scholarly journals Plasma Metabolome Profiling for the Diagnosis of Catecholamine Producing Tumors

2021 ◽  
Vol 12 ◽  
Author(s):  
Juliane März ◽  
Max Kurlbaum ◽  
Oisin Roche-Lancaster ◽  
Timo Deutschbein ◽  
Mirko Peitzsch ◽  
...  
Keyword(s):  
Feature Selection ◽  
Individual Variability ◽  
Gradient Boosting ◽  
Curative Surgery ◽  
Quantitative Metabolomics ◽  
Catecholamine Excess ◽  
Plasma Metabolome ◽  
Liquid Chromatography Tandem Mass ◽  
Total Urine ◽  
Plasma Metanephrines

ContextPheochromocytomas and paragangliomas (PPGL) cause catecholamine excess leading to a characteristic clinical phenotype. Intra-individual changes at metabolome level have been described after surgical PPGL removal. The value of metabolomics for the diagnosis of PPGL has not been studied yet.ObjectiveEvaluation of quantitative metabolomics as a diagnostic tool for PPGL.DesignTargeted metabolomics by liquid chromatography-tandem mass spectrometry of plasma specimens and statistical modeling using ML-based feature selection approaches in a clinically well characterized cohort study.PatientsProspectively enrolled patients (n=36, 17 female) from the Prospective Monoamine-producing Tumor Study (PMT) with hormonally active PPGL and 36 matched controls in whom PPGL was rigorously excluded.ResultsAmong 188 measured metabolites, only without considering false discovery rate, 4 exhibited statistically significant differences between patients with PPGL and controls (histidine p=0.004, threonine p=0.008, lyso PC a C28:0 p=0.044, sum of hexoses p=0.018). Weak, but significant correlations for histidine, threonine and lyso PC a C28:0 with total urine catecholamine levels were identified. Only the sum of hexoses (reflecting glucose) showed significant correlations with plasma metanephrines.By using ML-based feature selection approaches, we identified diagnostic signatures which all exhibited low accuracy and sensitivity. The best predictive value (sensitivity 87.5%, accuracy 67.3%) was obtained by using Gradient Boosting Machine Modelling.ConclusionsThe diabetogenic effect of catecholamine excess dominates the plasma metabolome in PPGL patients. While curative surgery for PPGL led to normalization of catecholamine-induced alterations of metabolomics in individual patients, plasma metabolomics are not useful for diagnostic purposes, most likely due to inter-individual variability.

scholarly journals Metabolic impact of pheochromocytoma/paraganglioma: targeted metabolomics in patients before and after tumor removal

2019 ◽  
Vol 181 (6) ◽  
pp. 647-657
Author(s):  
Zoran Erlic ◽  
Max Kurlbaum ◽  
Timo Deutschbein ◽  
Svenja Nölting ◽  
Aleksander Prejbisz ◽  
...  
Keyword(s):  
Acid Metabolism ◽  
Urinary Catecholamine ◽  
Targeted Metabolomics ◽  
Tumor Removal ◽  
Chromatography Tandem Mass Spectrometry ◽  
Catecholamine Excess ◽  
Before And After ◽  
Liquid Chromatography Tandem Mass ◽  
Tumor Phenotype ◽  
Total Urine

Objective Excess catecholamine release by pheochromocytomas and paragangliomas (PPGL) leads to characteristic clinical features and increased morbidity and mortality. The influence of PPGLs on metabolism is ill described but may impact diagnosis and management. The objective of this study was to systematically and quantitatively study PPGL-induced metabolic changes at a systems level. Design Targeted metabolomics by liquid chromatography-tandem mass spectrometry of plasma specimens in a clinically well-characterized prospective cohort study. Methods Analyses of metabolic profiles of plasma specimens from 56 prospectively enrolled and clinically well-characterized patients (23 males, 33 females) with catecholamine-producing PPGL before and after surgery, as well as measurement of 24-h urinary catecholamine using LC-MS/MS. Results From 127 analyzed metabolites, 15 were identified with significant changes before and after surgery: five amino acids/biogenic amines (creatinine, histidine, ornithine, sarcosine, tyrosine) and one glycerophospholipid (PCaeC34:2) with increased concentrations and six glycerophospholipids (PCaaC38:1, PCaaC42:0, PCaeC40:2, PCaeC42:5, PCaeC44:5, PCaeC44:6), two sphingomyelins (SMC24:1, SMC26:1) and hexose with decreased levels after surgery. Patients with a noradrenergic tumor phenotype had more pronounced alterations compared to those with an adrenergic tumor phenotype. Weak, but significant correlations for 8 of these 15 metabolites with total urine catecholamine levels were identified. Conclusions This first large prospective metabolomics analysis of PPGL patients demonstrates broad metabolic consequences of catecholamine excess. Robust impact on lipid and amino acid metabolism may contribute to increased morbidity of PPGL patients.

scholarly journals Apixaban concentration variability and relation to clinical outcomes in real-life patients with atrial fibrillation

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Alenka Mavri ◽  
Nina Vene ◽  
Mojca Božič-Mijovski ◽  
Marko Miklič ◽  
Lisbeth Söderblom ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Clinical Outcomes ◽  
Thromboembolic Event ◽  
Real Life ◽  
Individual Variability ◽  
Blood Samples ◽  
Chromatography Tandem Mass Spectrometry ◽  
Significant Difference ◽  
Liquid Chromatography Tandem Mass ◽  
Peak Blood

AbstractIn some clinical situations, measurements of anticoagulant effect of apixaban may be needed. We investigated the inter- and intra-individual apixaban variability in patients with atrial fibrillation and correlated these results with clinical outcome. We included 62 patients receiving either 5 mg (A5, n = 32) or 2.5 mg (A2.5, n = 30) apixaban twice-daily. We collected three trough and three peak blood samples 6–8 weeks apart. Apixaban concentration was measured by liquid chromatography-tandem mass-spectrometry (LC–MS/MS) and by anti-Xa. Patients on A2.5 were older, had lower creatinine clearance, higher CHA2DS2VASc (4.7 ± 1.0 vs. 3.4 ± 1.7) and lower trough (85 ± 39 vs. 117 ± 53 ng/mL) and peak (170 ± 56 vs. 256 ± 91 ng/mL) apixaban concentrations than patients on A5 (all p < 0.01). In patients on A5, LC–MS/MS showed a significant difference between through levels and between peak levels (p < 0.01). During apixaban treatment, 21 patients suffered bleeding (2 major). There was no association between bleeding and apixaban concentrations or variability. Four patients who suffered thromboembolic event had lower peak apixaban concentrations than patients without it (159 ± 13 vs. 238 ± 88 ng/mL, p = 0.05). We concluded, that there was a significant intra- and inter-individual variability in apixaban trough and peak concentrations. Neither variability nor apixaban concentrations were associated with clinical outcomes.

scholarly journals Development of a Machine Learning Model for Optimal Applicator Selection in High-Dose-Rate Cervical Brachytherapy

2021 ◽  
Vol 11 ◽  
Author(s):  
Kailyn Stenhouse ◽  
Michael Roumeliotis ◽  
Robyn Banerjee ◽  
Svetlana Yanushkevich ◽  
Philip McGeachy
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Dose Rate ◽  
High Dose Rate ◽  
Gradient Boosting ◽  
Classification Algorithms ◽  
High Dose ◽  
Discriminative Performance ◽  
The Individual ◽  
Voting Model

PurposeTo develop and validate a preliminary machine learning (ML) model aiding in the selection of intracavitary (IC) versus hybrid interstitial (IS) applicators for high-dose-rate (HDR) cervical brachytherapy.MethodsFrom a dataset of 233 treatments using IC or IS applicators, a set of geometric features of the structure set were extracted, including the volumes of OARs (bladder, rectum, sigmoid colon) and HR-CTV, proximity of OARs to the HR-CTV, mean and maximum lateral and vertical HR-CTV extent, and offset of the HR-CTV centre-of-mass from the applicator tandem axis. Feature selection using an ANOVA F-test and mutual information removed uninformative features from this set. Twelve classification algorithms were trained and tested over 100 iterations to determine the highest performing individual models through nested 5-fold cross-validation. Three models with the highest accuracy were combined using soft voting to form the final model. This model was trained and tested over 1,000 iterations, during which the relative importance of each feature in the applicator selection process was determined.ResultsFeature selection indicated that the mean and maximum lateral and vertical extent, volume, and axis offset of the HR-CTV were the most informative features and were thus provided to the ML models. Relative feature importances indicated that the HR-CTV volume and mean lateral extent were most important for applicator selection. From the comparison of the individual classification algorithms, it was found that the highest performing algorithms were tree-based ensemble methods – AdaBoost Classifier (ABC), Gradient Boosting Classifier (GBC), and Random Forest Classifier (RFC). The accuracy of the individual models was compared to the voting model for 100 iterations (ABC = 91.6 ± 3.1%, GBC = 90.4 ± 4.1%, RFC = 89.5 ± 4.0%, Voting Model = 92.2 ± 1.8%) and the voting model was found to have superior accuracy. Over the final 1,000 evaluation iterations, the final voting model demonstrated a high predictive accuracy (91.5 ± 0.9%) and F1 Score (90.6 ± 1.1%).ConclusionThe presented model demonstrates high discriminative performance, highlighting the potential for utilization in informing applicator selection prospectively following further clinical validation.

scholarly journals Techniques for Detecting Malware Traffic: A Comprehensive Approach to Feature Selection and Classification

2021 ◽  
Vol 9 (12) ◽  
pp. 1-10
Author(s):  
Harsha A K
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Random Forest ◽  
Learning Algorithms ◽  
Malware Detection ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Steady Increase ◽  
Extreme Gradient Boosting

Abstract: Since the advent of encryption, there has been a steady increase in malware being transmitted over encrypted networks. Traditional approaches to detect malware like packet content analysis are inefficient in dealing with encrypted data. In the absence of actual packet contents, we can make use of other features like packet size, arrival time, source and destination addresses and other such metadata to detect malware. Such information can be used to train machine learning classifiers in order to classify malicious and benign packets. In this paper, we offer an efficient malware detection approach using classification algorithms in machine learning such as support vector machine, random forest and extreme gradient boosting. We employ an extensive feature selection process to reduce the dimensionality of the chosen dataset. The dataset is then split into training and testing sets. Machine learning algorithms are trained using the training set. These models are then evaluated against the testing set in order to assess their respective performances. We further attempt to tune the hyper parameters of the algorithms, in order to achieve better results. Random forest and extreme gradient boosting algorithms performed exceptionally well in our experiments, resulting in area under the curve values of 0.9928 and 0.9998 respectively. Our work demonstrates that malware traffic can be effectively classified using conventional machine learning algorithms and also shows the importance of dimensionality reduction in such classification problems. Keywords: Malware Detection, Extreme Gradient Boosting, Random Forest, Feature Selection.

scholarly journals Evaluating Variable Selection and Machine Learning Algorithms for Estimating Forest Heights by Combining Lidar and Hyperspectral Data

2020 ◽  
Vol 9 (9) ◽  
pp. 507
Author(s):  
Sanjiwana Arjasakusuma ◽  
Sandiaga Swahyu Kusuma ◽  
Stuart Phinn
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Learning Algorithms ◽  
Principal Component ◽  
Hyperspectral Data ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Forest Height ◽  
Extreme Gradient Boosting

Machine learning has been employed for various mapping and modeling tasks using input variables from different sources of remote sensing data. For feature selection involving high- spatial and spectral dimensionality data, various methods have been developed and incorporated into the machine learning framework to ensure an efficient and optimal computational process. This research aims to assess the accuracy of various feature selection and machine learning methods for estimating forest height using AISA (airborne imaging spectrometer for applications) hyperspectral bands (479 bands) and airborne light detection and ranging (lidar) height metrics (36 metrics), alone and combined. Feature selection and dimensionality reduction using Boruta (BO), principal component analysis (PCA), simulated annealing (SA), and genetic algorithm (GA) in combination with machine learning algorithms such as multivariate adaptive regression spline (MARS), extra trees (ET), support vector regression (SVR) with radial basis function, and extreme gradient boosting (XGB) with trees (XGbtree and XGBdart) and linear (XGBlin) classifiers were evaluated. The results demonstrated that the combinations of BO-XGBdart and BO-SVR delivered the best model performance for estimating tropical forest height by combining lidar and hyperspectral data, with R2 = 0.53 and RMSE = 1.7 m (18.4% of nRMSE and 0.046 m of bias) for BO-XGBdart and R2 = 0.51 and RMSE = 1.8 m (15.8% of nRMSE and −0.244 m of bias) for BO-SVR. Our study also demonstrated the effectiveness of BO for variables selection; it could reduce 95% of the data to select the 29 most important variables from the initial 516 variables from lidar metrics and hyperspectral data.

Sign in / Sign up

Export Citation Format

Share Document