Integrated biomarker profiling for predicting the response of type 2 diabetes to metformin.

AIM: To explore biomarkers that can predict the response of type 2 diabetes (T2D) patients to metformin at an early stage to provide better treatment for T2D. METHODS: T2D patients with (responders) or without response (non-responders) to metformin were recruited, and their serum samples were used for metabolomic analysis to identify candidate biomarkers. Moreover, the efficacy of metformin was verified by insulin-resistant mice, and the candidate biomarkers were verified to determine the biomarkers. Five different machine learning methods were used to construct the integrated biomarker profiling (IBP) with the biomarkers to predict the response of T2D patients to metformin. RESULTS: A total of 73 responders and 63 non-responders were recruited, and 88 differential metabolites were identified in the serum samples. After being verified in mice, 19 of the 88 were considered as candidate biomarkers. Next, after metformin regulation, nine candidate biomarkers were confirmed as the biomarkers. After comparing five machine learning models, the nine biomarkers were constructed into the IBP for predicting the response of T2D patients to metformin based on the Naïve Bayes classifier, which was verified with an accuracy of 89.70%. CONCLUSIONS: The IBP composed of nine biomarkers can be used to predict the response of T2D patients to metformin, enabling clinicians to start a combined medication strategy as soon as possible if T2D patients do not respond to metformin.

Multidisciplinary Management Strategies for Long COVID: A Narrative Review.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused millions of infections to date and has led to a worldwide pandemic. Most patients had a complete recovery from the acute infection, however, a large number of the affected individuals experienced symptoms that persisted more than 3 months after diagnosis. These symptoms most commonly include fatigue, memory difficulties, brain fog, dyspnea, cough, and other less common ones such as headache, chest pain, paresthesias, mood changes, muscle pain, and weakness, skin rashes, and cardiac, endocrine, renal and hepatic manifestations. The treatment of this syndrome remains challenging. A multidisciplinary approach to address combinations of symptoms affecting multiple organ systems has been widely adopted. This narrative review aims to bridge the gap surrounding the broad treatment approaches by providing an overview of multidisciplinary management strategies for the most common long COVID conditions.

The effect of fine particulate matter (PM2.5) pollution on health inequality: an intergenerational perspective.

Air pollution poses a serious challenge to public health and simultaneously exacerbating regional & intergenerational health inequality. This research introduces PM2.5 pollution into the intergenerational health transmission model, and estimates its impact on health inequality in China using Ordered Logit Regression (OLR) and Multi-scale Geographically Weighted Regression (MGWR) model. The results indicate that PM2.5 pollution exacerbate the intergenerational health inequality, and its impacts show inconsistency across family income levels, parental health insurance status, and area of residence. Specifically, it is more difficult for offspring in low-income families to escape from the influence of unhealthy family to become upwardly mobile. Additionally, this health inequality is more significant in households in which at least one parent does not have health insurance. Moreover, the intergenerational solidification caused by PM2.5 pollution is higher in the east and lower in the west. Both the PM2.5 level and solidification effect are high in Beijing-Tianjin-Hebei region, Yangtze River Delta region and central areas of China, which is the focus of air pollution management. These findings suggest that more emphasis should be placed on family-based health promotion. In areas with high PM2.5 pollution levels, resources, subsidies and air pollution protection should be provided for less healthy families with lower incomes and no health insurance.

IAIH-PG consensus for histological criteria of AIH: Multicentre validation with focus on chronic liver diseases in China.

BACKGROUND AND AIMS: The International AIH Pathology Group (IAIH-PG) put forward the new histological criteria of autoimmune hepatitis (AIH) in 2022, which have not undergone adequate verification. In this study, we verified the applicability of the new histological criteria in the population of Chinese patients with chronic liver disease, comparing it with the simplified criteria. METHODS: The gold standard for diagnosis in all patients was based on histological findings, combined with clinical manifestations and laboratory tests and determined after a follow-up period of at least 3 years. A total of 640 patients with various chronic liver diseases from multiple centres underwent scoring using the new histological criteria and the simplified criteria, comparing their diagnostic performance. RESULTS: In this study, the new histological criteria showed a sensitivity of 73.6% and 100% for likely and possible AIH, with specificities of 100% and 69.0% respectively. The coincidence rates of possible AIH for the new histological criteria, simplified histological criteria and simplified score were 81.7%, 72.8% and 69.7% respectively. For likely AIH, the rates were 89.2%, 75.9% and 65.6% respectively. Based on the new histological criteria, all patients with AIH were correctly diagnosed. Specifically, 73.6% were diagnosed with likely AIH and 26.4% were possible AIH. Additionally, the simplified histological criteria achieved a diagnosis rate of 98.6% for AIH, while the simplified score could only diagnose 53.8% of AIH. CONCLUSIONS: Compared with the simplified score and simplified histological criteria, the sensitivity and specificity of the new histological criteria for AIH were significantly improved. The results indicate that the new histological criteria exhibit high sensitivity and specificity for diagnosing AIH in China.

A systematic review on the appropriate discounting rates for the economic evaluation of gene therapies: whether a specific approach is justified to tackle the challenges?

OBJECTIVES: Discounting the cost and effect for health intervention is a controversial topic over the last two decades. In particular, the cost-effectiveness of gene therapies is especially sensitive to the discount rate because of the substantial delay between the upfront cost incurred and long-lasing clinical benefits received. This study aims to investigate the influence of employing alternative discount rates on the incremental cost-effectiveness ratio (ICER) of gene therapies. METHODS: A systematic review was conducted to include health economic evaluations of gene therapies that were published until April 2023. RESULTS: Sensitivity or scenario analysis indicated that discount rate represented one of the most influential factors for the ICERs of gene therapies. Discount rate for cost and benefit was positively correlated with the cost-effectiveness of gene therapies, that is, a lower discount rate significantly improves the ICERs. The alternative discount rate employed in some cases could be powerful to alter the conclusion on whether gene therapies are cost-effective and acceptable for reimbursement. CONCLUSIONS: Although discount rate will have substantial influence on the ICERs of gene therapies, there lacks solid evidence to justify a different discounting rule for gene therapies. However, it is proposed that the discount rate in the reference case should be updated to reflect the real-time preference, which in turn will affect the ICERs and reimbursement of gene therapies more profoundly than conventional therapies.

Mechanism Exploration on the Immunoregulation of Allogeneic Heart Transplantation Rejection in Rats With Exosome miRNA and Proteins From Overexpressed IDO1 BMSCs.

Immunoregulation and indoleamine 2,3-dioxygenase 1 (IDO1) play pivotal roles in the rejection of allogeneic organ transplantation. This study aims to elucidate the immune-related functional mechanisms of exosomes (Exos) derived from bone marrow-derived mesenchymal stem cells (BMSCs) overexpressing IDO1 in the context of allogeneic heart transplantation (HTx) rejection. A rat model of allogeneic HTx was established. Exos were extracted after transfection with oe-IDO1 and oe-NC from rat BMSCs. Exos were administered via the caudal vein for treatment. The survival of rats was analyzed, and reverse transcription qualitative PCR (RT-qPCR) and immunohistochemistry (IHC) were employed to detect the expression of related genes. Histopathological examination was conducted using hematoxylin and eosin (HE) staining, and flow cytometry was utilized to analyze T-cell apoptosis. Proteomics and RNA-seq analyses were performed on Exos. The data were subjected to functional enrichment analysis using the R language. A protein interaction network was constructed using the STRING database, and miRWalk, TargetScan, and miRDB databases predicted the target genes, differentially expressed miRNAs, and transcription factors (TFs). Exos from BMSCs overexpressing IDO1 prolonged the survival time of rats undergoing allogeneic HTx. These Exos reduced inflammatory cell infiltration, mitigated myocardial damage, induced CD4 T-cell apoptosis, and alleviated transplantation rejection. The correlation between Exos from BMSCs overexpressing IDO1 and immune regulation was profound. Notably, 13 immune-related differential proteins (Anxa1, Anxa2, C3, Ctsb, Hp, Il1rap, Ntn1, Ptx3, Thbs1, Hspa1b, Vegfc, Dcn, and Ptpn11) and 10 significantly different miRNAs were identified. Finally, six key immune proteins related to IDO1 were identified through common enrichment pathways, including Thbs1, Dcn, Ptpn11, Hspa1b, Il1rap, and Vegfc. Thirteen TFs of IDO1-related key miRNAs were obtained, and a TF-miRNA-mRNA-proteins regulatory network was constructed. Exosome miRNA derived from BMSCs overexpressing IDO1 may influence T-cell activation and regulate HTx rejection by interacting with mRNA.

Precirrhotic Primary Biliary Cholangitis with Portal Hypertension: Bile Duct Injury Correlate.

Background/Aims: : The histological characteristics and natural history of precirrhotic primary biliary cholangitis (PBC) with portal hypertension (PH) are unclear. Our aim was to clarify the prevalence, risk factors, and histological characteristics of precirrhotic PBC patients with PH. Methods: : This retrospective study compared the clinical features, histological characteristics, and response to ursodeoxycholic acid (UDCA) between the PH and non-PH groups of precirrhotic PBC patients. Results: : Out of 165 precirrhotic PBC patients, 40 (24.2%) also had PH. According to histological stage 1, 2 and 3 disease, 5.3% (1/19), 17.3% (17/98), and 45.8% (22/48) of patients also had PH, respectively. Precirrhotic PBC with PH was significantly positively correlated with bile duct loss, degree of cytokeratin 7 positivity, and degree of fibrosis in the portal area, but significantly negatively correlated with lymphoid follicular aggregation. Compared to the non-PH group, patients in the PH group showed a higher prevalence of obliterative portal venopathy, incomplete septal fibrosis, portal tract abnormalities and non-zonal sinusoidal dilatation (p<0.05). In addition, patients with PH were more likely to present with symptoms of jaundice, ascites, epigastric discomfort, a poorer response to UDCA, and more decompensation events (p<0.05). High alkaline phosphatase levels, low white blood cell counts, high Mayo scores, and high FIB-4 index values were risk factors for precirrhotic PBC with PH. Conclusions: : Approximately 24.2% of precirrhotic PBC patients have PH, which is histologically related to the injury of bile ducts. High alkaline phosphatase levels, low white blood cell counts, high Mayo scores, and high FIB-4 index values are associated with increased risk of precirrhotic PBC with PH.

Discovery of Novel Macrocyclic MERTK/AXL Dual Inhibitors.

MERTK and AXL are members of the TAM (TYRO3, AXL, MERTK) family of receptor tyrosine kinases that are aberrantly expressed and have been implicated as therapeutic targets in a wide variety of human tumors. Dual MERTK and AXL inhibition could provide antitumor action mediated by both direct tumor cell killing and modulation of the innate immune response in some tumors such as nonsmall cell lung cancer. We utilized our knowledge of MERTK inhibitors and a structure-based drug design approach to discover a novel class of macrocyclic dual MERTK/AXL inhibitors. The lead compound 43 had low-nanomolar activity against both MERTK and AXL and good selectivity over TYRO3 and FLT3. Its target engagement and selectivity were also confirmed by NanoBRET and cell-based MERTK and AXL phosphorylation assays. Compound 43 had excellent pharmacokinetic properties (large AUC and long half-life) and mediated antitumor activity against lung cancer cell lines, indicating its potential as a therapeutic agent.

Pre-rigor salting improves gel strength and water-holding of surimi gel made from snakehead fish (Channa argus): The role of protein oxidation.

The purpose of this study was to determine the effect of pre-rigor salting on the quality characteristics of surimi gels prepared from snakehead fish muscle. Pre-rigor and post-rigor muscle were mixed with 0.3% or 3% NaCl (w/w) and made into surimi gels, respectively. Results showed that pre-rigor muscle had a higher content of ATP, longer sarcomere, higher pH and greater protein solubility. Metabolic profile suggested that pre-rigor muscle had higher content (a 28-fold increase) of antioxidants such as butyryl-l-carnitine. Transmission electron microscopy showed more damage of mitochondria in post-rigor muscle. Surimi paste from pre-rigor meat chopped with 3% NaCl generally showed greater radical scavenging ability and had higher content of free sulfhydryl. Surimi gel made from pre-rigor muscle salted with 3% NaCl showed a larger gel strength (3.18 kg*mm vs. 2.22 kg*mm) and better water-holding (86% vs. 80%) than that of post-rigor group. Based on these findings, we hypothesized that: In addition to other factors such as pH, degree of denaturation, etc., less protein oxidation in pre-rigor salted surimi also contributes to the improved gel properties.

3D-QSAR and Molecular Dynamics Study of Isoxazole Derivatives to Identify the Structural Requirements for Farnesoid X Receptor (FXR) Agonists.

The farnesoid X receptor (FXR) has been recognized as a potential drug target for the treatment of non-alcoholic fatty liver disease (NAFLD). FXR agonists benefit NAFLD by modulating bile acid synthesis and transport, lipid metabolism, inflammation, and fibrosis pathways. However, there are still great challenges involved in developing safe and effective FXR agonists. To investigate the critical factors contributing to their activity on the FXR, 3D-QSAR molecular modeling was applied to a series of isoxazole derivatives, using comparative molecular field analysis (CoMFA (q2 = 0.664, r2 = 0.960, r2pred = 0.872)) and comparative molecular similarity indices analysis (CoMSIA (q2 = 0.706, r2 = 0.969, r2pred = 0.866)) models, which demonstrated strong predictive ability in our study. The contour maps generated from molecular modeling showed that the presence of hydrophobicity at the R2 group and electronegativity group at the R3 group in these compounds is crucial to their agonistic activity. A molecular dynamics (MD) simulation was carried out to further understand the binding modes and interactions between the FXR and its agonists in preclinical or clinical studies. The conformational motions of loops L: H1/H2 and L: H5/H6 in FXR-ligand binding domain (LBD) were crucial to the protein stability and agonistic activity of ligands. Hydrophobic interactions were formed between residues (such as LEU287, MET290, ALA291, HIS294, and VAL297) in helix H3 and ligands. In particular, our study found that residue ARG331 participated in salt bridges, and HIS447 participated in salt bridges and hydrogen bonds with ligands; these interactions were significant to protein-ligand binding. Eight new potent FXR agonists were designed according to our results, and their activities were predicted to be better than that of the first synthetic FXR agonist, GW4064.

Antibiotic combinations prediction based on machine learning to multicentre clinical data and drug interaction correlation.

BACKGROUND: With increasing antibiotic resistance and regulation, the issue of antibiotic combination has been emphasised. However, antibiotic combination prescribing lacks a rapid identification of feasibility, while its risk of drug interactions is unclear. METHODS: We conducted statistical descriptions on 16 101 antibiotic coprescriptions for inpatients with bacterial infections from 2015 to 2023. By integrating the frequency and effectiveness of prescriptions, we formulated recommendations for the feasibility of antibiotic combinations. Initially, a machine learning algorithm was utilised to optimise grading thresholds and habits for antibiotic combinations. A feedforward neural network (FNN) algorithm was employed to develop antibiotic combination recommendation model (ACRM). To enhance interpretability, we combined sequential methods and DrugBank to explore the correlation between antibiotic combinations and drug interactions. RESULTS: A total of 55 antibiotics, covering 657 empirical clinical antibiotic combinations were used for ACRM construction. Model performance on the test dataset showed AUROCs of 0.589-0.895 for various antibiotic recommendation classes. The ACRM showed satisfactory clinical relevance with 61.54-73.33% prediction accuracy in a new independent retrospective cohort. Antibiotic interaction detection showed that the risk of drug interactions was 29.2% for strongly recommended and 43.5% for not recommended. A positive correlation was identified between the level of clinical recommendation and the risk of drug interactions. CONCLUSIONS: Machine learning modelling of retrospective antibiotic prescriptions habits has the potential to predict antibiotic combination recommendations. The ACRM plays a supporting role in reducing the incidence of drug interactions. Clinicians are encouraged to adopt such systems to improve the management of antibiotic usage and medication safety.

FXR/Menin-mediated epigenetic regulation of E2F3 expression controls ß-cell proliferation and is increased in islets from diabetic GK rats after RYGB.

Farnesoid X receptor (FXR) improves the function of islets, especially in the setting of Roux-en-Y gastric bypass (RYGB). Here we investigated how FXR activation regulates ß-cell proliferation and explored the potential link between FXR signaling and the menin pathway in controlling E2F3 expression, a key transcription factor for controlling adult ß-cell proliferation. Stimulation with the FXR agonist GW4064 or chenodeoxycholic acid (CDCA) increased E2F3 expression and ß-cell proliferation. Consistently, E2F3 knockdown abolished GW4064-induced proliferation. Treatment with GW4064 increased E2F3 expression in ß-cells via enhancing Steroid receptor coactivator-1 (SRC1) recruitment, increasing the pro-transcriptional acetylation of histone H3 at the E2f3 promoter. GW4064 treatment also decreased the association between FXR and menin, leading to the induction of FXR-mediated SRC1 recruitment. Mimicking the impact of FXR agonists, RYGB also increased E2F3 expression and ß-cell proliferation in GK rats and SD rats. These findings unravel the crucial role of the FXR/menin signaling in epigenetically controlling E2F3 expression and ß-cell proliferation, a mechanism possibly underlying RYGB-induced ß-cell proliferation.

Progranulin Facilitates Corneal Repair Through Dual Mechanisms of Inflammation Suppression and Regeneration Promotion.

The cornea serves as a vital protective barrier for the eye; however, it is prone to injury and damage that can disrupt corneal epithelium and nerves, triggering inflammation. Therefore, understanding the biological effects and molecular mechanisms involved in corneal wound healing and identifying drugs targeting these pathways is crucial for researchers in this field. This study aimed to investigate the therapeutic potential of progranulin (PGRN) in treating corneal injuries. Our findings demonstrated that PGRN significantly enhanced corneal wound repair by accelerating corneal re-epithelialization and re-innervation. In vitro experiments with cultured epithelial cells and trigeminal ganglion cells further revealed that PGRN stimulated corneal epithelial cell proliferation and promoted axon growth in trigeminal ganglion cells. Through RNA-sequencing (RNA-seq) analysis and other experimental techniques, we discovered that PGRN exerted its healing effects modulating Wnt signaling pathway, which played a critical role in repairing epithelial cells and promoting axon regeneration in trigeminal neurons. Importantly, our study highlighted the anti-inflammatory properties of PGRN by inhibiting the NF-κB signaling pathway, leading to decreased infiltration of macrophages. In conclusion, our findings underscored the potential of PGRN in facilitating corneal wound healing by promoting corneal epithelial cell proliferation, trigeminal ganglion cell axon regeneration, and suppressing ocular inflammation. These results suggest that PGRN could potentially expedite the healing process and improve visual outcomes in patients with corneal injuries.

Predicting the role of the human gut microbiome in type 1 diabetes using machine-learning methods.

Gut microbes is a crucial factor in the pathogenesis of type 1 diabetes (T1D). However, it is still unclear which gut microbiota are the key factors affecting T1D and their influence on the development and progression of the disease. To fill these knowledge gaps, we constructed a model to find biomarker from gut microbiota in patients with T1D. We first identified microbial markers using Linear discriminant analysis Effect Size (LEfSe) and random forest (RF) methods. Furthermore, by constructing co-occurrence networks for gut microbes in T1D, we aimed to reveal all gut microbial interactions as well as major beneficial and pathogenic bacteria in healthy populations and type 1 diabetic patients. Finally, PICRUST2 was used to predict Kyoto Encyclopedia of Genes and Genomes (KEGG) functional pathways and KO gene levels of microbial markers to investigate the biological role. Our study revealed that 21 identified microbial genera are important biomarker for T1D. Their AUC values are 0.962 and 0.745 on discovery set and validation set. Functional analysis showed that 10 microbial genera were significantly positively associated with D-arginine and D-ornithine metabolism, spliceosome in transcription, steroid hormone biosynthesis and glycosaminoglycan degradation. These genera were significantly negatively correlated with steroid biosynthesis, cyanoamino acid metabolism and drug metabolism. The other 11 genera displayed an inverse correlation. In summary, our research identified a comprehensive set of T1D gut biomarkers with universal applicability and have revealed the biological consequences of alterations in gut microbiota and their interplay. These findings offer significant prospects for individualized management and treatment of T1D.

Neutrophil-to-lymphocyte ratio associated with symptomatic saccular unruptured intracranial aneurysm.

BACKGROUND AND PURPOSE: Whether symptomatic unruptured intracranial aneurysms (UIAs) lead to change in circulating inflammation remains unclear. This study aims to evaluate the role of hematological inflammatory indicators in predicting symptomatic UIA. METHODS: Adult patients diagnosed with saccular intracranial aneurysm from March 2019 to September 2023 were recruited retrospectively. Clinical and laboratory data, including the white blood cells (WBC), neutral counts (NEUT), lymphocyte counts (LYM), and monocyte counts (MONO) of each patient, were collected. The neutrophil-to-lymphocyte ratio (NLR) and lymphocyte-to-monocyte ratio (LMR) were calculated as NLR = NEUT/LYM, LMR = LYM/MONO, SII = PLT*NEUT/LYM. The hematological inflammatory indicators were compared in symptomatic saccular and asymptomatic UIA patients. Multivariable logistic regression analyses were performed to explore the factors predicting symptomatic UIA. RESULTS: One hundred and fifty UIA patients with a mean age of 58.5 ± 12.4 were included, of which 68% were females. The NLR and LMR were significantly associated with symptomatic UIA, and the association remained in small UIAs (< 7 mm). The multiple logistic regression analysis showed that NLR was independently associated with symptomatic UIA. On ROC curve analysis, the optimal cutoff value of NLR to differentiate symptomatic from asymptomatic was 2.38. In addition, LMR was significantly associated with symptomatic UIA smaller than 7 mm. CONCLUSION: There was a significant correlation between NLR and symptomatic UIA. The NLR was independently associated with symptomatic UIA.

Effect of Helicobacter pylori infection on body fat percentage in middle-aged and elderly populations.

Obesity, which is associated with excessive accumulation of body fat, is emerging as a new public health problem. Bioelectrical impedance analysis (BIA) is a non-invasive and straightforward method to analyze body composition, providing a more accurate estimate of obesity than the commonly used body mass index. The primary objective of this study was to examine the potential impact of Helicobacter pylori (H. pylori) infection on body fat percentage in a population using cross-sectional and cohort studies. METHODS: A population of people who underwent physical examinations at Taizhou Hospital between 2017 and 2022 was included. The participants underwent various tests, including urea breath test, hematological examination, and anthropometric measurement, in addition, their body fat percentage was determined through the use of BIA. Univariate and multifactorial regression analyses were conducted to identify factors associated with excess body fat. RESULTS: There was a difference in body fat percentage between H. pylori positive and negative populations. The population was divided into young and middle-aged and elderly according to age, and H. pylori infection was found to differ only in the middle-aged and elderly population. Multifactorial logistic regression showed that H. pylori infection remained associated with excess body fat in the middle-aged and elderly population. A subsequent cohort study confirmed the association of persistent H. pylori infection with excess body fat in the population. CONCLUSION: H. pylori was negatively associated with excess body fat in middle-aged and elderly populations, and long-term H. pylori infection has a negative effect on body fat in people.

GLP-1 signaling-regulated SNAP25 is involved in improved insulin secretion in diabetic GK rats after Roux-en-Y gastric bypass surgery.

BACKGROUND: Roux-en-Y gastric bypass surgery (RYGB) improves glucose-stimulated insulin secretion (GSIS) in type 2 diabetes (T2D) patients. SNAP25 plays an essential role in GSIS. Clinical studies indicate that enhanced GLP-1 signaling is an important contributor to the improved ß-cell function in T2D. We aimed to explore whether GLP-1-regulated SNAP25 is involved in the enhanced secretory function of ß-cells in diabetic Goto-Kakizaki (GK) rats after RYGB. METHODS AND RESULTS: RYGB or sham surgery was conducted in GK rats. mRNA and protein expression of SNAP25 was assessed by qPCR and Western blot, respectively. Occupancy of CREB and acetyltransferase CBP and acetylation of histone H3 (ACH3) at the Snap25 promoter were determined using ChIP assay. RYGB led to increased SNAP25 expression and CREB phosphorylation in islets from GK rats. Increased SNAP25 improved GSIS in ß-cells cultured in high glucose conditions. Consistent with increased plasma GLP-1 after RYGB, GLP-1R agonist exendin4 increased SNAP25 expression and CREB phosphorylation in ß-cells. Mechanistically, exendin4 promoted the recruitment of CREB and CBP, thereby increasing ACH3 at the Snap25 promoter. Consistently, inhibition of CBP attenuated the effect of exendin4 on SNAP25 expression. Furthermore, the knockdown of SNAP25 diminished the increase of GSIS potentiated by chronic GLP-1 culture in INS-1 832/13 cells. CONCLUSIONS: Our findings unravel the novel mechanisms of RYGB-enhanced SNAP25 expression in ß-cells, and SNAP25 may contribute to the improved ß-cell secretory function induced by RYGB.

Predicting coronary heart disease in Chinese diabetics using machine learning.

Diabetes, a common chronic disease worldwide, can induce vascular complications, such as coronary heart disease (CHD), which is also one of the main causes of human death. It is of great significance to study the factors of diabetic patients complicated with CHD for understanding the occurrence of diabetes/CHD comorbidity. In this study, by analyzing the risk of CHD in more than 300,000 diabetes patients in southwest China, an artificial intelligence (AI) model was proposed to predict the risk of diabetes/CHD comorbidity. Firstly, we statistically analyzed the distribution of four types of features (basic demographic information, laboratory indicators, medical examination, and questionnaire) in comorbidities, and evaluated the predictive performance of three traditional machine learning methods (eXtreme Gradient Boosting, Random Forest, and Logistic regression). In addition, we have identified nine important features, including age, WHtR, BMI, stroke, smoking, chronic lung disease, drinking and MSP. Finally, the model produced an area under the receiver operating characteristic curve (AUC) of 0.701 on the test samples. These findings can provide personalized guidance for early CHD warning for diabetic populations.