Zipping up obesity: Chylomicrons are specialized particles that carry dietary fats from the intestine to the bloodstream for absorption into the body. Lacteals are lymphatic vessels that act as the highway for chylomicron transport, but it is unclear how passage occurs. Zhang et al. report that two endothelial cell receptors, neuropilin-1 (NRP1) and vascular endothelial growth factor receptor 1 (VEGFR1, also known as FLT1), are required to convert the entry spaces between lacteals from open junctions to closed, zipped structures (see the Perspective by McDonald). Mice that were fed a high-fat diet were subsequently rendered resistant to weight gain if NRP1 and FLT1 were inactivated. Science , this issue p. 599 ; see also p. 551

Background: This study aimed to evaluate the potential of human–machine interaction (HMI) in a deep learning software for discerning the malignancy of choroidal melanocytic lesions based on fundus photographs. Methods: The study enrolled individuals diagnosed with a choroidal melanocytic lesion at a tertiary clinic between 2011 and 2023, resulting in a cohort of 762 eligible cases. A deep learning-based assistant integrated into the software underwent training using a dataset comprising 762 color fundus photographs (CFPs) of choroidal lesions captured by various fundus cameras. The dataset was categorized into benign nevi, untreated choroidal melanomas, and irradiated choroidal melanomas. The reference standard for evaluation was established by retinal specialists using multimodal imaging. Trinary and binary models were trained, and their classification performance was evaluated on a test set consisting of 100 independent images. The discriminative performance of deep learning models was evaluated based on accuracy, recall, and specificity. Results: The final accuracy rates on the independent test set for multi-class and binary (benign vs. malignant) classification were 84.8% and 90.9%, respectively. Recall and specificity ranged from 0.85 to 0.90 and 0.91 to 0.92, respectively. The mean area under the curve (AUC) values were 0.96 and 0.99, respectively. Optimal discriminative performance was observed in binary classification with the incorporation of a single imaging modality, achieving an accuracy of 95.8%. Conclusions: The deep learning models demonstrated commendable performance in distinguishing the malignancy of choroidal lesions. The software exhibits promise for resource-efficient and cost-effective pre-stratification.

There is early evidence of extraocular systemic signals effecting function and morphology in neovascular age-related macular degeneration (nAMD). The prospective, cross-sectional BIOMAC study is an explorative investigation of peripheral blood proteome profiles and matched clinical features to uncover systemic determinacy in nAMD under anti-vascular endothelial growth factor intravitreal therapy (anti-VEGF IVT). It includes 46 nAMD patients stratified by the level of disease control under ongoing anti-VEGF treatment. Proteomic profiles in peripheral blood samples of every patient were detected with LC-MS/MS mass spectrometry. The patients underwent extensive clinical examination with a focus on macular function and morphology. In silico analysis includes unbiased dimensionality reduction and clustering, a subsequent annotation of clinical features, and non-linear models for recognition of underlying patterns. The model assessment was performed using leave-one-out cross validation. The findings provide an exploratory demonstration of the link between systemic proteomic signals and macular disease pattern using and validating non-linear classification models. Three main results were obtained: (1) Proteome-based clustering identifies two distinct patient subclusters with the smaller one (n = 10) exhibiting a strong signature for oxidative stress response. Matching the relevant meta-features on the individual patient’s level identifies pulmonary dysfunction as an underlying health condition in these patients. (2) We identify biomarkers for nAMD disease features with Aldolase C as a putative factor associated with superior disease control under ongoing anti-VEGF treatment. (3) Apart from this, isolated protein markers are only weakly correlated with nAMD disease expression. In contrast, applying a non-linear classification model identifies complex molecular patterns hidden in a high number of proteomic dimensions determining macular disease expression. In conclusion, so far unconsidered systemic signals in the peripheral blood proteome contribute to the clinically observed phenotype of nAMD, which should be examined in future translational research on AMD.

Background: To longitudinally investigate the impact of best-corrected visual acuity (BCVA), non-modifiable risk factors, modifiable habits, and disease course on the vision-related quality of life (VRQOL) of patients with central serous chorioretinopathy (CSCR). Methods: We longitudinally enrolled 109 CSCR patients and 42 non-diseased control participants from our clinic. In addition to clinical examination, the National Eye Institute Visual Function Questionnaire (NEI-VFQ-39) was employed for assessments, along with questions pertaining to various aspects of lifestyle habits. Alongside the cross-sectional analyses, the VRQOL of CSCR patients was tracked longitudinally over one year. Results: Consistent with prior studies, CSCR patients reported a lower VRQOL compared to non-diseased participants (79.3 ± 14.1 for CSCR and 92.6 ± 7.6 for CTRL; p < 0.0001), but fared better than those with other ocular conditions. No significant associations were observed between BCVA, any non-modifiable risk factors, or interventions, and VRQOL, both in cross-sectional and longitudinal contexts (cross-sectional BCVA with VRQOL: Pearson r correlation 0.173, p = 0.072). Among modifiable habits, sleep duration (p = 0.036), perceived quality of sleep rhythm (p = 0.006), hours of physical activity (p = 0.036), and the presence of non-ocular conditions (p = 0.001) were significantly correlated with VRQOL. Notably, enhanced sleep duration (+4.232 vs. −0.041 non-enhanced at 3 months, p = 0.033) and higher perceived quality of sleep rhythm (+6.248 vs. +0.094 non-higher, p = 0.009) showed a positive correlation with improved VRQOL over time. Conclusions: The study reveals that VRQOL has minimal dependence on BCVA or other clinical factors, suggesting that patient-reported outcome measures (PROMs) could serve as alternative endpoints in clinical studies for more holistic patient welfare assessment. Furthermore, the strong correlations between VRQOL and modifiable lifestyle habits indicate potential therapeutic value in targeting these areas for intervention.

Purpose: Retinal manifestations have been described in COVID-19 patients, but it is unknown whether SARS-CoV-2, the causal agent in COVID-19, can directly infect posterior ocular tissues. Here, we investigate SARS-CoV-2 host factor gene expression levels and their distribution across retinal and choroidal cell types. Methods: Query of single-cell RNA sequencing data from human retina and choroid. Results: We find no relevant expression of two key genes involved in SARS-CoV-2 entry, ACE2 and TMPRSS2, in retinal cell types. By contrast, scarce expression levels could be detected in choroidal vascular cells. Conclusion: Given the current understanding of viral host cell entry, these findings suggest a low vulnerability of the posterior eye segment to SARS-CoV-2 with a potential weak spot in the vasculature, which could play a putative causative role in ocular lesions in COVID-19 patients. This may qualify the vasculature of the human posterior eye segment as an in vivo biomarker for life-threatening vascular occlusions in COVID-19 patients.

Purpose: To investigate the xenobiotic profiles of patients with neovascular age-related macular degeneration (nAMD) undergoing anti-vascular endothelial growth factor (anti-VEGF) intravitreal therapy (IVT) to identify biomarkers indicative of clinical phenotypes through advanced AI methodologies. Methods: In this cross-sectional observational study, we analyzed 156 peripheral blood xenobiotic features in a cohort of 46 nAMD patients stratified by choroidal neovascularization (CNV) control under anti-VEGF IVT. We employed Liquid Chromatography—Tandem Mass Spectrometry (LC–MS/MS) for measurement and leveraged an AI-driven iterative Random Forests (iRF) approach for robust pattern recognition and feature selection, aligning molecular profiles with clinical phenotypes. Results: AI-augmented iRF models effectively refined the metabolite spectrum by discarding non-predictive elements. Perfluorooctanesulfonate (PFOS) and Ethyl β-glucopyranoside were identified as significant biomarkers through this process, associated with various clinically relevant phenotypes. Unlike single metabolite classes, drug metabolites were distinctly correlated with subretinal fluid presence. Conclusions: This study underscores the enhanced capability of AI, particularly iRF, in dissecting complex metabolomic data to elucidate the xenobiotic landscape of nAMD and environmental impact on the disease. The preliminary biomarkers discovered offer promising directions for personalized treatment strategies, although further validation in broader cohorts is essential for clinical application.