ライフサイエンスコーパス: ROC curve

1 sepsis from severe SIRS (0.742-0.917 AUC of ROC curves).

2 tive binding sites show a 0.85 area under an ROC curve.

3 d from SDUV provided a better area under the ROC curve.

4 inciple produce 50 positive instances in the ROC curves.

5 ulated by receiver operating characteristic (ROC) curve.

6 under the receiver operating characteristic (ROC) curve.

7 alidation receiver operating characteristic (ROC) curve.

8 under the receiver operating characteristic (ROC) curve.

9 ts to the receiver operating characteristic (ROC) curve.

10 under the receiver operating characteristic (ROC) curve.

11 imized by receiver operating characteristic (ROC) curve.

12 es with a receiver operating characteristic (ROC) curve.

13 (AUC) of receiver operating characteristic (ROC) curves.

14 he use of receiver operating characteristic (ROC) curves.

15 by using receiver operating characteristic (ROC) curves.

16 dependent receiver operating characteristic (ROC) curves.

17 red using receiver operating characteristic (ROC) curves.

18 e plotted receiver operating characteristic (ROC) curves.

19 tion uses receiver operating characteristic (ROC) curves.

20 ned using receiver operating characteristic (ROC) curves.

21 nted with receiver operating characteristic (ROC) curves.

22 acy of MIMA and MH was high (areas under the ROC curve 0.92).

23 under the receiver operating characteristic (ROC) curve 0.78 and 0.80, respectively).

24 racy than CAP in terms of the area under the ROC curve (0.99 vs 0.77, respectively; P = .0334).

25 ncer decreased after compression (area under ROC curve = 0.53 vs 0.71, respectively; P = .02).

26 ole and systole were similar (area under the ROC curve = 0.79 and 0.82, respectively; P = .30).

27 ntly good to excellent range (area under the ROC curve = 0.868-0.924).Future clinical studies will de

28 igher in AD compared to controls, area under ROC curve = 0.96) was identified as a fragment of pleiot

29 73 m(2) at 1 year [receiver operating curve (ROC curve), 0.78, 95% CI, 0.68-0.89].

30 hose with an unfavorable outcome (area under ROC curve, 0.48).

31 rimination of dCON (P < .001; area under the ROC curve, 0.66).

32 rrence of new adjacent OVCFs (area under the ROC curve, 0.70).

33 MP MR imaging (area under the ROC curve, 0.70-0.77) did not improve T2-weighted imagin

34 dicted subsequent grade 3-4 GVHD (area under ROC curve, 0.76).

35 morphologic assessment alone (area under the ROC curve, 0.767 vs 0.487 [P = .00005] and 0.802 vs 0.48

36 velopment of peak grade 3-4 GVHD (area under ROC curve, 0.88).

37 hin 1 year after transplantation (area under ROC curve, 0.90).

38 om immunocompetent patients (areas under the ROC curve, 0.91 and 0.97).

39 n the one for RV volume (mean area under the ROC curve, 0.96 +/- 0.02 vs 0.88 +/- 0.04; P = .009).

40 There was good accuracy (area under the ROC curve, 0.97) and interobserver agreement for detecti

41 f intra-abdominal infection (areas under the ROC curve: 0.775 vs 0.689, respectively, P = 0.03).

42 he fourth postoperative day (areas under the ROC curve: 0.783 vs 0.671, P = 0.0002).

43 city based on optimal operating point on the ROC curve (7.0 ng/mL) were both 93%.

44 ROC curve analyses demonstrated 60-100% sensitivity and

45 ROC curve analyses evaluated classification accuracy in

46 sing ROI-receiver operating characteristics (ROC) curve analyses for the latter.

47 Paired-receiver operating characteristic (ROC) curve analyses revealed no statistical differences

48 Receiver operating characteristic (ROC) curve analyses revealed that nDNA fragments, GDH, a

49 sed using receiver-operating-characteristic (ROC) curve analyses to differentiate between neoplastic

50 Receiver Operating Characteristics (ROC) curve analyses were conducted with four semi-struct

51 In receiver operating characteristic (ROC) curve analyses, the addition of BMD change to a mod

52 test and Receiver Operating Characteristic (ROC) curve analyses.

53 cted VF better than Sanger sequencing in the ROC curve analysis (area under the curve: 0.69 vs 0.60,

54 ROC curve analysis confirmed the reliability of PTX3 ser

55 ROC curve analysis demonstrated that the optimal cutoff

56 The ROC curve analysis identified an optimal cutoff value of

57 The ROC curve analysis indicated that the NCAR cylinder test

58 ROC curve analysis indicated that the optimal cutoff poi

59 ROC curve analysis of an independent, more heterogeneous

60 ylaxis and cardiovascular/febrile reactions, ROC curve analysis revealed a reasonably high area under

61 ROC curve analysis revealed a sensitivity and specificit

62 ROC curve analysis revealed a slight, non-significant in

63 ROC curve analysis revealed that no TJC or active joint

64 The ROC curve analysis was used for determining the appropri

65 At ROC curve analysis, a T2* value of 28 msec was identifie

66 e of the strain ratio (4.25) was obtained by ROC curve analysis, the sensitivity and specificity for

67 At ROC curve analysis, the sensitivity, specificity, and po

68 Cut-off values were established by applying ROC curve analysis.

69 tive and False Positive trade-off, through a ROC curve analysis.

70 ted using Receiver-Operating Characteristic (ROC) curve analysis (AUC) and its 95 % Confidence Interv

71 red using receiver-operating-characteristic (ROC) curve analysis and Kaplan-Meier survival curves.

72 included receiver operating characteristic (ROC) curve analysis and noninferiority analysis.

73 The receiver operator characteristic (ROC) curve analysis demonstrated that the CI candidacy e

74 ated with receiver operating characteristic (ROC) curve analysis for each method, with stress MBF and

75 e PCR and receiver operating characteristic (ROC) curve analysis in five cohorts (n = 345) from the N

76 BF) data, receiver operating characteristic (ROC) curve analysis of the posterior cingulate cortex (P

77 Receiver operating characteristic (ROC) curve analysis resulted in area under the ROC curve

78 r, receiver operating characteristic curves (ROC) curve analysis revealed a significant area under cu

79 Receiver operating characteristic (ROC) curve analysis showed excellent predictive accuracy

80 Receiver operator characteristic (ROC) curve analysis showed that IL17A can be used to dis

81 rformed a receiver operating characteristic (ROC) curve analysis to ascertain the RDQ's optimum cut-p

82 Receiver operating characteristic (ROC) curve analysis was carried out on diagnostic decisi

83 Receiver operating characteristic (ROC) curve analysis was performed to define cut-off valu

84 Receiver operating characteristic (ROC) curve analysis was used to assess whether joint cou

85 gression, receiver operating characteristic (ROC) curve analysis, and kappa test were performed.

86 by using receiver operating characteristic (ROC) curve analysis, logistic regression analysis, and i

87 ng by the receiver operating characteristic (ROC) curve analysis.

88 based on receiver operating characteristic (ROC) curve analysis.

89 ation and receiver operating characteristic (ROC) curve analysis.

90 sessed by receiver-operating-characteristic (ROC) curve analysis.

91 under the receiver operating characteristic (ROC) curve analysis.

92 ted using receiver operating characteristic (ROC) curve analysis.

93 ated with receiver operating characteristic (ROC) curve analysis.

94 d through receiver operating characteristic (ROC) curve analysis.

95 he receiver operating characteristic curves (ROC curves) analysis for evaluation of clinical diagnosi

96 tested by receiver operating characteristic (ROC) curve and Spearman's rank correlation and discrimin

97 Receiver operating characteristic (ROC) curves and area under the ROC curve (AUC) were calc

98 parison of receiver-operator characteristic (ROC) curves and Decision Curve Analysis (DCA).

99 under the receiver operator characteristic (ROC) curves and multivariate generalized additive model

100 and used receiver-operating characteristic (ROC) curves and network entropy to assess the accuracy a

101 lysis the receiver operating characteristic (ROC) curves and Spearman correlation coefficient were us

102 sessed by receiver operating characteristic (ROC) curves and survival analyses.

103 rithm with receiver operator characteristic (ROC) curves and the weighted kappa statistic.

104 nerated a receiver operating characteristic (ROC) curve, and calculated area under the curve (AUC) an

105 modeling, receiver-operator characteristic (ROC) curves, and calibration plots.

106 matrices, receiver operating characteristic (ROC) curves, and true and false positive rates (TPR and

107 under the receiver operator characteristic (ROC) curve (area under the curve (AUC)) of 0.87 in anten

108 Receiver operating characteristic (ROC) curves, area under the curve (AUC), and thresholds

109 Receiver operating characteristic (ROC) curve areas were calculated using full and optimize

110 from healthy controls (global area under the ROC curve (AUC) 0.90 [95% CI 0.85-0.95]), latent tubercu

111 Area under the ROC curve (AUC) analysis was used to define the optimum

112 sessed by the calculating the area under the ROC curve (AUC) and evaluating its difference from refer

113 (ROC) analysis to generate an area under the ROC curve (AUC) and sensitivity and specificity distribu

114 The largest area under the ROC curve (AUC) for any single parameter was 0.75.

115 ility, and approximately 0.89 area under the ROC curve (AUC) for disorder prediction.

116 In mild glaucoma (MD of -5 dB), area under ROC curve (AUC) for rim area, average RNFL thickness, an

117 The highest area under the ROC curve (AUC) for steatosis of PNPLA3 rs738409 genotyp

118 The area under the ROC curve (AUC) for tear osmolarity (ranging from 0.71 t

119 The area under the ROC curve (AUC) in the differentiation of stage F2 fibro

120 The integrated area under the ROC curve (AUC) is 0.91.

121 (ROC) was used to compare the area under the ROC curve (AUC) of each index.

122 FM framework, we compared the area under the ROC curve (AUC) of models developed with TRL-FM and othe

123 The area under the ROC curve (AUC) was highest for the 100%-count, 60-min i

124 aracteristic (ROC) curves and area under the ROC curve (AUC) were calculated for image-based classifi

125 pes (26%) were predicted with area-under-the-ROC curve (AUC)>0.7, and 23 (15.8%) of these were statis

126 ion performance, in terms of test area under ROC Curve (AUC), on all breast cancer case studies.

127 mance was evaluated using the area under the ROC curve (AUC), the Enrichment Factor (EF) and Hit Rate

128 ach to train it by maximizing area under the ROC curve (AUC), which is an unbiased measure for class-

129 l and was quantified with the area under the ROC curve (AUC).

130 rating characteristic (ROC), and areas under ROC curves (AUC-ROC) were used.

131 Under the Receiver Operating Characteristic (ROC) Curve (AUC) for two classes and the Volume Under th

132 under the receiver operating characteristic (ROC) curve (AUC) of 0.81, while EMR data alone achieved

133 under the receiver operating characteristic (ROC) curve (AUC), number of false discoveries and statis

134 rea under receiver operating characteristic (ROC) curve (AUC).

135 rea under receiver operating characteristic (ROC) curves (AUC) and sensitivities at fixed specificiti

136 ivity, 80%; specificity, 91%; area under the ROC curve [AUC] = 0.937; P = .0001), areas of lowest sig

137 s reached 78% using TBR(max) (area under the ROC curve [AUC], 0.822 +/- 0.07; sensitivity, 79%; speci

138 The accuracies of ECVDEP (area under the ROC curve [AUC], 0.85) and normalized ECVDEP (AUC, 0.86)

139 under the receiver operating characteristic [ROC] curve [AUC] = 0.981 for reader 1 and 0.961 for read

140 gh SAD vs HCs discrimination (area under the ROC curve, AUC, arithmetic mean of sensitivity and speci

141 e T1 and T2 yielded the best areas under the ROC curve (AUCs) of 0.975 and 0.979, respectively, for d

142 /= 2) as the criterion standard, areas under ROC curves (AUCs) and likelihood-ratios were calculated

143 ical differences between the areas under the ROC curves (AUCs) for each model pair were calculated, a

144 Pairwise comparisons of areas under ROC curves (AUCs) from the different grading systems wer

145 better predictive abilities [area under the ROC curves (AUCs) of 0.67 and 0.69] than did weight-for-

146 eas under receiver-operating characteristic (ROC) curves (AUCs) were used to evaluate their predictiv

147 e combined score exhibited an area under the ROC curve (AUROC) of 0.81 for discriminating future deme

148 osis grade 0-1 vs 2-3 with an area under the ROC curve (AUROC) of 0.95 (95% CI, 0.91-0.98), and grade

149 The area under the ROC curve (AUROC) of TE and HVPG for prediction of LREs

150 The area under the ROC curve (AUROC) of the prediction models for predictin

151 under the receiver operating characteristic [ROC] curve [AUROC] for wPRx was 0.73 versus 0.66 for PRx

152 The areas under the ROC curves (AUROCs) for RVMs trained on optimized featur

153 no significant difference in area under the ROC curve between detector-reconstruction combinations a

154 arker was more predictive than another using ROC curves, but multiple logistic regression suggested s

155 ing and interval censoring, we estimated the ROC curves by means of a weighting approach and a model-

156 P = 0.26) and there was no difference in the ROC curves (C statistic = 0.74 vs 0.73).

157 The ROC curve calculation provided the following optimum dia

158 Receiver operating characteristic (ROC) curves, category-free net reclassification index (c

159 A receiver-operating characteristics (ROC) curve combining both lipid levels predicted EAD wit

160 n that of receiver-operating-characteristic (ROC) curves, confirming similar findings in other class-

161 The ROC curve decided that the cutoff point of FENO was 37.8

162 Summary ROC curve demonstrated overall superiority of 3-T imagin

163 Summary receiver operator characteristic (ROC) curve demonstrated superior accuracy of direct MR a

164 arison of receiver operating characteristic (ROC) curves demonstrated that HAS-BLED had the best disc

165 ased on a Receiver operating characteristic (ROC) curve - derived optimum cut-off level of >140mAU/ml

166 ROC curves displayed an AUC higher than 0.8 and simulati

167 The model yielded an area under the ROC curve exceeding 0.81 in an independent testing set,

168 The area under the ROC curve for 2D-MRE discriminating advanced fibrosis (s

169 The area under the ROC curve for AH diagnosis was estimated to be 0.83 (0.7

170 DNI demonstrated the highest area under the ROC curve for diagnosis of VUR (0.620, 95% CI 0.542-0.69

171 The area under the ROC curve for differentiating between grade F0-F1 fibros

172 The ROC curve for percent change in H. pylori IgG-antibody t

173 The test set area under the ROC curve for predicting EGFR mutation status was 0.89.

174 without IFI (P = 0.618); the area under the ROC curve for predicting IFIs was 0.56 (poor test).

175 nstrated significantly higher area under the ROC curve for protocol B (P < .0022), with interreader a

176 The ROC curve for ROPtool's tortuosity assessment had an are

177 The AUC ROC curve for the detection of IBI for the PCT assay was

178 e without IA (P = 0.098); the area under the ROC curve for the diagnosis of IA was 0.77 (fair test, i

179 Results The average area under the ROC curve for the groups increased with experience (0.94

180 The area under the ROC curve for the model and validation subsets of the di

181 The global ROC curve for the Offsides ADE candidates ranked with th

182 Area under the ROC curve for the SCORAD was 0.70 [95% confidence interv

183 The area under the ROC curves for OD/LREs was 0.648 and 0.742 for LB and FI

184 location receiver operating characteristic (ROC) curve for an interval of low false-positive fractio

185 under the receiver operating characteristic (ROC) curve for case-control discrimination based on firs

186 a under a receiver-operating characteristic (ROC) curve for each analyte were used to determine assoc

187 test and Receiver operating characteristics (ROC) curve for NAA/Cho, NAA/Cr and Cho/Cr ratios.

188 C) of the receiver operating characteristic (ROC) curve for performance evaluation.

189 nder the Receiver Operating Characteristics (ROC) curve for predicting in-hospital mortality using th

190 under the receiver operating characteristic (ROC) curve for the classifiers was 0.973 with a sensitiv

191 Receiver operating characteristic (ROC) curves for BTI were used to predict a 5% change in

192 outcome (p = 0.009), while the corresponding ROC curve had AUC of 0.784 and 0.783.

193 ROC curves had higher areas under the curve for day-0 CT

194 ROC curves indicated that baseline IgE against peanut an

195 e form of receiver operating characteristic (ROC) curves indicated that GeneOut performed well in the

196 as well as receiver operator characteristic (ROC) curves, integrated discrimination improvement (IDI)

197 The integrated area under ROC curve is 0.904.

198 ing best as determined by the area under the ROC curve (Mean AUC = 0.722).

199 Using pCR as the reference standard and ROC curve methodology, %TOITN AUC was 0.60 (95% CI, 0.39

200 r detection, with the highest area under the ROC curve obtained for LWF (0.97 in the peripheral zone

201 Furthermore, the area under the ROC curve obtained was 0.93, demonstrating that the prob

202 d specificity of 77% (with an area under the ROC curve of 0.595).

203 C) curve analysis resulted in area under the ROC curve of 0.676 (95% confidence interval: 0.58, 0.77)

204 ri negative patients, with an area under the ROC curve of 0.70 (95 % CI 0.59 to 0.79, P = 0.085) at 3

205 and atypical bacteria with an area under the ROC curve of 0.79 (95% CI, .75-.82).

206 ferior RNFL quadrant (with an area under the ROC curve of 0.806) finally with PERG amplitude we found

207 antly (p-value <0.0001) lower area under the ROC curve of 0.832 (95% CI: 0.819 to 0.845) versus the n

208 e steatosis and NASH, with an area under the ROC curve of 0.85 (95% confidence interval: 0.75, 0.91)

209 ved excellent discrimination as indicated by ROC curve of 0.85.

210 ROC analysis revealed an area under the ROC curve of 0.893 for FAcontra and of 0.815 for FAint,

211 anced accuracy of 0.82 and an area under the ROC curve of 0.90.

212 tortuosity assessment had an area under the ROC curve of 0.917.

213 ctively, for FDT-PSD (with an area under the ROC curve of 0.940), whereas with OCT, a sensitivity of

214 ROC curve of combined IL-4 and IL-13 analysis showed an

215 The area under the ROC curve of EV was significantly higher than that of CC

216 The ROC curve of hypoxanthine returned an AUC of 0.79 (p < 0

217 The area under the ROC curve of the SWV ratio (mean SWV/applied strain) for

218 (ROC) analysis and obtain an area under the ROC curve of up to .

219 under the receiver operating characteristic (ROC) curve of 0.73 (95% confidence interval [CI], .69-.7

220 under the receiver operating characteristic (ROC) curve of 0.75 +/- 0.1, 0.80 +/- 0.1 and 0.89 +/- 0.

221 Curve) of receiver operating characteristic (ROC) curves of miR-9 for all tumors and ER positive tumo

222 Receiver operating characteristic (ROC) curves of the predictive factors were used to ident

223 these are in good agreement (area under the ROC-curve of 0.778 to 0.972 for the six MHC-II variants)

224 rage Specificity (MAS), a scalar measure for ROC curve, of 0.97 (0.96).

225 threshold receiver operating characteristic (ROC) curve optimal cutoff value (P = .001, P = .018, P =

226 ches marginally increased the area under the ROC curve over 0.97, but in a subset of proteins that co

227 ase balanced accuracy and the area under the ROC curve over several rounds.

228 nt difference within the methods between the ROC curves (P > 0.4) for progression-free survival and o

229 LS mimics (difference between area under the ROC curves: p=0.0001 and p=0.0005; respectively).

230 Based on analyses of ROC curves, PLR, and NLR, endoscopic response was define

231 ted using receiver operating characteristic (ROC) curves, positive likelihood ratios (PLR), and negat

232 ation and receiver operating characteristic (ROC) curves produced.

233 te urinary tract obstruction (area under the ROC curve ranged from 0.50 to 0.62).

234 Areas under the ROC curve ranged from 0.88 (95% confidence interval: 0.8

235 under the receiver operating characteristic (ROC) curve, relative to the other five methods.

236 For comparison with current practice, ROC curves relying solely on percent weight loss were al

237 y identified markers were evaluated applying ROC curves resulting in individual marker AUC >90% both

238 ROC curve results from RVM analyses of CSLO, SAP, and CS

239 Visual inspection of the ROC curve revealed that the performance of the uncorrect

240 The receiver operating characteristics (ROC) curve revealed a mean area under the curve (AUC) of

241 The AUC statistic quantified the ROC curve's capacity to classify participants likely to

242 Area under the ROC curve, sensitivity, and specificity, respectively, w

243 The area under the curve (AUC) for each ROC curve serves as a quantitative metric to optimize tw

244 ROC curve showed that miR-125a-3p abundant level may pre

245 ROC curves showed poor diagnostic performance of median

246 ROC curves showed that addition of SNPs better improved

247 say offered an area under the curve (AUC) of ROC curve similar to that for CRP concentration for the

248 On the basis of the area under the ROC curve, the LDF performed better than any single para

249 On the basis of ROC curves, the most discriminative cutoff value for MTV

250 ROC curves to determine the optimal viral load cutoff pr

251 ploys the receiver operating characteristic (ROC) curve to minimize false discovery rate (FDR) and ca

252 We used receiver operating characteristic (ROC) curves to determine the ability of LB and FIB-4 to

253 We used receiver operating characteristic (ROC) curves to determine the ability of TE and HVPG to p

254 We used receiver operating characteristic (ROC) curves to present balance in sensitivity and specif

255 The area under the ROC curve using these significant VOCs to discriminate e

256 ROC curves using both terms of baseline BTI predicted a

257 racy was 64% (16/25), and the area under the ROC curve was 0.601 (95% confidence interval [95% CI], 0

258 The area under the ROC curve was 0.734 in ALERT and 0.721 in PORT, indicati

259 The area under the ROC curve was 0.738 in ALERT and 0.740 in PORT, indicati

260 The resulting area under the ROC curve was 0.77 (95% CI, 0.73 to 0.81).

261 The largest area under the ROC curve was 0.834 for our LDF in the validating popula

262 The C statistic for the Abeta oligomer ROC curve was 0.86, with 80% sensitivity and 88% specifi

263 obability-of-malignancy-based area under the ROC curve was 0.87 for tomosynthesis versus 0.83 for sup

264 The area under the ROC curve was 0.91 (0.80 with 4-fold cross-validation, P

265 (23/25) (P < 0.001), and the area under the ROC curve was 0.929 (95% CI, 0.740-0.990).

266 The area under the ROC curve was 0.942.

267 (25/25) (P < 0.001), and the area under the ROC curve was 1 (95% CI, 0.863-1).

268 The area under the ROC curve was calculated for the ROPtool, and sensitivit

269 Cut-off point of the ROC curve was established at 2.8 mm for neck diameter, a

270 Area under the ROC curve was significantly higher (P = .002) for ADC (0

271 The area under ROC curve was significantly larger with the new score 0.

272 A receiver operating characteristic (ROC) curve was calculated, showing the sensitivity and s

273 Receiver operating characteristic (ROC) curve was drawn to determine a cut-off ADC value fo

274 under the receiver-operating-characteristic (ROC) curve was used to assess the prognostic accuracy of

275 Receiver operating characteristic (ROC) curve was used to calculate optimal referral cutoff

276 Using receiver operating characteristic (ROC) curves, we determined the optimal cut-off values fo

277 Sensitivity, specificity, and ROC curves were compared for both sexes.

278 ROC curves were similar for both sexes, and equal combin

279 nder the receiver operative characteristics (ROC) curves were 1.0, which represents a highly sensitiv

280 Receiver operating characteristic (ROC) curves were analyzed by evaluating the area under t

281 Receiver operating characteristic (ROC) curves were constructed to assess the diagnostic ab

282 Receiver operating characteristic (ROC) curves were constructed to assess the performance o

283 Receiver operating characteristic (ROC) curves were constructed to describe the ability of

284 Receiver operating characteristic (ROC) curves were constructed to determine optimal discri

285 Receiver operating characteristic (ROC) curves were constructed to determine the optimal th

286 Receiver operating characteristic (ROC) curves were constructed to estimate the ability of

287 test, and receiver operating characteristic (ROC) curves were created to assess diagnostic performanc

288 Receiver operating characteristic (ROC) curves were created.

289 Receiver operating characteristic (ROC) curves were generated.

290 Receiver Operating Characteristic (ROC) curves were obtained.

291 Receiver operating characteristic (ROC) curves were plotted, and the outcome of the OFC was

292 ethod, and receiver operator characteristic (ROC) curves were plotted.

293 of TMJOA, receiver operating characteristic (ROC) curves were plotted.

294 quisition, receiver operator characteristic (ROC) curves were used to delineate predictive factors.

295 ysis, and receiver operating characteristic (ROC) curves were used to examine the association of the

296 Receiver operating characteristic (ROC) curves were used to measure the ability of MPP to d

297 Area under the ROC curve with stress MBF and MPR as the outcome measure

298 The average partial area under the location ROC curve with unaided reading was 0.57, and it increase

299 ptimal models for months 1, 2, and 3 yielded ROC curves with AUCs of 0.68 (95% CI: 0.63, 0.74), 0.75

300 using the receiver operating characteristic (ROC) curve, with 2 different definitions depending on th