Abstract:Real-world digital Parkinson's disease assessment faces challenges such as heterogeneous modalities, cross-device bias, and incomplete labeling. Existing methods often focus on average predictive performance, lacking the reliability mechanisms needed for retrospective reliability-aware assessment - namely, determining when the model is reliable, when to reject an assessment, when to retest, and from which symptom dimensions the predictions are based. This paper proposes SGC-RML, which maps speech, gait, wearable motion, mobility tasks, and clinical variables to a shared 8-dimensional symptom node space (7 clinical symptom nodes and 1 reliability_state auxiliary node), unifying motor and non-motor representations through a symptom atlas. By jointly introducing uncertainty estimation, conformal calibration, and selective decision routing, the model can not only predict symptoms and severity but also reject assessments or suggest retests when evidence is insufficient. We validate this framework on five real-world PD datasets, covering classification, regression, event detection, and longitudinal severity prediction. Experiments show that SGC-RML achieves an MAE of 4.579 / R^2 of 0.772 on PPMI, an AUC of 0.953 on mPower, and an AUC of 0.825 on PADS. Under leak-free temporal anchoring, as few as 5 subject-specific anchors transform UCI from an essentially non-predictive subject-independent setting (motor MAE 8.38, CCC 0.02) into a calibrated longitudinal assessment (motor MAE 3.24, CCC 0.756) with split-conformal coverage held at the 0.80 target. Under the Daphnet LOSO protocol, it achieves an F1 of 0.803 / AUC of 0.872. These results demonstrate that SGC-RML provides a unified paradigm for accurate, calibrated, auditable, and symptom-interpretable retrospective longitudinal assessment of PD under incomplete multimodal conditions.
| Comments: | Preprint. The first five authors contributed equally. Corresponding author: Hen-Wei Huang. 9 pages main text + appendix; 4 figures, 5 tables in main text |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08302 [cs.LG] |
| (or arXiv:2605.08302v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08302 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenbin Wei [view email]
[v1]
Fri, 8 May 2026 12:10:08 UTC (15,977 KB)