Measuring the accuracy of diagnostic systems.

By J. Swets. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Robust Classification for Imprecise Environments (2000, methodology): “…can be made with Receiver Operating Characteristic (ROC) analysis, a classic methodology from signal detection theory that is common in medical diagnosis and has recently begun to be used more generally in AI classiﬁer work (Beck & Schultz, 1986; Egan, 1975; Swets, 1988; Friedman & Wyatt, 1997).”
Prospective sampling based on model ensembles improves the detection of rare species (2010, background): “9 to 1 indicate good predictions (Swets 1988).”
Ecological niches of open ocean phytoplankton taxa (2015, methodology): “Model performance We evaluate the receiver operating characteristic (ROC) metric (Swets 1988; Manel et al. 2001) to quantify the predictive quality of MaxEnt models.”
Using AUC and accuracy in evaluating learning algorithms (2005, background): “It has been extensively studied and applied in medical diagnosis since the 1970s [24], [35].”
Prediction of residues in discontinuous B‐cell epitopes using protein 3D structures (2006, methodology): “The area under a receiver operator characteristics curve (AUC) (Swets 1988) was used as performance measure.”
Effects of landscape-scale broadleaved woodland configuration and extent on roost location for six bat species across the UK (2011, unknown): “877, representing reasonable predictive accuracy (Swets, 1988).”
A readers' guide to the interpretation of diagnostic test properties: clinical example of sepsis (2003, background): “As a rule of thumb a test with an area under the curve greater than 0.9 has high accuracy, while 0.7 – 0.9 indicates moderate accuracy, 0.5–0.7 low accuracy, and 0.5 a tossup (chance result) [ 20 ].”
Landslide susceptibility evaluation and hazard zonation techniques – a review (2020, methodology): “With the selection of decision parameter that adjust the tradeoff between the proportion of correctly identified pixels and the incorrectly identified pixels, the ROC performance curve can be varied systematically (Kavzoglu et al. 2014; Swets 1988).”
Ensemble modelling of species distribution: the effects of geographical and environmental ranges (2011, background): “5 indicates that the model’s discrimination is no better than random sorting, and 1 indicates that the model discriminates perfectly (Swets 1988).”
BIOMOD – optimizing predictions of species distributions and projecting potential future shifts under global change (2003, methodology): “Conclusions are similar according to AUC, where subjective guidelines (Swets, 1988) suggest a very good agreement for AUC above 0.”
AUC: A Better Measure than Accuracy in Comparing Learning Algorithms (2003, methodology): “Thus, given only classification labels in training and testing sets, are there better methods than accuracy to evaluate classifiers that also produce rankings? AUC (area under the curve) of the ROC (Receiver Operating Characteristics) curve has been recently used as an alternative measure for machin”
Global warming will affect the genetic diversity and uniqueness of Lycaena helle populations (2011, methodology): “In our models, we received ‘good’ to ‘excellent’ AUC values following previously given definitions (Swets, 1988), suggesting that our SDM output was of high quality (Fig.”
Validating a Number Sense Screening Tool for Use in Kindergarten and First Grade: Prediction of Mathematics Proficiency in Third Grade (2010, background): “50, signifying that the true-positive rates and falsepositive rates are equal across all possible cut scores and that the test provides no discrimination (Swets, 1988).”
The use of receiver operating characteristic curves in biomedical informatics (2005, background): “The ROC curve captures in a single graph the trade-off between a test s sensitivity and specificity over its entire range [7].”
Constrain to perform: Regularization of habitat models (2006, methodology): “Discrimination We use the AUC (area under the receiver operatng characteristic curve) as a measure of overall model iscrimination (Swets, 1988).”