Browsing by Subject "receiver operating characteristic"

Now showing 1 - 3 of 3

Open Access
Comparison of original EuroSCORE, EuroSCORE II and STS risk models in a Turkish cardiac surgical cohort
(2013) Kunt, A.G.; Kurtcephe, M.; Hidiroglu, M.; Cetin L.; Kucuker, A.; Bakuy V.; Ruchan Akar, A.; Sener, E.
OBJECTIVESThe aim of this study was to compare additive and logistic European System for Cardiac Operative Risk Evaluation (EuroSCORE), EuroSCORE II and the Society of Thoracic Surgeons (STS) models in calculating mortality risk in a Turkish cardiac surgical population.METHODSThe current patient population consisted of 428 patients who underwent isolated coronary artery bypass grafting (CABG) between 2004 and 2012, extracted from the TurkoSCORE database. Observed and predicted mortalities were compared for the additive/logistic EuroSCORE, EuroSCORE II and STS risk calculator. The area under the receiver operating characteristics curve (AUC) values were calculated for these models to compare predictive power.RESULTSThe mean patient age was 74.5 ± 3.9 years at the time of surgery, and 35.0% were female. For the entire cohort, actual hospital mortality was 7.9% (n = 34; 95% confidence interval [CI] 5.4-10.5). However, the additive EuroSCORE-predicted mortality was 6.4% (P = 0.23 vs observed; 95% CI 6.2-6.6), logistic EuroSCORE-predicted mortality was 7.9% (P = 0.98 vs observed; 95% CI 7.3-8.6), EuroSCORE II- predicted mortality was 1.7% (P = 0.00 vs observed; 95% CI 1.6-1.8) and STS predicted mortality was 5.8% (P = 0.10 vs observed; 95% CI 5.4-6.2). The mean predictive performance of the analysed models for the entire cohort was fair, with 0.7 (95% CI 0.60-0.79). AUC values for additive EuroSCORE, logistic EuroSCORE, EuroSCORE II and STS risk calculator were 0.70 (95% CI 0.60-0.79), 0.70 (95% CI 0.59-0.80), 0.72 (95% CI 0.62-0.81) and 0.62 (95% CI 0.51-0.73), respectively.CONCLUSIONSEuroSCORE II significantly underestimated mortality risk for Turkish cardiac patients, whereas additive and logistic EuroSCORE and STS risk calculators were well calibrated. © 2013 The Author 2013.
Open Access
A comprehensive methodology for determining the most informative mammographic features
(2013) Wu, Y.; Alagoz O.; Ayvaci, M.U.S.; Munoz Del Rio, A.; Vanness, D.J.; Woods, R.; Burnside, E.S.
This study aims to determine the most informative mammographic features for breast cancer diagnosis using mutual information (MI) analysis. Our Health Insurance Portability and Accountability Act-approved database consists of 44,397 consecutive structured mammography reports for 20,375 patients collected from 2005 to 2008. The reports include demographic risk factors (age, family and personal history of breast cancer, and use of hormone therapy) and mammographic features from the Breast Imaging Reporting and Data System lexicon. We calculated MI using Shannon's entropy measure for each feature with respect to the outcome (benign/malignant using a cancer registry match as reference standard). In order to evaluate the validity of the MI rankings of features, we trained and tested naïve Bayes classifiers on the feature with tenfold cross-validation, and measured the predictive ability using area under the ROC curve (AUC). We used a bootstrapping approach to assess the distributional properties of our estimates, and the DeLong method to compare AUC. Based on MI, we found that mass margins and mass shape were the most informative features for breast cancer diagnosis. Calcification morphology, mass density, and calcification distribution provided predictive information for distinguishing benign and malignant breast findings. Breast composition, associated findings, and special cases provided little information in this task. We also found that the rankings of mammographic features with MI and AUC were generally consistent. MI analysis provides a framework to determine the value of different mammographic features in the pursuit of optimal (i.e., accurate and efficient) breast cancer diagnosis. © 2013 Society for Imaging Informatics in Medicine.
Open Access
GOPred: GO molecular function prediction by combined classifiers
(2010) Saraç Ö.S.; Atalay V.; Cetin-Atalay, R.
Functional protein annotation is an important matter for in vivo and in silico biology. Several computational methods have been proposed that make use of a wide range of features such as motifs, domains, homology, structure and physicochemical properties. There is no single method that performs best in all functional classification problems because information obtained using any of these features depends on the function to be assigned to the protein. In this study, we portray a novel approach that combines different methods to better represent protein function. First, we formulated the function annotation problem as a classification problem defined on 300 different Gene Ontology (GO) terms from molecular function aspect. We presented a method to form positive and negative training examples while taking into account the directed acyclic graph (DAG) structure and evidence codes of GO. We applied three different methods and their combinations. Results show that combining different methods improves prediction accuracy in most cases. The proposed method, GOPred, is available as an online computational annotation tool (http://kinaz.fen.bilkent.edu.tr/gopred). © 2010 Saraç et al.