Primary immune thrombocytopenia (ITP) is an autoimmune bleeding disorder, and chemokines have been shown to be dysregulated in autoimmune disorders. We conducted a prospective analysis to identify potential chemokines that could enhance the diagnostic accuracy and bleeding evaluation in ITP patients. In the discovery cohort, a Luminex-based assay was employed to quantify concentrations of plasma multiple chemokines. These levels were subjected to comparative analysis using a cohort of 60 ITP patients and 17 patients with thrombocytopenia other than ITP (non-ITP). Additionally, comparative evaluation was conducted between a subgroup of 12 ITP patients characterised by bleeding episodes (ITP-B, as defined by an ITP-2016 bleeding grade ≥2) and 33 ITP patients without bleeding episodes (ITP-NB, as defined by an ITP-2016 bleeding grade ≤1). Machine learning algorithms further identified CCL20, interleukin-2, CCL26, CCL25, and CXCL1 as promising indicators for accurate diagnosis of ITP and CCL21, CXCL8, CXCL10, CCL8, CCL3, and CCL15 as biomarkers for assessing bleeding risk in ITP patients. The results were confirmed using enzyme-linked immunosorbent assays in a validation cohort (43 ITP patients and 19 non-ITP patients). Overall, the findings suggest that specific chemokines show promise as potential biomarkers for diagnosis and bleeding evaluation in ITP patients.

The dysregulation of alternative splicing (AS) is increasingly recognized as a pivotal player in the pathogenesis, progression, and treatment resistance of B-cell acute lymphoblastic leukemia (B-ALL). Despite its significance, the clinical implications of AS events in B-ALL remain largely unexplored. This study developed a prognostic model based on 18 AS events (18-AS), derived from a meticulous integration of bioinformatics methodologies and advanced machine learning algorithms. The 18-AS signature observed in B-ALL distinctly categorized patients into different groups with significant differences in immune infiltration, V(D)J rearrangement, drug sensitivity, and immunotherapy outcomes. Patients classified within the high 18-AS group exhibited lower immune infiltration scores, poorer chemo- and immune-therapy responses, and worse overall survival, underscoring the model\'s potential in refining therapeutic strategies. To validate the clinical applicability of the 18-AS, we established an SF-AS regulatory network and identified candidate drugs. More importantly, we conducted in vitro cell proliferation assays to confirm our analysis, demonstrating that the High-18AS cell line (SUP-B15) exhibited significantly enhanced sensitivity to Dasatinib, Dovitinib, and Midostaurin compared to the Low-18AS cell line (REH). These findings reveal AS events as novel prognostic biomarkers and therapeutic targets, advancing personalized treatment strategies in B-ALL management.

UNASSIGNED: β-thalassemia (β-TH) is a hereditary hemolytic anemia that results in deficient hemoglobin (Hb) synthesis. It is characterized by ineffective erythropoiesis, anemia, splenomegaly, and systemic iron overload. Exploration new potential biomarkers and drug candidates is important to facilitate the prevention and treatment of β-TH.
UNASSIGNED: We applied quasi-targeted metabolomics between wild type (Wt) and heterozygous β-TH mice (Th3/+), a model of non-transfusion-dependent β-TH intermedia, in plasma and peripheral blood (PB) cells. Futher data was deeply mined by Kyoto Encyclopedia of Genomes (KEGG) and machine algorithms methods.
UNASSIGNED: Using KEGG enrichment analysis, we found that taurine and hypotaurine metabolism disorders in plasma and alanine, aspartate and glutamate metabolism disorders in PB cells. After systematically anatomize the metabolites by machine algorithms, we confirmed that alpha-muricholic acidUP and N-acetyl-DL-phenylalanineUP in plasma and Dl-3-hydroxynorvalineUP, O-acetyl-L-serineUP, H-abu-OHUP, S-(Methyl) glutathioneUP, sepiapterinDOWN, and imidazoleacetic acidDOWN in PB cells play key roles in predicting the occurrence of β-TH. Furthermore, Sepiapterin, Imidazoleacetic acid, Methyl alpha-D-glucopyranoside and alpha-ketoglutaric acid have a good binding capacity to hemoglobin E through molecular docking and are considered to be potential drug candidates for β-TH.
UNASSIGNED: Those results may help in identify useful molecular targets in the diagnosis and treatment of β-TH and lays a strong foundation for further research.

Intrahepatic cholangiocarcinoma (iCCA) is a hepatobiliary malignancy which accounts for approximately 5-10 % of primary liver cancers and has a high mortality rate. The diagnosis of iCCA remains significant challenges owing to the lack of specific and sensitive diagnostic tests available. Hence, improved methods are needed to detect iCCA with high accuracy. In this study, we evaluated the efficacy of serum amino acid profiling combined with machine learning modeling for the diagnosis of iCCA. A comprehensive analysis of 28 circulating amino acids was conducted in a total of 140 blood samples from patients with iCCA and normal individuals. We screened out 6 differentially expressed amino acids with the criteria of |Log2(Fold Change, FC)| > 0.585, P-value < 0.05, variable importance in projection (VIP) > 1.0 and area under the curve (AUC) > 0.8, in which amino acids L-Asparagine and Kynurenine showed an increasing tendency as the disease progressed. Five frequently used machine learning algorithms (Logistic Regression, Random Forest, Supporting Vector Machine, Neural Network and Naïve Bayes) for diagnosis of iCCA based on the 6 circulating amino acids were established and validated with high sensitivity and good overall accuracy. The resulting models were further improved by introducing a clinical indicator, gamma-glutamyl transferase (GGT). This study introduces a new approach for identifying potential serum biomarkers for the diagnosis of iCCA with high accuracy.

UNASSIGNED: Hyperkalemia is a potentially life-threatening electrolyte disturbance that if not diagnosed on time may lead to devastating conditions and sudden cardiac death. Blood sampling for potassium level checks is time-consuming and can delay the treatment of severe hyperkalemia on time. So, we propose a non-invasive method for correct and rapid hyperkalemia detection.
UNASSIGNED: The cardiac signal of patients referred to the Pediatrics Emergency room of Shahid Rejaee Hospital was measured by a 12-lead Philips electrocardiogram (ECG) device. Immediately, the blood samples of the patients were sent to the laboratory for potassium serum level determination. We defined 16 features for each cardiac signal at lead 2 and extracted them automatically using the algorithm developed. With the help of the principal component analysis (PCA) algorithm, the dimension reduction operation was performed. The algorithms of decision tree (DT), random forest (RF), logistic regression, and support vector machine (SVM) were used to classify serum potassium levels. Finally, we used the receiver operation characteristic (ROC) curve to display the results.
UNASSIGNED: In the period of 5 months, 126 patients with a serum level above 4.5 (hyperkalemia) and 152 patients with a serum potassium level below 4.5 (normal potassium) were included in the study. Classification with the help of a RF algorithm has the best result. Accuracy, Precision, Recall, F1, and area under the curve (AUC) of this algorithm are 0.71, 0.87, 0.53, 0.66, and 0.69, respectively.
UNASSIGNED: A lead2-based RF classification model may help clinicians to rapidly detect severe dyskalemias as a non-invasive method and prevent life-threatening cardiac conditions due to hyperkalemia.

Wildfires pose significant threats worldwide, requiring accurate prediction for mitigation. This study uses machine learning techniques to forecast wildfire severity in the Upper Colorado River basin. Datasets from 1984 to 2019 and key indicators like weather conditions and land use were employed. Random Forest outperformed Artificial Neural Network, achieving 72 % accuracy. Influential predictors include air temperature, vapor pressure deficit, NDVI, and fuel moisture. Solar radiation, SPEI, precipitation, and evapotranspiration also contribute significantly. Validation against actual severities from 2016 to 2019 showed mean prediction errors of 11.2 %, affirming the model\'s reliability. These results highlight the efficacy of machine learning in understanding wildfire severity, especially in vulnerable regions.

Cell-derived extracellular vesicles (EVs) have emerged as a promising non-invasive liquid biopsy technique due to their accessibility and their ability to encapsulate and transport diverse biomolecules. EVs have garnered substantial research interest, notably in cardiovascular diseases (CVDs), where their roles in pathophysiology and as diagnostic and prognostic biomarkers are increasingly recognized. This review provides a comprehensive overview of EVs, starting with their origins, followed by the techniques used for their isolation and characterization. We explore the diverse cargo of EVs, including nucleic acids, proteins, lipids, and metabolites, highlighting their roles in intercellular communication and as potential biomarkers. We then delve into the application of genomics, transcriptomics, proteomics, and metabolomics in the analysis of EVs, particularly within the context of CVDs. Finally, we discuss how integrated multi-omics approaches are unveiling novel biomarkers, offering fresh insights into the diagnosis and prognosis of CVDs. This review underscores the growing importance of EVs in clinical diagnostics and the potential of multi-omics to propel future advancements in CVD biomarker discovery.

BACKGROUND: Hypodontia is the most prevalent dental anomaly in humans, and is primarily attributed to genetic factors. Although genome-wide association studies (GWAS) have identified single-nucleotide polymorphisms (SNP) associated with hypodontia, genetic risk assessment remains challenging due to population-specific SNP variants. Therefore, we aimed to conducted a genetic analysis and developed a machine-learning-based predictive model to examine the association between previously reported SNPs and hypodontia in the Saudi Arabian population. Our case-control study included 106 participants (aged 8-50 years; 64 females and 42 males), comprising 54 hypodontia cases and 52 controls. We utilized TaqManTM Real-Time Polymerase Chain Reaction and allelic genotyping to analyze three selected SNPs (AXIN2: rs2240308, PAX9: rs61754301, and MSX1: rs12532) in unstimulated whole saliva samples. The chi-square test, multinomial logistic regression, and machine-learning techniques were used to assess genetic risk by using odds ratios (ORs) for multiple target variables.
RESULTS: Multivariate logistic regression indicated a significant association between homozygous AXIN2 rs2240308 and the hypodontia phenotype (ORs [95% confidence interval] 2.893 [1.28-6.53]). Machine-learning algorithms revealed that the AXIN2 homozygous (A/A) genotype is a genetic risk factor for hypodontia of teeth #12, #22, and #35, whereas the AXIN2 homozygous (G/G) genotype increases the risk for hypodontia of teeth #22, #35, and #45. The PAX9 homozygous (C/C) genotype is associated with an increased risk for hypodontia of teeth #22 and #35.
CONCLUSIONS: Our study confirms a link between AXIN2 and hypodontia in Saudi orthodontic patients and suggests that combining machine-learning models with SNP analysis of saliva samples can effectively identify individuals with non-syndromic hypodontia.

Asthma comprises one of the most common chronic inflammatory conditions, yet still lacks effective diagnostic markers and treatment targets. To gain deeper insights, we comprehensively analyzed microarray datasets of airway epithelial samples from asthmatic patients and healthy subjects in the Gene Expression Omnibus database using three machine learning algorithms. Our investigation identified a pivotal gene, STEAP4. The expression of STEAP4 in patients with allergic asthma was found to be reduced. Furthermore, it was found to negatively correlate with the severity of the disease and was subsequently validated in asthmatic mice in this study. A ROC analysis of STEAP4 showed the AUC value was greater than 0.75. Functional enrichment analysis of STEAP4 indicated a strong correlation with IL-17, steroid hormone biosynthesis, and ferroptosis signaling pathways. Subsequently, intercellular communication analysis was performed using single-cell RNA sequencing data obtained from airway epithelial cells. The results revealed that samples exhibiting low levels of STEAP4 expression had a richer MIF signaling pathway in comparison to samples with high STEAP4 expression. Through both in vitro and in vivo experiments, we further confirmed the overexpression of STEAP4 in airway epithelial cells resulted in decreased expression of MIF, which in turn caused a decrease in the levels of the cytokines IL-33, IL-25, and IL-4; In contrast, when the STEAP4 was suppressed in airway epithelial cells, there was an upregulation of MIF expression, resulting in elevated levels of the cytokines IL-33, IL-25, and IL-4. These findings suggest that STEAP4 in the airway epithelium reduces allergic asthma Th2-type inflammatory reactions by inhibiting the MIF signaling pathway.

Accurately predicting the spatial-temporal distribution of PM2.5 is challenging due to missing data and selecting an appropriate modeling method. Effective imputation of missing data must consider the relationships between variables while preserving their inherent variability and uncertainty. In this study, we employed machine learning techniques to impute missing data by analyzing the relationships between meteorological variables and other pollutants. Subsequently, we introduced an innovative spatiotemporal hybrid model, AC_GRU, which integrates a one-dimensional convolutional neural network (CNN), GRU, and an attention-based network to predict PM2.5 concentrations in urban areas. The AC_GRU model utilizes meteorological variables, PM2.5 concentrations from nearby air quality monitoring stations, and concentrations of other pollutants as inputs. This approach allows the model to learn spatiotemporal correlations within the time-series data, enhancing the accuracy of PM2.5 predictions. Additionally, the attention mechanism improves prediction accuracy by automatically weighting the past input variables based on their importance for future PM2.5 predictions. The experimental results demonstrate that our AC_GRU model outperforms state-of-the-art methods, making it a valuable tool for urban air quality management and public health protection.