Framework for Mining and Analysis of Standardized Nursing Care Plan Data.
Ashfaq Khokhar, Muhammad Kamran Lodhi, Yingwei Yao and 3 others
PMID 27756852WHAT IT FOUND
Mining standardized nursing data from 34,927 patients revealed associations between specific care plans and outcomes.
Gerontology units showed better comfort for dying patients, and family involvement improved fall prevention behaviors.
Key findings
01Patients with Death Anxiety had a better chance of meeting the Comfortable Death goal when admitted to Gerontology units compared to other units.
02Patients at risk for falls who had pain reached their Fall Prevention Behavior outcome when nurses used interventions from the Family domain, unlike those without such interventions.
03Among patients with pain and cardiopulmonary problems, those without coping or stress tolerance issues had a better chance of meeting symptom control outcomes.
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 is observational and identifies associations, not causal effects. The data comes from a single EHR system (HANDS), which may limit generalizability. The high dimensionality and sparsity of the data required complex feature selection methods that may obscure some relationships. The paper focuses on the framework and data mining techniques rather than clinical validation of the findings.
Declared interests
The HANDS software used in the study is owned and distributed by HealthTeam IQ, LLC. Dr. Gail Keenan is the President and CEO of this company and has a conflict of interest statement in place with the University of Florida.
The easy way to misread this
Do not interpret these findings as proof that specific interventions cause better outcomes. The study identifies statistical associations within a large dataset but does not establish causality or account for all potential confounders.