Sentiment Analysis of Patient- and Family-Related Sepsis Events: Exploratory Study.
Mabel Ntiamoah, Teenu Xavier, Joshua Lambert
PMID 38557694WHAT IT FOUND
Sepsis narratives from 170 patients and families showed more fear and sadness words when mentioning hospital, ICU, medical terms and organ failure.
Medical terms also showed more anger and trust. This reports emotional tone, not tested care effects.
Key findings
01Hospital, medical and failure mentions were linked to higher estimated fear and sadness word rates.
02Medical terminology was associated with increased trust, with an average of 12.4 trust words.
03Death mentions were linked to lower estimated joy (0.90) and higher fear (1.03) and anger (1.09) rates.
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 analyzed public blog comments, not interviews or medical records, so it does not measure emotions directly. 4 comments were removed, and age and sex data were excluded because of missing values or reliability concerns. The initial blog story may have drawn more negative narratives and may not represent milder sepsis experiences. The sentiment lexicon may not tell sarcasm from genuine positive language. The analysis is exploratory, and many results are in tables that the text does not fully discuss.
Declared interests
The authors declared no conflicts of interest.
The easy way to misread this
Do not read the emotion word counts as proof that patients actually felt those emotions, or that any communication approach improves outcomes. The comments came from a public blog, the lexicon may not catch sarcasm or context, and the analysis is exploratory.