Machine Learning Algorithms Identify Clinical Subtypes and Cancer in Anti-TIF1γ+ Myositis: A Longitudinal Study of 87 Patients

Machine learning algorithms able to predict the prognosis of gastric cancer patients treated with immune checkpoint inhibitors

BACKGROUND

Although immune checkpoint inhibitors (ICIs) have demonstrated significant survival benefits in some patients diagnosed with gastric cancer (GC), existing prognostic markers are not universally applicable to all patients with advanced GC.

AIM

To investigate biomarkers that predict prognosis in GC patients treated with ICIs and develop accurate predictive models.

METHODS

Data from 273 patients diagnosed with GC and distant metastasis, who un-derwent ≥ 1 cycle(s) of ICIs therapy were included in this study. Patients were randomly divided into training and test sets at a ratio of 7:3. Training set data were used to develop the machine learning models, and the test set was used to validate their predictive ability. Shapley additive explanations were used to provide insights into the best model.

RESULTS

Among the 273 patients with GC treated with ICIs in this study, 112 died within 1 year, and 129 progressed within the same timeframe. Five features related to overall survival and 4 related to progression-free survival were identified and used to construct eXtreme Gradient Boosting (XGBoost), logistic regression, and decision tree. After comprehensive evaluation, XGBoost demonstrated good accuracy in predicting overall survival and progression-free survival.

CONCLUSION

The XGBoost model aided in identifying patients with GC who were more likely to benefit from ICIs therapy. Patient nutritional status may, to some extent, reflect prognosis.

Pathogenic role and clinical significance of neutrophils and neutrophil extracellular traps in idiopathic inflammatory myopathies

Idiopathic inflammatory myopathies (IIM) are a heterogeneous group of chronic autoimmune diseases characterized by muscle damage and extramuscular symptoms, including specific skin rash, arthritis, interstitial lung disease, and cardiac involvement. While the etiology and pathogenesis of IIM are not yet fully understood, emerging evidence suggests that neutrophils and neutrophil extracellular traps (NETs) have a role in the pathogenesis. Recent research has identified increased levels of circulating and tissue neutrophils as well as NETs in patients with IIM; these contribute to the activation of the type I and type II interferons pathway. During active IIM disease, myositis-specific antibodies are associated with the formation and incomplete degradation of NETs, leading to damage in the lungs, muscles, and blood vessels of patients. This review focuses on the pathogenic role and clinical significance of neutrophils and NETs in IIM, and it includes a discussion of potential targeted treatment strategies.

From data to diagnosis: how machine learning is revolutionizing biomarker discovery in idiopathic inflammatory myopathies

Idiopathic inflammatory myopathies (IIMs) are a heterogeneous group of muscle disorders including adult and juvenile dermatomyositis, polymyositis, immune-mediated necrotising myopathy and sporadic inclusion body myositis, all of which present with variable symptoms and disease progression. The identification of effective biomarkers for IIMs has been challenging due to the heterogeneity between IIMs and within IIM subgroups, but recent advances in machine learning (ML) techniques have shown promises in identifying novel biomarkers. This paper reviews recent studies on potential biomarkers for IIM and evaluates their clinical utility. We also explore how data analytic tools and ML algorithms have been used to identify biomarkers, highlighting their potential to advance our understanding and diagnosis of IIM and improve patient outcomes. Overall, ML techniques have great potential to revolutionize biomarker discovery in IIMs and lead to more effective diagnosis and treatment.

Inflammatory myopathies and beyond: The dual role of neutrophils in muscle damage and regeneration

Skeletal muscle is one of the most abundant tissues of the human body and is responsible for the generation of movement. Muscle injuries can lead to severe disability. Skeletal muscle is characterized by an important regeneration capacity, which is possible due to the interaction between the myoblasts and immune cells. Neutrophils are fundamental as inducers of muscle damage and as promoters of the initial inflammatory response which eventually allows the muscle repair. The main functions of the neutrophils are phagocytosis, respiratory burst, degranulation, and the production of neutrophil extracellular traps (NETs). An overactivation of neutrophils after muscle injuries may lead to an expansion of the initial damage and can hamper the successful muscle repair. The importance of neutrophils as inducers of muscle damage extends beyond acute muscle injury and recently, neutrophils have become more relevant as part of the immunopathogenesis of chronic muscle diseases like idiopathic inflammatory myopathies (IIM). This heterogeneous group of systemic autoimmune diseases is characterized by the presence of muscle inflammation with a variable amount of extramuscular features. In IIM, neutrophils have been found to have a role as biomarkers of disease activity, and their expansion in peripheral blood is related to certain clinical features like interstitial lung disease (ILD) and cancer. On the other hand, low density granulocytes (LDG) are a distinctive subtype of neutrophils characterized by an enhanced production of NETs. These cells along with the NETs have also been related to disease activity and certain clinical features like ILD, vasculopathy, calcinosis, dermatosis, and cutaneous ulcers. The role of NETs in the immunopathogenesis of IIM is supported by an enhanced production and deficient degradation of NETs that have been observed in patients with dermatomyositis and anti-synthetase syndrome. Finally, new interest has arisen in the study of other phenotypes of LDG with a phenotype corresponding to myeloid-derived suppressor cells, which were also found to be expanded in patients with IIM and were related to disease activity. In this review, we discuss the role of neutrophils as both orchestrators of muscle repair and inducers of muscle damage, focusing on the immunopathogenesis of IIM.

Identification of Metabolic Signature Associated with Idiopathic Inflammatory Myopathy Reveals Polyamine Pathway Alteration in Muscle Tissue

Idiopathic inflammatory myopathy (IIM) is hard to diagnose without a muscle biopsy. We aimed to identify a metabolite panel for IIM detection by metabolomics approach in serum samples and to explore the metabolomic signature in tissue samples from a mouse model. We obtained serum samples from IIM patients, ankylosing spondylitis (AS) patients, healthy volunteers and muscle tissue samples from IIM murine model. All samples were subjected to a targeted metabolomic approach with various statistical analyses on serum and tissue samples to identify metabolic alterations. Three machine learning methods, such as logistic regression (LR), support vector machine (SVM), and random forest (RF), were applied to build prediction models. A set of 7 predictive metabolites was calculated using backward stepwise selection, and the model was evaluated within 5-fold cross-validation by using three machine algorithms. The model produced an area under the receiver operating characteristic curve values of 0.955 (LR), 0.908 (RF) and 0.918 (SVM). A total of 68 metabolites were significantly changed in mouse tissue. Notably, the most influential pathways contributing to the inflammation of muscle were the polyamine pathway and the beta-alanine pathway. Our metabolomic approach offers the potential biomarkers of IIM and reveals pathologically relevant metabolic pathways that are associated with IIM.

Zengye Decoction Attenuated Severe Acute Pancreatitis Complicated with Acute Kidney Injury by Modulating the Gut Microbiome and Serum Amino Acid Metabolome

Objective

To explore the effect and underlying mechanism of Zengye decoction (ZYD), a traditional formula from China, on the severe acute pancreatitis (SAP) rat model with acute kidney injury (AKI).

Methods

The SAP-AKI model was induced by 3.5% sodium taurocholate. Rats were treated with normal saline or ZYD twice and sacrificed at 36 h after modeling. Amylase, lipase, creatinine, blood urea nitrogen, kidney injury molecule 1(KIM-1), and multiple organs' pathological examinations were used to assess the protective effect of ZYD. Gut microbiome detected by 16S rRNA sequencing analysis and serum amino acid metabolome analyzed by liquid chromatography-mass spectrometry explained the underlying mechanism. The Spearman correlation analysis presented the relationship between microflora and metabolites.

Results

ZYD significantly decreased KIM-1(P < 0.05) and the pathological score of the pancreas (P < 0.05), colon (P < 0.05), and kidney (P < 0.05). Meanwhile, ZYD shifted the overall gut microbial structure (β-diversity, ANOSIM R = 0.14, P=0.025) and altered the microbial compositions. Notably, ZYD reduced the potentially pathogenic bacteria—Bacteroidetes, Clostridiales vadin BB60 group, and uncultured_Clostridiales_bacterium, but promoted the short-chain fatty acid (SCFA) producers—Erysipelotrichaceae, Bifidobacterium, Lactobacillus, and Moryella (all P < 0.05). Moreover, principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), and hierarchical clustering analysis (HCA) presented a remarkable change in amino acid metabolome after SAP-AKI induction and an apparent regulation by ZYD treatment (R2Y 0.878, P=0.01; Q2 0.531, P=0.01). Spearman's correlation analysis suggested that gut bacteria likely influenced serum metabolites levels (absolute r > 0.4 and FDR P < 0.02).

Conclusions

ZYD attenuated SAP-AKI by modulating the gut microbiome and serum amino acid metabolome, which may be a promising adjuvant treatment.