Predictive diagnosis of chronic obstructive pulmonary disease using serum metabolic biomarkers and least-squares support vector machine

Metabolic pathways in immune senescence and inflammaging: Novel therapeutic strategy for chronic inflammatory lung diseases. An EAACI position paper from the Task Force for Immunopharmacology

The accumulation of senescent cells drives inflammaging and increases morbidity of chronic inflammatory lung diseases. Immune responses are built upon dynamic changes in cell metabolism that supply energy and substrates for cell proliferation, differentiation, and activation. Metabolic changes imposed by environmental stress and inflammation on immune cells and tissue microenvironment are thus chiefly involved in the pathophysiology of allergic and other immune-driven diseases. Altered cell metabolism is also a hallmark of cell senescence, a condition characterized by loss of proliferative activity in cells that remain metabolically active. Accelerated senescence can be triggered by acute or chronic stress and inflammatory responses. In contrast, replicative senescence occurs as part of the physiological aging process and has protective roles in cancer surveillance and wound healing. Importantly, cell senescence can also change or hamper response to diverse therapeutic treatments. Understanding the metabolic pathways of senescence in immune and structural cells is therefore critical to detect, prevent, or revert detrimental aspects of senescence-related immunopathology, by developing specific diagnostics and targeted therapies. In this paper, we review the main changes and metabolic alterations occurring in senescent immune cells (macrophages, B cells, T cells). Subsequently, we present the metabolic footprints described in translational studies in patients with chronic asthma and chronic obstructive pulmonary disease (COPD), and review the ongoing preclinical studies and clinical trials of therapeutic approaches aiming at targeting metabolic pathways to antagonize pathological senescence. Because this is a recently emerging field in allergy and clinical immunology, a better understanding of the metabolic profile of the complex landscape of cell senescence is needed. The progress achieved so far is already providing opportunities for new therapies, as well as for strategies aimed at disease prevention and supporting healthy aging.

Machine learning-based clinical decision support using laboratory data

Artificial intelligence (AI) and machine learning (ML) are becoming vital in laboratory medicine and the broader context of healthcare. In this review article, we summarized the development of ML models and how they contribute to clinical laboratory workflow and improve patient outcomes. The process of ML model development involves data collection, data cleansing, feature engineering, model development, and optimization. These models, once finalized, are subjected to thorough performance assessments and validations. Recently, due to the complexity inherent in model development, automated ML tools were also introduced to streamline the process, enabling non-experts to create models. Clinical Decision Support Systems (CDSS) use ML techniques on large datasets to aid healthcare professionals in test result interpretation. They are revolutionizing laboratory medicine, enabling labs to work more efficiently with less human supervision across pre-analytical, analytical, and post-analytical phases. Despite contributions of the ML tools at all analytical phases, their integration presents challenges like potential model uncertainties, black-box algorithms, and deskilling of professionals. Additionally, acquiring diverse datasets is hard, and models' complexity can limit clinical use. In conclusion, ML-based CDSS in healthcare can greatly enhance clinical decision-making. However, successful adoption demands collaboration among professionals and stakeholders, utilizing hybrid intelligence, external validation, and performance assessments.

Whole-Blood Metabolomics of a Rat Model of Repetitive Concussion

Mild traumatic brain injury (mTBI) and repetitive mTBI (RmTBI) are silent epidemics, and so far, there is no objective diagnosis. The severity of the injury is solely based on the Glasgow Coma Score (GCS) scale. Most patients suffer from one or more behavioral abnormalities, such as headache, amnesia, cognitive decline, disturbed sleep pattern, anxiety, depression, and vision abnormalities. Additionally, most neuroimaging modalities are insensitive to capture structural and functional alterations in the brain, leading to inefficient patient management. Metabolomics is one of the established omics technologies to identify metabolic alterations, mostly in biofluids. NMR-based metabolomics provides quantitative metabolic information with non-destructive and minimal sample preparation. We employed whole-blood NMR analysis to identify metabolic markers using a high-field NMR spectrometer (800 MHz). Our approach involves chemical-free sample pretreatment and minimal sample preparation to obtain a robust whole-blood metabolic profile from a rat model of concussion. A single head injury was given to the mTBI group, and three head injuries to the RmTBI group. We found significant alterations in blood metabolites in both mTBI and RmTBI groups compared with the control, such as alanine, branched amino acid (BAA), adenosine diphosphate/adenosine try phosphate (ADP/ATP), creatine, glucose, pyruvate, and glycerphosphocholine (GPC). Choline was significantly altered only in the mTBI group and formate in the RmTBI group compared with the control. These metabolites corroborate previous findings in clinical and preclinical cohorts. Comprehensive whole-blood metabolomics can provide a robust metabolic marker for more accurate diagnosis and treatment intervention for a disease population.

Update on metabolomic findings in COPD patients

COPD is a heterogeneous disorder that shows diverse clinical presentations (phenotypes and "treatable traits") and biological mechanisms (endotypes). This heterogeneity implies that to carry out a more personalised clinical management, it is necessary to classify each patient accurately. With this objective, and in addition to clinical features, it would be very useful to have well-defined biological markers. The search for these markers may either be done through more conventional laboratory and hypothesis-driven techniques or relatively blind high-throughput methods, with the omics approaches being suitable for the latter. Metabolomics is the science that studies biological processes through their metabolites, using various techniques such as gas and liquid chromatography, mass spectrometry and nuclear magnetic resonance. The most relevant metabolomics studies carried out in COPD highlight the importance of metabolites involved in pathways directly related to proteins (peptides and amino acids), nucleic acids (nitrogenous bases and nucleosides), and lipids and their derivatives (especially fatty acids, phospholipids, ceramides and eicosanoids). These findings indicate the relevance of inflammatory-immune processes, oxidative stress, increased catabolism and alterations in the energy production. However, some specific findings have also been reported for different COPD phenotypes, demographic characteristics of the patients, disease progression profiles, exacerbations, systemic manifestations and even diverse treatments. Unfortunately, the studies carried out to date have some limitations and shortcomings and there is still a need to define clear metabolomic profiles with clinical utility for the management of COPD and its implicit heterogeneity.

L-Arginine, as an essential amino acid, is a potential substitute for treating COPD via regulation of ROS/NLRP3/NF-κB signaling pathway

BACKGROUNDS

Chronic obstructive pulmonary disease (COPD) is a frequent and common disease in clinical respiratory medicine and its mechanism is unclear. The purpose of this study was to find the new biomarkers of COPD and elucidate its role in the pathogenesis of COPD. Analysis of metabolites in plasma of COPD patients were performed by ultra-high performance liquid chromatography (UPLC) and quadrupole time-of-flight mass spectrometry (TOF-MS). The differential metabolites were analyzed and identified by multivariate analysis between COPD patients and healthy people. The role and mechanisms of the differential biomarkers in COPD were verified with COPD rats, arginosuccinate synthetase 1 (ASS-l) KO mice and bronchial epithelial cells (BECs). Meanwhile, whether the differential biomarkers can be the potential treatment targets for COPD was also investigated. 85 differentials metabolites were identified between COPD patients and healthy people by metabonomic.

RESULTS

L-Arginine (LA) was the most obvious differential metabolite among the 85 metabolites. Compare with healthy people, the level of LA was markedly decreased in serum of COPD patients. It was found that LA had protective effects on COPD with in vivo and in vitro experiments. Silencing Ass-1, which regulates LA metabolism, and α-methy-DL-aspartic (NHLA), an Ass-1 inhibitor, canceled the protective effect of LA on COPD. The mechanism of LA in COPD was related to the inhibition of ROS/NLRP3/NF-κB signaling pathway. It was also found that exogenous LA significantly improved COPD via regulation of ROS/NLRP3/NF-κB signaling pathway. L-Arginine (LA) as a key metabolic marker is identified in COPD patients and has a protective effect on COPD via regulation of ROS/NLRP3/NF-κB signaling pathway.

CONCLUSION

LA may be a novel target for the treatment of COPD and also a potential substitute for treating COPD.

Metabolomics in COPD

The clinical presentation of chronic obstructive pulmonary disease (COPD) is highly heterogeneous. Attempts have been made to define subpopulations of patients who share clinical characteristics (phenotypes and treatable traits) and/or biological characteristics (endotypes), in order to offer more personalized care. Assigning a patient to any of these groups requires the identification of both clinical and biological markers. Ideally, biological markers should be easily obtained from blood or urine, but these may lack specificity. Biomarkers can be identified initially using conventional or more sophisticated techniques. However, the more sophisticated techniques should be simplified in the future if they are to have clinical utility. The -omics approach offers a methodology that can assist in the investigation and identification of useful markers in both targeted and blind searches. Specifically, metabolomics is the science that studies biological processes involving metabolites, which can be intermediate or final products. The metabolites associated with COPD and their specific phenotypic and endotypic features have been studied using various techniques. Several compounds of particular interest have emerged, namely, several types of lipids and derivatives (mainly phospholipids, but also ceramides, fatty acids and eicosanoids), amino acids, coagulation factors, and nucleic acid components, likely to be involved in their function, protein catabolism, energy production, oxidative stress, immune-inflammatory response and coagulation disorders. However, clear metabolomic profiles of the disease and its various manifestations that may already be applicable in clinical practice still need to be defined.

Metabolome Features of COPD: A Scoping Review

Chronic obstructive pulmonary disease (COPD) is a complex heterogeneous disease state with multiple phenotypic presentations that include chronic bronchitis and emphysema. Although COPD is a lung disease, it has systemic manifestations that are associated with a dysregulated metabolome in extrapulmonary compartments (e.g., blood and urine). In this scoping review of the COPD metabolomics literature, we identified 37 publications with a primary metabolomics investigation of COPD phenotypes in human subjects through Google Scholar, PubMed, and Web of Science databases. These studies consistently identified a dysregulation of the TCA cycle, carnitines, sphingolipids, and branched-chain amino acids. Many of the COPD metabolome pathways are confounded by age and sex. The effects of COPD in young versus old and male versus female need further focused investigations. There are also few studies of the metabolome's association with COPD progression, and it is unclear whether the markers of disease and disease severity are also important predictors of disease progression.

The Integration of Metabolomics with Other Omics: Insights into Understanding Prostate Cancer

Our understanding of prostate cancer (PCa) has shifted from solely caused by a few genetic aberrations to a combination of complex biochemical dysregulations with the prostate metabolome at its core. The role of metabolomics in analyzing the pathophysiology of PCa is indispensable. However, to fully elucidate real-time complex dysregulation in prostate cells, an integrated approach based on metabolomics and other omics is warranted. Individually, genomics, transcriptomics, and proteomics are robust, but they are not enough to achieve a holistic view of PCa tumorigenesis. This review is the first of its kind to focus solely on the integration of metabolomics with multi-omic platforms in PCa research, including a detailed emphasis on the metabolomic profile of PCa. The authors intend to provide researchers in the field with a comprehensive knowledge base in PCa metabolomics and offer perspectives on overcoming limitations of the tool to guide future point-of-care applications.

Metabolic Dysfunction-associated Fatty Liver Disease is Associated with Greater Impairment of Lung Function than Nonalcoholic Fatty Liver Disease

BACKGROUND AND AIMS

We compared lung function parameters in nonalcoholic fatty liver disease (NAFLD) and metabolic dysfunction-associated fatty liver disease (MAFLD), and examined the association between lung function parameters and fibrosis severity in MAFLD.

METHODS

In this cross-sectional study, we randomly recruited 2,543 middle-aged individuals from 25 communities across four cities in China during 2016 and 2020. All participants received a health check-up including measurement of anthropometric parameters, biochemical variables, liver ultrasonography, and spirometry. The severity of liver disease was assessed by the fibrosis (FIB)-4 score.

RESULTS

The prevalence of MAFLD was 20.4% (n=519) and that of NAFLD was 18.4% (n=469). After adjusting for age, sex, adiposity measures, smoking status, and significant alcohol intake, subjects with MAFLD had a significantly lower predicted forced vital capacity (FVC, 88.27±17.60% vs. 90.82±16.85%, p<0.05) and lower 1 s forced expiratory volume (FEV₁, 79.89±17.34 vs. 83.02±16.66%, p<0.05) than those with NAFLD. MAFLD with an increased FIB-4 score was significantly associated with decreased lung function. For each 1-point increase in FIB-4, FVC was diminished by 0.507 (95% CI: -0.840, -0.173, p=0.003), and FEV₁ was diminished by 0.439 (95% CI: -0.739, -0.140, p=0.004). The results remained unchanged when the statistical analyses was performed separately for men and women.

CONCLUSIONS

MAFLD was significantly associated with a greater impairment of lung function parameters than NAFLD.

Machine Learning and Image Processing Enabled Evolutionary Framework for Brain MRI Analysis for Alzheimer’s Disease Detection

Alzheimer's disease is characterized by the presence of abnormal protein bundles in the brain tissue, but experts are not yet sure what is causing the condition. To find a cure or aversion, researchers need to know more than just that there are protein differences from the usual; they also need to know how these brain nerves form so that a remedy may be discovered. Machine learning is the study of computational approaches for enhancing performance on a specific task through the process of learning. This article presents an Alzheimer's disease detection framework consisting of image denoising of an MRI input data set using an adaptive mean filter, preprocessing using histogram equalization, and feature extraction by Haar wavelet transform. Classification is performed using LS-SVM-RBF, SVM, KNN, and random forest classifier. An adaptive mean filter removes noise from the existing MRI images. Image quality is enhanced by histogram equalization. Experimental results are compared using parameters such as accuracy, sensitivity, specificity, precision, and recall.

Multivariate analysis of NMR-based metabolomic data

Nuclear magnetic resonance (NMR) spectroscopy allows for simultaneous detection of a wide range of metabolites and lipids. As metabolites act together in complex metabolic networks, they are often highly correlated, and optimal biological insight is achieved when using methods that take the correlation into account. For this reason, latent-variable-based methods, such as principal component analysis and partial least-squares discriminant analysis, are widely used in metabolomic studies. However, with increasing availability of larger population cohorts, and a shift from analysis of spectral data to using quantified metabolite levels, both more traditional statistical approaches and alternative machine learning methods have become more widely used. This review aims at providing an overview of the current state-of-the-art multivariate methods for the analysis of NMR-based metabolomic data as well as alternative methods, highlighting their strengths and limitations.

Analyzing the use of artificial intelligence for the management of chronic obstructive pulmonary disease (COPD)

OBJECTIVE

Chronic obstructive pulmonary disease (COPD) is a disease that causes airflow limitation to the lungs and has a high morbidity around the world. The objective of this study was to evaluate how artificial intelligence (AI) is being applied for the management of the disease, analyzing the objectives that are raised, the algorithms that are used and what results they offer.

METHODS

We conducted a scoping review following the Arksey and O'Malley (2005) and Levac et al. (2010) guidelines. Two reviewers independently searched, analyzed and extracted data from papers of five databases: Web of Science, PubMed, Scopus, Cinahl and Cochrane. To be included, the studies had to apply some AI techniques for the management of at least one stage of the COPD clinical process. In the event of any discrepancy between both reviewers, the criterion of a third reviewer prevailed.

RESULTS

380 papers were identified through database searches. After applying the exclusion criteria, 67 papers were included in the study. The studies were of a different nature and pursued a wide range of objectives, highlighting mainly those focused on the identification, classification and prevention of the disease. Neural nets, support vector machines and decision trees were the AI algorithms most commonly used. The mean and median values of all the performance metrics evaluated were between 80% and 90%.

CONCLUSIONS

The results obtained show a growing interest in the development of medical applications that manage the different phases of the COPD clinical process, especially predictive models. According to the performance shown, these models could be a useful complementary tool in the decision-making by health specialists, although more high-quality ML studies are needed to endorse the findings of this study.

Artificial Intelligence and Machine Learning in Chronic Airway Diseases: Focus on Asthma and Chronic Obstructive Pulmonary Disease

Chronic airway diseases are characterized by airway inflammation, obstruction, and remodeling and show high prevalence, especially in developing countries. Among them, asthma and chronic obstructive pulmonary disease (COPD) show the highest morbidity and socioeconomic burden worldwide. Although there are extensive guidelines for the prevention, early diagnosis, and rational treatment of these lifelong diseases, their value in precision medicine is very limited. Artificial intelligence (AI) and machine learning (ML) techniques have emerged as effective methods for mining and integrating large-scale, heterogeneous medical data for clinical practice, and several AI and ML methods have recently been applied to asthma and COPD. However, very few methods have significantly contributed to clinical practice. Here, we review four aspects of AI and ML implementation in asthma and COPD to summarize existing knowledge and indicate future steps required for the safe and effective application of AI and ML tools by clinicians.

Predictive diagnosis of chronic obstructive pulmonary disease using serum metabolic biomarkers and least-squares support vector machine

Objective

Development of biofluid‐based biomarkers is attractive for the diagnosis of chronic obstructive pulmonary disease (COPD) but still lacking. Thus, here we aimed to identify serum metabolic biomarkers for the diagnosis of COPD.

Methods

In this study, we investigated serum metabolic features between COPD patients (n = 54) and normal individuals (n = 74) using a ¹H NMR‐based metabolomics approach and developed an integrated method of least‐squares support vector machine (LS‐SVM) and serum metabolic biomarkers to assist COPD diagnosis.

Results

We observed a hypometabolic state in serum of COPD patients, as indicated by decreases in N‐acetyl‐glycoprotein (NAG), lipoprotein (LOP, mainly LDL/VLDL), polyunsaturated fatty acid (pUFA), glucose, alanine, leucine, histidine, valine, and lactate. Using an integrated method of multivariable and univariate analyses, NAG and LOP were identified as two important metabolites for distinguishing between COPD patients and controls. Subsequently, we developed a LS‐SVM classifier using these two markers and found that LS‐SVM classifiers with linear and polynomial kernels performed better than the classifier with RBF kernel. Linear and polynomial LS‐SVM classifiers can achieve the total accuracy rates of 80.77% and 84.62% and the AUC values of 0.87 and 0.90 for COPD diagnosis, respectively.

Conclusions

This study suggests that artificial intelligence integrated with serum metabolic biomarkers has a great potential for auxiliary diagnosis of COPD.