A distinct metabolic signature predicts development of fasting plasma glucose

Hische, Manuela; Larhlimi, Abdelhalim; Schwärz, F.; Fischer-Rosinský, Antje; Bobbert, Thomas; Assmann, Anke; Catchpole, Gareth; Pfeiffer, Andreas F. H.; Willmitzer, Lothar; Selbig, Joachim; Spranger, Joachim

doi:10.1186/2043-9113-2-3

Cited by 6 publications

(2 citation statements)

References 65 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data mining was used to predict the probability of diabetes from classification. This model is one of the most commonly used methods of machine learning for prediction of medical data (14). In data sorting algorithms, the division of data into two educational and experimental parts is 75 to 25 and using the technique of the method, the fold-10 division of the models are created, the fold-10 method randomly divides the whole data into 10 sections.…”

Section: Data Modelingmentioning

confidence: 99%

Prediction and Diagnosis of Diabetes by Using Data Mining Techniques

Mirzajani

salimi

2018

Avicenna J Med Biochem

View full text Add to dashboard Cite

Background: Diabetes mellitus (DM) is one of the most common diseases in the world. Complications of this disease include nephropathy, cardiac arrest, blindness, and even mutilation of the body. The accurate diagnosis of this condition is very important. Objectives: This study was to identify and provide a model for diagnosis of DM using data mining. Methods: The data used in this study were obtained from 768 women aged 21-83 year old. Nine variables were selected for investigation. The neural network, Basin network, C5.0, and support vector machine models were compared for predicting diabetes and their precision to this end. Clementine 12 software was used to analyze the data. Results: The proposed method for classification of records with the C5.0 algorithm for accuracy data is 80.2% and for accuracy data 87.5%. In comparison with similar studies, it was better to diagnose people with diabetes, while glucose, body mass index and age variables were important in this study. Conclusion: The C5.0 algorithm showed the highest value of accuracy, specificity, and sensitivity compared with other methods studied. Therefore, the C5.0 algorithm probably performs the best classification among other algorithms and is recommended as the best method for diabetes prediction using available data.

show abstract

Section: Data Modelingmentioning

confidence: 99%

Prediction and Diagnosis of Diabetes by Using Data Mining Techniques

Mirzajani

salimi

2018

Avicenna J Med Biochem

View full text Add to dashboard Cite

show abstract

“…However, consistency of selected feature rankings has been shown to be problematic for high dimensional problems (Verikas, Gelzinis, & Bacauskiene, 2011). It has been used in several metabolomics studies (Hische et al, 2012;Houtkooper et al, 2011;Patterson et al, 2011) and is readily available in the R package randomForest (Liaw & Wiener, 2002).…”

Section: Random Forest (Rf)mentioning

confidence: 99%

Optimal Algorithm for Metabolomics Classification and Feature Selection varies by Dataset

Determan¹

2014

IJB

View full text Add to dashboard Cite

Metabolomics, the systematic identification and quantification of all metabolites in a biological system, is increasingly applied towards identification of biomarkers for disease diagnosis, prognosis and risk prediction. Applications of metabolomics extend across the health spectrum including Alzheimer's, cancer, diabetes, and trauma. Despite the continued interest in metabolomics there are numerous techniques for analyzing metabolomics datasets with the intent to classify group membership (e.g. Control or Treated). These include Partial Least Squares Discriminant Analysis, Support Vector Machines, Random Forest, Regularized Generalized Linear Models, and Prediction Analysis for Microarrays. Each classification algorithm is dependent upon different assumptions and can potentially lead to alternate conclusions. This project seeks to conduct an in depth comparison of algorithm performance on both simulated and real datasets to determine which algorithms perform best given alternate dataset structures. Three simulated datasets were generated to validate algorithm performance and mimic 'real' metabolomics data: (Han et al., 2011) independent null dataset (no correlation, no discriminatory variables), (Davis, Schiller, Eurich, & Sawyer, 2012) correlated null (no discriminating variables), (Guan et al., 2009) correlated discriminatory. This comparison is also applied to 3 open-access datasets including two Nuclear Magnetic Resonance (NMR) and one Mass Spectrometry (MS) dataset. Performance was evaluated based on the Robustness-Performance-Trade-off (RPT) incorporating a balance between model classification accuracy and feature selection stability. We also provide a free, open-source R Bioconductor package (OmicsMarkeR) that conducts the analyses herein. The proposed work provides an important advancement in metabolomics analysis and helps alleviate the confusion of potentially paradoxical analyses thereby leading to improved exploration of disease states and identification of clinically important biomarkers.

show abstract

Reduced mitochondrial DNA content in lymphocytes is associated with insulin resistance and inflammation in patients with impaired fasting glucose

2018

View full text Add to dashboard Cite

Altered mitochondrial DNA (mtDNA) is the most common denominator to numerous metabolic diseases. The present study sought to investigate the correlation between mtDNA content in lymphocytes and associated clinical risk factors for impaired fasting glucose (IFG). We included 23 healthy control and 42 IFG participants in this cross-sectional study. The measurements of mtDNA content in lymphocytes and pro-inflammatory markers derived from both normal and diseased individuals were quantified. Spearman partial correlation and multivariate statistical analyses were employed to evaluate the association between mtDNA content and other metabolic covariates in IFG. Reduced mtDNA content was observed in the IFG group with microvascular complications than those without complications. The IFG patients with lowest median of mtDNA content had considerably elevated hyperglycemia, insulin resistance and inflammation. The adjusted partial correlation analysis showed that mtDNA content was positively correlated with HDL-cholesterol and IL-10 (P < 0.005 for all). Further, multiple linear regression analyses verified that reduced mtDNA content in lymphocytes was independently associated with HOMA-IR (β = 0.027, P = 0.003), HbA1c (β = 0.652, P = 0.002), HDL-cholesterol (β = - 1.056, P = 0.021), IL-6 (β = 0.423, P = 0.002), IL-10 (β = - 1.234, P = 0.043) and TNF-α (β = 0.542, P < 0.001) after adjustment for confounding factors. Our data show that reduced mtDNA content in lymphocytes was associated with insulin resistance and inflammation in individuals with IFG.

show abstract

A distinct metabolic signature predicts development of fasting plasma glucose

Cited by 6 publications

References 65 publications

Prediction and Diagnosis of Diabetes by Using Data Mining Techniques

Prediction and Diagnosis of Diabetes by Using Data Mining Techniques

Optimal Algorithm for Metabolomics Classification and Feature Selection varies by Dataset

Reduced mitochondrial DNA content in lymphocytes is associated with insulin resistance and inflammation in patients with impaired fasting glucose

Contact Info

Product

Resources

About