Probiotics combined with atorvastatin administration in the treatment of hyperlipidemia: A randomized, double-blind, placebo-controlled clinical trial.

BACKGROUND: Hyperlipidemia is a common feature of chronic diseases. The aim of this work was designed to assess the role of probiotics (Lactobacillus casei Zhang, Bifidobactetium animalis subsp. lactis V9, and Lactobacillus plantarum P-8) in the treatment of hyperlipidemia. METHODS: Thirty three patients with hyperlipidemia were randomly divided into a probiotic group (n = 18) and a control group (n = 15). The probiotic group was administered probiotics (2 g once daily) and atorvastatin 20 mg (once daily), and the control group was administered a placebo (2 g once daily) and atorvastatin 20 mg (once daily). Serum and fecal samples were gathered for subsequent analyses. RESULTS: Time had a significant effect on the total cholesterol (TC), triglycerides (TG), and low-density lipoprotein-cholesterol (LDL-C) levels in the probiotic and control groups (P < .05). The gut microbial abundance in the probiotic group was markedly higher than that in the control group following 3-month probiotic treatment (P < .05). At the phylum level, probiotics exerted no notable effects on the relative abundance of Firmicutes, Bacteroidetes, and Actinobacteria but elevated that of Tenericutes and reduced Proteobacteria. At the genus level, probiotics increased the relative abundance of Bifidobacterium, Lactobacillus, and Akkermansia, and decreased that of Escherichia, Eggerthella, and Sutterella relative to the control group in months 1, 2, and 3 (P < .05). CONCLUSIONS: Probiotics optimize the gut microbiota structure and decrease the amount of harmful bacteria in patients with hyperlipidemia. Probiotics can influence the composition of gut microorganisms and increase their diversity and abundance in vivo. It is recommended to use probiotics combined with atorvastatin to treat patients with hyperlipidemia.

ComCo: Complementary supervised contrastive learning for complementary label learning.

Complementary label learning (CLL) is an important problem that aims to reduce the cost of obtaining large-scale accurate datasets by only allowing each training sample to be equipped with labels the sample does not belong. Despite its promise, CLL remains a challenging task. Previous methods have proposed new loss functions or introduced deep learning-based models to CLL, but they mostly overlook the semantic information that may be implicit in the complementary labels. In this work, we propose a novel method, ComCo, which leverages a contrastive learning framework to assist CLL. Our method includes two key strategies: a positive selection strategy that identifies reliable positive samples and a negative selection strategy that skillfully integrates and leverages the information in the complementary labels to construct a negative set. These strategies bring ComCo closer to supervised contrastive learning. Empirically, ComCo significantly achieves better representation learning and outperforms the baseline models and the current state-of-the-art by up to 14.61% in CLL.

Generalized robust loss functions for machine learning.

Loss function is a critical component of machine learning. Some robust loss functions are proposed to mitigate the adverse effects caused by noise. However, they still face many challenges. Firstly, there is currently a lack of unified frameworks for building robust loss functions in machine learning. Secondly, most of them only care about the occurring noise and pay little attention to those normal points. Thirdly, the resulting performance gain is limited. To this end, we put forward a general framework of robust loss functions for machine learning (RML) with rigorous theoretical analyses, which can smoothly and adaptively flatten any unbounded loss function and apply to various machine learning problems. In RML, an unbounded loss function serves as the target, with the aim of being flattened. A scale parameter is utilized to limit the maximum value of noise points, while a shape parameter is introduced to control both the compactness and the growth rate of the flattened loss function. Later, this framework is employed to flatten the Hinge loss function and the Square loss function. Based on this, we build two robust kernel classifiers called FHSVM and FLSSVM, which can distinguish different types of data. The stochastic variance reduced gradient (SVRG) approach is used to optimize FHSVM and FLSSVM. Extensive experiments demonstrate their superiority, with both consistently occupying the top two positions among all evaluated methods, achieving an average accuracy of 81.07% (accompanied by an F-score of 73.25%) for FHSVM and 81.54% (with an F-score of 75.71%) for FLSSVM.

[Heart sound classification algorithm based on time-frequency combination feature and adaptive fuzzy neural network].

Feature extraction methods and classifier selection are two critical steps in heart sound classification. To capture the pathological features of heart sound signals, this paper introduces a feature extraction method that combines mel-frequency cepstral coefficients (MFCC) and power spectral density (PSD). Unlike conventional classifiers, the adaptive neuro-fuzzy inference system (ANFIS) was chosen as the classifier for this study. In terms of experimental design, we compared different PSDs across various time intervals and frequency ranges, selecting the characteristics with the most effective classification outcomes. We compared four statistical properties, including mean PSD, standard deviation PSD, variance PSD, and median PSD. Through experimental comparisons, we found that combining the features of median PSD and MFCC with heart sound systolic period of 100-300 Hz yielded the best results. The accuracy, precision, sensitivity, specificity, and F1 score were determined to be 96.50%, 99.27%, 93.35%, 99.60%, and 96.35%, respectively. These results demonstrate the algorithm's significant potential for aiding in the diagnosis of congenital heart disease.

Causal multi-label learning for image classification.

In this paper, we investigate the problem of causal image classification with multi-label learning. As multi-label learning involves a diversity of supervision signals, it is considered a challenging issue to solve. Previous approaches have attempted to improve performance by identifying label-related image areas or exploiting the co-occurrence of labels. However, these methods are often characterized by complicated procedures, tedious computations, and a lack of intuitive interpretations. To overcome these limitations, we propose a novel approach that incorporates the concept of causal inference, which has been shown to be beneficial in other computer vision problems. Our method, called causal multi-label learning (CMLL), enables the selection of multiple objects from the original image through a multi-class attention module. These objects are then subjected to causal intervention to learn the causal relationships between different labels. Our proposed approach is both elegant and effective, with low computational cost and few parameters required for the multi-class causal intervention approach. Extensive tests and ablation studies demonstrate that the proposed method significantly improves prediction performance without a significant increase in training and inference times.

A simple and reliable instance selection for fast training support vector machine: Valid Border Recognition.

Support vector machines (SVMs) are powerful statistical learning tools, but their application to large datasets can cause time-consuming training complexity. To address this issue, various instance selection (IS) approaches have been proposed, which choose a small fraction of critical instances and screen out others before training. However, existing methods have not been able to balance accuracy and efficiency well. Some methods miss critical instances, while others use complicated selection schemes that require even more execution time than training with all original instances, thus violating the initial intention of IS. In this work, we present a newly developed IS method called Valid Border Recognition (VBR). VBR selects the closest heterogeneous neighbors as valid border instances and incorporates this process into the creation of a reduced Gaussian kernel matrix, thus minimizing the execution time. To improve reliability, we propose a strengthened version of VBR (SVBR). Based on VBR, SVBR gradually adds farther heterogeneous neighbors as complements until the Lagrange multipliers of already selected instances become stable. In numerical experiments, the effectiveness of our proposed methods is verified on benchmark and synthetic datasets in terms of accuracy, execution time and inference time.

Fucoidan from Saccharina japonica Alleviates Hyperuricemia-Induced Renal Fibrosis through Inhibiting the JAK2/STAT3 Signaling Pathway.

Fucoidan is a native sulfated polysaccharide mainly isolated from brown seaweed, with diverse pharmacological activities, such as anti-inflammatory and antifibrosis. Hyperuricemia (HUA) is a common metabolic disease worldwide and mainly causes hyperuricemic nephropathy, including chronic kidney disease and end-stage renal fibrosis. The present study investigated the protective function of fucoidan in renal fibrosis and its pharmacological mechanism. The renal fibrotic model was established with the administration of potassium oxonate for 10 weeks. The protein levels of related factors were assessed in HUA mice by an enzyme-linked immunosorbent assay (ELISA) and western blotting. The results showed that fucoidan significantly reduced the levels of serum uric acid, blood urea nitrogen (BUN), α-smooth muscle actin (α-SMA), and collagen I, and improved kidney pathological changes. Furthermore, renal fibrosis had been remarkably elevated through the inhibition of the epithelial-to-mesenchymal transition (EMT) progression after fucoidan intervention, suppressing the Janus kinase 2 (JAK2) signal transducer and activator of transcription protein 3 (STAT3) signaling pathway activation. Together, this study provides experimental evidence that fucoidan may protect against hyperuricemia-induced renal fibrosis via downregulation of the JAK2/STAT3 signaling pathway.

SMOC2 plays a role in heart failure via regulating TGF-ß1/Smad3 pathway-mediated autophagy.

Heart failure (HF) is a major global cause of morbidity and mortality. This study aimed to elucidate the role of secreted protein acidic and rich in cysteine-related modular calcium-binding protein 2 (SMOC2) in HF development and its underlying mechanism. Using a rat HF model, SMOC2 expression was examined and then knocked down via transfection to assess its impact on cardiac function and damage. The study also evaluated the effects of SMOC2 knockdown on autophagy-related molecules and the transforming growth factor beta 1 (TGF-ß1)/SMAD family member 3 (Smad3) signaling pathway. Intraperitoneal injection of the TGF-ß agonist (SRI-011381) into the HF rat model was performed to explore the SMOC2-TGF-ß1/Smad3 pathway relationship. SMOC2 expression was elevated in HF rats, while its downregulation improved cardiac function and damage. SMOC2 knockdown reversed alterations in the LC3-II/I ratio, Beclin-1, and p62 levels in HF rats. Through transmission electron microscope, we observed that SMOC2 knockdown restored autophagosome levels. Furthermore, SMOC2 downregulation inhibited the TGF-ß1/Smad3 signaling pathway, which was counteracted by SRI-011381. In conclusion, SMOC2 knockdown inhibits HF development by modulating TGF-ß1/Smad3 signaling-mediated autophagy, suggesting its potential as a therapeutic target for HF.

Linear-exponential loss incorporated deep learning for imbalanced classification.

The class imbalance issue is a pretty common and enduring topic all the time. When encountering unbalanced data distribution, conventional methods are prone to classify minority samples as majority ones, which may cause severe consequences in reality. It is crucial yet challenging to cope with such problems. In this paper, inspired by our previous work, we borrow the linear-exponential (LINEX) loss function in statistics into deep learning for the first time and extend it into a multi-class form, denoted as DLINEX. Compared with existing loss functions in class imbalance learning (e.g., the weighted cross entropy-loss and the focal loss), DLINEX has an asymmetric geometry interpretation, which can adaptively focus more on the minority and hard-to-classify samples by solely adjusting one parameter. Besides, it simultaneously achieves between and within class diversities via caring about the inherent properties of each instance. As a result, DLINEX achieves 42.08% G-means on the CIFAR-10 dataset at the imbalance ratio of 200, 79.06% G-means on the HAM10000 dataset, 82.74% F1 on the DRIVE dataset, 83.93% F1 on the CHASEDB1 dataset and 79.55% F1 on the STARE dataset The quantitative and qualitative experiments convincingly demonstrate that DLINEX can work favorably in imbalanced classifications, either at the image-level or the pixel-level.

CSAST: Content self-supervised and style contrastive learning for arbitrary style transfer.

Arbitrary artistic style transfer has achieved great success with deep neural networks, but it is still difficult for existing methods to tackle the dilemma of content preservation and style translation due to the inherent content-and-style conflict. In this paper, we introduce content self-supervised learning and style contrastive learning to arbitrary style transfer for improved content preservation and style translation, respectively. The former one is based on the assumption that stylization of a geometrically transformed image is perceptually similar to applying the same transformation to the stylized result of the original image. This content self-supervised constraint noticeably improves content consistency before and after style translation, and contributes to reducing noises and artifacts as well. Furthermore, it is especially suitable to video style transfer, due to its ability to promote inter-frame continuity, which is of crucial importance to visual stability of video sequences. For the latter one, we construct a contrastive learning that pull close style representations (Gram matrices) of the same style and push away that of different styles. This brings more accurate style translation and more appealing visual effect. A large number of qualitative and quantitative experiments demonstrate superiority of our method in improving arbitrary style transfer quality, both for images and videos.

End-to-End Multitask Learning With Vision Transformer.

Multitask learning (MTL) is a challenging puzzle, particularly in the realm of computer vision (CV). Setting up vanilla deep MTL requires either hard or soft parameter sharing schemes that employ greedy search to find the optimal network designs. Despite its widespread application, the performance of MTL models is vulnerable to under-constrained parameters. In this article, we draw on the recent success of vision transformer (ViT) to propose a multitask representation learning method called multitask ViT (MTViT), which proposes a multiple branch transformer to sequentially process the image patches (i.e., tokens in transformer) that are associated with various tasks. Through the proposed cross-task attention (CA) module, a task token from each task branch is regarded as a query for exchanging information with other task branches. In contrast to prior models, our proposed method extracts intrinsic features using the built-in self-attention mechanism of the ViT and requires just linear time on memory and computation complexity, rather than quadratic time. Comprehensive experiments are carried out on two benchmark datasets, including NYU-Depth V2 (NYUDv2) and CityScapes, after which it is found that our proposed MTViT outperforms or is on par with existing convolutional neural network (CNN)-based MTL methods. In addition, we apply our method to a synthetic dataset in which task relatedness is controlled. Surprisingly, experimental results reveal that the MTViT exhibits excellent performance when tasks are less related.

Exosomes secreted from bone marrow mesenchymal stem cells suppress cardiomyocyte hypertrophy through Hippo-YAP pathway in heart failure.

Mesenchymal stem cells-derived exosomes (MSCs-exosomes) reportedly possess cardioprotective effects. This study investigated the therapeutic potential and mechanisms of MSCs-exosomes on heart failure (HF). H9c2 cells were used to establish a cardiomyocyte hypertrophy model by angiotensin II (Ang II) treatment. Isolated MSCs-exosomes were identified by transmission electron microscope and CD63 detection. Apoptosis rate was measured by terminal deoxynucleotidyl transferase (TdT) dUTP Nick-End Labeling (TUNEL) assay. Levels of inflammatory factors [interleukin (IL)-1ß, IL-4, IL-6, and tumor necrosis factor (TNF)-α] and brain natriuretic peptide (BNP) were determined by ELISA. Expression of apoptosis-related proteins [Bax, B-cell lymphoma-2 (Bcl-2), and caspase 3] and Hippo-Yes-associated protein (YAP) pathway-related proteins [YAP, phosphor (p)-YAP, and tafazzin (TAZ)] was detected by western blotting. Cardiomyocyte hypertrophy of H9c2 cells induced by Ang II was ameliorated by MSCs-exosomes treatment. MSCs-exosomes downregulated Bax and caspase 3 levels and upregulated Bcl-2 level in Ang II-induced H9c2 cells. MSCs-exosomes also reduced the levels of BNP, IL-1ß, IL-4, IL-6, and TNF-α in Ang II-induced H9c2 cells. Meanwhile, p-YAP was downregulated and TAZ was upregulated after MSCs-exosomes administration. In conclusion, MSCs-exosomes alleviate the apoptosis and inflammatory response of cardiomyocyte via deactivating Hippo-YAP pathway in HF.

Partial label learning: Taxonomy, analysis and outlook.

Partial label learning (PLL) is an emerging framework in weakly supervised machine learning with broad application prospects. It handles the case in which each training example corresponds to a candidate label set and only one label concealed in the set is the ground-truth label. In this paper, we propose a novel taxonomy framework for PLL including four categories: disambiguation strategy, transformation strategy, theory-oriented strategy and extensions. We analyze and evaluate methods in each category and sort out synthetic and real-world PLL datasets which are all hyperlinked to the source data. Future work of PLL is profoundly discussed in this article based on the proposed taxonomy framework.

GAN-CL: Generative Adversarial Networks for Learning From Complementary Labels.

Learning from complementary labels (CLs) is a useful learning paradigm, where the CL specifies the classes that the instance does not belong to, instead of providing the ground truth as in the ordinary supervised learning scenario. In general, although it is less laborious and more efficient to collect CLs compared with ordinary labels, the less informative signal in the complementary supervision is less helpful to learn competent feature representation. Consequently, the final classifier's performance greatly deteriorates. In this article, we leverage generative adversarial networks (GANs) to derive an algorithm GAN-CL to effectively learn from CLs. In addition to the role in original GAN, the discriminator also serves as a normal classifier in GAN-CL, with the objective constructed partly with the complementary information. To further prove the effectiveness of our schema, we study the global optimality of both generator and discriminator for the GAN-CL under mild assumptions. We conduct extensive experiments on benchmark image datasets using deep models, to demonstrate the compelling improvements, compared with state-of-the-art CL learning approaches.

Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function.

Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance. Fortunately, modification of loss function appears to solve this puzzle once and for all. In this article, we propose a pixel-based adaptive weighted cross-entropy (WCE) loss in conjunction with Jaccard distance to facilitate high-quality pixel-level road crack detection. Our work profoundly demonstrates the influence of loss functions on detection outcomes and sheds light on the sophisticated consecutive improvements in the realm of crack detection. Specifically, to verify the effectiveness of the proposed loss, we conduct extensive experiments on four public databases, that is, CrackForest, AigleRN, Crack360, and BJN260. Compared to the vanilla WCE, the proposed loss significantly speeds up the training process while retaining the performance.

LLP-GAN: A GAN-Based Algorithm for Learning From Label Proportions.

Learning from label proportions (LLP) is a widespread and important learning paradigm: only the bag-level proportional information of the grouped training instances is available for the classification task, instead of the instance-level labels in the fully supervised scenario. As a result, LLP is a typical weakly supervised learning protocol and commonly exists in privacy protection circumstances due to the sensitivity in label information for real-world applications. In general, it is less laborious and more efficient to collect label proportions as the bag-level supervised information than the instance-level one. However, the hint for learning the discriminative feature representation is also limited as a less informative signal directly associated with the labels is provided, thus deteriorating the performance of the final instance-level classifier. In this article, delving into the label proportions, we bypass this weak supervision by leveraging generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN. Endowed with an end-to-end structure, LLP-GAN performs approximation in the light of an adversarial learning mechanism without imposing restricted assumptions on distribution. Accordingly, the final instance-level classifier can be directly induced upon the discriminator with minor modification. Under mild assumptions, we give the explicit generative representation and prove the global optimality for LLP-GAN. In addition, compared with existing methods, our work empowers LLP solvers with desirable scalability inheriting from deep models. Extensive experiments on benchmark datasets and a real-world application demonstrate the vivid advantages of the proposed approach.

Nicotinamide riboside ameliorates high-fructose-induced lipid metabolism disorder in mice via improving FGF21 resistance in the liver and white adipose tissue.

Fructose has been reported to acutely elevate the circulating fibroblast growth factor 21 (FGF21) levels, which ultimately causes FGF21 resistance. FGF21 resistance is suggested to result in lipid metabolism disorder. Nicotinamide riboside (NR) can alleviate lipid metabolism disorder in mice. It is unknown whether NR supplementation would alleviate lipid metabolism disorder in high-fructose exposed mice via improving FGF21 resistance. In this study, C57BL/6J mice were given 20% fructose solution for free drinking with the supplementation of NR in 400 mg kg-1 day-1. The results showed that NR supplementation decreased the serum and hepatic lipid profile levels. The increase of lipid droplets in the liver and the size of adipose cells in WAT induced by a high-fructose diet were alleviated by the addition of NR. NR supplementation increased the NAD+/NADH ratio and activated the SIRT1/NF-κB pathway. The down-regulation of NF-κB is accompanied by a decrease in inflammation, which may increase the expression of the FGF21 receptor complex, namely KLB and FGFR, then restore its downstream signaling cascade, including ERK phosphorylation and EGR1 and c-FOS expression, and ultimately improve FGF21 resistance. With the FGF21 function recovery, hepatic PGC-1α expression was up-regulated, and hepatic SREBP-1c expression was down-regulated, resulting in decreased lipogenesis. Furthermore, restoration of the FGF21 signaling pathway also led to increased expression of ATGL and HSL in WAT, which promotes lipolysis. In conclusion, we found that NR supplementation could ameliorate high-fructose-induced lipid metabolism disorder by improving FGF21 resistance in the liver and WAT, which may be related to the regulation of inflammation mediated by the SIRT1/NF-κB signaling pathway.

Protective effect of fucoidan against iron overload and ferroptosis-induced liver injury in rats exposed to alcohol.

This study was aimed to explore the effects of fucoidan on iron overload and ferroptosis-induced liver injury, and the underlying mechanisms in rats exposed to alcohol. Sprague-Dawley rats were used to establish alcoholic liver injury model by intragastric administration with alcohol for 16 weeks. The results showed that fucoidan treatment reversed alcohol-induced increases in reactive oxygen species and malondialdehyde levels, and increased glutathione peroxidase and glutathione levels, thus protecting against liver damage. Long-term alcohol feeding resulted in abnormal increase of serum ferritin, liver total iron and the "free" iron levels. Fucoidan treatment reduced serum ferritin level and alleviated liver iron deposition. Fucoidan reversed the reduction of hepcidin induced by alcohol exposure and decreased divalent metal transporter 1 (DMT1) and ferroportin1 (FPN1) expressions in the duodenum. Electron microscope observation of liver tissues showed that alcohol exposure induced ferroptosis changes in the liver. However, fucoidan treatment could alleviate alcohol-induced ferroptosis via upregulating the expressions of p62, Nrf2, SLC7A11 and GPX4. The liver endogenous metabolites analysis by liquid chromatography and mass spectrometry showed that after fucoidan intervention, mineral absorption, biosynthesis of amino acids pathways and lipid metabolism were changed. Fucoidan intervention reduced the levels of oxidized glutathione and regulated the levels of phosphatidylethanolamines in liver tissues. Our data showed that fucoidan supplementation could inhibit iron load via regulating hepcidin-intestinal DMT1/FPN1 axis, alleviate the liver oxidative damage and protect hepatocytes from ferroptosis induced by long-term alcohol exposure through upregulating p62/Nrf2/SLC7A11 pathway in rats.

Antarctic krill oil ameliorates liver injury in rats exposed to alcohol by regulating bile acids metabolism and gut microbiota.

Bile acids (BAs) metabolism plays an important role in alcohol liver disease through the gut microflora-bile acids-liver axis. Antarctic Krill Oil (AKO) has protective effects on the liver, while whether AKO can protect against liver injury caused by alcohol is unclear. This study investigated the effects of AKO on BAs metabolism and intestinal microbiota in a rat model of alcohol-induced liver disease. Sprague-Dawley rats were randomly divided into five groups: control group, model group, low-dose AKO-treatment group (100 mg/kg/d), high-dose AKO-treatment group (200 mg/kg/d), and AKO control group (200 mg/kg/d). Administration of alcohol (8 to 10 mL/kg/d) for 16 weeks induced liver injury in rats. We found that AKO supplementation significantly protected the liver against alcohol-induced injury, evidenced by allayed hepatic histopathological changes, and inhibited the alcohol-induced elevation of serum biochemical indices. Furthermore, AKO could regulate BAs metabolism by activating the intestinal-hepatic FXR-FGF15-FGFR4 signaling axis with subsequently decreased cholesterol 7α-hydroxylase (CYP7A1) and sterol 12α-hydroxylase (CYP8B1) levels, reduced hepatic BAs production, decreased serum BAs level and increased fecal excretion of BAs. Additionally, 16S rDNA sequencing revealed that the gut microbiome richness and composition were altered in alcohol-treated rats in comparison to the control and AKO-administrated rats. Spearman's correlation analysis showed that differential gut bacterial genera correlated with the levels of BAs profiles in the serum, liver, and feces. These findings suggested that AKO dietary supplementation may protect against alcohol-induced liver injury through modulating BAs metabolism and altering the gut microbiome.

Mapping the risk distribution of Borrelia burgdorferi sensu lato in China from 1986 to 2020: a geospatial modelling analysis.

Lyme borreliosis, recognized as one of the most important tick-borne diseases worldwide, has been increasing in incidence and spatial extent. Currently, there are few geographic studies about the distribution of Lyme borreliosis risk across China. Here we established a nationwide database that involved Borrelia burgdorferi sensu lato (B. burgdorferi) detected in humans, vectors, and animals in China. The eco-environmental factors that shaped the spatial pattern of B. burgdorferi were identified by using a two-stage boosted regression tree model and the model-predicted risks were mapped. During 1986-2020, a total of 2,584 human confirmed cases were reported in 25 provinces. Borrelia burgdorferi was detected from 35 tick species with the highest positive rates in Ixodes granulatus, Hyalomma asiaticum, Ixodes persulcatus, and Haemaphysalis concinna ranging 20.1%-24.0%. Thirteen factors including woodland, NDVI, rainfed cropland, and livestock density were determined as important drivers for the probability of B. burgdorferi occurrence based on the stage 1 model. The stage 2 model identified ten factors including temperature seasonality, NDVI, and grasslands that were the main determinants used to distinguish areas at high or low-medium risk of B. burgdorferi, interpreted as potential occurrence areas within the area projected by the stage 1 model. The projected high-risk areas were not only concentrated in high latitude areas, but also were distributed in middle and low latitude areas. These high-resolution evidence-based risk maps of B. burgdorferi was first created in China and can help as a guide to future surveillance and control and help inform disease burden and infection risk estimates.