The identification of clusters of risk factors and their association with hospitalizations or emergency department visits in home health care.
Jiyoun Song, Sena Chae, Kathryn H Bowles and 9 others
PMID 36414419WHAT IT FOUND
Home health patients with high comorbidity burden or cognitive, psychological, and skin problems were more likely to need hospital or emergency care within 60 days than patients in a pain-focused cluster.
Key findings
01The analysis grouped home health episodes into three clusters: a pain-focused cluster, a high comorbidity cluster, and a cluster combining cognitive/psychological and skin problems.
02Compared with Cluster 1, Cluster 2 had 1.95 times higher risk and Cluster 3 had 2.12 times higher risk of hospitalization or emergency department visit within 60 days.
03When hospitalization or emergency department visit occurred, Cluster 1 reached the event in 38 days, compared with 41.7 days in Cluster 2.
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
The study was done at one home health organization in an urban northeastern U.S. area, so it may not apply to other places. The data were from 2015 to 2017, so they may not match current home health patients. Because the data were retrospective, the study cannot show that the clusters caused hospitalization or emergency visits. Some clinical characteristics were not included in clustering if they were rare, and the natural language processing tool was built for English clinical notes. Hospitalizations or emergency visits after discharge from home health were not available, so these events may have been underestimated. The cluster labels were reached by author consensus after analysis.
Declared interests
All authors reported no conflicts of interest. No funding source was stated in the supplied text.
The easy way to misread this
Do not conclude that intervening on these clusters will reduce hospitalizations or emergency visits. The study found associations in home health records and did not test an intervention based on the clusters.