Search

Objective: This study develops and evaluates multimodal machine learning models for differentiating bacterial and fungal keratitis using a prospective representative dataset from South India. Design: Machine learning classifier training and validation study. Participants: Five hundred ninety-nine subjects diagnosed with acute infectious keratitis at Aravind Eye Hospital in Madurai, India. Methods: We developed and compared 3 prediction models to distinguish bacterial and fungal keratitis using a prospective, consecutively-collected, representative dataset gathered over a full calendar year (the MADURAI dataset). These models included a clinical data model, a computer vision model using the EfficientNet architecture, and a multimodal model combining both imaging and clinical data. We partitioned the MADURAI dataset into 70% train/validation and 30% test sets. Model training was performed with fivefold cross-validation. We also compared the performance of the MADURAI-trained computer vision model against a model with identical architecture but trained on a preexisting dataset collated from multiple prior bacterial and fungal keratitis randomized clinical trials (RCTs) (the RCT-trained computer vision model). Main Outcome Measures: The primary evaluation metric was the area under the precision-recall curve (AUPRC). Secondary metrics included area under the receiver operating characteristic curve (AUROC), accuracy, and F1 score. Results: The MADURAI-trained computer vision model outperformed the clinical data model and the RCT-trained computer vision model on the hold-out test set, with an AUPRC 0.94 (95% confidence interval: 0.92–0.96), AUROC 0.81 (0.76–0.85), accuracy 77%, and F1 score 0.85. The multimodal model did not substantially improve performance compared with the computer vision model. Conclusions: The best-performing machine learning classifier for infectious keratitis was a computer vision model trained using the MADURAI dataset. These findings suggest that image-based deep learning could significantly enhance diagnostic capabilities for infectious keratitis and emphasize the importance of using prospective, consecutively-collected, representative data for machine learning model training and evaluation. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Purpose: Retinopathy of prematurity (ROP) stage is defined by the visual appearance of the vascular-avascular border, which reflects a spectrum of pathologic neurovascular tissue (NVT). Previous work demonstrated that the thickness of the ridge lesion, measured using OCT, corresponds to higher clinical diagnosis of stage. This study evaluates whether the volume of anomalous NVT (ANVTV), defined as abnormal tissue protruding from the regular contour of the retina, can be measured automatically using deep learning to develop quantitative OCT-based biomarkers in ROP. Design: Single-center retrospective case series. Participants: Thirty-three infants with ROP in the Oregon Health & Science University neonatal intensive care unit. Methods: OCT B-scans were collected using an investigational ultrawidefield OCT. The ANVTV was manually segmented. A set of 3347 B-scans and corresponding manual segmentations from 12 volumes from 6 patients were used to train an automated segmentation tool using a U-Net. An additional held-out test data set of 60 B-scans from 6 infants was used to evaluate model performance. The Dice–Sorensen coefficient (DSC) comparing manual and automated segmentation of ANVTV was calculated. Scans from 21 additional infants were used for clinical evaluation of ANVTV using the visit in which they had developed their peak stage of ROP. Each infant had every B-scan in a volume automatically segmented for ANVTV (total number of segmented voxels within the 60° temporal to the optic disc). The ANVTV was compared between infants with stage 1 to 3 ROP using a Kruskal–Wallis test and tracked over time in all infants with stage 3 ROP. Main Outcome Measurements: Cross sectional and longitudinal association between ANVTV and stages 1 to 3 ROP. Results: Comparing automated and manual segmentation of ANVTV achieved a DSC of 0.61 ± 0.13. Using the U-Net, ANVTV was associated with higher disease stage both cross sectionally and longitudinally. Median ANVTV significantly increased as ROP stage worsened from 1 (0, [interquartile range: 0–0] kilovoxels) to 2 (170.1 [interquartile range: 104.2–183.6] kilovoxels) to 3 (421.4 [interquartile range: 312.3–1110.8] kilovoxels; P < 0.001). Conclusions: Automated OCT-based measurement of ANVTV was associated with clinical disease stage in ROP, both cross sectionally and longitudinally. Ultrawidefield-OCT may facilitate more objective screening, diagnosis, and monitoring in the future. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Communication about health often involves descriptions of risk: the probability or likelihood of an unfavorable outcome. Communicating risk helps individuals make choices about their own health by building understanding of potential outcomes and providing context for the importance of procedures, health interventions, and lifestyle choices. However, medical education in the United States does not provide future physicians with adequate statistical literacy to communicate risk effectively and rarely encourages them to practice communicating risk in pre-clinical years. Risk communication in military intelligence, a field with formalized risk language and training, offers a unique perspective into potential improvements for medical risk communication. With backgrounds in the military, public health, communication, surgery, and medical education, the authors offer the following recommendations to improve risk communication for medical students. (1) Encourage the use of numerical absolute risk when communicating among health practitioners to avoid varied interpretations of what different risk descriptors (“uncommon,” “likely,” or “low”) might mean; (2) build efficient, teachable skills in use of patient-facing risk communication tools like comparative probabilities and visual aids; and (3) practice estimating risk through role-play of risk communication between medical students and standardized patients. By improving risk communication in medical education, future doctors will be better equipped to build trust through open communication and improve the health of the patients and the communities for whom they care.

Summary: Background: It is uncertain which biological features underpin the response of rectal cancer (RC) to radiotherapy. No biomarker is currently in clinical use to select patients for treatment modifications. Methods: We identified two cohorts of patients (total N = 249) with RC treated with neoadjuvant radiotherapy (45Gy/25) plus fluoropyrimidine. This discovery set included 57 cases with pathological complete response (pCR) to chemoradiotherapy (23%). Pre-treatment cancer biopsies were assessed using transcriptome-wide mRNA expression and targeted DNA sequencing for copy number and driver mutations. Biological candidate and machine learning (ML) approaches were used to identify predictors of pCR to radiotherapy independent of tumour stage. Findings were assessed in 107 cases from an independent validation set (GSE87211). Findings: Three gene expression sets showed significant independent associations with pCR: Fibroblast-TGFβ Response Signature (F-TBRS) with radioresistance; and cytotoxic lymphocyte (CL) expression signature and consensus molecular subtype CMS1 with radiosensitivity. These associations were replicated in the validation cohort. In parallel, a gradient boosting machine model comprising the expression of 33 genes generated in the discovery cohort showed high performance in GSE87211 with 90% sensitivity, 86% specificity. Biological and ML signatures indicated similar mechanisms underlying radiation response, and showed better AUC and p-values than published transcriptomic signatures of radiation response in RC. Interpretation: RCs responding completely to chemoradiotherapy (CRT) have biological characteristics of immune response and absence of immune inhibitory TGFβ signalling. These tumours may be identified with a potential biomarker based on a 33 gene expression signature. This could help select patients likely to respond to treatment with a primary radiotherapy approach as for anal cancer. Conversely, those with predicted radioresistance may be candidates for clinical trials evaluating addition of immune-oncology agents and stromal TGFβ signalling inhibition. Funding: The Stratification in Colorectal Cancer Consortium (S:CORT) was funded by the Medical Research Council and Cancer Research UK (MR/M016587/1).

Objective To investigate the views, hopes and concerns of patients living with glaucoma and age-related macular degeneration (AMD) regarding vision home-monitoring.Design Qualitative study using focus groups and questionnaires. Participants were given three disease-relevant home-monitoring tests to try. The tests consisted of three visual field tests for the glaucoma groups (Melbourne Rapid Fields, Eyecatcher, Visual Fields Fast) and three acuity and/or contrast-sensitivity tests for AMD groups (Alleye, PopCSF, SpotChecks). Focus group data were thematically analysed.Setting University meeting rooms in London, UK.Participants Eight people with glaucoma (five women, median age 74) and seven people with AMD (four women, median age 77) volunteered through two UK-based charities. Participants were excluded if they did not self-report a diagnosis of glaucoma or AMD or if they lived further than a 1-hour travel distance from the university (to ensure minimal travel burden on participants).Results Six themes emerged from focus groups, the two most frequently referenced being: ‘concerns about home-monitoring’ and ‘patient and practitioner access to results’. Overall, participants believed home-monitoring could provide patients with a greater sense of control, but also expressed concerns, including: the possibility of home-monitoring replacing face-to-face appointments; the burden placed on clinicians by the need to process additional data; struggles to keep up with requisite technologies; and potential anxiety from seeing worrying results. Most devices were scored highly for usability, though several practical improvements were suggested.Conclusion Patients with mild-to-moderate glaucoma/AMD expect vision home-monitoring to be beneficial, but have significant concerns about its potential implementation.

Abstract We conducted a genome-wide association study (GWAS) in a multiethnic cohort of 920 at-risk infants for retinopathy of prematurity (ROP), a major cause of childhood blindness, identifying 1 locus at genome-wide significance level (p

Purpose: This study sought to identify the sources of differential performance and misclassification error among local (Indian) and external (non-Indian) corneal specialists in identifying bacterial and fungal keratitis based on corneal photography. Methods: This study is a secondary analysis of survey data assessing the ability of corneal specialists to identify acute bacterial versus fungal keratitis by using corneal photography. One-hundred images of 100 eyes from 100 patients with acute bacterial or fungal keratitis in South India were previously presented to an international cohort of cornea specialists for interpretation over the span of April to July 2021. Each expert provided a predicted probability that the ulcer was either bacterial or fungal. Using these data, we performed multivariable linear regression to identify factors predictive of expert performance, accounting for primary practice location and surrogate measures to infer local fungal ulcer prevalence, including locality, latitude, and dew point. In addition, Brier score decomposition was used to determine experts' reliability (“calibration”) and resolution (“boldness”) and were compared between local (Indian) and external (non-Indian) experts. Results: Sixty-six experts from 16 countries participated. Indian practice location was the only independently significant predictor of performance in multivariable linear regression. Resolution among Indian experts was significantly better (0.08) than among non-Indian experts (0.01; P < 0.001), indicating greater confidence in their predictions. There was no significant difference in reliability between the two groups (P = 0.40). Conclusion: Local cornea experts outperformed their international counterparts independent of regional variability in tropical risk factors for fungal keratitis. This may be explained by regional characteristics of infectious ulcers with which local corneal specialists are familiar.

Purpose: The murine oxygen-induced retinopathy (OIR) model is one of the most widely used animal models of ischemic retinopathy, mimicking hallmark pathophysiology of initial vaso-obliteration (VO) resulting in ischemia that drives neovascularization (NV). In addition to NV and VO, human ischemic retinopathies, including retinopathy of prematurity (ROP), are characterized by increased vascular tortuosity. Vascular tortuosity is an indicator of disease severity, need to treat, and treatment response in ROP. Current literature investigating novel therapeutics in the OIR model often report their effects on NV and VO, and measurements of vascular tortuosity are less commonly performed. No standardized quantification of vascular tortuosity exists to date despite this metric’s relevance to human disease. This proof-of-concept study aimed to apply a previously published semi-automated computer-based image analysis approach (iROP-Assist) to develop a new tool to quantify vascular tortuosity in mouse models. Design: Experimental study. Subjects: C57BL/6J mice subjected to the OIR model. Methods: In a pilot study, vasculature was manually segmented on flat-mount images of OIR and normoxic (NOX) mice retinas and segmentations were analyzed with iROP-Assist to quantify vascular tortuosity metrics. In a large cohort of age-matched (postnatal day 12 [P12], P17, P25) NOX and OIR mice retinas, NV, VO, and vascular tortuosity were quantified and compared. In a third experiment, vascular tortuosity in OIR mice retinas was quantified on P17 following intravitreal injection with anti-VEGF (aflibercept) or Immunoglobulin G isotype control on P12. Main Outcome Measures: Vascular tortuosity. Results: Cumulative tortuosity index was the best metric produced by iROP-Assist for discriminating between OIR mice and NOX controls. Increased vascular tortuosity correlated with disease activity in OIR. Treatment of OIR mice with aflibercept rescued vascular tortuosity. Conclusions: Vascular tortuosity is a quantifiable feature of the OIR model that correlates with disease severity and may be quickly and accurately quantified using the iROP-Assist algorithm. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Purpose: Retinopathy of prematurity (ROP) is one of the leading causes of blindness in children. Although the role of oxygen in the pathophysiology of ROP is well established, a precise understanding of the dynamic relationship between oxygen exposure ROP incidence and severity is lacking. The purpose of this study was to evaluate the correlation between time-dependent oxygen variables and the onset of ROP. Design: Retrospective cohort study. Participants: Two hundred thirty infants who were born at a single academic center and met the inclusion criteria were included. Infants are mainly born between January 2011 and October 2022. Methods: Patient data were extracted from electronic health records (EHRs), with sufficient time-dependent oxygen data. Clinical outcomes for ROP were recorded as none/mild or moderate/severe (defined as type II or worse). Mixed-effects linear models were used to compare the 2 groups in terms of dynamic oxygen variables, such as daily average and the coefficient of variation (COV) fraction of inspired oxygen (FiO2). Support vector machine (SVM) and long-short-term memory (LSTM)-based multimodal models were trained with fivefold cross-validation to predict which infants would develop moderate/severe ROP. Gestational age (GA), birth weight, and time-dependent oxygen variables were used to develop predictive models. Main Outcome Measures: Model cross-validation performance was evaluated by computing the mean area under the receiver operating characteristic (AUROC) curve, precision, recall, and F1 score. Results: We found that both daily average and COV of FiO2 were associated with more severe ROP (adjusted P

Objective: To develop a generative adversarial network (GAN) to segment major blood vessels from retinal flat-mount images from oxygen-induced retinopathy (OIR) and demonstrate the utility of these GAN-generated vessel segmentations in quantifying vascular tortuosity. Design: Development and validation of GAN. Subjects: Three datasets containing 1084, 50, and 20 flat-mount mice retina images with various stains used and ages at sacrifice acquired from previously published manuscripts. Methods: Four graders manually segmented major blood vessels from flat-mount images of retinas from OIR mice. Pix2Pix, a high-resolution GAN, was trained on 984 pairs of raw flat-mount images and manual vessel segmentations and then tested on 100 and 50 image pairs from a held-out and external test set, respectively. GAN-generated and manual vessel segmentations were then used as an input into a previously published algorithm (iROP-Assist) to generate a vascular cumulative tortuosity index (CTI) for 20 image pairs containing mouse eyes treated with aflibercept versus control. Main Outcome Measures: Mean dice coefficients were used to compare segmentation accuracy between the GAN-generated and manually annotated segmentation maps. For the image pairs treated with aflibercept versus control, mean CTIs were also calculated for both GAN-generated and manual vessel maps. Statistical significance was evaluated using Wilcoxon signed-rank tests (P ≤ 0.05 threshold for significance). Results: The dice coefficient for the GAN-generated versus manual vessel segmentations was 0.75 ± 0.27 and 0.77 ± 0.17 for the held-out test set and external test set, respectively. The mean CTI generated from the GAN-generated and manual vessel segmentations was 1.12 ± 0.07 versus 1.03 ± 0.02 (P = 0.003) and 1.06 ± 0.04 versus 1.01 ± 0.01 (P < 0.001), respectively, for eyes treated with aflibercept versus control, demonstrating that vascular tortuosity was rescued by aflibercept when quantified by GAN-generated and manual vessel segmentations. Conclusions: GANs can be used to accurately generate vessel map segmentations from flat-mount images. These vessel maps may be used to evaluate novel metrics of vascular tortuosity in OIR, such as CTI, and have the potential to accelerate research in treatments for ischemic retinopathies. Financial Disclosure(s): The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Objective: To investigate the impact of corneal photograph quality on convolutional neural network (CNN) predictions. Design: A CNN trained to classify bacterial and fungal keratitis was evaluated using photographs of ulcers labeled according to 5 corneal image quality parameters: eccentric gaze direction, abnormal eyelid position, over/under-exposure, inadequate focus, and malpositioned light reflection. Participants: All eligible subjects with culture and stain-proven bacterial and/or fungal ulcers presenting to Aravind Eye Hospital in Madurai, India, between January 1, 2021 and December 31, 2021. Methods: Convolutional neural network classification performance was compared for each quality parameter, and gradient class activation heatmaps were generated to visualize regions of highest influence on CNN predictions. Main Outcome Measures: Area under the receiver operating characteristic and precision recall curves were calculated to quantify model performance. Bootstrapped confidence intervals were used for statistical comparisons. Logistic loss was calculated to measure individual prediction accuracy. Results: Individual presence of either light reflection or eyelids obscuring the corneal surface was associated with significantly higher CNN performance. No other quality parameter significantly influenced CNN performance. Qualitative review of gradient class activation heatmaps generally revealed the infiltrate as having the highest diagnostic relevance. Conclusions: The CNN demonstrated expert-level performance regardless of image quality. Future studies may investigate use of smartphone cameras and image sets with greater variance in image quality to further explore the influence of these parameters on model performance. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

The rapid progress of large language models (LLMs) driving generative artificial intelligence applications heralds the potential of opportunities in health care. We conducted a review up to April 2023 on Google Scholar, Embase, MEDLINE, and Scopus using the following terms: “large language models,” “generative artificial intelligence,” “ophthalmology,” “ChatGPT,” and “eye,” based on relevance to this review. From a clinical viewpoint specific to ophthalmologists, we explore from the different stakeholders’ perspectives—including patients, physicians, and policymakers—the potential LLM applications in education, research, and clinical domains specific to ophthalmology. We also highlight the foreseeable challenges of LLM implementation into clinical practice, including the concerns of accuracy, interpretability, perpetuating bias, and data security. As LLMs continue to mature, it is essential for stakeholders to jointly establish standards for best practices to safeguard patient safety. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Abstract The integration of artificial intelligence into clinical workflows requires reliable and robust models. Repeatability is a key attribute of model robustness. Ideal repeatable models output predictions without variation during independent tests carried out under similar conditions. However, slight variations, though not ideal, may be unavoidable and acceptable in practice. During model development and evaluation, much attention is given to classification performance while model repeatability is rarely assessed, leading to the development of models that are unusable in clinical practice. In this work, we evaluate the repeatability of four model types (binary classification, multi-class classification, ordinal classification, and regression) on images that were acquired from the same patient during the same visit. We study the each model’s performance on four medical image classification tasks from public and private datasets: knee osteoarthritis, cervical cancer screening, breast density estimation, and retinopathy of prematurity. Repeatability is measured and compared on ResNet and DenseNet architectures. Moreover, we assess the impact of sampling Monte Carlo dropout predictions at test time on classification performance and repeatability. Leveraging Monte Carlo predictions significantly increases repeatability, in particular at the class boundaries, for all tasks on the binary, multi-class, and ordinal models leading to an average reduction of the 95% limits of agreement by 16% points and of the class disagreement rate by 7% points. The classification accuracy improves in most settings along with the repeatability. Our results suggest that beyond about 20 Monte Carlo iterations, there is no further gain in repeatability. In addition to the higher test-retest agreement, Monte Carlo predictions are better calibrated which leads to output probabilities reflecting more accurately the true likelihood of being correctly classified.

Backgroundprecision-medicine quantitative tools for cross-sectional imaging require painstaking labeling of targets that vary considerably in volume, prohibiting scaling of data annotation efforts and supervised training to large datasets for robust and generalizable clinical performance. A straight-forward time-saving strategy involves manual editing of AI-generated labels, which we call AI-collaborative labeling (AICL). Factors affecting the efficacy and utility of such an approach are unknown. Reduction in time effort is not well documented. Further, edited AI labels may be prone to automation bias.PurposeIn this pilot, using a cohort of CTs with intracavitary hemorrhage, we evaluate both time savings and AICL label quality and propose criteria that must be met for using AICL annotations as a high-throughput, high-quality ground truth.Methods57 CT scans of patients with traumatic intracavitary hemorrhage were included. No participant recruited for this study had previously interpreted the scans. nnU-net models trained on small existing datasets for each feature (hemothorax/hemoperitoneum/pelvic hematoma; n = 77–253) were used in inference. Two common scenarios served as baseline comparison- de novo expert manual labeling, and expert edits of trained staff labels. Parameters included time effort and image quality graded by a blinded independent expert using a 9-point scale. The observer also attempted to discriminate AICL and expert labels in a random subset (n = 18). Data were compared with ANOVA and post-hoc paired signed rank tests with Bonferroni correction.ResultsAICL reduced time effort 2.8-fold compared to staff label editing, and 8.7-fold compared to expert labeling (corrected p

Abstract Background Up to 80% of cases of prostate cancer present with multifocal independent tumour lesions leading to the concept of a field effect present in the normal prostate predisposing to cancer development. In the present study we applied Whole Genome DNA Sequencing (WGS) to a group of morphologically normal tissue (n = 51), including benign prostatic hyperplasia (BPH) and non-BPH samples, from men with and men without prostate cancer. We assess whether the observed genetic changes in morphologically normal tissue are linked to the development of cancer in the prostate. Results Single nucleotide variants (P = 7.0 × 10–03, Wilcoxon rank sum test) and small insertions and deletions (indels, P = 8.7 × 10–06) were significantly higher in morphologically normal samples, including BPH, from men with prostate cancer compared to those without. The presence of subclonal expansions under selective pressure, supported by a high level of mutations, were significantly associated with samples from men with prostate cancer (P = 0.035, Fisher exact test). The clonal cell fraction of normal clones was always higher than the proportion of the prostate estimated as epithelial (P = 5.94 × 10–05, paired Wilcoxon signed rank test) which, along with analysis of primary fibroblasts prepared from BPH specimens, suggests a stromal origin. Constructed phylogenies revealed lineages associated with benign tissue that were completely distinct from adjacent tumour clones, but a common lineage between BPH and non-BPH morphologically normal tissues was often observed. Compared to tumours, normal samples have significantly less single nucleotide variants (P = 3.72 × 10–09, paired Wilcoxon signed rank test), have very few rearrangements and a complete lack of copy number alterations. Conclusions Cells within regions of morphologically normal tissue (both BPH and non-BPH) can expand under selective pressure by mechanisms that are distinct from those occurring in adjacent cancer, but that are allied to the presence of cancer. Expansions, which are probably stromal in origin, are characterised by lack of recurrent driver mutations, by almost complete absence of structural variants/copy number alterations, and mutational processes similar to malignant tissue. Our findings have implications for treatment (focal therapy) and early detection approaches.

Introduction: COVID-19 pandemic has had a great impact on health systems. Many non-urgent visits were done virtually to limit exposure risks. Objective: Assess the impact of the pandemic on STI (sexually transmitted infections) testing in a college health setting. Material and methods: Quantitative assessment of the number of STI tests done, positive rates and percentage of “compliance to follow-up” for diagnosed STI from March to December 2020 and its comparison with historical data (2015-2019) at the University Health Services, UW-Madison. Measurement: Observed (2020) vs expected (2015-2019) number of STI tests, positive rates and compliance to follow-up testing for STIs. Results: The 2020 period showed a significant decrease in the number of tests done and an increase of positive rate when compared to historical data for total sample and per sex. There was a decrease in the percentage of follow-up for the entire sample and for females and an increase for males. Conclusions: In accordance with national data, our analysis shows significant declines in STI testing and follow-up during 2020 compared to previous years and an increase in positivity rate. A higher positivity with lower number of tests is likely due to triaging patients, facilitating testing for those at highest risk.

Abstract Single cell technologies allow the interrogation of tumor heterogeneity, providing insights into tumor evolution and treatment resistance. To better understand whether circulating tumor cells (CTCs) could complement metastatic biopsies for tumor genomic profiling, we characterized 11 single CTCs and 10 pooled CTC samples at the mutational and copy number aberration (CNA) levels, and compared these results with matched synchronous tumor biopsies from 3 metastatic breast cancer patients with triple-negative (TNBC), HER2-positive and estrogen receptor-positive (ER+) tumors. Similar CNA profiles and the same patient-specific driver mutations were found in bulk tissue and CTCs for the HER2-positive and TNBC tumors, whereas different CNA profiles and driver mutations were identified for the ER+ tumor, which presented two distinct clones in CTCs defined by mutations in ESR1 Y537N and TP53, respectively. Furthermore, de novo mutational signatures derived from CTCs described patient-specific biological processes. These data suggest that tumor tissue and CTCs provide complementary clinically relevant information to map tumor heterogeneity and tumor evolution.

Abstract Background The incidence of non-alcoholic fatty liver disease (NAFLD)-associated hepatocellular carcinoma (HCC) is increasing worldwide, but the steps in precancerous hepatocytes which lead to HCC driver mutations are not well understood. Here we provide evidence that metabolically driven histone hyperacetylation in steatotic hepatocytes can increase DNA damage to initiate carcinogenesis. Methods Global epigenetic state was assessed in liver samples from high-fat diet or high-fructose diet rodent models, as well as in cultured immortalized human hepatocytes (IHH cells). The mechanisms linking steatosis, histone acetylation and DNA damage were investigated by computational metabolic modelling as well as through manipulation of IHH cells with metabolic and epigenetic inhibitors. Chromatin immunoprecipitation and next-generation sequencing (ChIP-seq) and transcriptome (RNA-seq) analyses were performed on IHH cells. Mutation locations and patterns were compared between the IHH cell model and genome sequence data from preneoplastic fatty liver samples from patients with alcohol-related liver disease and NAFLD. Results Genome-wide histone acetylation was increased in steatotic livers of rodents fed high-fructose or high-fat diet. In vitro, steatosis relaxed chromatin and increased DNA damage marker γH2AX, which was reversed by inhibiting acetyl-CoA production. Steatosis-associated acetylation and γH2AX were enriched at gene clusters in telomere-proximal regions which contained HCC tumour suppressors in hepatocytes and human fatty livers. Regions of metabolically driven epigenetic change also had increased levels of DNA mutation in non-cancerous tissue from NAFLD and alcohol-related liver disease patients. Finally, genome-scale network modelling indicated that redox balance could be a key contributor to this mechanism. Conclusions Abnormal histone hyperacetylation facilitates DNA damage in steatotic hepatocytes and is a potential initiating event in hepatocellular carcinogenesis.

ABSTRACT Malaria, especially Plasmodium falciparum infection, remains an enormous problem, and its treatment and control are seriously challenged by drug resistance. New antimalarial drugs are needed. To characterize the Medicines for Malaria Venture pipeline of antimalarials under development, we assessed the ex vivo drug susceptibilities to 19 compounds targeting or potentially impacted by mutations in P. falciparum ABC transporter I family member 1, acetyl-CoA synthetase, cytochrome b, dihydroorotate dehydrogenase, elongation factor 2, lysyl-tRNA synthetase, phenylalanyl-tRNA synthetase, plasmepsin X, prodrug activation and resistance esterase, and V-type H+ ATPase of 998 fresh P. falciparum clinical isolates collected in eastern Uganda from 2015 to 2022. Drug susceptibilities were assessed by 72-h growth inhibition (half-maximum inhibitory concentration [IC50]) assays using SYBR green. Field isolates were highly susceptible to lead antimalarials, with low- to midnanomolar median IC50s, near values previously reported for laboratory strains, for all tested compounds. However, outliers with decreased susceptibilities were identified. Positive correlations between IC50 results were seen for compounds with shared targets. We sequenced genes encoding presumed targets to characterize sequence diversity, search for polymorphisms previously selected with in vitro drug pressure, and determine genotype-phenotype associations. We identified many polymorphisms in target genes, generally in

Background As more preterm infants survive, complications of preterm birth, including retinopathy of prematurity (ROP), become more prevalent. ROP rates and blindness from ROP are higher in low-income and middle-income countries, where exposure to risk factors can be higher and where detection and treatment of ROP are under-resourced or non-existent. Access to low-cost imaging devices would improve remote screening capabilities for ROP.Methods Target product profiles (TPPs) are developed early in the medical device development process to define the setting, target user and range of product requirements. A Delphi-like process, consisting of an online survey and consensus meeting, was used to develop a TPP for an ROP imaging device, collecting feedback on a proposed set of 64 product requirements.Results Thirty-six stakeholders from 17 countries provided feedback: clinicians (72%), product developers (14%), technicians (6%) and other (8%). Thirty-six per cent reported not currently screening for ROP, with cited barriers including cost (44%), no training (17%) and poor image quality (16%). Among those screening (n=23), 48% use more than one device, with the most common being an indirect ophthalmoscope (87%), followed by RetCam (26%) and smartphone with image capture (26%). Consensus was reached on 53 (83%) product requirements. The 11 remaining were discussed at the consensus meeting, and all but two achieved consensus.Conclusions This TPP process was novel in that it successfully brought together diverse stakeholders to reach consensus on the product requirements for an ROP imaging devices. The resulting TPP provides a framework from which innovators can develop prototypes.

Purpose: To evaluate the performance of a deep learning (DL) algorithm for retinopathy of prematurity (ROP) screening in Nepal and Mongolia. Design: Retrospective analysis of prospectively collected clinical data. Participants: Clinical information and fundus images were obtained from infants in 2 ROP screening programs in Nepal and Mongolia. Methods: Fundus images were obtained using the Forus 3nethra neo (Forus Health) in Nepal and the RetCam Portable (Natus Medical, Inc.) in Mongolia. The overall severity of ROP was determined from the medical record using the International Classification of ROP (ICROP). The presence of plus disease was determined independently in each image using a reference standard diagnosis. The Imaging and Informatics for ROP (i-ROP) DL algorithm was trained on images from the RetCam to classify plus disease and to assign a vascular severity score (VSS) from 1 through 9. Main Outcome Measures: Area under the receiver operating characteristic curve and area under the precision-recall curve for the presence of plus disease or type 1 ROP and association between VSS and ICROP disease category. Results: The prevalence of type 1 ROP was found to be higher in Mongolia (14.0%) than in Nepal (2.2%; P

Summary: Succinate dehydrogenase (SDH)-deficient renal cell carcinoma represents a rare subtype of hereditary kidney cancer. Clinical diagnosis can be challenging and there is little evidence to guide systemic therapeutic options. We performed genomic profiling of a cohort of tumors through the analysis of whole genomes, transcriptomes, as well as flow cytometry and immunohistochemistry in order to gain a deeper understanding of their molecular biology. We find neutral evolution after early tumor activation with a lack of secondary driver events. We show that these tumors have epithelial derivation, possibly from the macula densa, a specialized paracrine cell of the renal juxtaglomerular apparatus. They subsequently develop into immune excluded tumors. We provide transcriptomic and protein expression evidence of a highly specific tumor marker, PAPPA2. These translational findings have implications for the diagnosis and treatment for this rare tumor subtype.

Optical coherence tomography (OCT) has changed the standard of care for diagnosis and management of macular diseases in adults. Current commercially available OCT systems, including handheld OCT for pediatric use, have a relatively narrow field of view (FOV), which has limited the potential application of OCT to retinal diseases with primarily peripheral pathology, including many of the most common pediatric retinal conditions. More broadly, diagnosis of all types of retinal detachment (exudative, tractional, and rhegmatogenous) may be improved with OCT-based assessment of retinal breaks, identification of proliferative vitreoretinopathy (PVR) membranes, and the pattern of subretinal fluid. Intraocular tumors both benign and malignant often occur outside of the central macula and may be associated with exudation, subretinal and intraretinal fluid, and vitreoretinal traction. The development of wider field OCT systems thus has the potential to improve the diagnosis and management of myriad diseases in both adult and pediatric retina. In this paper, we present a case series of pediatric patients with complex vitreoretinal pathology undergoing examinations under anesthesia (EUA) using a portable widefield (WF) swept-source (SS)-OCT device.

Abstract Retinopathy of prematurity (ROP) is a vasoproliferative retinal disease affecting premature infants. In addition to prematurity itself and oxygen treatment, genetic factors have been suggested to predispose to ROP. We aimed to identify potentially pathogenic genes and biological pathways associated with ROP by analyzing variants from whole exome sequencing (WES) data of premature infants. As part of a multicenter ROP cohort study, 100 non-Hispanic Caucasian preterm infants enriched in phenotypic extremes were subjected to WES. Gene-based testing was done on coding nonsynonymous variants. Genes showing enrichment of qualifying variants in severe ROP compared to mild or no ROP from gene-based tests with adjustment for gestational age and birth weight were selected for gene set enrichment analysis (GSEA). Mean BW of included infants with pre-plus, type-1 or type 2 ROP including aggressive posterior ROP (n = 58) and mild or no ROP (n = 42) were 744 g and 995 g, respectively. No single genes reached genome-wide significance that could account for a severe phenotype. GSEA identified two significantly associated pathways (smooth endoplasmic reticulum and vitamin C metabolism) after correction for multiple tests. WES of premature infants revealed potential pathways that may be important in the pathogenesis of ROP and in further genetic studies.

Purpose: Developing robust artificial intelligence (AI) models for medical image analysis requires large quantities of diverse, well-chosen data that can prove challenging to collect because of privacy concerns, disease rarity, or diagnostic label quality. Collecting image-based datasets for retinopathy of prematurity (ROP), a potentially blinding disease, suffers from these challenges. Progressively growing generative adversarial networks (PGANs) may help, because they can synthesize highly realistic images that may increase both the size and diversity of medical datasets. Design: Diagnostic validation study of convolutional neural networks (CNNs) for plus disease detection, a component of severe ROP, using synthetic data. Participants: Five thousand eight hundred forty-two retinal fundus images (RFIs) collected from 963 preterm infants. Methods: Retinal vessel maps (RVMs) were segmented from RFIs. PGANs were trained to synthesize RVMs with normal, pre-plus, or plus disease vasculature. Convolutional neural networks were trained, using real or synthetic RVMs, to detect plus disease from 2 real RVM test datasets. Main Outcome Measures: Features of real and synthetic RVMs were evaluated using uniform manifold approximation and projection (UMAP). Similarities were evaluated at the dataset and feature level using Fréchet inception distance and Euclidean distance, respectively. CNN performance was assessed via area under the receiver operating characteristic curve (AUC); AUCs were compared via bootstrapping and Delong’s test for correlated receiver operating characteristic curves. Confusion matrices were compared using McNemar’s chi-square test and Cohen’s κ value. Results: The CNN trained on synthetic RVMs showed a significantly higher AUC (0.971; P = 0.006 and P = 0.004) and classified plus disease more similarly to a set of 8 international experts (κ = 0.922) than the CNN trained on real RVMs (AUC = 0.934; κ = 0.701). Real and synthetic RVMs overlapped, by plus disease diagnosis, on the UMAP manifold, showing that synthetic images spanned the disease severity spectrum. Fréchet inception distance and Euclidean distances suggested that real and synthetic RVMs were more dissimilar to one another than real RVMs were to one another, further suggesting that synthetic RVMs were distinct from the training data with respect to privacy considerations. Conclusions: Synthetic datasets may be useful for training robust medical AI models. Furthermore, PGANs may be able to synthesize realistic data for use without protected health information concerns.

Purpose: Develop computer vision models for image-based differentiation of bacterial and fungal corneal ulcers and compare their performance against human experts. Design: Cross-sectional comparison of diagnostic performance. Participants: Patients with acute, culture-proven bacterial or fungal keratitis from 4 centers in South India. Methods: Five convolutional neural networks (CNNs) were trained using images from handheld cameras collected from patients with culture-proven corneal ulcers in South India recruited as part of clinical trials conducted between 2006 and 2015. Their performance was evaluated on 2 hold-out test sets (1 single center and 1 multicenter) from South India. Twelve local expert cornea specialists performed remote interpretation of the images in the multicenter test set to enable direct comparison against CNN performance. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) individually and for each group collectively (i.e., CNN ensemble and human ensemble). Results: The best-performing CNN architecture was MobileNet, which attained an AUC of 0.86 on the single-center test set (other CNNs range, 0.68–0.84) and 0.83 on the multicenter test set (other CNNs range, 0.75–0.83). Expert human AUCs on the multicenter test set ranged from 0.42 to 0.79. The CNN ensemble achieved a statistically significantly higher AUC (0.84) than the human ensemble (0.76; P < 0.01). CNNs showed relatively higher accuracy for fungal (81%) versus bacterial (75%) ulcers, whereas humans showed relatively higher accuracy for bacterial (88%) versus fungal (56%) ulcers. An ensemble of the best-performing CNN and best-performing human achieved the highest AUC of 0.87, although this was not statistically significantly higher than the best CNN (0.83; P = 0.17) or best human (0.79; P = 0.09). Conclusions: Computer vision models achieved superhuman performance in identifying the underlying infectious cause of corneal ulcers compared with cornea specialists. The best-performing model, MobileNet, attained an AUC of 0.83 to 0.86 without any additional clinical or historical information. These findings suggest the potential for future implementation of these models to enable earlier directed antimicrobial therapy in the management of infectious keratitis, which may improve visual outcomes. Additional studies are ongoing to incorporate clinical history and expert opinion into predictive models.

Purpose: To compare the efficacy and efficiency of training neural networks for medical image classification using comparison labels indicating relative disease severity versus diagnostic class labels from a retinopathy of prematurity (ROP) image dataset. Design: Evaluation of diagnostic test or technology. Participants: Deep learning neural networks trained on expert-labeled wide-angle retinal images obtained from patients undergoing diagnostic ROP examinations obtained as part of the Imaging and Informatics in ROP (i-ROP) cohort study. Methods: Neural networks were trained with either class or comparison labels indicating plus disease severity in ROP retinal fundus images from 2 datasets. After training and validation, all networks underwent evaluation using a separate test dataset in 1 of 2 binary classification tasks: normal versus abnormal or plus versus nonplus. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) values were measured to assess network performance. Results: Given the same number of labels, neural networks learned more efficiently by comparison, generating significantly higher AUCs in both classification tasks across both datasets. Similarly, given the same number of images, comparison learning developed networks with significantly higher AUCs across both classification tasks in 1 of 2 datasets. The difference in efficiency and accuracy between models trained on either label type decreased as the size of the training set increased. Conclusions: Comparison labels individually are more informative and more abundant per sample than class labels. These findings indicate a potential means of overcoming the common obstacle of data variability and scarcity when training neural networks for medical image classification tasks.

Retinopathy of prematurity (ROP) is a vasoproliferative retinal disorder that can have devastating visual sequelae if not managed appropriately. From an ophthalmology standpoint, ROP care is complex, since it spans multiple care settings and providers, including those in the neonatal intensive care unit (NICU), step down nurseries, and the outpatient clinic setting. This requires coordination and communication between providers, ancillary staff, and most importantly, effective communication with the patient's family members and caregivers. Often, factors related to the social determinants of health play a significant role in effective communication and care coordination with the family, and it is important for ophthalmologists to recognize these risk factors. The aim of this article is to (1) review the literature related to disparities in preterm birth outcomes and infants at risk for ROP; (2) identify barriers to ROP care and appropriate follow up, and (3) describe patient-oriented solutions and future directions for improving ROP care through a health equity lens.

Plant growth and responses of the microbial profile of the rhizosphere soil and root endosphere were investigated for avocado plants infested or not infested with Phytophthora cinnamomi and the changes were compared in plants grown with various soil additives or by spraying plants with phosphite. Soil treatments were organic mulches or silica-based mineral mulch. Reduction of root growth and visible root damage was least in the infested plants treated with phosphite or mineral mulch applied to the soil. Rhizosphere soils and root endospheres were analyzed for bacterial communities using metabarcoding. Bacterial abundance and diversity were reduced in infested rhizospheres and root endospheres. The presence or absence of mineral mulch resulted in greater diversity and larger differences in rhizosphere community composition between infested and non-infested pots than any other treatment. Some rhizosphere bacterial groups, especially Actinobacteria and Proteobacteria, had significantly higher relative abundance in the presence of Phytophthora. The bacterial communities of root endospheres were lower in abundance than rhizosphere communities and not affected by soil treatments or phosphite but increased in abundance after infection with P. cinnamomi. These findings suggested that the addition of silicate-based mineral mulch protects against Phytophthora root rot, which may be partly mediated through changes in rhizosphere bacterial community composition. However, the changes to the microbiome induced by spraying plants with phosphite are different from those resulting from the application of mineral mulch to the soil.