In sum, despite the modest classification accuracy of the clusters according to their acoustic features, the underlying semantic structure embedded into tags could nonetheless be more clearly explained in terms of their relative positions to each other within the cluster space.
The authors reported overall modest classification accuracies ranging from 50% to 78% depending on the combination of features employed [ 20].
We also note that the relatively modest classification accuracies reported here could indeed be improved upon if classification were the only aim.
It might be because sample number was modest after classification or that elderly individuals without CKD were more strongly affected by the physical component than by the mental component.
Training a classifier to use those event-related responses in order to separate 'Seen Correct' vs 'Unseen Correct' trials yielded a modest but significant classification success, again based on the late part of the epoch (see Figure 2 figure supplement 3).
This information is now included in the paper (in the subsection headed "Relation to previous findings from event-related responses"): "Training a classifier to use those event-related responses in order to separate "Seen-Correct" versus "Unseen-Correct" trials yielded a modest but significant classification success.
The association of tumour marker response alone with the patient response classification was modest and did not add significantly to F-FES-PET/CT.
Given the amount of reduction from 32 to 5−6, its classification as modest bias (at least) appears to be in order.
An alternative reason for the modest implementation of the classification approach may be that assessment schemes do not adequately integrate the multiple dimensions that can contribute to, or perpetuate LBP.
This is best exemplified by the modest agreement in the classification of samples (agreement of 64%, kappa score of 0.527, and 95% confidence interval of 0.456 to 0.597) when a cohort of 295 breast cancers was classified into the molecular subtypes by the authors of the original studies on the molecular classification using SSPs by Sorlie's [ 13, 30] and Perou's [ 26, 31] groups.
There was a modest improvement in risk classification with the addition of FEV1 and a small improvement in the IDI with the addition of WBC count, aPTT, albumin, factor VIII, magnesium, heart rate, hip circumference, and the genetic risk score in the total cohort and adiponectin, leptin, GGT, ferritin, ICAM-1, and complement C3 in the case-control sample.
