Decision Curve Analysis: A Novel Method for Evaluating Prediction Models

By Andrew J. Vickers, E. Elkin. 2006

4,610 citations recorded by the source corpus.

Subfields: Pulmonary and Respiratory Medicine, Rheumatology

How researchers see this paper

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

In Pulmonary and Respiratory Medicine

In Rheumatology

Citations in the corpus

Developing an optimal short-form of the PTSD Checklist for DSM-5 (PCL-5) (2019, background): “NB is typically evaluated through decision curves (Vickers & Elkin, 2006), which plot the minimum PPV the clinician would require to designate a patient as screening positive (x‐axis), and the NB of the screening scale at that threshold (y‐axis).”
External validation of clinical prediction models using big datasets from e-health records or IPD meta-analysis: opportunities and challenges (2016, background): “80 A full discussion of the different research questions one may address in big datasets, such as an IPD meta-analysis, for clinical prediction model research is given by Debray and colleagues.”
Computer‐aided diagnosis of prostate cancer using a deep convolutional neural network from multiparametric MRI (2018, methodology): “Second, the cost-effect benefit analysis proposed by Vickers and Elkin was performed to evaluate the additional benefits of the DCNN method when combined with the conventional PI-RADS scheme.(19) Statistical analysis was conducted using the R package (Risk Model Decision Analysis, https://github.”
Extensions of net reclassification improvement calculations to measure usefulness of new biomarkers (2010, positive): “If categories are sensibly defined, the decision theory suggests that the category threshold is the decision threshold [20, 21], which means weights are proportional to the sizes of the two intervals into which the (0, 1) interval is partitioned.”
External validation of multivariable prediction models: a systematic review of methodological conduct and reporting (2014, methodology): “New methods based on decision curve analysis (net benefit) [50] and relative utility [51] have recently been introduced.”
Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies: The CHARMS Checklist (2014, background): “Their use has been criticised as they rely on a priori–defined probability thresholds and do not account for difference in consequences of falsely reclassified individuals [122,127,128].”
Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges (2016, methodology): “Once we have chosen the ‘best’ model we use the testing data to calculate clinical performance metrics (e.g. calibration, net-beneﬁt, 38 etc.) and compare with any other existing approaches.”
Focus on : Contemporary Methods in Biostatistics ( I ) Regression Modeling Strategies (2017, methodology): “Several approaches have been proposed, the most important being net reclassification improvement, integrated discrimination improvement,(41,42) and decision curve analysis.(43) In summary, a good model calibration and discrimination, evaluated through bootstrapping, is currently considered an import”
Predicting Current Glycated Hemoglobin Values in Adults: Development of an Algorithm From the Electronic Health Record (2018, positive): “Prediction model metrics included measures of discrimination (concordance statistic), calibration (calibration curves), and decision curves [40].”