Cross-Validation

Refaeilzadeh, Payam; Tang, Lei; Liu, Huan

doi:10.1007/978-0-387-39940-9_565

Cited by 1,467 publications

(747 citation statements)

References 6 publications

Supporting

Mentioning

715

Contrasting

Unclassified

Order By: Relevance

“…Group comparisons of categorical variables were performed using Pearson's x 2 -test. To avoid overestimating the accuracy of measurement results and validate the model, we assessed the K-fold crossvalidation by taking random LS measurements in groups of five and partitioning them from our cohort [33].…”

Section: Discussionmentioning

confidence: 99%

Performance of 2D-SWE.GE for predicting different stages of liver fibrosis, using Transient Elastography as the reference method

et al. 2017

View full text Add to dashboard Cite

Aim: To evaluate the performance of 2D shear-wave elastography from General Electric (2D-SWE.GE) for the noninvasiveassessment of liver fibrosis and to identify liver stiffness (LS) cut-off values for predicting different stages of fibrosisusing Transient Elastography (TE) as the reference method. Material and method: We included 331 consecutive subjectswith or without chronic hepatopathies in whom LS was evaluated in the same session by means of 2 elastographic techniques:TE and 2D-SWE.GE. Reliable LS measurements were defined for TE as the median value of 10 measurements with a successrate of ≥60% and an interquartile range (IQR)<30% and for 2D-SWE.GE as the median value of 10 measurements acquiredin a homogenous area and an IQR<30%. To discriminate between TE fibrosis stages we used the following cut-offs: F2- 7;F3- 9.5 and F4- 12kPa. Results: Reliable LS measurements were obtained in 95.8% subjects by 2D-SWE.GE, and 94.2%by TE (p=0.44). Based on TE cut-off values we divided our cohort into four groups: F<2: 30.1%; F=2: 10.2%; F=3: 12.2%;F=4: 47.5%. A strong correlation was found between the LS values obtained by the 2 methods: r=0.83, p<0.0001.LS valuesobtained by 2D-SWE.GE were significantly lower than those obtained by TE: 10.14±4.24 kPa vs. 16.72±13.4 kPa (p<0.0001).The best cut-off value for F≥2, F≥3 and for F=4 were 6.7, 8.2 and 9.3 kPa. Conclusions: The best 2D-SWE.GE cut-off valuesfor predicting F≥2, F≥3 and F=4 were 6.7, 8.2 and 9.3kPa.

show abstract

Section: Discussionmentioning

confidence: 99%

Performance of 2D-SWE.GE for predicting different stages of liver fibrosis, using Transient Elastography as the reference method

et al. 2017

View full text Add to dashboard Cite

show abstract

“…According to Petocz and Reid (2001), in domains related to Mathematics or Computer Sciences it is more common to teach technical contents rather than to develop studentsí creative and emotional skills. Finally, students of domains related to Business and Sociocultural Services (e.g., Administration and Finance, Tourism) are encouraged to actively use creative processes: Defining their own areas of need, determining a project that would support their learning and assessing the quality of their own learning outcomes (Reid & Petocz, 2004). Along the same lines, Sánchez-Ruiz, Hernández-Torrano, Pérez-Gonzalez, Batey, and Petrides (2011) found that emotional self-efficacy and personality traits associated to creativity varied across domains, being Art students those who obtained higher scores on both aspects.…”

Section: Academic Domainmentioning

confidence: 99%

Assessing interactions between cognition, emotion, and motivation in creativity: The construction and validation of EDICOS

Soroa

Balluerka

Hommel

et al. 2015

Thinking Skills and Creativity

View full text Add to dashboard Cite

“…survival time greater or equal to the median survival time). 32 Based on prior experiments, the number of RF decision trees was set to 100. A fivefold cross-validation strategy was used to evaluate the performance of the model, in which the 40 patients were randomly divided into 5 even-sized groups.…”

Section: Statistical Analysesmentioning

confidence: 99%

A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome

Chaddad¹,

Desrosiers²,

Hassan³

et al. 2016

The British Journal of Radiology

View full text Add to dashboard Cite

Objective: Predicting the survival outcome of patients with glioblastoma multiforme (GBM) is of key importance to clinicians for selecting the optimal course of treatment. The goal of this study was to evaluate the usefulness of geometric shape features, extracted from MR images, as a potential non-invasive way to characterize GBM tumours and predict the overall survival times of patients with GBM. Methods: The data of 40 patients with GBM were obtained from the Cancer Genome Atlas and Cancer Imaging Archive. The T 1 weighted post-contrast and fluid-attenuated inversion-recovery volumes of patients were co-registered and segmented into delineate regions corresponding to three GBM phenotypes: necrosis, active tumour and oedema/invasion. A set of two-dimensional shape features were then extracted slicewise from each phenotype region and combined over slices to describe the three-dimensional shape of these phenotypes. Thereafter, a Kruskal–Wallis test was employed to identify shape features with significantly different distributions across phenotypes. Moreover, a Kaplan–Meier analysis was performed to find features strongly associated with GBM survival. Finally, a multivariate analysis based on the random forest model was used for predicting the survival group of patients with GBM. Results: Our analysis using the Kruskal–Wallis test showed that all but one shape feature had statistically significant differences across phenotypes, with p-value < 0.05, following Holm–Bonferroni correction, justifying the analysis of GBM tumour shapes on a per-phenotype basis. Furthermore, the survival analysis based on the Kaplan–Meier estimator identified three features derived from necrotic regions (i.e. Eccentricity, Extent and Solidity) that were significantly correlated with overall survival (corrected p-value < 0.05; hazard ratios between 1.68 and 1.87). In the multivariate analysis, features from necrotic regions gave the highest accuracy in predicting the survival group of patients, with a mean area under the receiver-operating characteristic curve (AUC) of 63.85%. Combining the features of all three phenotypes increased the mean AUC to 66.99%, suggesting that shape features from different phenotypes can be used in a synergic manner to predict GBM survival. Conclusion: Results show that shape features, in particular those extracted from necrotic regions, can be used effectively to characterize GBM tumours and predict the overall survival of patients with GBM. Advances in knowledge: Simple volumetric features have been largely used to characterize the different phenotypes of a GBM tumour (i.e. active tumour, oedema and necrosis). This study extends previous work by considering a wide range of shape features, extracted in different phenotypes, for the prediction of survival in patients with GBM.

show abstract

Cross-Validation

Cited by 1,467 publications

References 6 publications

Performance of 2D-SWE.GE for predicting different stages of liver fibrosis, using Transient Elastography as the reference method

Performance of 2D-SWE.GE for predicting different stages of liver fibrosis, using Transient Elastography as the reference method

Assessing interactions between cognition, emotion, and motivation in creativity: The construction and validation of EDICOS

A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome

Contact Info

Product

Resources

About