Machine learning applied to serum and cerebrospinal fluid metabolomes revealed altered arginine metabolism in neonatal sepsis with meningoencephalitis

A sensitive method for the profiling of phenyl- and indole-containing metabolites in blood serum and cerebrospinal fluid samples of patients with severe brain damage using ultra-high-pressure liquid chromatography-tandem mass spectrometry

The metabolic profiling of biological fluids is important in understanding the various biochemical processes in the human body. The content of aromatic metabolites, including microbial ones, in the blood and cerebrospinal fluid, can provide essential information reflecting infectious processes, both systemic and in the central nervous system. A sensitive method with protein precipitation and sample concentration using ultra-high-pressure liquid chromatography-tandem mass spectrometry was proposed and subsequently validated to determine the number of aromatic metabolites of phenylalanine, tyrosine, and tryptophan in the blood serum and cerebrospinal fluid at 2.0-3.7 × 103 nmol/L. Reference values of 4-hydroxybenzoic, 3-(4-hydroxyphenyl)propionic, and indole-3-carboxylic acids were measured in the blood serum of healthy donors (n = 48). Profile of eleven phenyl- and indole-containing acids was revealed in the serum samples (n = 29) of the patients with long-term sequelae of severe brain damage and in the cerebrospinal fluid samples (n = 29) of the post-neurosurgical patients using different sample preparation methods to measure analytes in a wide (nmol/L and μmol/L) concentration range. Statistically significant differences in concentrations of most analytes were detected in serum samples of patients compared to healthy donors (p ≤ 0.03) and in concentrations of 3-phenyllactic, 3-(4-hydroxyphenyl)lactic, indole-3-lactic, and indole-3-carboxylic acids in cerebrospinal fluid samples of patients with signs of secondary bacterial meningitis compared to those without signs of secondary bacterial meningitis (p ≤ 0.027).

Utilizing drip metabolites and predictive modeling for non-destructive freshness assessment in pork loin

This study validated the use of pork drip metabolites for non-destructive freshness prediction. The pork loin was vacuum-packaged and stored for 27 days at 4 °C. The pH, drip loss, total aerobic bacterial counts (TAB), microbial composition and drip metabolites were examined. LASSO and Random Forest (RF) were selected and used for variable selection, while Ridge regression and Support Vector Regression were utilized to develop predictive models. Validation was performed using leave-one-out cross-validation. LASSO and RF selected 13 and 10 metabolites, respectively. The metabolites selected by each method were trained using Ridge regression and SVR. Each of the four trained models achieved R2 values of over 0.9. In the validation step, the model trained by Ridge regression using drip metabolites selected through LASSO showed the lowest RMSE value of 0.283 log CFU/g. Therefore, selected drip metabolites can be used to predict TAB and microbial composition of pork loin through mathematical modeling.

A Metabolic Signature Specific to the Patients with Type 2 Diabetes and its Association with the Pathogenesis of Diabetic-Foot Syndrome

Oxidative stress and protein nonenzymatic glycation are key factors in diabetic-foot syndrome pathogenesis. Type 2 diabetes (T2DM) progression involves excessive gluconolactone (GDL) production, linked to endothelial injury and diabetic arteriosclerosis. This study explored GDL's role in diabetic-foot syndrome using high-performance liquid chromatography-tandem mass spectrometry to analyze sera from 75 T2DM patients (including 32 with diabetic-foot) and 36 healthy controls. GDL levels were significantly higher in T2DM patients and correlated with increased hemoglobin A1c glycation and reactive oxygen species production in endothelial cells, suggesting GDL's role in accelerating macrovascular arteriosclerosis and diabetic-foot syndrome. These findings highlight GDL's potential as a diagnostic biomarker and therapeutic target for diabetic macrovascular complications.

Gut microbiota metabolites impact immunologic responses to antiretroviral therapy in HIV-infected men who have sex with men

BACKGROUND

The association between gut microbial metabolites and immunologic non-response among people living with HIV (PLHIV) receiving antiretroviral therapy (ART) has not been well established. We aimed to characterize gut microbial metabolites among HIV-infected men who have sex with men (MSM) with different immunologic responses.

METHODS

We recruited HIV-infected MSM from Guangzhou Eighth People's Hospital and HIV-uninfected MSM (healthy controls, HC) from a local MSM community-based organization in Guangzhou between June and October 2021. HIV-infected MSM were grouped into good immunological responders (GIR) (CD4 + T cell count ≥ 350 cells/μl) and poor immunological responders (PIR) (CD4 + T cell count < 350 cells/μl) after 24 months of ART treatment. Online questionnaires and stool samples were collected. Microbial metabolites in stool were obtained through ultra-performance liquid chromatography coupled to a tandem mass spectrometry (UPLC-MS/MS) system. Differential metabolites were identified and analyzed using the Kruskal-Wallis test, followed by pairwise comparisons with the Wilcoxon rank-sum test. The least absolute selection and shrinkage operator was used to select potential metabolites biomarkers.

RESULTS

A total of 51 HC, 56 GIR, and 42 PIR were included. No statistically significant differences were observed in the median time since HIV diagnosis and ART duration between GIR and PIR. Among the 174 quantified metabolites, 81 significantly differed among HC, GIR, and PIR (P < 0.05). Among differential metabolites, indole-3-propionic acid significantly decreased from HC (11.39 nmol/g) and GIR (8.16 nmol/g) to PIR (6.50 nmol/g). The pathway analysis showed that tryptophan metabolism differed significantly between GIR and PIR (P < 0.05). Four potential metabolites biomarkers (dimethylglycine, cinnamic acid, 3-hydroxyisovaleric acid, and propionic acid) that distinguish GIR and PIR were identified, and the corresponding area under the curve based on potential biomarkers was 0.773 (95% CI: 0.675-0.871).

CONCLUSIONS

This study identified significant differences in gut microbial metabolites among HIV-infected MSM with different immunologic responses. These results indicate the potential of gut microbial metabolites as novel disease progression markers and therapeutic targets.

GENETIC INSIGHTS INTO SEPSIS: MENDELIAN RANDOMIZATION ANALYSIS OF CEREBROSPINAL FLUID METABOLITES

ABSTRACT

Background: Sepsis, a life-threatening response to infection leading to systemic inflammation and organ dysfunction, has been hypothesized to be influenced by metabolic alterations in cerebrospinal fluid (CSF). Despite extensive research, the specific metabolic pathways contributing to sepsis remain unclear. This study aims to elucidate the causal relationships between CSF metabolites and sepsis risk using Mendelian randomization (MR), offering insights that could lead to novel therapeutic strategies. Methods: We conducted a two-sample MR analysis using genetic variants as instrumental variables (IVs) to investigate 338 CSF metabolites identified through a genome-wide association study. Data on sepsis-related outcomes were extracted from the genome-wide association study catalog encompassing 486,484 individuals of European descent. IVs were rigorously selected based on stringent genetic association and linkage disequilibrium criteria. Statistical analyses, including inverse variance weighting (IVW) and weighted median methods, were performed using the "TwoSampleMR" package in R software, supplemented by comprehensive sensitivity analyses to ensure the robustness of our findings. Results: Our analysis identified 19 CSF metabolites causally associated with sepsis risk. Notably, metabolites such as 1-palmitoyl-2-stearoyl-gpc (16:0/18:0) and 2-hydroxyglutarate showed significant negative correlations with sepsis risk. The reverse MR analysis further revealed that sepsis could negatively impact certain CSF metabolite levels, particularly ribonate, suggesting a bidirectional relationship. These relationships were substantiated by rigorous statistical testing and sensitivity analyses confirming the absence of horizontal pleiotropy and the stability of our results across various MR methods. Conclusions: This study demonstrates significant causal associations between specific CSF metabolites and the risk of developing sepsis, highlighting the potential for these metabolites to serve as biomarkers or therapeutic targets. The bidirectional nature of these findings also suggests that sepsis itself may alter metabolic profiles, offering further avenues for intervention.

Mechanisms of Homoarginine: Looking Beyond Clinical Outcomes

PURPOSE

Homoarginine (hArg) is an arginine metabolite that has been known for years, but its physiological role in the body remains poorly understood. For instance, it is well known that high hArg concentrations in the blood are protective against several disease states, yet the mechanisms behind these health benefits are unclear. This review compiles what is known about hArg, namely its synthetic pathways, its role in different diseases and conditions, and its proposed mechanisms of action in humans and experimental animals.

FINDINGS

Previous work has identified multiple pathways that control hArg synthesis and degradation in the body. Furthermore, endogenous hArg can modulate the cardiovascular system, with decreased hArg being associated with cardiovascular complications and increased mortality. Studies also suggest that hArg could serve as a diagnostic biomarker for a variety of immune, pancreatic, renal, and hepatic dysfunctions. Finally, in women, hArg concentrations rapidly increase throughout pregnancy and there are suggestions that alterations in hArg could indicate pregnancy complications like pre-eclampsia.

SUMMARY

Homoarginine is an under-appreciated amino acid with potential wide-ranging roles in systemic health, pregnancy, and pathophysiology. Although recent research has focused on its health or disease associations, there is a need for more investigations into understanding the mechanistic pathways by which hArg may operate. This could be aided using metabolomics, which provides a comprehensive approach to correlating multiple metabolites and metabolic pathways with physiological effects. Increasing our knowledge of hArg's roles in the body could pave the way for its routine use as both a diagnostic and therapeutic molecule.

Development and internal validation of a metabolism-related model for predicting 30-day mortality in neonatal sepsis

OBJECTIVE

Neonatal sepsis, a severe infectious disease associated with high mortality rates, is characterized by metabolic disturbances that play a crucial role in its progression. The aim of this study is to develop a metabolism-related model for assessing 30-day mortality in neonatal sepsis.

METHODS

The clinical data of neonatal sepsis at Ganzhou Women and Children's Health Care Hospital from January 2019 to December 2022 were retrospectively analyzed. Neonatal sepsis cases were divided into survival and non-survival groups. Multivariate logistic regression analysis was used to identify the independent risk factors for 30-day mortality. A nomogram model was developed based on these risk factors. Internal validation of the model was performed using 10-fold cross-validation. The predictive performance was evaluated through receiver operating characteristic (ROC) curves and calibration curve analyses. Decision curve analysis (DCA) was conducted to evaluate the clinical applicability of the developed model.

RESULTS

The study included a total of 156 cases of neonatal sepsis. Multivariate logistic regression analysis revealed that alanine(ALA), citrulline(CIT)), octadecanoylcarnitine(C18) and methionine(MET) were identified as independent risk factors for 30-day mortality of neonatal sepsis. The ROC curve showed an area under the curve of AUC = 0.866 (95% CI 0.796-0.936, P < 0.05). The calibration curve and DCA indicated excellent performance of the model.

CONCLUSION

This study establishes a predictive model for neonatal sepsis-associated 30-day mortality, effectively capturing the perturbations in amino acid metabolism and fatty acid oxidation, thereby demonstrating robust predictive capabilities.

Elucidating ferroptosis mechanisms in heart failure through transcriptomics, single-cell sequencing, and experimental validation

BACKGROUND

The mechanisms underlying ferroptosis in heart failure (HF) remain incompletely understood.

METHODS

This study analyzed the heart failure dataset from the Gene Expression Omnibus to identify differentially expressed ferroptosis-related genes (DFRGs). Key DFRGs were selected using LASSO regression and SVM-RFE machine learning techniques. Their diagnostic accuracy was evaluated via ROC curve analysis. Single-cell sequencing data, heart failure cell, and mouse models were utilized to validate these key DFRGs. Additionally, potential non-coding RNAs targeting these genes were predicted, and analyses for gene set enrichment, immune cell infiltration, and drug targeting were conducted.

RESULTS

A total of 127 DFRGs were identified, with 83 downregulated and 44 upregulated compared to controls. Seven key DFRGs (PTGS2, BECN1, SLC39A14, QSOX1, MLST8, TMSB4X, KDM4A) were identified, showing high diagnostic accuracy (AUC 0.988) in the GSE5406 dataset. GO and KEGG analyses linked these genes to ferroptosis, FoxO signaling, and autophagy pathways. A ceRNA network identified 217 miRNAs and 243 lncRNAs potentially targeting these genes, and 64 drugs were predicted as potential targets. Single-cell sequencing and in vitro experiments revealed differential expression of SLC39A14 and QSOX1, which was further confirmed in vivo.

CONCLUSION

This study provides novel insights into the role of ferroptosis in heart failure by identifying and validating DFRGs that exhibit differential expression across various cell types. The differential expression patterns of these genes, particularly SLC39A14 and QSOX1, indicate their potential involvement in the pathophysiological mechanisms contributing to HF. These findings offer new insights for the development of targeted therapies for HF.

Constructing a predictive model for early-onset sepsis in neonatal intensive care unit newborns based on SHapley Additive exPlanations explainable machine learning

Background

The clinical characteristics of neonatal sepsis (NS) are subtle and non-specific, posing a serious threat to the lives of newborn infants. Early-onset sepsis (EOS) is sepsis that occurs within 72 hours after birth, with a high mortality rate. Identifying key factors of NS and conducting early diagnosis are of great practical significance. Thus, we developed a robust machine learning (ML) model for the early prediction of EOS in neonates admitted to the neonatal intensive care unit (NICU), investigated the pivotal risk factors associated with EOS development, and provided interpretable insights into the model's predictions.

Methods

A retrospective cohort study was conducted. This includes 668 newborns (EOS and non-EOS) admitted to the NICU of Bozhou People's Hospital from January to December 2023, excluding 72 newborns born more than three days ago and 166 newborns with medical record data missing more than 30%. Finally, 430 newborns (EOS and non-EOS) were included in the study. Clinical case data were meticulously analyzed, and the dataset was randomly partitioned, allocating 75% for model training and the remaining 25% for test. Data preprocessing was meticulously performed using R language, and the least absolute shrinkage and selection operator (LASSO) regression was implemented to select salient features, mitigating the risk of overfitting. Six ML models were leveraged to forecast the incidence of EOS in neonates. The predictive performance of these models was rigorously evaluated using the receiver operating characteristic (ROC) curve and precision-recall (PR) curve. Furthermore, the SHapley Additive exPlanations (SHAP) framework was employed to provide intuitive explanations for the predictions made by the Categorical Boosting (CatBoost) model, which emerged as the top performer.

Results

The ROC area under the curve (ROCAUC) of six ML models, CatBoost, random forest (RF), eXtreme Gradient Boosting (XGBoost), multilayer perceptron (MLP), support vector machine (SVM), logistic regression (LR) all exceeded 0.900 on the test set. Especially the CatBoost model exhibited superior performance, with favorable outcomes in calibration, decision curve analysis (DCA), and learning curves. Notably, the ROCAUC attained 0.975, and the area under the PR curve (PRAUC) reached 0.947, signifying a high degree of predictive accuracy. Utilizing the SHAP method, seven key features were identified and ranked by their importance: respiratory rate (RR), procalcitonin (PCT), nasal congestion (NC), yellow staining (YS), white blood cell count (WBC), fever, and amniotic fluid turbidity (AFT).

Conclusions

By constructing a precision-oriented ML model and harnessing the SHAP method for interpretability, this study effectively identified crucial risk factors for EOS development in neonates. This approach enables early prediction of EOS risk, thereby facilitating timely and targeted clinical interventions for precise diagnosis and treatment.

Abnormalities in Clostridioides and related metabolites before ACTH treatment may be associated with its efficacy in patients with infantile epileptic spasm syndrome

OBJECTIVE

Adrenocorticotropic hormone (ACTH) is the first-line treatment of infantile epileptic spasm syndrome (IESS). Its reported effectiveness varies, and our current understanding regarding the role of gut microbiota composition in IESS treatment response is limited. This study assessed the microbiome-metabolome association to understand the role and mechanism of gut microbiota composition in IESS treatment outcomes.

METHODS

Children with IESS undergoing ACTH treatment were enrolled. Pre-treatment stool and serum samples were collected for 16S rRNA gene sequencing and liquid chromatography-tandem mass spectrometry, respectively. The children were divided into "responsive" and "non-responsive" groups, and gut microbiota and serum metabolome differences were analyzed.

RESULTS

Of the 30 patients with IESS, 14 responded to ACTH and 16 did not. The "non-responsive" group had larger maleficent Clostridioides and Peptoclostridium_phage_p630P populations (linear discriminant analysis >2; false discovery rate q < 0.05). Ten metabolites were upregulated (e.g., xanthurenic acid) and 15 were downregulated (e.g., vanillylmandelic acid) (p < 0.05). Association analysis of the gut microbiome and serum metabolome revealed that Clostridioides and Peptoclostridium_phage_p630P2 were positively correlated with linoleic and xanthurenic acids, while Clostridioides was negatively correlated with vanillylmandelic acid (p < 0.05). A classifier using differential gut bacteria and metabolites achieved an area under the receiver operating characteristic curve of 0.906 to distinguish responders from non-responders.

CONCLUSION

This study found significant differences in pre-treatment gut microbiota and serum metabolome between children with IESS who responded to ACTH and those who did not. Additional exploration may provide valuable information for treatment selection and potential interventions. Our results suggest that varying ACTH responses in patients with IESS may be associated with increased gut Clostridioides bacteria and kynurenine pathway alteration, but additional experiments are needed to verify this association.

Machine learning-causal inference based on multi-omics data reveals the association of altered gut bacteria and bile acid metabolism with neonatal jaundice

Early identification of neonatal jaundice (NJ) appears to be essential to avoid bilirubin encephalopathy and neurological sequelae. The interaction between gut microbiota and metabolites plays an important role in early life. It is unclear whether the composition of the gut microbiota and metabolites can be used as an early indicator of NJ or to aid clinical decision-making. This study involved a total of 196 neonates and conducted two rounds of "discovery-validation" research on the gut microbiome-metabolome. It utilized methods of machine learning, causal inference, and clinical prediction model evaluation to assess the significance of gut microbiota and metabolites in classifying neonatal jaundice (NJ), as well as the potential causal relationships between corresponding clinical variables and NJ. In the discovery stage, NJ-associated gut microbiota, network modules, and metabolite composition were identified by gut microbiome-metabolome association analysis. The NJ-associated gut microbiota was closely related to bile acid metabolites. By Lasso machine learning assessment, we found that the gut bacteria were associated with abnormal bile acid metabolism. The machine learning-causal inference approach revealed that gut bacteria affected serum total bilirubin and NJ by influencing bile acid metabolism. NJ-associated gut bile acids are potential biomarkers of NJ, and clinical prediction models constructed based on these biomarkers have some clinical effects and the model may be used for disease risk prediction. In the validation stage, it was found that intestinal metabolites can predict NJ, and the machine learning-causal inference approach revealed that bile acid metabolites affected NJ itself by affecting the total bilirubin content. Intestinal bile acid metabolites are potential biomarkers of NJ. By applying machine learning-causal inference methods to gut microbiome-metabolome association studies, we found NJ-associated intestinal bacteria and their network modules and bile acid metabolite composition. The important role of intestinal bacteria and bile acid metabolites in NJ was determined, which can predict the risk of NJ.

Identification of CXCL16 as a diagnostic biomarker for obesity and intervertebral disc degeneration based on machine learning

Intervertebral disc degeneration (IDD) is the primary cause of neck and back pain. Obesity has been established as a significant risk factor for IDD. The objective of this study was to explore the molecular mechanisms affecting obesity and IDD by identifying the overlapping crosstalk genes associated with both conditions. The identification of specific diagnostic biomarkers for obesity and IDD would have crucial clinical implications. We obtained gene expression profiles of GSE70362 and GSE152991 from the Gene Expression Omnibus, followed by their analysis using two machine learning algorithms, least absolute shrinkage and selection operator and support vector machine-recursive feature elimination, which enabled the identification of C-X-C motif chemokine ligand 16 (CXCL16) as a shared diagnostic biomarker for obesity and IDD. Additionally, gene set variant analysis was used to explore the potential mechanism of CXCL16 in these diseases, and CXCL16 was found to affect IDD through its effect on fatty acid metabolism. Furthermore, correlation analysis between CXCL16 and immune cells demonstrated that CXCL16 negatively regulated T helper 17 cells to promote IDD. Finally, independent external datasets (GSE124272 and GSE59034) were used to verify the diagnostic efficacy of CXCL16. In conclusion, a common diagnostic biomarker for obesity and IDD, CXCL16, was identified using a machine learning algorithm. This study provides a new perspective for exploring the possible mechanisms by which obesity impacts the development of IDD.

Metabolomics and machine learning approaches for diagnostic and prognostic biomarkers screening in sepsis

BACKGROUND

Sepsis is a life-threatening disease with a poor prognosis, and metabolic disorders play a crucial role in its development. This study aims to identify key metabolites that may be associated with the accurate diagnosis and prognosis of sepsis.

METHODS

Septic patients and healthy individuals were enrolled to investigate metabolic changes using non-targeted liquid chromatography-high-resolution mass spectrometry metabolomics. Machine learning algorithms were subsequently employed to identify key differentially expressed metabolites (DEMs). Prognostic-related DEMs were then identified using univariate and multivariate Cox regression analyses. The septic rat model was established to verify the effect of phenylalanine metabolism-related gene MAOA on survival and mean arterial pressure after sepsis.

RESULTS

A total of 532 DEMs were identified between healthy control and septic patients using metabolomics. The main pathways affected by these DEMs were amino acid biosynthesis, phenylalanine metabolism, tyrosine metabolism, glycine, serine and threonine metabolism, and arginine and proline metabolism. To identify sepsis diagnosis-related biomarkers, support vector machine (SVM) and random forest (RF) algorithms were employed, leading to the identification of four biomarkers. Additionally, analysis of transcriptome data from sepsis patients in the GEO database revealed a significant up-regulation of the phenylalanine metabolism-related gene MAOA in sepsis. Further investigation showed that inhibition of MAOA using the inhibitor RS-8359 reduced phenylalanine levels and improved mean arterial pressure and survival rate in septic rats. Finally, using univariate and multivariate cox regression analysis, six DEMs were identified as prognostic markers for sepsis.

CONCLUSIONS

This study employed metabolomics and machine learning algorithms to identify differential metabolites that are associated with the diagnosis and prognosis of sepsis patients. Unraveling the relationship between metabolic characteristics and sepsis provides new insights into the underlying biological mechanisms, which could potentially assist in the diagnosis and treatment of sepsis.

TRIAL REGISTRATION

This human study was approved by the Ethics Committee of the Research Institute of Surgery (2021-179) and was registered by the Chinese Clinical Trial Registry (Date: 09/12/2021, ChiCTR2200055772).

Identification and verification of characteristic differentially expressed ferroptosis-related genes in osteosarcoma using bioinformatics analysis

BACKGROUND

This study identified and verified the characteristic differentially expressed ferroptosis-related genes (CDEFRGs) in osteosarcoma (OS).

METHODS

We extracted ferroptosis-related genes (FRGs), identified differentially expressed FRGs (DEFRGs) in OS, and conducted correlation analysis between DEFRGs. Next, we conducted GO and KEGG analyses to explore the biological functions and pathways of DEFRGs. Furthermore, we used LASSO and SVM-RFE algorithms to screen CDEFRGs, and evaluated its accuracy in diagnosing OS through ROC curves. Then, we demonstrated the molecular function and pathway enrichment of CDEFRGs through GSEA analysis. In addition, we evaluated the differences in immune cell infiltration between OS and NC groups, as well as the correlation between CDEFRGs expressions and immune cell infiltrations. Finally, the expression of CDEFRGs was verified through qRT-PCR, western blotting, and immunohistochemistry experiments.

RESULTS

We identified 51 DEFRGs and the expression relationship between them. GO and KEGG analysis revealed their key functions and important pathways. Based on four CDEFRGs (PEX3, CPEB1, NOX1, and ALOX5), we built the OS diagnostic model, and verified its accuracy. GSEA analysis further revealed the important functions and pathways of CDEFRGs. In addition, there were differences in immune cell infiltration between OS group and NC group, and CDEFRGs showed significant correlation with certain infiltrating immune cells. Finally, we validated the differential expression levels of four CDEFRGs through external experiments.

CONCLUSIONS

This study has shed light on the molecular pathological mechanism of OS and has offered novel perspectives for the early diagnosis and immune-targeted therapy of OS patients.

Lower serum branched-chain amino acid catabolic intermediates are predictive signatures specific to patients with diabetic foot

Diabetic foot (DF) is one of the serious chronic complications of diabetes. Accurate prediction of the risk of DF may take timely intervention measures to prevent its occurrence. The understanding of metabolomic changes in the progression of diabetes to DF may reveal new targets for interventions. We hypothesized that changes in metabolic pathways during DF would lead to changes in the metabolic profile, which could be predictive signature specific to it. In the present study, 43 participants with type 2 diabetes mellitus (T2DM), 32 T2DM participants with DF (T2DM-F), and 36 healthy subjects were enrolled and their serum samples were used for targeted and nonpolar metabolic analysis with liquid chromatography-tandem mass spectrometry. Differential metabolites related to T2DM-F were discovered in metabolomic analysis. Lasso machine learning regression model, random forest algorithm, causal mediation analysis, disease risk assessment, and clinical decision model were carried out. T2DM and T2DM-F groups could be distinguished with the healthy control group. The differential metabolites were all enriched in alpha-linolenic acid and linoleic acid metabolic pathways including arachidonic acid, docosapentaenoic-acid 22N-6, and docosahexaenoic-acid, which were significantly lower in the T2DM and T2DM-F groups compared with the healthy control group. The differential metabolites in T2DM-F vs T2DM groups were enriched to branched-chain amino acid (BCAA) catabolic pathways involving in methylmalonic acid, succinic acid, 3-methyl-2-oxovaleric acid, and ketoleucine, which were the BCAA catabolic intermediates and significantly lower in the T2DM-F compared with the T2DM group except for succinic acid. We reveal a new set of predictive signatures and associate the lower BCAA catabolic intermediates with the progression from T2DM to T2DM-F.

Machine learning applications on neonatal sepsis treatment: a scoping review

INTRODUCTION

Neonatal sepsis is a major cause of health loss and mortality worldwide. Without proper treatment, neonatal sepsis can quickly develop into multisystem organ failure. However, the signs of neonatal sepsis are non-specific, and treatment is labour-intensive and expensive. Moreover, antimicrobial resistance is a significant threat globally, and it has been reported that over 70% of neonatal bloodstream infections are resistant to first-line antibiotic treatment. Machine learning is a potential tool to aid clinicians in diagnosing infections and in determining the most appropriate empiric antibiotic treatment, as has been demonstrated for adult populations. This review aimed to present the application of machine learning on neonatal sepsis treatment.

METHODS

PubMed, Embase, and Scopus were searched for studies published in English focusing on neonatal sepsis, antibiotics, and machine learning.

RESULTS

There were 18 studies included in this scoping review. Three studies focused on using machine learning in antibiotic treatment for bloodstream infections, one focused on predicting in-hospital mortality associated with neonatal sepsis, and the remaining studies focused on developing machine learning prediction models to diagnose possible sepsis cases. Gestational age, C-reactive protein levels, and white blood cell count were important predictors to diagnose neonatal sepsis. Age, weight, and days from hospital admission to blood sample taken were important to predict antibiotic-resistant infections. The best-performing machine learning models were random forest and neural networks.

CONCLUSION

Despite the threat antimicrobial resistance poses, there was a lack of studies focusing on the use of machine learning for aiding empirical antibiotic treatment for neonatal sepsis.

Regulated Arginine Metabolism in Immunopathogenesis of a Wide Range of Diseases: Is There a Way to Pass between Scylla and Charybdis?

More than a century has passed since arginine was discovered, but the metabolism of the amino acid never ceases to amaze researchers. Being a conditionally essential amino acid, arginine performs many important homeostatic functions in the body; it is involved in the regulation of the cardiovascular system and regeneration processes. In recent years, more and more facts have been accumulating that demonstrate a close relationship between arginine metabolic pathways and immune responses. This opens new opportunities for the development of original ways to treat diseases associated with suppressed or increased activity of the immune system. In this review, we analyze the literature describing the role of arginine metabolism in the immunopathogenesis of a wide range of diseases, and discuss arginine-dependent processes as a possible target for therapeutic approaches.

Convergence of Artificial Intelligence and Neuroscience towards the Diagnosis of Neurological Disorders-A Scoping Review

Artificial intelligence (AI) is a field of computer science that deals with the simulation of human intelligence using machines so that such machines gain problem-solving and decision-making capabilities similar to that of the human brain. Neuroscience is the scientific study of the struczture and cognitive functions of the brain. Neuroscience and AI are mutually interrelated. These two fields help each other in their advancements. The theory of neuroscience has brought many distinct improvisations into the AI field. The biological neural network has led to the realization of complex deep neural network architectures that are used to develop versatile applications, such as text processing, speech recognition, object detection, etc. Additionally, neuroscience helps to validate the existing AI-based models. Reinforcement learning in humans and animals has inspired computer scientists to develop algorithms for reinforcement learning in artificial systems, which enables those systems to learn complex strategies without explicit instruction. Such learning helps in building complex applications, like robot-based surgery, autonomous vehicles, gaming applications, etc. In turn, with its ability to intelligently analyze complex data and extract hidden patterns, AI fits as a perfect choice for analyzing neuroscience data that are very complex. Large-scale AI-based simulations help neuroscientists test their hypotheses. Through an interface with the brain, an AI-based system can extract the brain signals and commands that are generated according to the signals. These commands are fed into devices, such as a robotic arm, which helps in the movement of paralyzed muscles or other human parts. AI has several use cases in analyzing neuroimaging data and reducing the workload of radiologists. The study of neuroscience helps in the early detection and diagnosis of neurological disorders. In the same way, AI can effectively be applied to the prediction and detection of neurological disorders. Thus, in this paper, a scoping review has been carried out on the mutual relationship between AI and neuroscience, emphasizing the convergence between AI and neuroscience in order to detect and predict various neurological disorders.

Hybrid XGBoost model with hyperparameter tuning for prediction of liver disease with better accuracy

BACKGROUND

Liver disease indicates any pathology that can harm or destroy the liver or prevent it from normal functioning. The global community has recently witnessed an increase in the mortality rate due to liver disease. This could be attributed to many factors, among which are human habits, awareness issues, poor healthcare, and late detection. To curb the growing threats from liver disease, early detection is critical to help reduce the risks and improve treatment outcome. Emerging technologies such as machine learning, as shown in this study, could be deployed to assist in enhancing its prediction and treatment.

AIM

To present a more efficient system for timely prediction of liver disease using a hybrid eXtreme Gradient Boosting model with hyperparameter tuning with a view to assist in early detection, diagnosis, and reduction of risks and mortality associated with the disease.

METHODS

The dataset used in this study consisted of 416 people with liver problems and 167 with no such history. The data were collected from the state of Andhra Pradesh, India, through https://www.kaggle.com/datasets/uciml/indian-liver-patient-records. The population was divided into two sets depending on the disease state of the patient. This binary information was recorded in the attribute "is_patient".

RESULTS

The results indicated that the chi-square automated interaction detection and classification and regression trees models achieved an accuracy level of 71.36% and 73.24%, respectively, which was much better than the conventional method. The proposed solution would assist patients and physicians in tackling the problem of liver disease and ensuring that cases are detected early to prevent it from developing into cirrhosis (scarring) and to enhance the survival of patients. The study showed the potential of machine learning in health care, especially as it concerns disease prediction and monitoring.

CONCLUSION

This study contributed to the knowledge of machine learning application to health and to the efforts toward combating the problem of liver disease. However, relevant authorities have to invest more into machine learning research and other health technologies to maximize their potential.

Inductively coupled plasma mass spectrometry based urine metallome to construct clinical decision models for autism spectrum disorder

BACKGROUND

The global prevalence of autism spectrum disorder (ASD) is on the rise, and high levels of exposure to toxic heavy metals may be associated with this increase. Urine analysis is a noninvasive method for investigating the accumulation and excretion of heavy metals. The aim of this study was to identify ASD-associated urinary metal markers.

METHODS

Overall, 70 children with ASD and 71 children with typical development (TD) were enrolled in this retrospective case-control study. In this metallomics investigation, inductively coupled plasma mass spectrometry was performed to obtain the urine profile of 27 metals.

RESULTS

Children with ASD could be distinguished from children with TD based on the urine metal profile, with ASD children showing an increased urine metal Shannon diversity. A metallome-wide association analysis was used to identify seven ASD-related metals in urine, with cobalt, aluminum, selenium, and lithium significantly higher, and manganese, mercury, and titanium significantly lower in the urine of children with ASD than in children with TD. The least absolute shrinkage and selection operator (LASSO) machine learning method was used to rank the seven urine metals in terms of their effect on ASD. On the basis of these seven urine metals, we constructed a LASSO regression model for ASD classification and found an area under the receiver operating characteristic curve of 0.913. We also constructed a clinical prediction model for ASD based on the seven metals that were different in the urine of children with ASD and found that the model would be useful for the clinical prediction of ASD risk.

CONCLUSIONS

The study findings suggest that altered urine metal concentrations may be an important risk factor for ASD, and we recommend further exploration of the mechanisms and clinical treatment measures for such alterations.

Low-dose radiation exaggerates HFD-induced metabolic dysfunction by gut microbiota through PA-PYCR1 axis

Co-exposure of High-fat-diet (HFD) behavior and environmental low-dose radiation (LDR) is common among majority occupational workers, but the synergism of this co-exposure in metabolic health is poorly understood. This study aimed to investigate the impact of gut microbiota and its metabolites on the regulation of HFD accompanied by LDR-associated with metabolic dysfunction and insulin resistance. Here, we reported that Parasutterella was markedly elevated in the gut microbiota of mice in co-exposure of HFD and LDR, accompanied by increased pyrrolidinecarboxylic acid (PA) level in both intestine and plasma. Transplantation of fecal microbiota from mice with co-exposure HFD and LDR with metabolic dysfunction resulted in increased disruption of metabolic dysfunction, insulin resistance and increased PYCR1 (Pyrroline-5-carboxylate reductase 1) expression. Mechanistically, intestinal barrier was damaged more serious in mice with co-exposure of HFD and LDR, leading high PA level in plasma, activating PYCR1 expression to inhibit insulin Akt/mTOR (AKT kinase-transforming protein/Serine threonine-protein kinase) signaling pathway to aggravate HFD-induced metabolic impairments. This study suggests a new avenue for interventions against western diet companied with low dose radiation exposure-driven metabolic impairments.

Machine learning approach identifies meconium metabolites as potential biomarkers of neonatal hyperbilirubinemia

Background

The gut microbiota plays an important role in the early stages of human life. Our previous study showed that the abundance of intestinal flora involved in galactose metabolism was altered and correlated with increased serum bilirubin levels in children with jaundice. We conducted the present study to systematically evaluate alterations in the meconium metabolome of neonates with jaundice and search for metabolic markers associated with neonatal jaundice.

Methods

We included 68 neonates with neonatal hyperbilirubinemia, also known as neonatal jaundice (NJ) and 68 matched healthy controls (HC), collected meconium samples from them at birth, and performed metabolomic analysis via liquid chromatography-mass spectrometry.

Results

Gut metabolites enabled clearly distinguishing the neonatal jaundice (NJ) and healthy control (HC) groups. We also identified the compositions of the gut metabolites that differed significantly between the NJ and HC groups; these differentially significant metabolites were enriched in aminyl tRNA biosynthesis; pantothenic acid and coenzyme biosynthesis; and the valine, leucine and isoleucine biosynthesis pathways. Gut branched-chain amino acid (BCAA) levels were positively correlated with serum bilirubin levels, and the area under the receiver operating characteristic curve of the random forest classifier model based on BCAAs, proline, methionine, phenylalanine and total bilirubin reached 96.9%, showing good potential for diagnostic applications. Machine learning-based causal inference analysis revealed the causal effect of BCAAs on serum total bilirubin and NJ.

Conclusions

Altered gut metabolites in neonates with jaundice showed that increased BCAAs and total serum bilirubin were positively correlated. BCAAs proline, methionine, phenylalanine are potential biomarkers of NJ.