Background: For medical artificial intelligence (AI) training and validation, human expert labels are considered the gold standard that represents the correct answers or desired outputs for a given data set. These labels serve as a reference or benchmark against which the model's predictions are compared.
Objective: This study aimed to assess the accuracy of a custom deep learning (DL) algorithm on classifying diabetic retinopathy (DR) and further demonstrate how label errors may contribute to this assessment in a nationwide DR-screening program.
As the healthcare community increasingly harnesses the power of generative artificial intelligence (AI), critical issues of security, privacy and regulation take centre stage. In this paper, we explore the security and privacy risks of generative AI from model-level and data-level perspectives. Moreover, we elucidate the potential consequences and case studies within the domain of ophthalmology.
View Article and Find Full Text PDFArtificial intelligence (AI) models have shown great accuracy in health screening. However, for real-world implementation, high accuracy may not guarantee cost-effectiveness. Improving AI's sensitivity finds more high-risk patients but may raise medical costs while increasing specificity reduces unnecessary referrals but may weaken detection capability.
View Article and Find Full Text PDFTolerogenic dendritic cells are promising for restoring immune homeostasis and may be an alternative therapy for autoimmune diseases such as rheumatoid arthritis. The kynurenine pathway is a vital mechanism that induces tolerance in dendritic cells (DCs). Tryptophan 2,3-dioxygenase (TDO2) is an important rate-limiting enzyme in the kynurenine pathway and participates in immune regulation.
View Article and Find Full Text PDFPurpose: The purpose of this study was to improve the automated diagnosis of glaucomatous optic neuropathy (GON), we propose a generative adversarial network (GAN) model that translates Optain images to Topcon images.
Methods: We trained the GAN model on 725 paired images from Topcon and Optain cameras and externally validated it using an additional 843 paired images collected from the Aravind Eye Hospital in India. An optic disc segmentation model was used to assess the disparities in disc parameters across cameras.
Background And Aims: The high mortality rate and huge disease burden of coronary heart disease (CHD) highlight the importance of its early detection and timely intervention. Given the non-invasive nature of fundus photography and recent development in the quantification of retinal microvascular parameters with deep learning techniques, our study aims to investigate the association between incident CHD and retinal microvascular parameters.
Methods: UK Biobanks participants with gradable fundus images and without a history of diagnosed CHD at recruitment were included for analysis.
It has been proven that intra-articular injection of mesenchymal stromal cells (MSCs) can alleviate cartilage damage in osteoarthritis (OA) by differentiating into chondrocytes and protecting inherent cartilage. However, the mechanism by which the OA articular microenvironment affects MSCs' therapeutic efficiency is yet to be fully elucidated. The aryl hydrocarbon receptor (AHR) is a ligand-activated transcription factor involved in various cellular processes, such as osteogenesis and immune regulation.
View Article and Find Full Text PDFBackground: Plasma metabolomic profile is disturbed in dementia patients, but previous studies have discordant conclusions.
Methods: Circulating metabolomic data of 110,655 people in the UK Biobank study were measured with nuclear magnetic resonance technique, and incident dementia records were obtained from national health registers. The associations between plasma metabolites and dementia were estimated using Cox proportional hazard models.
Background: Dual sensory impairment is affecting over 10% of older adults worldwide. However, the long-term effect of dual sensory impairment (DSI) on the risk of mortality remains controversial. We aim to investigate the impact of single or/and dual sensory impairment on the risk of mortality in a large population-based sample of the adult in the UK with 14-years of follow-up.
View Article and Find Full Text PDFBackground: Retinal parameters could reflect systemic vascular changes. With the advances of deep learning technology, we have recently developed an algorithm to predict retinal age based on fundus images, which could be a novel biomarker for aging and mortality. Therefore, we aim to investigate associations of retinal age gap with arterial stiffness index and incident cardiovascular disease (CVD).
View Article and Find Full Text PDFFront Aging Neurosci
June 2022
Introduction: The relationship between sensory impairments and the risk of dementia is inconclusive. We aim to investigate the association of visual impairment (VI), hearing impairment (HI), and dual sensory impairment (DSI) with incident dementia.
Methods: The UK Biobank study recruited more than 500,000 participants aged 40-69 years across the United Kingdom.
Purpose: To evaluate the nature and association of different phenotypes associated with ABCA4 mutations in Chinese.
Methods: All patients were recruited from our pediatric and genetic eye clinic. Detailed ocular phenotypes were characterized.
Aryl hydrocarbon receptor (Ahr) is thought to be a crucial factor that regulates immune responses, which may be involved in the pathogenesis of autoimmune inflammation including rheumatoid arthritis (RA). The results of our group in recent years have shown that Paeoniflorin-6'-O-benzene sulfonate (code: CP-25), a novel ester derivative of paeoniflorin, has a good effect on improving RA animal models. However, whether the anti-arthritis effect of CP-25 is related to Ahr remains unclear.
View Article and Find Full Text PDFIntroduction: retinal age derived from fundus images using deep learning has been verified as a novel biomarker of ageing. We aim to investigate the association between retinal age gap (retinal age-chronological age) and incident Parkinson's disease (PD).
Methods: a deep learning (DL) model trained on 19,200 fundus images of 11,052 chronic disease-free participants was used to predict retinal age.
Background And Purpose: Abnormal kynurenine (Kyn) metabolism has been closely linked to the pathogenesis of rheumatoid arthritis (RA). The aims of this study were to investigate the role of tryptophan 2,3-dioxygenase 2 (TDO2), a rate-limiting enzyme that converts tryptophan (Trp) to Kyn, in regulating fibroblast-like synoviocyte (FLS)-mediated synovial inflammation in autoimmune arthritis.
Experimental Approach: The expression of TDO2 was determined by immunohistochemistry, confocal laser scanning fluorescence microscopy, imaging flow cytometry and Western blot.
Front Med (Lausanne)
November 2021
To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR). We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable DR. Study images were obtained from the Lingtou Cohort Study, and captured at participant enrollment in 2009-2010 ("baseline images") and annual follow-up between 2011 and 2017.
View Article and Find Full Text PDFStudy Objectives: To investigate the association between daytime napping and retinal microcirculation.
Methods: This is a cross-sectional study from a prospective population-based cohort. 2,662 participants were recruited after quota sampling.
Background: Tumor necrosis factor (TNF)-α inhibitors represented by Etanercept (a fusion protein containing soluble TNF receptor II (sTNFRII) and the Fc segment of human IgG1) play a pivotal role in Rheumatoid arthritis (RA) treatment. However, long-term use increases the risk of infection and tumors for their systemic inhibition of TNF-α, which disrupts the regular physiological function of this molecular. Mesenchymal stem cells (MSCs)-based delivery system provides new options for RA treatment with their "homing" and immune-regulation capacities, whereas inflammatory environment (especially TNF-α) is not conducive to MSCs' therapeutic effects by inducing apoptosis/autophagy.
View Article and Find Full Text PDFTryptophan 2,3-dioxygenase (TDO2) was an initial rate-limiting enzyme of the kynurenine (Kyn) pathway in tryptophan (Trp) metabolism. We undertook this study to determine a comprehensive analysis of TDO2 expression in immune cells and assess the characterization of immune cell phenotype in TDO2 knockout mice. The expression of TDO2 in various tissues of DBA/1 mice was detected by quantitative real-time PCR (qPCR) and immunohistochemistry.
View Article and Find Full Text PDFMoyamoya disease (MMD) is a chronic cerebrovascular disease that frequently results in intracranial ischemia or hemorrhage. Its concurrence with varying ophthalmic findings is relatively rare yet may lead to irreversible blindness. We performed a search and review of the literature to characterize the relevance of MMD (excluding moyamoya syndrome) and ophthalmic findings.
View Article and Find Full Text PDFFront Public Health
December 2020
The outbreak of the current 2019 novel coronavirus (2019-nCoV, now named SARS-CoV-2) infection has become a worldwide health threat. Currently, more information is needed so as to further understand the transmission and clinical characteristics of 2019-nCoV infection and the infection control procedures required. Recently, the role of the eye in transmitting 2019-nCoV has been intensively discussed.
View Article and Find Full Text PDFBackground: Epithelial-mesenchymal transition (EMT) of the retinal pigment epithelial (RPE) cells is a critical step in the pathogenesis of proliferative vitreoretinopathy (PVR). Some microRNAs (miRNAs) participate in regulating RPE cell EMT as post-transcriptional regulators. However, the function of miR-194 in RPE cell EMT remains elusive.
View Article and Find Full Text PDF