Artificial intelligence to predict bed bath time in Intensive Care Units.
Luana Vieira Toledo, Leonardo Lopes Bhering, Flávia Falci Ercole
PMID 38422311WHAT IT FOUND
Best AI model predicted ICU bed bath time with average error 1.9 minutes in 50 patients from one unit, but it should not replace nurse judgment.
Key findings
01The model was built from 50 adult critically ill ICU patients whose mean bed bath time was 26.45 minutes.
02The radial basis function neural network had the best correlation with actual bath times, with R2 = 62.3%, RMSE = 0.7 and MAE = 1.9.
03The model was built from a single ICU where all baths were performed by two people, and the authors caution that predictions can be inaccurate and should be used with clinical judgment.
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 model was built from a small sample in a single ICU, so it may not apply to other units or patient groups. All baths were performed by two nurses using one traditional method, which may not reflect usual practice. The paper reports model performance, not patient outcomes, nurse workload or implementation results. The authors acknowledge that predictions can be inaccurate and should be used with clinical judgment.
Declared interests
Funded by FAPEMIG and CAPES.
The easy way to misread this
Do not conclude that AI can now reliably plan bed baths or reduce nurse workload. The study only tested prediction accuracy in 50 patients from one ICU, and the authors say the models can be inaccurate and should not be used without clinical judgment.