Attention-based MIL fuses irregular smartwatch activity, sleep, and ECG HRV data to predict discretized changes in handgrip strength and FACIT-F with balanced accuracies of 0.59-0.70 under LOSO evaluation.
Characteristics associated with physical func- tion trajectories in older adults with cancer during chemotherapy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Frailty Estimation in Elderly Oncology Patients Using Multimodal Wearable Data and Multi-Instance Learning
Attention-based MIL fuses irregular smartwatch activity, sleep, and ECG HRV data to predict discretized changes in handgrip strength and FACIT-F with balanced accuracies of 0.59-0.70 under LOSO evaluation.