Creating Perinatal Nursing Care Plans Using ChatGPT: A Pathway to Improve Nursing Care Plans and Reduce Documentation Burden.
Lisa G Johnson, Olatunde O Madandola, Fabiana Cristina Dos Santos and 4 others
PMID 39491050WHAT IT FOUND
ChatGPT-4 made a care plan for a preterm labor patient that matched the nurses' main priorities.
It missed some standardized nursing labels and changed top priorities, so a nurse must review and approve each suggestion.
Key findings
01For the exemplar patient, ChatGPT-4 produced four nursing diagnoses, eight nursing outcomes, and twelve nursing interventions, and its content was comparable to the nurse-generated plan.
02Eight of the twelve ChatGPT-4 interventions were exact matches for the standardized nursing language in the nurse-generated plan.
03The plans differed in priority: ChatGPT-4 made gestational diabetes the top priority and preterm labor the second priority, while the nurse-generated plan made preterm labor the highest priority and gestational diabetes the second.
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 comparison was made for an exemplar patient, not a group of patients, so it does not show how ChatGPT-4 performs across cases. The authors say this is an early step and that the prompt still needs testing in real clinical settings. ChatGPT-4 did not use correct standardized nursing terminology for all labels, with 16 of 24 labels correct. The same prompt sometimes produced different formats or content. The paper does not describe all risks of using ChatGPT-4 in patient care. Copyright limits meant ChatGPT-4 could not capture updated NANDA-I terminology in every linkage.
Declared interests
No conflicts of interest were declared. The article is listed as supported by NIH extramural research.
The easy way to misread this
Do not conclude that ChatGPT-4 can create safe perinatal care plans on its own. It was tested on an exemplar patient, used correct standardized terminology for 16 of 24 labels, and reversed the top two priorities compared with the nurses' plan.