length and greater MvD area and angular circumference were associated with worse 10-2 VF MD. CONCLUSIONS: MvD was more prevalent and larger in POAG eyes with high myopia than in non-highly myopic POAG eyes. In both groups, eyes with MvD showed worse glaucoma severity and more central VF defects.

Deep Learning Estimation of 10-2 Visual Field Map Based on Macular Optical Coherence Tomography Angiography Measurements.

PURPOSE: To develop deep learning (DL) models estimating the central visual field (VF) from optical coherence tomography angiography (OCTA) vessel density (VD) measurements. DESIGN: Development and validation of a deep learning model. METHODS: A total of 1051 10-2 VF OCTA pairs from healthy, glaucoma suspects, and glaucoma eyes were included. DL models were trained on en face macula VD images from OCTA to estimate 10-2 mean deviation (MD), pattern standard deviation (PSD), 68 total deviation (TD) and pattern deviation (PD) values and compared with a linear regression (LR) model with the same input. Accuracy of the models was evaluated by calculating the average mean absolute error (MAE) and the R2 (squared Pearson correlation coefficients) of the estimated and actual VF values. RESULTS: DL models predicting 10-2 MD achieved R2 of 0.85 (95% confidence interval [CI], 74-0.92) for 10-2 MD and MAEs of 1.76 dB (95% CI, 1.39-2.17 dB) for MD. This was significantly better than mean linear estimates for 10-2 MD. The DL model outperformed the LR model for the estimation of pointwise TD values with an average MAE of 2.48 dB (95% CI, 1.99-3.02) and R2 of 0.69 (95% CI, 0.57-0.76) over all test points. The DL model outperformed the LR model for the estimation of all sectors. CONCLUSIONS: DL models enable the estimation of VF loss from OCTA images with high accuracy. Applying DL to the OCTA images may enhance clinical decision making. It also may improve individualized patient care and risk stratification of patients who are at risk for central VF damage.

One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis.

Convolutional neural networks (CNNs) are a promising technique for automated glaucoma diagnosis from images of the fundus, and these images are routinely acquired as part of an ophthalmic exam. Nevertheless, CNNs typically require a large amount of well-labeled data for training, which may not be available in many biomedical image classification applications, especially when diseases are rare and where labeling by experts is costly. This article makes two contributions to address this issue: 1) It extends the conventional Siamese network and introduces a training method for low-shot learning when labeled data are limited and imbalanced, and 2) it introduces a novel semi-supervised learning strategy that uses additional unlabeled training data to achieve greater accuracy. Our proposed multi-task Siamese network (MTSN) can employ any backbone CNN, and we demonstrate with four backbone CNNs that its accuracy with limited training data approaches the accuracy of backbone CNNs trained with a dataset that is 50 times larger. We also introduce One-Vote Veto (OVV) self-training, a semi-supervised learning strategy that is designed specifically for MTSNs. By taking both self-predictions and contrastive predictions of the unlabeled training data into account, OVV self-training provides additional pseudo labels for fine-tuning a pre-trained MTSN. Using a large (imbalanced) dataset with 66,715 fundus photographs acquired over 15 years, extensive experimental results demonstrate the effectiveness of low-shot learning with MTSN and semi-supervised learning with OVV self-training. Three additional, smaller clinical datasets of fundus images acquired under different conditions (cameras, instruments, locations, populations) are used to demonstrate the generalizability of the proposed methods.

Review of Visualization Approaches in Deep Learning Models of Glaucoma.

Glaucoma is a major cause of irreversible blindness worldwide. As glaucoma often presents without symptoms, early detection and intervention are important in delaying progression. Deep learning (DL) has emerged as a rapidly advancing tool to help achieve these objectives. In this narrative review, data types and visualization approaches for presenting model predictions, including models based on tabular data, functional data, and/or structural data, are summarized, and the importance of data source diversity for improving the utility and generalizability of DL models is explored. Examples of innovative approaches to understanding predictions of artificial intelligence (AI) models and alignment with clinicians are provided. In addition, methods to enhance the interpretability of clinical features from tabular data used to train AI models are investigated. Examples of published DL models that include interfaces to facilitate end-user engagement and minimize cognitive and time burdens are highlighted. The stages of integrating AI models into existing clinical workflows are reviewed, and challenges are discussed. Reviewing these approaches may help inform the generation of user-friendly interfaces that are successfully integrated into clinical information systems. This review details key principles regarding visualization approaches in DL models of glaucoma. The articles reviewed here focused on usability, explainability, and promotion of clinician trust to encourage wider adoption for clinical use. These studies demonstrate important progress in addressing visualization and explainability issues required for successful real-world implementation of DL models in glaucoma.

Multimodal Deep Learning Classifier for Primary Open Angle Glaucoma Diagnosis Using Wide-Field Optic Nerve Head Cube Scans in Eyes With and Without High Myopia.

PRCIS: An optical coherence tomography (OCT)-based multimodal deep learning (DL) classification model, including texture information, is introduced that outperforms single-modal models and multimodal models without texture information for glaucoma diagnosis in eyes with and without high myopia. BACKGROUND/AIMS: To evaluate the diagnostic accuracy of a multimodal DL classifier using wide OCT optic nerve head cube scans in eyes with and without axial high myopia. MATERIALS AND METHODS: Three hundred seventy-one primary open angle glaucoma (POAG) eyes and 86 healthy eyes, all without axial high myopia [axial length (AL) ≤ 26 mm] and 92 POAG eyes and 44 healthy eyes, all with axial high myopia (AL > 26 mm) were included. The multimodal DL classifier combined features of 3 individual VGG-16 models: (1) texture-based en face image, (2) retinal nerve fiber layer (RNFL) thickness map image, and (3) confocal scanning laser ophthalmoscope (cSLO) image. Age, AL, and disc area adjusted area under the receiver operating curves were used to compare model accuracy. RESULTS: Adjusted area under the receiver operating curve for the multimodal DL model was 0.91 (95% CI = 0.87, 0.95). This value was significantly higher than the values of individual models [0.83 (0.79, 0.86) for texture-based en face image; 0.84 (0.81, 0.87) for RNFL thickness map; and 0.68 (0.61, 0.74) for cSLO image; all P ≤ 0.05]. Using only highly myopic eyes, the multimodal DL model showed significantly higher diagnostic accuracy [0.89 (0.86, 0.92)] compared with texture en face image [0.83 (0.78, 0.85)], RNFL [0.85 (0.81, 0.86)] and cSLO image models [0.69 (0.63, 0.76)] (all P ≤ 0.05). CONCLUSIONS: Combining OCT-based RNFL thickness maps with texture-based en face images showed a better ability to discriminate between healthy and POAG than thickness maps alone, particularly in high axial myopic eyes.

Usability and Clinician Acceptance of a Deep Learning-Based Clinical Decision Support Tool for Predicting Glaucomatous Visual Field Progression.

PRCIS: We updated a clinical decision support tool integrating predicted visual field (VF) metrics from an artificial intelligence model and assessed clinician perceptions of the predicted VF metric in this usability study. PURPOSE: To evaluate clinician perceptions of a prototyped clinical decision support (CDS) tool that integrates visual field (VF) metric predictions from artificial intelligence (AI) models. METHODS: Ten ophthalmologists and optometrists from the University of California San Diego participated in 6 cases from 6 patients, consisting of 11 eyes, uploaded to a CDS tool ("GLANCE", designed to help clinicians "at a glance"). For each case, clinicians answered questions about management recommendations and attitudes towards GLANCE, particularly regarding the utility and trustworthiness of the AI-predicted VF metrics and willingness to decrease VF testing frequency. MAIN OUTCOMES AND MEASURES: Mean counts of management recommendations and mean Likert scale scores were calculated to assess overall management trends and attitudes towards the CDS tool for each case. In addition, system usability scale scores were calculated. RESULTS: The mean Likert scores for trust in and utility of the predicted VF metric and clinician willingness to decrease VF testing frequency were 3.27, 3.42, and 2.64, respectively (1=strongly disagree, 5=strongly agree). When stratified by glaucoma severity, all mean Likert scores decreased as severity increased. The system usability scale score across all responders was 66.1±16.0 (43rd percentile). CONCLUSIONS: A CDS tool can be designed to present AI model outputs in a useful, trustworthy manner that clinicians are generally willing to integrate into their clinical decision-making. Future work is needed to understand how to best develop explainable and trustworthy CDS tools integrating AI before clinical deployment.

Deep Learning Estimation of 10-2 Visual Field Map Based on Circumpapillary Retinal Nerve Fiber Layer Thickness Measurements.

PURPOSE: To estimate central 10-degree visual field (VF) map from spectral-domain optical coherence tomography (SD-OCT) retinal nerve fiber layer thickness (RNFL) measurements in glaucoma with artificial intelligence. DESIGN: Artificial intelligence (convolutional neural networks) study. METHODS: This study included 5352 SD-OCT scans and 10-2 VF pairs from 1365 eyes of 724 healthy patients, patients with suspected glaucoma, and patients with glaucoma. Convolutional neural networks (CNNs) were developed to estimate the 68 individual sensitivity thresholds of 10-2 VF map using all-sectors (CNNA) and temporal-sectors (CNNT) RNFL thickness information of the SD-OCT circle scan (768 thickness points). 10-2 indices including pointwise total deviation (TD) values, mean deviation (MD), and pattern standard deviation (PSD) were generated using the CNN-estimated sensitivity thresholds at individual test locations. Linear regression (LR) models with the same input were used for comparison. RESULTS: The CNNA model achieved an average pointwise mean absolute error of 4.04 dB (95% confidence interval [CI] 3.76-4.35) and correlation coefficient (r) of 0.59 (95% CI 0.52-0.64) over 10-2 map and the mean absolute error and r of 2.88 dB (95% CI 2.63-3.15) and 0.74 (95% CI 0.67-0.80) for MD, and 2.31 dB (95% CI 2.03-2.61) and 0.59 (95% CI 0.51-0.65) for PSD estimations, respectively, significantly outperforming the LRA model. CONCLUSIONS: The proposed CNNA model improved the estimation of 10-2 VF map based on circumpapillary SD-OCT RNFL thickness measurements. These artificial intelligence methods using SD-OCT structural data show promise to individualize the frequency of central VF assessment in patients with glaucoma and would enable the reallocation of resources from patients at lowest risk to those at highest risk of central VF damage.

Combining Optical Coherence Tomography and Optical Coherence Tomography Angiography Longitudinal Data for the Detection of Visual Field Progression in Glaucoma.

PURPOSE: To use longitudinal optical coherence tomography (OCT) and OCT angiography (OCTA) data to detect glaucomatous visual field (VF) progression with a supervised machine learning approach. DESIGN: Prospective cohort study. METHODS: One hundred ten eyes of patients with suspected glaucoma (33.6%) and patients with glaucoma (66.4%) with a minimum of 5 24-2 VF tests and 3 optic nerve head and macula images over an average follow-up duration of 4.1 years were included. VF progression was defined using a composite measure including either a "likely progression event" on Guided Progression Analysis, a statistically significant negative slope of VF mean deviation or VF index, or a positive pointwise linear regression event. Feature-based gradient boosting classifiers were developed using different subsets of baseline and longitudinal OCT and OCTA summary parameters. The area under the receiver operating characteristic curve (AUROC) was used to compare the classification performance of different models. RESULTS: VF progression was detected in 28 eyes (25.5%). The model with combined baseline and longitudinal OCT and OCTA parameters at the global and hemifield levels had the best classification accuracy to detect VF progression (AUROC = 0.89). Models including combined OCT and OCTA parameters had higher classification accuracy compared with those with individual subsets of OCT or OCTA features alone. Including hemifield measurements significantly improved the models' classification accuracy compared with using global measurements alone. Including longitudinal rates of change of OCT and OCTA parameters (AUROCs = 0.80-0.89) considerably increased the classification accuracy of the models with baseline measurements alone (AUROCs = 0.60-0.63). CONCLUSIONS: Longitudinal OCTA measurements complement OCT-derived structural metrics for the evaluation of functional VF loss in patients with glaucoma.

Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization.

Purpose: To compare the diagnostic accuracy and explainability of a Vision Transformer deep learning technique, Data-efficient image Transformer (DeiT), and ResNet-50, trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS) to detect primary open-angle glaucoma (POAG) and identify the salient areas of the photographs most important for each model's decision-making process. Design: Evaluation of a diagnostic technology. Subjects Participants and Controls: Overall 66 715 photographs from 1636 OHTS participants and an additional 5 external datasets of 16 137 photographs of healthy and glaucoma eyes. Methods: Data-efficient image Transformer models were trained to detect 5 ground-truth OHTS POAG classifications: OHTS end point committee POAG determinations because of disc changes (model 1), visual field (VF) changes (model 2), or either disc or VF changes (model 3) and Reading Center determinations based on disc (model 4) and VFs (model 5). The best-performing DeiT models were compared with ResNet-50 models on OHTS and 5 external datasets. Main Outcome Measures: Diagnostic performance was compared using areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities. The explainability of the DeiT and ResNet-50 models was compared by evaluating the attention maps derived directly from DeiT to 3 gradient-weighted class activation map strategies. Results: Compared with our best-performing ResNet-50 models, the DeiT models demonstrated similar performance on the OHTS test sets for all 5 ground-truth POAG labels; AUROC ranged from 0.82 (model 5) to 0.91 (model 1). Data-efficient image Transformer AUROC was consistently higher than ResNet-50 on the 5 external datasets. For example, AUROC for the main OHTS end point (model 3) was between 0.08 and 0.20 higher in the DeiT than ResNet-50 models. The saliency maps from the DeiT highlight localized areas of the neuroretinal rim, suggesting important rim features for classification. The same maps in the ResNet-50 models show a more diffuse, generalized distribution around the optic disc. Conclusions: Vision Transformers have the potential to improve generalizability and explainability in deep learning models, detecting eye disease and possibly other medical conditions that rely on imaging for clinical diagnosis and management.

A Deep Learning Approach to Improve Retinal Structural Predictions and Aid Glaucoma Neuroprotective Clinical Trial Design.

PURPOSE: To investigate the efficacy of a deep learning regression method to predict macula ganglion cell-inner plexiform layer (GCIPL) and optic nerve head (ONH) retinal nerve fiber layer (RNFL) thickness for use in glaucoma neuroprotection clinical trials. DESIGN: Cross-sectional study. PARTICIPANTS: Glaucoma patients with good quality macula and ONH scans enrolled in 2 longitudinal studies, the African Descent and Glaucoma Evaluation Study and the Diagnostic Innovations in Glaucoma Study. METHODS: Spectralis macula posterior pole scans and ONH circle scans on 3327 pairs of GCIPL/RNFL scans from 1096 eyes (550 patients) were included. Participants were randomly distributed into a training and validation dataset (90%) and a test dataset (10%) by participant. Networks had access to GCIPL and RNFL data from one hemiretina of the probe eye and all data of the fellow eye. The models were then trained to predict the GCIPL or RNFL thickness of the remaining probe eye hemiretina. MAIN OUTCOME MEASURES: Mean absolute error (MAE) and squared Pearson correlation coefficient (r2) were used to evaluate model performance. RESULTS: The deep learning model was able to predict superior and inferior GCIPL thicknesses with a global r2 value of 0.90 and 0.86, r2 of mean of 0.90 and 0.86, and mean MAE of 3.72 µm and 4.2 µm, respectively. For superior and inferior RNFL thickness predictions, model performance was slightly lower, with a global r2 of 0.75 and 0.84, r2 of mean of 0.81 and 0.82, and MAE of 9.31 µm and 8.57 µm, respectively. There was only a modest decrease in model performance when predicting GCIPL and RNFL in more severe disease. Using individualized hemiretinal predictions to account for variability across patients, we estimate that a clinical trial can detect a difference equivalent to a 25% treatment effect over 24 months with an 11-fold reduction in the number of patients compared to a conventional trial. CONCLUSIONS: Our deep learning models were able to accurately estimate both macula GCIPL and ONH RNFL hemiretinal thickness. Using an internal control based on these model predictions may help reduce clinical trial sample size requirements and facilitate investigation of new glaucoma neuroprotection therapies. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.

Postmortem survey of haemoglobin A1c, non-alcoholic steatohepatitis and liver fibrosis within a general population.

AIMS: Non-alcoholic steatohepatitis (NASH), fatty liver disease and fibrosis are associated with diabetes mellitus and obesity. Previous autopsy series have reported prevalence of fatty liver disease to be 11%-24%. Recent studies, using imaging and serology, suggest a prevalence of 20%-35%, NASH of 5% and advanced fibrosis of 2%-3%. We examined the prevalence of NASH and liver fibrosis in a general autopsy population. METHODS: A cross-sectional study of consecutive, adult, medicolegal autopsies over a 1-year period was conducted. Liver sections were scored for fibrosis, inflammation and steatosis using a modified NASH scoring system. Stepwise logistic regression was used to identify associations between NASH or moderate/severe fibrosis and several clinicopathological parameters, including postmortem haemoglobin A1c (HbA1c). RESULTS: Of 376 cases, 86 (22.9%) were classified as NASH. Prevalence of diabetes mellitus, body mass index (BMI) and postmortem HbA1c were significantly higher in NASH cases (39.5%, 32.3 kg/m2 and 6.88%) than non-NASH cases (12.1%, 27.0 kg/m2 and 5.73%). Decedents with moderate/severe fibrosis (6.9%) had higher prevalence of diabetes, BMI and HbA1c (50%, 31.4 kg/m2 and 6.7%) compared with those with no/mild fibrosis (16%, 28 kg/m2 and 5.9%). HbA1c ≥7% was found to be an independent predictor of NASH (OR 5.11, 95% CI 2.61 to 9.98) and advanced fibrosis (OR 3.94, 95% CI 1.63 to 9.53). CONCLUSIONS: NASH and advanced fibrosis were higher in our general adult autopsy population compared with previously published estimates. This is a large series with histological evaluation showing that HbA1c >7.0% is independently associated with NASH and advanced fibrosis.

Macula structural and vascular differences in glaucoma eyes with and without high axial myopia.

AIMS: To identify clinically relevant parameters for identifying glaucoma in highly myopic eyes, an investigation was conducted of the relationship between the thickness of various retinal layers and the superficial vessel density (sVD) of the macula with axial length (AL) and visual field mean deviation (VFMD). METHODS: 270 glaucoma patients (438 eyes) participating in the Diagnostic Innovations in Glaucoma cross-sectional study representing three axial myopia groups (non-myopia: n=163 eyes; mild myopia: n=218 eyes; high myopia (AL>26 mm): n=57 eyes) who completed macular optical coherence tomography (OCT) and OCT-angiography imaging were included. Associations of AL and VFMD with the thickness of the ganglion cell inner plexiform layer (GCIPL), macular retinal nerve fibre layer (mRNFL), ganglion cell complex (GCC), macular choroidal thickness (mCT) and sVD were evaluated. RESULTS: Thinner Global GCIPL and GCC were significantly associated with worse VFMD (R2=34.5% and R2=32.9%; respectively p<0.001), but not with AL (all p>0.1). Thicker mRNFL showed a weak association with increasing AL (R2=2.4%; p=0.005) and a positive association with VFMD (global R2=19.2%; p<0.001). Lower sVD was weakly associated with increasing AL (R2=1.8%; p=0.028) and more strongly associated with more severe glaucoma VFMD (R2=29.6%; p<0.001). Thinner mCT was associated with increasing AL (R2=15.5% p<0.001) and not associated with VFMD (p=0.194). mRNFL was thickest while mCT was thinnest in all sectors of high myopic eyes. CONCLUSIONS: As thinner GCIPL and GCC were associated with increasing severity of glaucoma but were not significantly associated with AL, they may be useful for monitoring glaucoma in highly myopic eyes.

Single-cell transcriptomics reveals common epithelial response patterns in human acute kidney injury.

BACKGROUND: Acute kidney injury (AKI) occurs frequently in critically ill patients and is associated with adverse outcomes. Cellular mechanisms underlying AKI and kidney cell responses to injury remain incompletely understood. METHODS: We performed single-nuclei transcriptomics, bulk transcriptomics, molecular imaging studies, and conventional histology on kidney tissues from 8 individuals with severe AKI (stage 2 or 3 according to Kidney Disease: Improving Global Outcomes (KDIGO) criteria). Specimens were obtained within 1-2 h after individuals had succumbed to critical illness associated with respiratory infections, with 4 of 8 individuals diagnosed with COVID-19. Control kidney tissues were obtained post-mortem or after nephrectomy from individuals without AKI. RESULTS: High-depth single cell-resolved gene expression data of human kidneys affected by AKI revealed enrichment of novel injury-associated cell states within the major cell types of the tubular epithelium, in particular in proximal tubules, thick ascending limbs, and distal convoluted tubules. Four distinct, hierarchically interconnected injured cell states were distinguishable and characterized by transcriptome patterns associated with oxidative stress, hypoxia, interferon response, and epithelial-to-mesenchymal transition, respectively. Transcriptome differences between individuals with AKI were driven primarily by the cell type-specific abundance of these four injury subtypes rather than by private molecular responses. AKI-associated changes in gene expression between individuals with and without COVID-19 were similar. CONCLUSIONS: The study provides an extensive resource of the cell type-specific transcriptomic responses associated with critical illness-associated AKI in humans, highlighting recurrent disease-associated signatures and inter-individual heterogeneity. Personalized molecular disease assessment in human AKI may foster the development of tailored therapies.