Recurrence Biomarkers
The recurrence biomarker model achieved a mean cross-validated AUC of 0.689. Recurrence biomarkers were the strongest-performing feature family tested in the study. The pooled cross-validated recurrence model achieved AUC 0.665 with a 95%…
1 sources - 5 claims
The recurrence biomarker model achieved a mean cross-validated AUC of 0.689. Recurrence biomarkers were the strongest-performing feature family tested in the study. The pooled cross-validated recurrence model achieved AUC 0.665 with a 95% bootstrap confidence interval from 0.568 to 0.758. Permutation testing found the recurrence model unlikely to perform that well under random label assignment. Recurrence rate is interpreted as a nonlinear biomarker because it quantifies how often vocal dynamics revisit similar states.