Biobank Dataset Research Articles

Association between vegetable intake and major depressive disorder: results from National Health and Nutrition Examination Survey 2005-2018 and bidirectional two-sample Mendelian randomisation.

This study aimed to evaluate the association between vegetable intake and major depressive disorder (MDD) through cross-sectional analysis and bidirectional two-sample Mendelian randomisation (MR). Cross-sectional analysis was conducted on National Health and Nutrition Examination Survey (NHANES) data from 2005 to 2018 and the corresponding Food Patterns Equivalents Database (FPED). Genome-wide association study (GWAS) data were obtained from UK Biobank and Psychiatric Genomics Consortium (PGC) dataset. Logistic regression analysis was performed after calculating the weights of the samples. Inverse variance weighted, MR-Egger and weighted median methods were used to evaluate the causal effects. A Patient Health Questionnaire-9 score ≥ 10 was considered to indicate MDD. Low vegetable intake was defined as < 2 cups of vegetables per day. 30 861 U.S. adults from NHANES. The GWAS data sample size related to vegetable intake were comprised 448 651 and 435 435 cases respectively, while the GWAS data sample size associated with MDD encompassed 500 199 cases. There were 23 249 (75·33 %) participants with low vegetable intake. The relationship between vegetable intake and MDD was nonlinear. In the multivariate model adjusted for sex, age, education, marital status, poverty income ratio, ethnicity and BMI, participants with low vegetable intake were associated with an increased risk of MDD (OR = 1·53, 95 % CI (1·32, 1·77), P < 0·001). Bidirectional MR showed no causal effects between vegetable intake and MDD. Cross-sectional analysis identified a significant relationship between vegetable intake and MDD, whereas the results from bidirectional two-sample MR did not support a causal role.

Causal relationship between circulating immune cells and gastric cancer: a bidirectional Mendelian randomization analysis using UK Biobank and FinnGen datasets.

The role of immune cells in cancer pathogenesis remains controversial due to conflicting reports, potentially arising from various confounding factors. Emerging evidence suggests that cancer can also influence immune cell populations and functions, making it challenging to investigate their causal relationship. Traditional observational studies often fail to eliminate all confounding factors and are prone to reverse causality. Therefore, we employ Mendelian randomization (MR) to determine the causal relationship between immune cells and cancer, as this method can identify causal relationships independent of confounding factors and avoid reverse causality. Genome-wide association study (GWAS) summary statistics on immune traits, encompassing 310 immune cell phenotypes, were obtained from 3,757 European individuals, with peripheral blood immune cells tested using flow cytometry. GWAS summary statistics for gastric cancer were derived from 476,116 European individuals across two large-scale biobanks: the UK Biobank and FinnGen. Gastric cancer was identified by the International Classification of Diseases, 9th Revision (ICD-9), and 10th Revision (ICD-10) codes. Significant single nucleotide polymorphisms (SNPs) for immune traits were extracted at a threshold of P<1×10-5, while a threshold of P<5×10-8 was used for gastric cancer GWAS data. Linkage imbalance-based clumping was performed to obtain independent SNPs, and those with F<10 were excluded to mitigate weak instrument bias. Phenoscanner V2 was used to exclude SNPs directly associated with potential confounders or outcomes. Two-sample MR was conducted using five MR methods, with inverse-variance-weighted (IVW) as the primary analysis method. A false discovery rate (FDR) correction was used to reduce the likelihood of type 1 errors. In addition, we conducted MR-Egger intercept tests and Cochran's Q tests. The numbers of CD4-CD8- T cells and IgD-CD27- B cells were positively correlated with the development of gastric cancer, with odds ratios (ORs) of 1.15 [95% confidence interval (CI), 1.07-1.24; P<0.001; PFDR=0.041; IVW method] and 1.07 (95% CI, 1.03-1.11; P=0.001; PFDR=0.187; IVW method), respectively. However, the percentage of IgD+CD24- B cells in lymphocytes were negatively associated with the development of gastric cancer (OR =0.90; 95% CI, 0.84-0.96; P=0.002; PFDR=0.187; IVW method). MR analysis of the above three immune cell phenotypes showed no significant heterogeneity or horizontal pleiotropy. In the reverse MR analysis, gastric cancer was not causally associated with any of the immune cell phenotypes. Circulating CD4-CD8- T cells and IgD-CD27- B cells are positively correlated with the development of gastric cancer, while the percentage of IgD+CD24- B cells in lymphocytes are negatively correlated. These findings provide insight into the relationship between immune cells and gastric cancer pathogenesis and may serve as a basis for the development of immunotherapies for gastric cancer.

Application of a deep-learning marker for morbidity and mortality prediction derived from retinal photographs: a cohort development and validation study

Biological ageing markers are useful to risk stratify morbidity and mortality more precisely than chronological age. In this study, we aimed to develop a novel deep-learning-based biological ageing marker (referred to as RetiPhenoAge hereafter) using retinal images and PhenoAge, a composite biomarker of phenotypic age. We used retinal photographs from the UK Biobank dataset to train a deep-learning algorithm to predict the composite score of PhenoAge. We used a deep convolutional neural network architecture with multiple layers to develop our deep-learning-based biological ageing marker, as RetiPhenoAge, with the aim of identifying patterns and features in the retina associated with variations of blood biomarkers related to renal, immune, liver functions, inflammation, and energy metabolism, and chronological age. We determined the performance of this biological ageing marker for the prediction of morbidity (cardiovascular disease and cancer events) and mortality (all-cause, cardiovascular disease, and cancer) in three independent cohorts (UK Biobank, the Singapore Epidemiology of Eye Diseases [SEED], and the Age-Related Eye Disease Study [AREDS] from the USA). We also compared the performance of RetiPhenoAge with two other known ageing biomarkers (hand grip strength and adjusted leukocyte telomere length) and one lifestyle factor (physical activity) for risk stratification of mortality and morbidity. We explored the underlying biology of RetiPhenoAge by assessing its associations with different systemic characteristics (eg, diabetes or hypertension) and blood metabolite levels. We also did a genome-wide association study to identify genetic variants associated with RetiPhenoAge, followed by expression quantitative trait loci mapping, a gene-based analysis, and a gene-set analysis. Cox proportional hazards models were used to estimate the hazard ratios (HRs) and corresponding 95% CIs for the associations between RetiPhenoAge and the different morbidity and mortality outcomes. Retinal photographs for 34 061UK Biobank participants were used to train the model, and data for 9429participants from the SEED cohort and for 3986participants from the AREDS cohort were included in the study. RetiPhenoAge was associated with all-cause mortality (HR 1·92 [95% CI 1·42-2·61]), cardiovascular disease mortality (1·97 [1·02-3·82]), cancer mortality (2·07 [1·29-3·33]), and cardiovascular disease events (1·70[1·17-2·47]), independent of PhenoAge and other possible confounders. Similar findings were found in the two independent cohorts (HR 1·67 [1·21-2·31] for cardiovascular disease mortality in SEED and 2·07 [1·10-3·92] in AREDS). RetiPhenoAge had stronger associations with mortality and morbidity than did hand grip strength, telomere length, and physical activity. We identified two genetic variants that were significantly associated with RetiPhenoAge (single nucleotide polymorphisms rs3791224 and rs8001273), and were linked to expression quantitative trait locis in various tissues, including the heart, kidneys, and the brain. Our new deep-learning-derived biological ageing marker is a robust predictor of mortality and morbidity outcomes and could be used as a novel non-invasive method to measure ageing. Singapore National Medical Research Council and Agency for Science, Technology and Research, Singapore.

Well-Being and Cardiovascular Health: Insights From the UK Biobank Study.

Cardiovascular diseases (CVDs) are a leading global health concern. Emerging evidence suggests a potential protective role of well-being in reducing CVD risk. We conducted a cohort analysis using the UK Biobank data set, encompassing 121 317 participants. We assessed the well-being of participants using a well-being index derived from baseline questionnaires. Well-being categories were derived by latent class analysis using general happiness and satisfaction with family, friendships, health, and finance situations. The relationship between well-being and 4 major CVDs was analyzed using Cox proportional hazards models and Mendelian randomization. The study also examined the impacts of well-being on lifestyle factors and inflammatory markers, and its mediating role in the well-being-CVD relationship. Higher well-being was associated with a significantly reduced risk of various CVDs. Latent class analysis identified 4 distinct well-being groups (low, variable, moderate-to-high, and high satisfaction), with higher satisfaction levels generally associated with lower risk of CVDs. Mendelian randomization suggested potential causal relationships between well-being and reduced risk of CVDs. Participants with greater well-being demonstrated healthier behaviors and lower levels of inflammatory markers. Mediation analysis indicated that lifestyle and inflammatory markers partially mediated the relationship between well-being and CVDs. This study demonstrates a robust inverse association between well-being and the risks of CVDs, suggesting that enhancing well-being may be a viable strategy for CVD prevention. The role of lifestyle factors and inflammation as a mediator provides insight into possible biological pathways linking psychological states and cardiovascular health.

Causal association between hyperthyroidism and risk of gastroesophageal reflux or esophageal cancer: a bidirectional Mendelian randomization investigation.

Emerging observational studies indicated an association between hyperthyroidism and gastrointestinal disorders. However, it remains unclear whether this association is causal, particularly in the case of gastroesophageal reflux (GERD) and esophageal cancer. To assess the potential causal relationship between hyperthyroidism and GERD or esophageal cancer, we conducted a bidirectional 2-sample Mendelian randomization study. Independent genetic instruments for hyperthyroidism from the UK Biobank (N case=3,545 and N control=459,388) and public genome-wide association study (GWAS) dataset (N case=3,731 and N control=480,867) were used to investigate the association with esophageal cancer in the UK Biobank study (N case=740 and N control=372,016) and GERD in the public GWAS database (N case=20,381 and N control=464,217). Four different approaches (inverse variance weighted (IVW), weighted mode, MR-Egger, and weighted median regression) were used to ensure that our results more reliable. Additional sensitivity analyses were also performed to validate our results. When hyperthyroidism was considered as the exposure factor, it appeared to act as a protective factor for GERD (ORIVW = 0.88, 95% CI, 0.79-0.99, P = 0.039), while as a risk factor for esophageal cancer (ORIVW = 1.03, 95% CI, 1.01-1.06, P = 0.003). However, there is no evidence supporting a reverse causal relationship between genetic susceptibility to hyperthyroidism and GERD or esophageal cancer. Our findings provided genetic evidence supporting bidirectional causal relationships between hyperthyroidism and GERD or esophageal cancer. These results substantiate certain discoveries from previous observational studies on a causal level and provide insight into relevant genetic susceptibility factors.

Quality control of cardiac magnetic resonance imaging segmentation, feature tracking, aortic flow, and native T1 analysis using automated batch processing in the UK Biobank study.

Automated algorithms are regularly used to analyse cardiac magnetic resonance (CMR) images. Validating data output reliability from this method is crucial for enabling widespread adoption. We outline a visual quality control (VQC) process for image analysis using automated batch processing. We assess the performance of automated analysis and the reliability of replacing visual checks with statistical outlier (SO) removal approach in UK Biobank CMR scans. We included 1987 CMR scans from the UK Biobank COVID-19 imaging study. We used batch processing software (Circle Cardiovascular Imaging Inc.-CVI42) to automatically extract chamber volumetric data, strain, native T1, and aortic flow data. The automated analysis outputs (∼62 000 videos and 2000 images) were visually checked by six experienced clinicians using a standardized approach and a custom-built R Shiny app. Inter-observer variability was assessed. Data from scans passing VQC were compared with a SO removal QC method in a subset of healthy individuals (n = 1069). Automated segmentation was highly rated, with over 95% of scans passing VQC. Overall inter-observer agreement was very good (Gwet's AC2 0.91; 95% confidence interval 0.84, 0.94). No difference in overall data derived from VQC or SO removal in healthy individuals was observed. Automated image analysis using CVI42 prototypes for UK Biobank CMR scans demonstrated high quality. Larger UK Biobank data sets analysed using these automated algorithms do not require in-depth VQC. SO removal is sufficient as a QC measure, with operator discretion for visual checks based on population or research objectives.

Replacement of sedentary behavior with various physical activities and the risk of all-cause and cause-specific mortality

BackgroundSedentary behavior (SB) has emerged as a significant health concern that deserves attention. This study aimed to examine the associations between prolonged sedentary behavior and the risk of all-cause and cause-specific mortality as well as to explore desirable alternatives to sitting in terms of physical activity (PA).MethodsTwo prospective cohort investigations were conducted using the UK Biobank and NHANES datasets, with a total of 490,659 and 33,534 participants, respectively. Cox proportional hazards regression models were used to estimate the associations between SB and the risk of all-cause and cause-specific mortality due to cancer, cardiovascular disease (CVD), respiratory diseases, and digestive diseases. In addition, we employed isotemporal substitution models to examine the protective effect of replacing sitting with various forms of PA.ResultsDuring the average follow-up times of 13.5 and 6.7 years, 36,109 and 3057 deaths were documented in the UK Biobank and NHANES, respectively. Both cohorts demonstrated that, compared with individuals sitting less than 5 h per day, individuals with longer periods of sitting had higher risks of all-cause and cause-specific mortality due to cancer, CVD, and respiratory diseases but not digestive diseases. Moreover, replacing SB per day with PA, even substituting 30 min of walking for pleasure, reduced the risk of all-cause mortality by 3.5% (hazard ratio [HR] 0.965, 95% confidence interval [CI] 0.954–0.977), whereas cause-specific mortality from cancer, CVD, and respiratory diseases was reduced by 1.6% (HR 0.984, 95% CI 0.968–1.000), 4.4% (HR 0.956, 95% CI 0.930–0.982), and 15.5% (HR 0.845, 95% CI 0.795–0.899), respectively. Furthermore, the protective effects of substitution became more pronounced as the intensity of exercise increased or the alternative duration was extended to 1 h.ConclusionsSB was significantly correlated with substantially increased risks of all-cause mortality and cause-specific mortality from cancer, CVD, and respiratory diseases. However, substituting sitting with various forms of PA, even for short periods involving relatively light and relaxing physical activity, effectively reduced the risk of both overall and cause-specific mortality.Graphical

Validation of neuron activation patterns for artificial intelligence models in oculomics

Recent advancements in artificial intelligence (AI) have prompted researchers to expand into the field of oculomics; the association between the retina and systemic health. Unlike conventional AI models trained on well-recognized retinal features, the retinal phenotypes that most oculomics models use are more subtle. Consequently, applying conventional tools, such as saliency maps, to understand how oculomics models arrive at their inference is problematic and open to bias. We hypothesized that neuron activation patterns (NAPs) could be an alternative way to interpret oculomics models, but currently, most existing implementations focus on failure diagnosis. In this study, we designed a novel NAP framework to interpret an oculomics model. We then applied our framework to an AI model predicting systolic blood pressure from fundus images in the United Kingdom Biobank dataset. We found that the NAP generated from our framework was correlated to the clinically relevant endpoint of cardiovascular risk. Our NAP was also able to discern two biologically distinct groups among participants who were assigned the same predicted systolic blood pressure. These results demonstrate the feasibility of our proposed NAP framework for gaining deeper insights into the functioning of oculomics models. Further work is required to validate these results on external datasets.

Using Data-Driven Algorithms with Large-Scale Plasma Proteomic Data to Discover Novel Biomarkers for Diagnosing Depression.

Given recent technological advances in proteomics, it is now possible to quantify plasma proteomes in large cohorts of patients to screen for biomarkers and to guide the early diagnosis and treatment of depression. Here we used CatBoost machine learning to model and discover biomarkers of depression in UK Biobank data sets (depression n = 4,479, healthy control n = 19,821). CatBoost was employed for model construction, with Shapley Additive Explanations (SHAP) being utilized to interpret the resulting model. Model performance was corroborated through 5-fold cross-validation, and its diagnostic efficacy was evaluated based on the area under the receiver operating characteristic (AUC) curve. A total of 45 depression-related proteins were screened based on the top 20 important features output by the CatBoost model in six data sets. Of the nine diagnostic models for depression, the performance of the traditional risk factor model was improved after the addition of proteomic data, with the best model having an average AUC of 0.764 in the test sets. KEGG pathway analysis of 45 screened proteins showed that the most significant pathway involved was the cytokine-cytokine receptor interaction. It is feasible to explore diagnostic biomarkers of depression using data-driven machine learning methods and large-scale data sets, although the results require validation.

Foundation model-driven distributed learning for enhanced retinal age prediction.

The retinal age gap (RAG) is emerging as a potential biomarker for various diseases of the human body, yet its utility depends on machine learning models capable of accurately predicting biological retinal age from fundus images. However, training generalizable models is hindered by potential shortages of diverse training data. To overcome these obstacles, this work develops a novel and computationally efficient distributed learning framework for retinal age prediction. The proposed framework employs a memory-efficient 8-bit quantized version of RETFound, a cutting-edge foundation model for retinal image analysis, to extract features from fundus images. These features are then used to train an efficient linear regression head model for predicting retinal age. The framework explores federated learning (FL) as well as traveling model (TM) approaches for distributed training of the linear regression head. To evaluate this framework, we simulate a client network using fundus image data from the UK Biobank. Additionally, data from patients with type 1 diabetes from the UK Biobank and the Brazilian Multilabel Ophthalmological Dataset (BRSET) were utilized to explore the clinical utility of the developed methods. Our findings reveal that the developed distributed learning framework achieves retinal age prediction performance on par with centralized methods, with FL and TM providing similar performance (mean absolute error of 3.57 ± 0.18 years for centralized learning, 3.60 ± 0.16 years for TM, and 3.63 ± 0.19 years for FL). Notably, the TM was found to converge with fewer local updates than FL. Moreover, patients with type 1 diabetes exhibited significantly higher RAG values than healthy controls in all models, for both the UK Biobank and BRSET datasets (P < .001). The high computational and memory efficiency of the developed distributed learning framework makes it well suited for resource-constrained environments. The capacity of this framework to integrate data from underrepresented populations for training of retinal age prediction models could significantly enhance the accessibility of the RAG as an important disease biomarker.

Abstract P136: Phosphorylation and regulation of URAT1 by insulin and NaCl: a possible mechanism linking insulin resistance and excessive salt intake to hyperuricemia

Objective: Insulin resistance (IR) is the key environmental factor associated with hyperuricemia; however, the underlying mechanisms are not fully understood. Although several studies suggested that excessive salt intake results in hyperuricemia, the association still remains controversial. Focusing on urate transporter 1 (URAT1), we here investigated the mechanisms by which insulin and salt intake contribute to hyperuricemia. Methods: In a large UK Biobank (UKB) dataset involving 377,358 participants, we evaluated the association of TyG index (a surrogate of IR) and habitual salt intake with serum uric acid levels using multivariable regression models. We addressed whether single nucleotide polymorphisms (SNPs) that influence URAT1 expression (eQTL) modify the association of TyG index with serum uric acid levels. We also analyzed underlying mechanisms by using HEK cells expressing hURAT1. Results: In UKB dataset, TyG index and habitual salt intake were significantly and independently associated with elevated serum uric acid levels (P &lt; 0.05). From previous studies and imputation accuracy, we extracted an eQTL SNP for SLC22A12 gene and found that there is a positive interaction between TyG Index and the eQTL SNP. As post-translational modification is the key mechanism that enables adaptation to environmental changes, we evaluated the contribution of phosphorylation by AGC kinases, such as Akt, as possible downstream effectors of insulin signaling and salt-sensing pathway. Western blotting with phospho-Akt substrate motif antibody confirmed URAT1 phosphorylation and identified T350 and T408 as candidate sites. Among them, URAT1 carrying non-phosphorylatable A408 substitution (T408A-URAT1) suppressed glycosylation and plasma membrane translocation, while T350A had no effect. By using kinase screen assay involving 53 AGC and related Ser/Thr kinases, we found that SGK1, PKA, and PKG also phosphorylated URAT1-T408. Insulin and NaCl loading induced Akt and SGK1 expression respectively, which resulted in URAT1 phosphorylation and increased cell-surface membrane expression; this effect was abolished in T408A-URAT1. Finally, we found that URAT1-T408 phosphorylation was also detected in human kidney sections. Conclusion: IR and excessive salt intake contribute to hyperuricemia, and the effect is in part mediated by hURAT1. Mechanistically, insulin and NaCl promote membrane trafficking of URAT1 by inducing T408 phosphorylation through Akt and SGK1, respectively.

Posttraumatic stress disorder increases thrombosis risk: Evidence from a biobank data set.

Depression and anxiety are linked to deep venous thrombosis (DVT) and posttraumatic disorder (PTSD) increases risk of venous thromboembolism in women. However, the mechanisms underlying this relationship remain unknown. We hypothesized that PTSD would associate with increased DVT risk, that neuroimmune mechanisms would mediate the PTSD-DVT link, and that these associations would be stronger in women. This cohort study included N = 106 427 participants from a large biobank. PTSD and DVT were defined using ICD-10 codes. A subset (N = 1520) underwent imaging, from which we assessed stress-associated neural activity (SNA). High-sensitivity C-reactive protein (hs-CRP) levels and heart rate variability (HRV) were used as indicators of systemic inflammation and autonomic activity, respectively. Linear, logistic, and Cox regressions and mediation analyses were used to test our hypotheses. Of 106 427 participants, 4192 (3.9%) developed DVT. PTSD associated with increased DVT risk (HR [95% CI]: 1.66 [1.34, 2.07], p < .001), and this finding remained significant after adjustment for age, sex, and traditional DVT risk factors. When analyzed separately by sex, PTSD was significantly associated with DVT risk in women but not men. Further, heightened SNA and lower HRV mediated the effect of PTSD on DVT risk. Results suggest that individuals with PTSD are at increased risk for DVT, and that risk is higher in women. This relationship was partially driven by alterations in stress-associated neural activity and autonomic function, suggesting potential targets for preventive therapies. Future studies are needed to investigate whether intervening on PTSD-DVT mechanisms has downstream beneficial effects on DVT, especially among women.

A scalable adaptive quadratic kernel method for interpretable epistasis analysis in complex traits.

Our knowledge of the contribution of genetic interactions (epistasis) to variation in human complex traits remains limited, partly due to the lack of efficient, powerful, and interpretable algorithms to detect interactions. Recently proposed approaches for set-based association tests show promise in improving the power to detect epistasis by examining the aggregated effects of multiple variants. Nevertheless, these methods either do not scale to large Biobank data sets or lack interpretability. We propose QuadKAST, a scalable algorithm focused on testing pairwise interaction effects (quadratic effects) within small to medium-sized sets of genetic variants (window size ≤100) on a trait and provide quantified interpretation of these effects. Comprehensive simulations show that QuadKAST is well-calibrated. Additionally, QuadKAST is highly sensitive in detecting loci with epistatic signals and accurate in its estimation of quadratic effects. We applied QuadKAST to 52 quantitative phenotypes measured in ≈300,000 unrelated white British individuals in the UK Biobank to test for quadratic effects within each of 9515 protein-coding genes. We detect 32 trait-gene pairs across 17 traits and 29 genes that demonstrate statistically significant signals of quadratic effects (accounting for the number of genes and traits tested). Across these trait-gene pairs, the proportion of trait variance explained by quadratic effects is comparable to additive effects, with five pairs having a ratio >1. Our method enables the detailed investigation of epistasis on a large scale, offering new insights into its role and importance.

Integrating Multi-Organ Imaging-Derived Phenotypes and Genomic Information for Predicting the Occurrence of Common Diseases.

As medical imaging technologies advance, these tools are playing a more and more important role in assisting clinical disease diagnosis. The fusion of biomedical imaging and multi-modal information is profound, as it significantly enhances diagnostic precision and comprehensiveness. Integrating multi-organ imaging with genomic information can significantly enhance the accuracy of disease prediction because many diseases involve both environmental and genetic determinants. In the present study, we focused on the fusion of imaging-derived phenotypes (IDPs) and polygenic risk score (PRS) of diseases from different organs including the brain, heart, lung, liver, spleen, pancreas, and kidney for the prediction of the occurrence of nine common diseases, namely atrial fibrillation, heart failure (HF), hypertension, myocardial infarction, asthma, type 2 diabetes, chronic kidney disease, coronary artery disease (CAD), and chronic obstructive pulmonary disease, in the UK Biobank (UKBB) dataset. For each disease, three prediction models were developed utilizing imaging features, genomic data, and a fusion of both, respectively, and their performances were compared. The results indicated that for seven diseases, the model integrating both imaging and genomic data achieved superior predictive performance compared to models that used only imaging features or only genomic data. For instance, the Area Under Curve (AUC) of HF risk prediction was increased from 0.68 ± 0.15 to 0.79 ± 0.12, and the AUC of CAD diagnosis was increased from 0.76 ± 0.05 to 0.81 ± 0.06.

Metadata information and fundus image fusion neural network for hyperuricemia classification in diabetes

ObjectiveIn diabetes mellitus patients, hyperuricemia may lead to the development of diabetic complications, including macrovascular and microvascular dysfunction. However, the level of blood uric acid in diabetic patients is obtained by sampling peripheral blood from the patient, which is an invasive procedure and not conducive to routine monitoring. Therefore, we developed deep learning algorithm to detect noninvasively hyperuricemia from retina photographs and metadata of patients with diabetes and evaluated performance in multiethnic populations and different subgroups. Materials and methodsTo achieve the task of non-invasive detection of hyperuricemia in diabetic patients, given that blood uric acid metabolism is directly related to estimated glomerular filtration rate(eGFR), we first performed a regression task for eGFR value before the classification task for hyperuricemia and reintroduced the eGFR regression values into the baseline information. We trained 3 deep learning models: (1) metadata model adjusted for sex, age, body mass index, duration of diabetes, HbA1c, systolic blood pressure, diastolic blood pressure; (2) image model based on fundus photographs; (3)hybrid model combining image and metadata model. Data from the Shanghai General Hospital Diabetes Management Center (ShDMC) were used to develop (6091 participants with diabetes) and internally validated (using 5-fold cross-validation) the models. External testing was performed on an independent dataset (UK Biobank dataset) consisting of 9327 participants with diabetes. ResultsFor the regression task of eGFR, in ShDMC dataset, the coefficient of determination (R2) was 0.684±0.07 (95 % CI) for image model, 0.501±0.04 for metadata model, and 0.727±0.002 for hybrid model. In external UK Biobank dataset, a coefficient of determination (R2) was 0.647±0.06 for image model, 0.627±0.03 for metadata model, and 0.697±0.07 for hybrid model. Our method was demonstrably superior to previous methods. For the classification of hyperuricemia, in ShDMC validation, the area, under the curve (AUC) was 0.86±0.013for image model, 0.86±0.013 for metadata model, and 0.92±0.026 for hybrid model. Estimates with UK biobank were 0.82±0.017 for image model, 0.79±0.024 for metadata model, and 0.89±0.032 for hybrid model. ConclusionThere is a potential deep learning algorithm using fundus photographs as a noninvasively screening adjunct for hyperuricemia among individuals with diabetes. Meanwhile, combining patient's metadata enables higher screening accuracy. After applying the visualization tool, it found that the deep learning network for the identification of hyperuricemia mainly focuses on the fundus optic disc region.

Genotype-First Approach Identifies an Association between rs28374544/FOG2S657G and Liver Disease through Alterations in mTORC1 Signaling.

Metabolic dysfunction-associated Fatty Liver Disease (MAFLD) has emerged as one of the leading cardiometabolic diseases. Friend of GATA2 (FOG2) is a transcriptional co-regulator that has been shown to regulate hepatic lipid metabolism and accumulation. Using meta-analysis from several different biobank datasets, we identified a coding variant of FOG2 (rs28374544, A1969G, S657G) predominantly found in individuals of African ancestry (minor allele frequency~20%), which is associated with liver failure/cirrhosis phenotype and liver injury. To gain insight into potential pathways associated with this variant, we interrogated a previously published genomics dataset of 38 human induced pluripotent stem cell (iPSCs) lines differentiated into hepatocytes (iHeps). Using Differential Gene Expression Analysis and Gene Set Enrichment Analysis, we identified the mTORC1 pathway as differentially regulated between iHeps from individuals with and without the variant. Transient lipid-based transfections were performed on the human hepatoma cell line (Huh7) using wild-type FOG2 and FOG2S657G and demonstrated that FOG2S657G increased mTORC1 signaling, de novo lipogenesis, and cellular triglyceride synthesis and mass. In addition, we observed a significant downregulation of oxidative phosphorylation in FOG2S657G cells in fatty acid-loaded cells but not untreated cells, suggesting that FOG2S657G may also reduce fatty acid to promote lipid accumulation. Taken together, our multi-pronged approach suggests a model whereby the FOG2S657G may promote MAFLD through mTORC1 activation, increased de novo lipogenesis, and lipid accumulation. Our results provide insights into the molecular mechanisms by which FOG2S657G may affect the complex molecular landscape underlying MAFLD.

Stacking models of brain dynamics to improve prediction of subject traits in fMRI

Abstract Beyond structural and time-averaged functional connectivity brain measures, modelling the way brain activity dynamically unfolds can add important information to our understanding and characterisation of individual cognitive traits. One approach to leveraging this information is to extract features from models of brain network dynamics to predict individual traits. However, these predictions are susceptible to variability due to factors such as variation in model estimation induced by the choice of hyperparameters. We suggest that, rather than merely being statistical noise, this variability may be useful in providing complementary information that can be leveraged to improve prediction accuracy. To leverage this variability, we propose the use of stacking, a prediction-driven approach for model selection. Specifically, we combine predictions developed from multiple hidden Markov models—a probabilistic generative model of network dynamics that identifies recurring patterns of brain activity—to demonstrate that stacking can slightly improve the accuracy and robustness of cognitive trait predictions. By comparing analysis from the Human Connectome Project and UK Biobank datasets, we show that stacking is relatively effective at improving prediction accuracy and robustness when there are enough subjects, and that the effectiveness of combining predictions from static and dynamic functional connectivity approaches depends on the length of scan per subject. We also show that the effectiveness of stacking predictions is driven by the accuracy and diversity in the underlying model estimations.

Impact of hyperuricemia on CKD risk beyond genetic predisposition in a population-based cohort study

The bidirectional effect of hyperuricemia on chronic kidney disease (CKD) underscores the importance of hyperuricemia as a risk factor for CKD. We evaluated the effect of hyperuricemia on the presence and development of CKD after considering genetic background by calculating polygenic risk scores (PRSs). We employed genome-wide association study summary statistics—excluding the United Kingdom Biobank (UKB) datasets among published CKD Gen Consortium papers—to calculate the PRSs for CKD in white background subjects. To validate PRS performance, we divided the UKB into two datasets to validate and test the data. We used logistic regression analysis to evaluate the association between hyperuricemia and CKD, and performed Kaplan–Meier survival analysis exclusively for subjects with available follow-up data. In total, 438,253 clinical data and 4,307,940 single nucleotide polymorphisms from 459,155 samples were included. We observed a significant positive association between PRS and CKD and the presence and development of CKD. Hyperuricemia significantly increased CKD risk (adjusted odds ratio 1.55, 95% confidence interval 1.48–1.61). The impact of hyperuricemia on CKD was maintained irrespective of PRS range. In addition, negative interaction between hyperuricemia and PRS for CKD was found. Survival analysis indicates that the presence of hyperuricemia significantly increased the risk of CKD development. The PRS for CKD thoroughly reflects the risk of CKD development. Hyperuricemia is a significant indicator of CKD risk, even after incorporating the genetic risk score for CKD. Irrespective of genetic risk, patients with a prospective risk of developing CKD require uric acid monitoring and management.

Plasma Proteomes and Genome-Wide Association Data for Causal Protein Identification in Stroke.

Plasma proteins are promising biomarkers and potential drug targets for stroke. This study aimed to explore whether there is a causal relationship between plasma proteins and subtypes of stroke using a Mendelian randomization (MR) approach. A two-sample bidirectional Mendelian randomization approach was employed to investigate the causal link between plasma proteins and stroke. Data on plasma proteins were obtained from three studies, including INTERVAL, and pooled stroke information was sourced from the MEGASTROKE consortium and the UK Biobank dataset, covering four subtypes of stroke. MR analyses were primarily conducted using inverse variance weighting, and sensitivity analyses were also performed. Finally, potential reverse causality was assessed using bidirectional MR. We identified two proteins causally associated with stroke: one as a potential therapeutic target and another as a protective factor. CXCL8 was found to be positively associated with the risk of developing large-artery atherosclerotic (LAA) stroke (OR, 1.005; 95% CI 1.001 to 1.010; p = 0.022), whereas TNFRSF11b was negatively correlated with the risk of developing LAA stroke (OR, 0.937; 95% CI 0.892 to 0.984; p = 0.010), independently of other stroke subtypes. Reverse bivariate analysis did not indicate that ischemic stroke was causally associated with CXCL8 and TNFRSF11b. There is a causal relationship between CXCL8 and TNFRSF11b with LAA stroke, independent of other subtypes. This study offers a new perspective on the genetics of stroke.

Modeling 3D Cardiac Contraction and Relaxation With Point Cloud Deformation Networks.

Global single-valued biomarkers, such as ejection fraction, are widely used in clinical practice to assess cardiac function. However, they only approximate the heart's true 3D deformation process, thus limiting diagnostic accuracy and the understanding of cardiac mechanics. Metrics based on 3D shape have been proposed to alleviate these shortcomings. In this work, we present the Point Cloud Deformation Network (PCD-Net) as a novel geometric deep learning approach for direct modeling of 3D cardiac mechanics of the biventricular anatomy between the extreme ends of the cardiac cycle. Its encoder-decoder architecture combines a low-dimensional latent space with recent advances in point cloud deep learning for effective multi-scale feature learning directly on flexible and memory-efficient point cloud representations of the cardiac anatomy. We first evaluate the PCD-Net's predictive capability for both cardiac contraction and relaxation on a large UK Biobank dataset of over 10,000 subjects and find average Chamfer distances between the predicted and ground truth anatomies below the pixel resolution of the underlying image acquisition. We then show the PCD-Net's ability to capture subpopulation-specific differences in 3D cardiac mechanics between normal and myocardial infarction (MI) subjects and visualize abnormal phenotypes between predicted normal 3D shapes and corresponding observed ones. Finally, we demonstrate that the PCD-Net's learned 3D deformation encodings outperform multiple clinical and machine learning benchmarks by 11% in terms of area under the receiver operating characteristic curve for the tasks of prevalent MI detection and incident MI prediction and by 7% in terms of Harrell's concordance index for MI survival analysis.