Using a Text Mining Approach to Explore the Recording Quality of a Nursing Record System.
Hsiu-Mei Chang, Ean-Weng Huang, I-Ching Hou and 3 others
PMID 30694223WHAT IT FOUND
Text mining software accurately flagged inconsistent nursing documentation terms, but it could not verify if the recorded care was clinically appropriate.
Auditors need human experts to check the content of these records.
Key findings
01The text mining software demonstrated high accuracy (95-99%) in identifying when nurses used free-text descriptions that matched existing standardized system terms.
02Despite the software's ability to sort terms, human experts were still required to judge whether the clinical content of the records was accurate or relevant.
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 conducted in a single medical center in Taiwan using one specific software, so the results may not apply to other hospitals or different IT systems. The software could not assess the timeliness of the records, meaning it missed errors where nurses documented care late or inaccurately due to time pressure. Only one expert reviewed the testing set due to manpower limits, which reduces the reliability of the final classification compared to the multi-expert training set.
Declared interests
The authors declare no conflicts of interest.
The easy way to misread this
Do not assume that because the software achieved 99% accuracy, the nursing records are clinically safe or correct. The software only checked if nurses used the right words for the system's categories; it did not verify if the care described was appropriate or if the patient's condition was accurately assessed.