A Novel Multi-Modal Sensor Dataset and Benchmark to Detect Agitation in People Living with Dementia in a Residential Care Setting
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
People living with dementia (PwD) in residential care settings often exhibit responsive behaviors, with agitation being the most common behavior. Automated systems to detect agitation events have the potential to improve patient care by helping to track symptoms and their response to interventions. We conducted a study from 2017 to 2019 in which we collected a novel multi-modal sensor dataset from 20 PwD living in a dementia care unit. Each participant wore an Empatica E4 watch for a maximum period of up to 60 days, leading to a large dataset worth 600 days. This wearable device collects raw acceleration, blood volume pulse, electro-dermal activity, and skin temperature data. The data are annotated with the start and end times of agitation events. Our previous analyses have shown that agitation behavior can be detected with a high area under receiver operating characteristic curve. We are now releasing this novel dataset for the research community to advance research in the field. In this article, we describe the study details, protocol used for annotation, improved agitation labelling, signal processing steps, and feature extraction approach. We present a new baseline on this dataset that can fuel new research in this important area of research.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it