Machine Learning-Based Identification of Potentially Novel Non-Alcoholic Fatty Liver Disease Biomarkers

Diagnosis and Staging of Metabolic Dysfunction-Associated Steatotic Liver Disease Using Biomarker-Directed Aptamer Panels

Metabolic dysfunction-associated steatotic liver disease (MASLD) affects one-third of adults globally. Despite efforts to develop non-invasive diagnostic tools, liver biopsy remains the gold standard for diagnosing metabolic dysfunction-associated steatohepatitis (MASH) and assessing fibrosis. This study investigated RNA aptamer panels, selected using APTASHAPE technology, for non-invasive MASLD diagnosis and fibrosis stratification. Aptamer panels were selected in a cohort of individuals with MASLD (development cohort, n = 77) and tested in separate cohorts: one with MASLD (test cohort, n = 57) and one assessed for bariatric surgery (bariatric cohort, n = 62). A panel distinguishing MASLD without steatohepatitis from MASH accurately stratified individuals in the developmentcohort (AUC = 0.83) but failed in the test and bariatric cohorts. It did, however, distinguish healthy controls from individuals with MASLD, achieving an AUC of 0.72 in the test cohort. A panel for fibrosis stratification differentiated F0 from F3-4 fibrosis in the development cohort (AUC = 0.68) but not in other cohorts. Mass spectrometry identified five plasma proteins as potential targets of the discriminative aptamers, with complement factor H suggested as a novel MASLD biomarker. In conclusion, APTASHAPE shows promise as a non-invasive tool for diagnosing and staging MASLD and identifying associated plasma biomarkers.

Artificial Intelligence and Machine Learning for Inborn Errors of Immunity: Current State and Future Promise

Artificial intelligence (AI) and machine learning (ML) research within medicine has exponentially increased over the last decade, with studies showcasing the potential of AI/ML algorithms to improve clinical practice and outcomes. Ongoing research and efforts to develop AI-based models have expanded to aid in the identification of inborn errors of immunity (IEI). The use of larger electronic health record data sets, coupled with advances in phenotyping precision and enhancements in ML techniques, has the potential to significantly improve the early recognition of IEI, thereby increasing access to equitable care. In this review, we provide a comprehensive examination of AI/ML for IEI, covering the spectrum from data preprocessing for AI/ML analysis to current applications within immunology, and address the challenges associated with implementing clinical decision support systems to refine the diagnosis and management of IEI.

The Complement System and C4b-Binding Protein: A Focus on the Promise of C4BPα as a Biomarker to Predict Clopidogrel Resistance

The complement system plays a dual role in the body, either as a first-line defense barrier when balanced between activation and inhibition or as a potential driver of complement-associated injury or diseases when unbalanced or over-activated. C4b-binding protein (C4BP) was the first circulating complement regulatory protein identified and it functions as an important complement inhibitor. C4BP can suppress the over-activation of complement components and prevent the complement system from attacking the host cells through the binding of complement cleavage products C4b and C3b, working in concert as a cofactor for factor I in the degradation of C4b and C3b, and consequently preventing or reducing the assembly of C3 convertase and C5 convertase, respectively. C4BP, particularly C4BP α-chain (C4BPα), exerts its unique inhibitory effects on complement activation and opsonization, systemic inflammation, and platelet activation and aggregation. It has long been acknowledged that crosstalk or interplay exists between the complement system and platelets. Our unpublished preliminary data suggest that circulating C4BPα exerts its antiplatelet effects through inhibition of both complement activity levels and complement-induced platelet reactivity. Plasma C4BPα levels appear to be significantly higher in patients sensitive to, rather than resistant to, clopidogrel, and we suggest that a plasma C4BPα measurement could be used to predict clopidogrel resistance in the clinical settings.

From NAFLD to HCC: Advances in noninvasive diagnosis

Non-alcoholic fatty liver disease (NAFLD) has gradually become one of the major liver health problems in the world. The dynamic course of the disease goes through steatosis, inflammation, fibrosis, and carcinoma. Before progressing to carcinoma, timely and effective intervention will make the condition better, which highlights the importance of early diagnosis. With the further study of the biological mechanism in the pathogenesis and progression of NAFLD, some potential biomarkers have been discovered, and the possibility of their clinical application is gradually being discussed. At the same time, the progress of imaging technology and the emergence of new materials and methods also provide more possibilities for the diagnosis of NAFLD. This article reviews the diagnostic markers and advanced diagnostic methods of NAFLD in recent years.

Meta-analysis of the effects of proton pump inhibitors on the human gut microbiota

Mounting evidence has linked changes in human gut microbiota to proton pump inhibitor (PPI) use. Accordingly, multiple studies have analyzed the gut microbiomes of PPI users, but PPI-microbe interactions are still understudied. Here, we performed a meta-analysis of four studies with available 16S rRNA gene amplicon sequencing data to uncover the potential changes in human gut microbes among PPI users. Despite some differences, we found common features of the PPI-specific microbiota, including a decrease in the Shannon diversity index and the depletion of bacteria from the Ruminococcaceae and Lachnospiraceae families, which are crucial short-chain fatty acid-producers. Through training based on multiple studies, using a random forest classification model, we further verified the representativeness of the six screened gut microbial genera and 20 functional genes as PPI-related biomarkers, with AUC values of 0.748 and 0.879, respectively. Functional analysis of the PPI-associated 16S rRNA microbiome revealed enriched carbohydrate- and energy-associated genes, mostly encoding fructose-1,6-bisphosphatase and pyruvate dehydrogenase, among others. In this study, we have demonstrated alterations in bacterial abundance and functional metabolic potential related to PPI use, as a basis for future studies on PPI-induced adverse effects.

NAFLD: From Mechanisms to Therapeutic Approaches

Nonalcoholic fatty liver disease (NAFLD) now represents the most frequent chronic liver disease worldwide [...]

Machine-Learning Algorithm for Predicting Fatty Liver Disease in a Taiwanese Population

The rising incidence of fatty liver disease (FLD) poses a health challenge, and is expected to be the leading global cause of liver-related morbidity and mortality in the near future. Early case identification is crucial for disease intervention. A retrospective cross-sectional study was performed on 31,930 Taiwanese subjects (25,544 training and 6386 testing sets) who had received health check-ups and abdominal ultrasounds in Changhua Christian Hospital from January 2009 to January 2019. Clinical and laboratory factors were included for analysis by different machine-learning algorithms. In addition, the performance of the machine-learning algorithms was compared with that of the fatty liver index (FLI). Totally, 6658/25,544 (26.1%) and 1647/6386 (25.8%) subjects had moderate-to-severe liver disease in the training and testing sets, respectively. Five machine-learning models were examined and demonstrated exemplary performance in predicting FLD. Among these models, the xgBoost model revealed the highest area under the receiver operating characteristic (AUROC) (0.882), accuracy (0.833), F1 score (0.829), sensitivity (0.833), and specificity (0.683) compared with those of neural network, logistic regression, random forest, and support vector machine-learning models. The xgBoost, neural network, and logistic regression models had a significantly higher AUROC than that of FLI. Body mass index was the most important feature to predict FLD according to the feature ranking scores. The xgBoost model had the best overall prediction ability for diagnosing FLD in our study. Machine-learning algorithms provide considerable benefits for screening candidates with FLD.

Machine Learning-Based Identification of Colon Cancer Candidate Diagnostics Genes

Simple Summary

We developed a predictive approach using different machine learning methods to identify a number of genes that can potentially serve as novel diagnostic colon cancer biomarkers.

Abstract

Background: Colorectal cancer (CRC) is the third leading cause of cancer-related death and the fourth most commonly diagnosed cancer worldwide. Due to a lack of diagnostic biomarkers and understanding of the underlying molecular mechanisms, CRC’s mortality rate continues to grow. CRC occurrence and progression are dynamic processes. The expression levels of specific molecules vary at various stages of CRC, rendering its early detection and diagnosis challenging and the need for identifying accurate and meaningful CRC biomarkers more pressing. The advances in high-throughput sequencing technologies have been used to explore novel gene expression, targeted treatments, and colon cancer pathogenesis. Such approaches are routinely being applied and result in large datasets whose analysis is increasingly becoming dependent on machine learning (ML) algorithms that have been demonstrated to be computationally efficient platforms for the identification of variables across such high-dimensional datasets. Methods: We developed a novel ML-based experimental design to study CRC gene associations. Six different machine learning methods were employed as classifiers to identify genes that can be used as diagnostics for CRC using gene expression and clinical datasets. The accuracy, sensitivity, specificity, F1 score, and area under receiver operating characteristic (AUROC) curve were derived to explore the differentially expressed genes (DEGs) for CRC diagnosis. Gene ontology enrichment analyses of these DEGs were performed and predicted gene signatures were linked with miRNAs. Results: We evaluated six machine learning classification methods (Adaboost, ExtraTrees, logistic regression, naïve Bayes classifier, random forest, and XGBoost) across different combinations of training and test datasets over GEO datasets. The accuracy and the AUROC of each combination of training and test data with different algorithms were used as comparison metrics. Random forest (RF) models consistently performed better than other models. In total, 34 genes were identified and used for pathway and gene set enrichment analysis. Further mapping of the 34 genes with miRNA identified interesting miRNA hubs genes. Conclusions: We identified 34 genes with high accuracy that can be used as a diagnostics panel for CRC.