SGC-RML creates an 8D symptom atlas from multimodal PD data and integrates conformal calibration to deliver reliable, rejectable longitudinal assessments.
Goetz, Barbara C
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
For 5-item subsets of the MDS-UPDRS, coordinate descent item selection cuts expected standard deviation of severity estimates by 26% and adaptive selection by 34% versus random choice, outperforming Fisher-information ranking by 12 percentage points.
Normalized velocity descriptors from facial keypoints with Random Forest yield 0.826 balanced accuracy and 0.855 AUROC on YouTubePD video classification, stable across 10 seeds with region ablation and permutation importance.
citing papers explorer
-
SGC-RML: A reliable and interpretable longitudinal assessment for PD in real-world DNS
SGC-RML creates an 8D symptom atlas from multimodal PD data and integrates conformal calibration to deliver reliable, rejectable longitudinal assessments.
-
Optimized questionnaire item selection for tracking the progression of motor symptoms in Parkinson's disease
For 5-item subsets of the MDS-UPDRS, coordinate descent item selection cuts expected standard deviation of severity estimates by 26% and adaptive selection by 34% versus random choice, outperforming Fisher-information ranking by 12 percentage points.
-
Interpretable Temporal Facial-Region Motion Analysis for In-the-Wild Parkinson's Disease Video Classification
Normalized velocity descriptors from facial keypoints with Random Forest yield 0.826 balanced accuracy and 0.855 AUROC on YouTubePD video classification, stable across 10 seeds with region ablation and permutation importance.