ライフサイエンスコーパス: cross-validation

1 (baseline performance measured with 10-fold cross-validation).

2 oefficient of 0.9046 +/- 0.0058 for six-fold cross-validation).

3 -DA) and internally validated (leave 10%-out cross-validation).

4 clusters were identified and evaluated using cross validation.

5 by training with the MD set using a tenfold cross validation.

6 ession and internally validated with 10-fold cross validation.

7 fidence interval [0.85, 1.00]) via five-fold cross validation.

8 t 70% (range 65-76%) using stratified 5-fold cross validation.

9 n was performed with model-external fivefold cross validation.

10 ne classifiers were trained through fivefold cross validation.

11 ievement was trained and tested using 5-fold cross validation.

12 evaluate the segmentation model using 5-fold cross-validation.

13 in half-life predictions) and were robust in cross-validation.

14 average accuracy of 90.8% based on five-fold cross-validation.

15 ural language processing model using 10-fold cross-validation.

16 (P = 0.034), but the model was not robust to cross-validation.

17 through different data partition schemes in cross-validation.

18 sting for overconfidence using leave-one-out cross-validation.

19 tperforms traditional empirical models under cross-validation.

20 nd 0.700 for a more stringent position-based cross-validation.

21 er operating characteristic curve (AUC) with cross-validation.

22 ed and models underwent spatially stratified cross-validation.

23 95 white 17-y-old participants using 10-fold cross-validation.

24 rt vector classification and repeated nested cross-validation.

25 sted a random forest classifier using 5-fold cross-validation.

26 d within 21 months (0.97 +/- 0.02 AUCROC) on cross-validation.

27 ing 10 types of selected features and 5-fold cross-validation.

28 0.7562, and 0.5065, respectively for 10-fold cross-validation.

29 ting characteristic curve (AUC) using nested cross-validation.

30 8,939 hr of data) using a stratified 20-fold cross-validation.

31 haracteristic (ROC) curve of 0.93 on 10-fold cross-validation.

32 of the variance in treatment response after cross-validation.

33 gorithm was first evaluated by using 10-fold cross-validation.

34 odels were developed and tested using nested cross-validation.

35 tric of 0.39 with ten repetitions of 10-fold cross-validation.

36 R(2) of 0.966 and RMSE of 0.013 in a 10-fold cross-validation.

37 receiver operating characteristic of 0.93 in cross-validation.

38 t the genetic risk score (GRS) with ten-fold cross-validation.

39 nterval (CI): 0.65-0.94) using leave-one-out cross-validation.

40 prediction rates range from 62-100%) through cross-validation.

41 These models performed well in cross-validation.

42 Testing was performed based on ten-fold cross-validation.

43 rate of 93.3%, and performed similarly upon cross-validation.

44 which cannot be obtained in the conventional cross-validation.

45 ining all selected predictors was 0.85 after cross-validation.

46 tion pathway CNNs was trained using fivefold cross-validation.

47 ResNet34 architecture with sevenfold nested cross-validation.

48 ovement scores (P = 0.003) and was robust to cross-validation.

49 model validated confirmed with and fivefold cross-validation.

50 hen validated using split-sample and 10-fold cross-validation.

51 %-25% training-validation split and fourfold cross-validation.

52 f GR binders in a 25% test set using holdout cross-validation.

53 k performance was assessed by using fivefold cross-validation.

54 ovement scores (P = 0.012) and was robust to cross-validation.

55 treated for aSAH (2016-2017) using five-fold-cross-validation.

56 s with an AUC of 0.89, as assessed by nested cross-validation.

57 on with best performing models determined by cross-validation.

58 boosting, and tuned with 10 repeated 4-fold cross-validations.

59 e of 2.03%-101.09% accuracy gain in internal cross-validations.

60 igh accuracy (92%) when evaluated via strict cross-validations.

61 with other competing methods via the 5-fold cross validation, 10-cross validation and de novo drug v

62 rt vector machine (SVM) combined with nested cross-validation, a prediction accuracy of 91.2% was ach

63 group was used to develop two algorithms via cross-validation: a classifier to diagnose NAFLD (MRI PD

64 rvised learning approaches, achieving better cross-validation accuracy across different sets of gold-

65 The average cross-validation accuracy was much higher for models usi

66 y the end of 80 weeks of follow-up with 100% cross-validation accuracy.

67 69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70-60.6

68 Using cross-validation across independent fMRI studies, we dem

69 respective other sample, and a leave-one-out cross-validation across the whole group further demonstr

70 -sample cross-validation and a leave-one-out cross-validation across the whole group.

71 Classifiers were evaluated by 10-fold cross-validation across three combined data sets or by t

72 AI predictions were evaluated using 10-fold cross-validation against annotations by expert surgeons.

73 It is based on k-fold cross-validation algorithm, but in contrast to conventio

74 Using leave-one-out cross-validation, all the models incorporating clinical

75 Cross-validation analysis is employed to optimize model

76 evaluated in both de novo and leave-one-out cross-validation analysis using known DTIs as the gold s

77 In 10-fold cross-validation analysis with 100 replications, Das-1 i

78 0.23 versus 0.19, P-value<1e-4) in a de novo cross-validation analysis.

79 rophilic asthma, and this was confirmed in a cross-validation analysis.

80 In 5-fold cross validation and 10-cross validation, DDRGIP method

81 or Autoregression, Estimation Stability with Cross Validation and a nonparametric change point detect

82 eved correlations of up to 0.72 and 0.67 (on cross validation and blind tests, respectively), while o

83 methods via the 5-fold cross validation, 10-cross validation and de novo drug validation.

84 ion, and accuracy) was tested using ten-fold cross validation and externally validated on data from t

85 achieved consistent results between ten-fold cross validation and independent test for predicting hum

86 n the training set (80% of the data) through cross validation and subsequently externally validated o

87 G, HPRD, and TRRUST databases by the 10-fold cross validation and test verification, and to identify

88 ogen combinations) internally through nested cross validation and were also validated using external

89 to predict outcome in both an out-of-sample cross-validation and a leave-one-out cross-validation ac

90 Tests using both cross-validation and a separate replication cohort of 27

91 assification accuracy of 83.7% in the 5-fold cross-validation and an accuracy of 92.6% for the test s

92 (AUC) of 0.831 with 77% accuracy on 10-fold cross-validation and an AUC of 0.883 with 83% accuracy i

93 ethod's predictive capacity was tested using cross-validation and assessed for robustness to varying

94 matically evaluated TargetPredict in de novo cross-validation and compared it to a state-of-the-art p

95 yield higher prediction accuracy in 10-fold cross-validation and de novo experiments.

96 ed regional wall motion abnormalities in the cross-validation and external validation datasets with a

97 provided the highest prediction abilities in cross-validation and external validation with mean value

98 valuate model stability, we performed 5-fold cross-validation and external validation.

99 tion, and accuracy) was tested using 10-fold cross-validation and externally validated on data from n

100 to each half, each analyzed separately using cross-validation and hold-out validation.

101 ) from visceral (rectal) stimulation in both cross-validation and independent cohorts.

102 Benchmarking experiments using cross-validation and independent tests showed that iProt

103 ve a better prediction performance on 5-fold cross-validation and jackknife tests.

104 Nested 5-fold cross-validation and leave-one-pathogen-out validation w

105 Using cross-validation and model selection, we identify a mode

106 assifier performance was evaluated by 5-fold cross-validation and on an independent test dataset.

107 ovariation, which were robust as assessed by cross-validation and permutation testing, taking into ac

108 e explained with OSM features alone, and use cross-validation and recursive feature elimination to ev

109 Through cross-validation and resampling the probability of gener

110 orous framework comprised of classification, cross-validation and statistical analyses that was devel

111 We used nested leave-one-pair-out cross-validation and supervised principal components ana

112 The multiple modes of enquiry enabled cross-validation and triangulation of the findings.

113 ch outperformed other available tools across cross-validation and two independent blind tests, achiev

114 unbiased prediction model in two scenarios- cross-validations and independent predictions.

115 on performance (average accuracy of 99.7% in cross-validation) and outperformed four baseline methods

116 ristic curve (ROC-AUC) of 0.799 using random cross-validation, and 0.700 for a more stringent positio

117 In this study, hold-out, leave-one-out cross-validation, and ten-fold cross-validation methods

118 erm survival patients) using a leave-one-out cross validation approach for performance evaluation.

119 d multi-omics factor analysis (MOFA) using a cross-validation approach to assess overfitting and cons

120 imate models using a novel and comprehensive cross-validation approach, running a series of h-block c

121 Using a cross-validation approach, we first explored in subjects

122 e metabolites and applying the leave-one-out cross-validation approach.

123 and tested their generalizability via nested cross-validation as well as via external validation.

124 , showed robust performance based on tenfold cross-validations as well as candidate prioritization wi

125 other methods by obtaining higher five-fold cross-validation AUC values (CV-AUC) and Leave-One-Chrom

126 oning algorithm, yielding strong results via cross-validation, averaging 0.95 AUROC on test-set indic

127 The model predictions were tested using cross validation based on empirical data collected from

128 o prediction of probable FA, with a combined cross-validation-based AUC of 0.73.

129 ication accuracy of 83 percent under 10-fold cross-validation, but its performance could be severely

130 iocarbon dating of 23 individuals, including cross-validation by compound-specific analysis, that E.

131 and holdout sets.We develop consensus nested cross-validation (cnCV) that combines the idea of featur

132 rating of ResNet-50 iterations from fivefold cross-validation, consensus technologists' rating, and c

133 net regression analysis with a leave-one-out cross validation (CV) and 100 CV runs.

134 sed prediction model with an improved random cross-validation (CV) R(2) of 0.86, an improved spatial

135 e quantification of Ca content in INF (R(2) (cross-validation (CV))-0.99, RMSECV-0.29 mg/g; R(2) (pre

136 ion to diabetes (AUC 0.92) based on standard cross-validation (CV).

137 95% confidence interval, 0.925-0.941) on the cross-validation dataset and 0.928 on the test dataset.

138 peting CNN classifiers were developed with a cross-validation dataset of 3396 images (1632 open, 1764

139 and Queensland cohorts formed a training and cross-validation dataset used to identify structural con

140 tput on a publicly-available match algorithm cross-validation dataset.

141 In 5-fold cross validation and 10-cross validation, DDRGIP method achieves the area under

142 Hold-out cross-validation demonstrated that these were significan

143 ated the feature matrices in a leave-one-out cross validation design across patients.

144 67% specificity and 95% sensitivity, in the cross-validation development cohort.

145 with standard nCV, Elastic Net optimized by cross-validation, differential privacy and private evapo

146 model hyperparameters optimised to minimise cross validation error, ten methods of automated variabl

147 erator (LASSO) and Estimation Stability with Cross Validation (ES-CV), we were able to, without any p

148 The 5-fold cross-validation experiment of GCNCDA achieved 91.2% acc

149 In the cross-validation experiment, LMTRDA obtained 90.51% pred

150 In the ten-fold cross-validation experiment, the logistic classifier ide

151 version of the yeast PPI network in rigorous cross validation experiments.

152 est classification accuracy (average 10-fold cross-validation F(1)-Score of 0.992) using an external

153 predictor composition is less stable across cross-validation folds and estimation takes 40 times as

154 Cross-validation for feature selection in these high-dim

155 to empower practical applications by using a cross validation framework that assesses the predictive

156 -operative MRI using a leave-one-patient-out cross validation framework.

157 learning techniques within a repeated nested cross-validation framework.

158 ogistic regression models with leave-one-out cross validation in the training set.

159 -19 related mortality (AUC = 0.86) following cross-validation in a training set.

160 We performed threefold cross-validation in the training dataset and generated t

161 Our multiple cross-validations indicate the promising accuracy and ro

162 Cross-validation indicates that FM-UE endpoints and FM-U

163 Leave-one-out-cross-validation is applied to verify the predictive ski

164 A machine learning model with cross-validation is then applied for classification.

165 A leave-one-out cross-validation is used for the independent assessment

166 lection of a minimum norm solution optimizes cross-validation leave-one-out stability and thereby the

167 Standard cross-validation led to over-optimistic performance esti

168 Using five-fold cross-validation, logistic regression and Cox regression

169 ge model performances based on leave-one-out cross validation (loocv) over ten different negative sam

170 error as 40.3 +/- 2.9 HU from leave-one-out-cross-validation (LOOCV) across all six patients, which

171 tory prediction results by the leave-one-out-cross-validation (LOOCV) compared with existing methods.

172 rough the leave-one-object (tissue site)-out cross-validation (LOOCV) method.

173 stic regression with a nested leave-pair out cross validation (LPOCV) scheme and recursive feature el

174 tratified into 100 iterations of Monte-Carlo cross validation (MCCV).

175 Using the 200-repeats Monte-Carlo cross-validation method, these models provided a multicl

176 y, and net benefit (decision curves)-using a cross-validation method, with that of the reference mode

177 dies are still rare and alternative internal cross-validation methods (e.g., leave-one out, split-hal

178 leave-one-out cross-validation, and ten-fold cross-validation methods are implemented on three public

179 Using volume and cortical thickness, cross-validation methods indicated 2 highly stable subty

180 ated the calibration performance using three cross-validation methods, which consistently indicated t

181 A k-fold cross-validation model-comparison selected a model where

182 machine learning-based method incorporating cross-validation, multiple regression, grid search, and

183 om these slides; performance was assessed by cross-validation (N = 6406 specimens) and validated in a

184 Nested cross-validation (nCV) is a common approach that chooses

185 Cross-validation of human- and mouse-derived protocols i

186 Cross-validation of loci reaching genome-wide significan

187 Future avenues of research focused on cross-validation of plant hydraulics methods are discuss

188 prediction capabilities were observed in the cross-validation of PLS and PCR analysis for the adulter

189 Following the cross-validation of previously published estimates of th

190 Four datasets are employed for cross-validation of spatial gene expression prediction a

191 A tenfold cross-validation of the classifier resulted in 84% accur

192 Internal-external cross-validation of the model demonstrated a random effe

193 e determined its accuracy to be 98 +/- 2% by cross-validation on analyzing 277 perspiration samples.

194 The leave-one-out cross-validation on experimentally characterized Acr-Aca

195 Using inter-site cross-validation on functional magnetic resonance images

196 es that we split into eleven subsets (10 for cross-validation, one for testing) using a novel cluster

197 e methods were all validated in simulations, cross-validations or independent retrospective data sets

198 n algorithm, but in contrast to conventional cross-validation, our approach makes it possible to crea

199 Using a patient-holdout cross-validation, our method achieved classification acc

200 ps were calibrated by matching sextant-based cross-validation performance to clinical performance of

201 tic variant and Multiple Phenotypes based on cross-validation Prediction Error (MultP-PE).

202 output and their performance in three tasks: cross validation, prediction of drug targets, and behavi

203 ting characteristic curve of 0.81 in 10-fold cross-validation, prevailing over using any single featu

204 acting drug pairs, their use of conventional cross-validation prevents them from achieving generaliza

205 Based on the leave-on-out cross validation procedure of 4 independent data sets we

206 tive disease in a novel leave-one-center-out cross-validation procedure equivalent to external valida

207 istinct distributed functional networks in a cross-validation procedure, identifying neurotraits.

208 against several existing algorithms using a cross-validation procedure, SArKS identified larger moti

209 arries sampling uncertainty estimated by the cross-validation procedure.

210 sed increase in grain yield accuracy under a cross-validation procedure.

211 By challenging our methodology with rigorous cross-validation procedures and prognostic analyses, we

212 The five-fold cross-validation process produced an average AUC of 0.83

213 te oral toxicity using read-across through a cross-validation process.

214 (reference, normal scale, plug-in and biased cross-validation) produced comparable estimates of niche

215 meteorology in California for the year 2016 (cross-validation R(2) = 0.73 (site-based) and 0.81 (obse

216 determination for calibration (R(c)(2)) and cross-validation (R(cv)(2)), with values of 0.96 and 0.8

217 Based on the cross validation results, our model gave F1 score and AU

218 Moreover, cross-validation results indicate that 58% of DO variabi

219 Cross-validation results reach accuracies between 85% an

220 erating characteristic analyses with 10-fold cross validation.ResultsIn participants with acute heart

221 Cross-validation revealed that EAGLE outperformed other

222 reover, a systematic evaluation using nested cross-validation revealed that the RILP algorithm select

223 Cross-validation revealed the generalizability of these

224 using a penalized matrix decomposition with cross-validation; risk scores of 50 and 400 SNPs were id

225 gnostic categories using a 5 x 5-fold nested cross-validation scheme and demonstrated their generaliz

226 n a partially labeled dataset, and develop a cross-validation scheme to enable supervised prediction.

227 ates major benefits of this variable h-block cross-validation scheme, as the effect of spatial autoco

228 mission models following a stratified 5-fold cross-validation scheme.

229 th promising results consistently on various cross-validation schemes and outperforms other state of

230 Our proposed biologically-motivated cross-validation schemes provide insight into the robust

231 e introduced two novel protein complex-aware cross-validation schemes.

232 mplexes that were not a part of the training/cross-validation set; deviations of the predicted mobili

233 Comparative analysis of 10 randomly drawn cross-validation sets verified the stability of the resu

234 ion for training and validation in a tenfold cross validation setting.

235 tual and predicted phenotypes in a five-fold cross-validation setting.

236 Cross validation showed that 32% of the model-predicted

237 Cross-validation showed 95.2% sensitivity and 94.6% spec

238 ive profiles within the sample, and hold-out cross-validation showed that these profiles were signifi

239 Ten-fold cross-validation shows that these networks are internall

240 ignificant long-term agreement is found with cross-validation sites over North America (R(2) = 0.57-0

241 sion criteria, through randomised seven-fold cross-validation (six-fold training set: n = 433; test s

242 as evaluated by comparing internal five-fold cross-validation statistics of the training data.

243 algorithms, was evaluated by internal 5-fold cross-validation statistics.

244 rank normalized scores of internal five-fold cross-validation statistics.

245 t-boosted tree regression model with 10-fold cross-validation strategy.

246 Five-fold cross-validation summaries out to 1000 single-nucleotide

247 With 10-fold cross-validation, tensor factorization achieved AUROC =

248 Accuracy of jackknife test, 10-fold cross-validation test and independent test for these PPI

249 Cross-validation testing reveals that ligand-binding pos

250 Additionally, standard leave-one-out cross validation tests show how our approach outperforms

251 Cross-validation tests on exactly the same experiment-co

252 piens, and compared using randomized 10-fold cross-validation tests.

253 uggest experimental controls and measures of cross-validation that improve data interpretation.

254 Through leave-one-out cross validation, the overall prediction error in the on

255 In a de novo cross-validation, the area under the receiver operating

256 In internal cross-validation, the average C statistic was 0.74.

257 In a leave-one-out cross-validation, the average rank was top 3.2% for know

258 In the cross-validation, the GBM showed better performance, wit

259 At cross-validation, the newly developed SYNTAX score II, t

260 patterns and validate, using left-trial-out cross-validation, the predictive performance of the mode

261 cent of these data was used for training and cross-validation, the remaining 20% for independent inte

262 tree, and Random Forest (RF), using a k-fold cross validation to assess the model's generalization ca

263 AUC analysis using K-fold cross validation to predict eGFR loss of >= 3 ml/min/1.7

264 We used 10-fold cross validation to validate the exposure models and the

265 After using cross-validation to assess robustness, we applied the La

266 a machine learning (ML) pipeline with nested cross-validation to avoid overfitting, the stacked model

267 optimized, and evaluated with 10-fold nested cross-validation to predict the probability of AF recurr

268 Training models include nested leave-one-out cross-validation to select features, train the model, an

269 We used cross-validation to select the best model.

270 algorithm (random forest - RF, with 10-fold cross validation) to predict individuals' fall risk grou

271 nternal validation techniques (bootstrap and cross-validation) to account for model training.

272 in a manner that avoids 'leakage' during the cross-validation training procedure.

273 By using leave-one-out cross validation, two quantitative US multivariable mode

274 We applied 10-fold cross-validation using independent data not used to deve

275 Tenfold cross-validations using a linear discriminant classifier

276 dation approach, running a series of h-block cross-validations using h values of 100-1500 km.

277 ith logistic regression models and five-fold cross validation, using area under the ROC curve (AUC) a

278 For cross-validation, using epifluorescence microscopy, we d

279 For comparison and anatomic cross-validation, volunteers were also scanned with clin

280 A tenfold cross validation was used to train two 3-class (each for

281 A support vector machine with k-fold cross-validation was built using the graph metrics featu

282 CPM with leave-one-out cross-validation was conducted to identify pretreatment

283 Cross-validation was employed to test a Linear Discrimin

284 ning (80%) and test (20%) sets, and fivefold cross-validation was performed.

285 For training and testing, 5-fold cross-validation was used.

286 Accuracy for cross-validations was assessed using a diverse panel und

287 ogistic regression analysis with leave-1-out cross validation, we developed a model, including a vira

288 Applying extensive cross-validation, we benchmarked the imputation using th

289 With patient-wise leave-one-out cross-validation, we have been able to achieve predictio

290 egression and XGBoosting methods followed by cross-validation were applied to predict individual dise

291 test set and mean accuracies from threefold cross-validation were used to compare the performance of

292 gistic regression, followed by leave-one-out cross-validation, were used to determine the performance

293 teristic (ROC) curve was 0.97 in the de novo cross-validation when evaluated using 910 drugs.

294 ieved an average of 0.91 F1-score on tenfold cross validation with an average area under the curve (A

295 Its performance was compared in cross validation with that of standard supervised method

296 assessed the resulting models using 10-fold cross-validation with 100 repetitions for statistical co

297 o random chance) by leave-one-chromosome-out cross-validation with stratified linkage disequilibrium

298 sk difference between the two strategies) by cross-validation with the SYNTAX trial (n=1800 participa

299 tial autocorrelation is minimized, while the cross-validations with increasing h values can reveal in

300 hine learning applied to multisite data with cross-validation yielded a factorization generalizable a