Shotgun mass spectrometry-based lipid profiling identifies and distinguishes between chronic inflammatory diseases

AbstractBackgroundInflammation impacts several acute and chronic diseases causing localized stress and cell death, releasing tissue-specific lipids into the circulation from inflamed cells and tissues. The plasma lipidome may be expected to reflect the type of inflammation and the specific cells and tissues involved. However, deep lipid profiles of major chronic inflammatory diseases have not been compared.MethodsWe compare the plasma lipidomes of patients suffering from two etiologically distinct chronic inflammatory diseases, atherosclerosis-related cardiovascular disease (CVD) including ischemic stroke (IS), and systemic lupus erythematosus (SLE), to each other and to age-matched controls. The controls had never suffered from any of these diseases. Blood plasma lipidomes were screened by a top-down shotgun MS-based analysis without liquid chromatographic separation. Lipid profiling based on MS was performed on a cohort of 427 individuals. The cohort constitutes 85 controls (control), 217 with cardiovascular disease (further classified into CVD 1-5), 21 ischemic stroke patients (IS), and 104 patients suffering from systemic lupus erythematosis (SLE). 596 lipids were profiled which were quality filtered for further evaluation and determination of potential biomarkers. Lipidomes were compared by linear regression and evaluated by machine learning classifiers.ResultsMachine learning classifiers based on the plasma lipidomes of patients suffering from CVD and SLE allowed clear distinction of these two chronic inflammatory diseases from each other and from healthy age-matched controls and body mass index (BMI). We demonstrate convincing evidence for the capability of lipidomics to separate the studied chronic and inflammatory diseases from controls based on independent validation test set classification performance (CVD vs control - Sensitivity: 0.90, Specificity: 0.98; IS vs control - Sensitivity: 1.0, Specificity: 1.0; SLE vs control – Sensitivity: 1, Specificity: 0.88) and from each other (SLE vs CVD □ Sensitivity: 0.91, Specificity: 1). Preliminary linear discriminant analysis plots using all data clearly separated the clinical groups from each other and from the controls. In addition, CVD severities, as classified into five clinical groups, were partially separable by linear discriminant analysis. Notably, significantly dysregulated lipids between pathological groups versus control displayed a reverse lipid regulation pattern compared to statin treated controls versus non treated controls.ConclusionDysregulation of the plasma lipidome is characteristic of chronic inflammatory diseases. Lipid profiling accurately identifies the diseases and in the case of CVD also identifies sub-classes. Dysregulated lipids are partially but not fully counterbalanced by statin treatment.

Download Full-text

Cardiovascular Disease Prediction from Electrocardiogram by using Machine Learning Method: A Snapshot from the Subjects of the Malaysian Cohort

10.21203/rs.2.22561/v1 ◽

2020 ◽

Author(s):

Nazrul Anuar Nayan ◽

Hafifah Ab Hamid ◽

Mohd Zubir Suboh ◽

Noraidatulakma Abdullah ◽

Rosmina Jaafar ◽

...

Keyword(s):

Machine Learning ◽

Cardiovascular Disease ◽

Nearest Neighbor ◽

Total Cholesterol Level ◽

Population Based ◽

Support Vector ◽

K Nearest Neighbor ◽

Cvd Risk ◽

Linear Discriminant ◽

Artificial Neural Network Ann

Abstract Background: Cardiovascular disease (CVD) is the leading cause of deaths worldwide. In 2017, CVD contributed to 13,503 deaths in Malaysia. The current approaches for CVD prediction are usually invasive and costly. Machine learning (ML) techniques allow an accurate prediction by utilizing the complex interactions among relevant risk factors. Results: This study presents a case–control study involving 60 participants from The Malaysian Cohort, which is a prospective population-based project. Five parameters, namely, the R–R interval and root mean square of successive differences extracted from electrocardiogram (ECG), systolic and diastolic blood pressures, and total cholesterol level, were statistically significant in predicting CVD. Six ML algorithms, namely, linear discriminant analysis, linear and quadratic support vector machines, decision tree, k-nearest neighbor, and artificial neural network (ANN), were evaluated to determine the most accurate classifier in predicting CVD risk. ANN, which achieved 90% specificity, 90% sensitivity, and 90% accuracy, demonstrated the highest prediction performance among the six algorithms. Conclusions: In summary, by utilizing ML techniques, ECG data can serve as a good parameter for CVD prediction among the Malaysian multiethnic population.

Download Full-text

Introduction and Implementation of Machine Learning Algorithms in R

Advances in Business Information Systems and Analytics - Sentiment Analysis and Knowledge Discovery in Contemporary Business ◽

10.4018/978-1-5225-4999-4.ch008 ◽

2019 ◽

pp. 126-147

Author(s):

S. R. Mani Sekhar ◽

G. M. Siddesh

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Support Vector Machine ◽

Discriminant Analysis ◽

Computer Science ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Linear Discriminant ◽

The Given

Machine learning is one of the important areas in the field of computer science. It helps to provide an optimized solution for the real-world problems by using past knowledge or previous experience data. There are different types of machine learning algorithms present in computer science. This chapter provides the overview of some selected machine learning algorithms such as linear regression, linear discriminant analysis, support vector machine, naive Bayes classifier, neural networks, and decision trees. Each of these methods is illustrated in detail with an example and R code, which in turn assists the reader to generate their own solutions for the given problems.

Download Full-text

Short-Term Traffic Forecasting in Optical Network using Linear Discriminant Analysis Machine Learning Classifier

2020 22nd International Conference on Transparent Optical Networks (ICTON) ◽

10.1109/icton51198.2020.9203040 ◽

2020 ◽

Cited By ~ 2

Author(s):

Daniel Szostak ◽

Krzysztof Walkowiak ◽

Adam Wlodarczyk

Keyword(s):

Machine Learning ◽

Discriminant Analysis ◽

Linear Discriminant Analysis ◽

Optical Network ◽

Short Term ◽

Linear Discriminant ◽

Traffic Forecasting ◽

Learning Classifier

Download Full-text

Cardiovascular Disease Prediction from Electrocardiogram by Using Machine Learning

International Journal of Online and Biomedical Engineering (iJOE) ◽

10.3991/ijoe.v16i07.13569 ◽

2020 ◽

Vol 16 (07) ◽

pp. 34

Author(s):

Nayan Nazrul Anuar ◽

Ab Hamid Hafifah ◽

Suboh Mohd Zubir ◽

Abdullah Noraidatulakma ◽

Jaafar Rosmina ◽

...

Keyword(s):

Machine Learning ◽

Cardiovascular Disease ◽

Nearest Neighbor ◽

Total Cholesterol Level ◽

Population Based ◽

Support Vector ◽

K Nearest Neighbor ◽

Cvd Risk ◽

Linear Discriminant ◽

Artificial Neural Network Ann

<p>Cardiovascular disease (CVD) is the leading cause of deaths worldwide. In 2017, CVD contributed to 13,503 deaths in Malaysia. The current approaches for CVD prediction are usually invasive and costly. Machine learning (ML) techniques allow an accurate prediction by utilizing the complex interactions among relevant risk factors. This study presents a case–control study involving 60 participants from The Malaysian Cohort, which is a prospective population-based project. Five parameters, namely, the R–R interval and root mean square of successive differences extracted from electrocardiogram (ECG), systolic and diastolic blood pressures, and total cholesterol level, were statistically significant in predicting CVD. Six ML algorithms, namely, linear discriminant analysis, linear and quadratic support vector machines, decision tree, k-nearest neighbor, and artificial neural network (ANN), were evaluated to determine the most accurate classifier in predicting CVD risk. ANN, which achieved 90% specificity, 90% sensitivity, and 90% accuracy, demonstrated the highest prediction performance among the six algorithms. In summary, by utilizing ML techniques, ECG data can serve as a good parameter for CVD prediction among the Malaysian multiethnic population.</p>

Download Full-text

Sex estimation in cranial remains: A comparison of machine learning and discriminant analysis in Italian populations

10.1101/2020.04.30.071597 ◽

2020 ◽

Author(s):

A Pozzi ◽

C Raffone ◽

MG Belcastro ◽

TL Camilleri-Carter

Keyword(s):

Machine Learning ◽

Discriminant Analysis ◽

Linear Discriminant Analysis ◽

Foramen Magnum ◽

Sex Estimation ◽

Learning Models ◽

Linear Discriminant ◽

Machine Learning Methods ◽

Cranial Measurements ◽

Machine Learning Models

ABSTRACTObjectivesUsing cranial measurements in two Italian populations, we compare machine learning methods to the more traditional method of linear discriminant analysis in estimating sex. We use crania in sex estimation because it is useful especially when remains are fragmented or displaced, and the cranium may be the only remains found.Materials and MethodsUsing the machine learning methods of decision tree learning, support-vector machines, k-nearest neighbor algorithm, and ensemble methods we estimate the sex of two populations: Samples from Bologna and samples from the island of Sardinia. We used two datasets, one containing 17 cranial measurements, and one measuring the foramen magnum.Results and DiscussionOur results indicate that machine learning models produce similar results to linear discriminant analysis, but in some cases machine learning produces more consistent accuracy between the sexes. Our study shows that sex can be accurately predicted (> 80%) in Italian populations using the cranial measurements we gathered, except for the foramen magnum, which shows a level of accuracy of ∼70% accurate which is on par with previous geometric morphometrics studies using crania in sex estimation. We also find that our trained machine learning models produce population-specific results; we see that Italian crania are sexually dimorphic, but the features that are important to this dimorphism differ between the populations.

Download Full-text

Single Cell Raman Spectroscopy to Identify Different Stages of Proliferating Human Hepatocytes for Cell Therapy

10.21203/rs.3.rs-421582/v1 ◽

2021 ◽

Author(s):

Chen Ma ◽

Ludi Zhang ◽

Ting He ◽

Huiying Cao ◽

Chenhui Ma ◽

...

Keyword(s):

Machine Learning ◽

Raman Spectroscopy ◽

Discriminant Analysis ◽

Cell Therapy ◽

Linear Discriminant Analysis ◽

Learning Model ◽

Human Hepatocytes ◽

Linear Discriminant ◽

Analytical Technique ◽

Machine Learning Model

Abstract Background: Cell therapy provides hope for treatment of advanced liver failure. Proliferating human hepatocytes (ProliHHs) were derived from primary human hepatocytes (PHH) and as potential alternative for cell therapy in liver diseases. Due to the continuous decline of mature hepatic genes and increase of progenitor like genes during ProliHHs expanding, it is challenge to monitor the critical changes of the whole process. Raman microspectroscopy is a noninvasive, label free analytical technique with high sensitivity capacity. In this study, we evaluated the potential and feasibility to identify ProliHHs from PHH with Raman spectroscopy.Methods: Raman spectra were collected at least 600 single spectrum for PHH and ProliHHs at different stages (Passage 1 to Passage 4). Linear discriminant analysis and a two-layer machine learning model were used to analyze the Raman spectroscopy data. Significant differences in Raman bands were validated by the associated conventional kits.Results: Linear discriminant analysis successfully classified ProliHHs at different stages and PHH. A two-layer machine learning model was established and the overall accuracy was at 84.6%. Significant differences in Raman bands have been found within different ProliHHs cell groups, especially changes at 1003 cm-1, 1206 cm-1 and 1300 cm-1. These changes were linked with reactive oxygen species, hydroxyproline and triglyceride levels in ProliHHs, and the hypothesis were consistent with the corresponding assay results. Conclusions: In brief, Raman spectroscopy was successfully employed to identify different stages of ProliHHs during dedifferentiation process. The approach can simultaneously trace multiple changes of cellular components from somatic cells to progenitor cells.

Download Full-text

Chronic Inflammatory Diseases and Atherosclerotic Cardiovascular Disease: Innocent Bystanders or Partners in Crime?

Current Pharmaceutical Design ◽

10.2174/1381612824666180110102341 ◽

2018 ◽

Vol 24 (3) ◽

pp. 281-290 ◽

Cited By ~ 4

Author(s):

Peter Riis Hansen

Keyword(s):

Risk Factors ◽

Cardiovascular Disease ◽

Inflammatory Diseases ◽

Atherosclerotic Cardiovascular Disease ◽

Cvd Risk Factors ◽

Cvd Risk ◽

Chronic Inflammatory Diseases ◽

Increased Risk ◽

Shared Risk

Inflammation plays a significant role in atherosclerosis and cardiovascular disease (CVD). Patients with chronic inflammatory diseases are at increased risk of CVD, but it is debated whether this association is causal or dependent on shared risk factors, other exposures, genes, and/or inflammatory pathways. The current review summarizes epidemiological, clinical, and experimental data supporting the role of shared inflammatory mechanisms between atherosclerotic CVD and rheumatoid arthritis, psoriasis, inflammatory bowel disease, and periodontitis, respectively, and provides insights to future prospects in this area of research. Awareness of the role of inflammation in CVD in patients with chronic inflammatory diseases and the potential for anti-inflammatory therapy, e.g., with tumor necrosis factor-α inhibitors, to also reduce atherosclerotic CVD has evolved into guideline- based recommendations. These include regular CVD risk assessment, aggressive treatment of traditional CVD risk factors, and recognition of reduced CVD as an added benefit of strict inflammatory disease control. At present, chronic inflammatory diseases would appear to qualify as partners in crime and not merely innocent bystanders to CVD. However, definite incremental contributions of inflammation versus effects of the complex interplay with other CVD risk factors may never be fully elucidated and for the foreseeable future, inflammation is posed to maintain its current position as both a marker and a maker of CVD, with clinical utility both for identification of patient at risk of CVD and as target for therapy to reduce CVD.

Download Full-text