The ROC curves and AUC values of the diagnostic model. by Zhe Wu (582498)

ROC curve and AUC value of all models. by Tiago de Oliveira Barreto (20485207)

“…As for Specificity (82.94%) and ROC-AUC (82.13%), the Multilayer Perceptron with SGD optimizer obtained the highest scores. …”

Area under the curve (AUC) for external validation performance. by Junichi Kushioka (12236447)

Significantly Enriched Pathways. by Jiyong Zhang (2498740)

“…Pathway analysis revealed a marked decrease in expression within certain key metabolic pathways (such as the one-carbon pool by folate) in the NAFLD group, while expression in DNA repair-related pathways (such as non-homologous end joining) was significantly increased. …”

AUC of various models to predict imeglimin efficacy for liver function evaluated by ROC curves. by Naruyoshi Gyoutoku (22537831)

Column charts of WiAUC in therapy and control group at baseline and follow-up. by Felix L. Herr (21544362)

AUC ROC curve. by Dieuwke Luijten (15282736)

Statistical analysis of the AUC measurement. by Esra Ayan (21156015)

“…<p>Analysis indicated that INSv application significantly changed spontaneous calcium activity (IAsp <i>p</i>-value: 0.1290, INSv <i>p</i>-value: 0.0002). The mean AUC decreased in both samples.…”

Area under the ROC Curve (AUC) analysis to predict AIS conversion at 6-months and 1-year following acute cervical tSCI. by Harshit Arora (22008280)

Area under the ROC curve (AUC) analysis to predict neurological severity at 6-months and 1-year following acute cervical tSCI. by Harshit Arora (22008280)

Daily number of adverse outcomes (bars) and area under the precision-recall curve (AUC-PRC) per day of the fullPIERS model. by Guiyou Yang (10259597)

Daily number of adverse outcomes (bars) and area under the precision-recall curve (AUC-PRC) per day of the PIERS-ML model. by Guiyou Yang (10259597)

Feature importance and beeswarm plot determined by mean absolute SHAP values for the DeepSurv model. by Theophilus Gyedu Baidoo (21162511)

AUC statistics comparing statistical trends in control and test populations. by Madeline Jarvis-Cross (22394247)

“…<p>To evaluate statistical trends, we calculated Kendall’s rank correlation coefficient during the pre-critical interval (here, days one to sixty), and compared control (constant temperature, non-epidemic) and warming (warming treatment, epidemic emergence) coefficients across simulations and experimental populations by calculating the area under the curve (AUC) statistic. Values less than 0.5 suggest that a decrease in the statistical metric indicates emergence, while values greater than 0.5 suggest that an increase in the statistical metric indicates emergence, with more extreme values indicating stronger trends. …”

AUC surface with respect to regularization parameters <i>λ</i> and . by Yangsong He (13909371)

Feature importance and beeswarm plot determined by mean absolute SHAP values for the random survival forest (RSF) model. by Theophilus Gyedu Baidoo (21162511)

Comparative Internal and External AUC Performance Across Single-Site Models. by Ioana Duta (18462981)

“…Boxplots describe the distribution of AUC values obtained through bootstrap resampling, indicating the variance within internal and external validations. …”

AUC statistics as calculated from simulated time series. Each statistical metric was calculated within sliding windows, throughout the pre-critical interval. We considered five-, fifteen-, and thirty-day sliding windows. Given that the temperature of the system increased to 12°C on day sixty, we also considered three pre-critical intervals: Days 1 to 60, Days 20 to 60, and Days 30 to 60. To evaluate trends in these metrics, we calculated Kendall’s rank correlation coefficient during the pre-critical interval, and compared control (constant temperature, non-epidemic) and warming (warming treatment, epidemic emergence) coefficients across simulations and experimental populations by calculating the area under the curve (AUC) statistic. Values less than 0.5 suggest that a decrease in the statistical metric indicates emergence, while values greater than 0.5 suggest that an increase in the statistical metric indicates emergence, with more extreme values indicating stronger tre by Madeline Jarvis-Cross (22394247)

“…To evaluate trends in these metrics, we calculated Kendall’s rank correlation coefficient during the pre-critical interval, and compared control (constant temperature, non-epidemic) and warming (warming treatment, epidemic emergence) coefficients across simulations and experimental populations by calculating the area under the curve (AUC) statistic. Values less than 0.5 suggest that a decrease in the statistical metric indicates emergence, while values greater than 0.5 suggest that an increase in the statistical metric indicates emergence, with more extreme values indicating stronger tre</p>…”

Percent difference in Precision-Recall AUC, sensitivity, and specificity for pooled models relative to eBird-only models. by Reid Rumelt (21680956)

“…<p>Precision-Recall AUC and sensitivity were higher in all species (positive values); decreases in specificity, present in all species, were more minor (negative values, note differences in x-axis scales between panels).…”

Feature engineering. by Youli Jiang (15249070)