Journal: European radiology

Article Title: Integrated prediction of lesion-specific ischemia from quantitative coronary CT Angiography using machine learning: a multicenter study

doi: 10.1007/s00330-017-5223-z

Figure Lengend Snippet: Prediction of lesion-specific ischemia by the integrated ischemia risk score by machine learning (ML-combined) and quantitative plaque volumes (LD-NCP, NCP and total plaque volume). ML-combined had a significantly higher AUC compared to individual quantitative CTA plaque volumes (*p<0.003 compared to LD-NCP, NCP and total plaque volume). AUC for LD-NCP plaque volume was significantly higher than for total plaque volume (p=0.01)

Article Snippet: We also compared the machine learning ischemia risk score with conventional statistical logistic regression performed using a Stata version 11 module, using the same data, 10-fold cross-validation and the same data folds.

Techniques:

Journal: European radiology

Article Title: Integrated prediction of lesion-specific ischemia from quantitative coronary CT Angiography using machine learning: a multicenter study

doi: 10.1007/s00330-017-5223-z

Figure Lengend Snippet: Prediction of lesion-specific ischemia by the integrated ischemia risk score by machine learning (ML-combined), quantitative stenosis and pre-test likelihood of coronary artery disease. Quantitative stenosis had significantly higher AUC than pre-test likelihood (p=0.0005). ML-combined(*) had a significantly higher AUC than quantitative stenosis (p=0.005) or pretest-likelihood of coronary artery disease (p<0.0001).

Article Snippet: We also compared the machine learning ischemia risk score with conventional statistical logistic regression performed using a Stata version 11 module, using the same data, 10-fold cross-validation and the same data folds.

Techniques:

Journal: European radiology

Article Title: Integrated prediction of lesion-specific ischemia from quantitative coronary CT Angiography using machine learning: a multicenter study

doi: 10.1007/s00330-017-5223-z

Figure Lengend Snippet: IDI for the integrated machine learning score over plaque measures

Article Snippet: We also compared the machine learning ischemia risk score with conventional statistical logistic regression performed using a Stata version 11 module, using the same data, 10-fold cross-validation and the same data folds.

Techniques:

Journal: PLoS ONE

Article Title: Absolute quantification of E . coli virulence and housekeeping genes to determine pathogen loads in enumerated environmental samples

doi: 10.1371/journal.pone.0260082

Figure Lengend Snippet: Graphs depicting the gadAB vs eaeA copies for the 2005–2006 clinical strains (a) and 2008–2009 clinical strains (c) drawn with the Corbett Research Thermal cycler software and gadAB vs eaeA N0 calculated with the LinRegPCR software for the 2005–2006 clinical strains (b) and 2008–2009 clinical strains (c). The red reference line in each graph indicates in each graph is when x = y.

Article Snippet: The LinRegPCR analysis program that was compared to the Corbett Research Thermal Cycler machine software works as follow: The Raw data before baseline was corrected, exported from the Corbett Research Thermal cycler machine software, and imported into the LinRegPCR analysis program.

Techniques: Software