Table 1 Respiratory disease diagnostic model performance across methodologies.

From: Machine-learning algorithms for asthma, COPD, and lung cancer risk assessment using circulating microbial extracellular vesicle data and their application to assess dietary effects

Model

Method

Mean AUC

SD of AUC

COPD

All-feature GLM

0.49

0.054

Selected-feature GLM

0.66

0.158

ANN

0.86

0.012

GBM

0.91

0.003

ANN/GBM ensemble

0.93

0.004

Asthma

All-feature GLM

0.50

0.031

Selected-feature GLM

0.80

0.057

ANN

0.97

0.007

GBM

0.98

0.001

ANN/GBM ensemble

0.99

0.002

Lung cancer

All-feature GLM

0.50

0.040

Selected-feature GLM

0.77

0.057

ANN

0.87

0.030

GBM

0.92

0.003

ANN/GBM ensemble

0.94

0.004

  1. AUC area under the curve, SD standard deviation, COPD chronic obstructive pulmonary disease, GLM general linearized model, ANN artificial neural network; GBM gradient boosting machine.
Back to article page