A LightGBM model using sensor features plus time-of-day and current agitation status predicts next-6-hour agitation with AUC-ROC 0.972 and AUC-PR 0.432 on the TIHM dataset, but random-fold evaluation and label-derived features leave the true predictive value unclear.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SP 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Benchmarking Early Agitation Prediction in Community-Dwelling People with Dementia Using Multimodal Sensors and Machine Learning
A LightGBM model using sensor features plus time-of-day and current agitation status predicts next-6-hour agitation with AUC-ROC 0.972 and AUC-PR 0.432 on the TIHM dataset, but random-fold evaluation and label-derived features leave the true predictive value unclear.