Unsupervised Learning Identifies Sleep Disturbance Subtypes Among Dementia Caregivers.
Eunbee Angela Kim, Jiuchen Zhang, Amir M Rahmani and 3 others
PMID 42565376WHAT IT FOUND
143 dementia caregivers split into three sleep groups: efficient sleep, trouble falling and staying asleep, and too little sleep.
The too little sleep group was 72.0% male, 64% reported no support, and 100% reported a non-English primary language.
Key findings
01Unsupervised clustering of wearable sleep data from 143 dementia caregivers identified three subtypes: Optimal Sleep (n = 76), Disturbed Onset & Maintenance (n = 42), and Insufficient Sleep (n = 25).
02The Disturbed Onset & Maintenance cluster had the longest sleep onset latency (21.4 min) and wake after sleep onset (106.0 min); the Insufficient Sleep cluster had the shortest total sleep time (5.2 hrs) and lowest sleep efficiency (73.1%).
03The Insufficient Sleep cluster was 72.0% male, 64% reported no support, and 100% reported a non-English primary language.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only 143 of the original 163 caregivers were analysed, and usual care participants were excluded because they did not receive a wearable device. Caregivers with 40% or more missing sleep data were excluded, and missing data were treated as non-use, transmission issues, or similar problems. Bed start and bed end times were derived automatically by the ring's algorithm rather than laboratory sleep testing. No data were available on self-reported sleep concerns, sleep aid use, or sleep disorders such as sleep apnea. The study did not formally examine the intervention's effect on overall sleep dynamics, and group assignment was not used in clustering. The sample was drawn from caregivers recruited in California from four racial and ethnic groups, and 89.5% co-resided with the care recipient.
Declared interests
The parent study was federally funded. The supplied text does not report a conflict-of-interest declaration.
The easy way to misread this
Do not read this as evidence that a home-visit intervention improved sleep or that these sleep subtypes cause caregiver health problems. The clustering did not include study group assignment, and intervention versus attention control did not differ across clusters (p > .5).