A Data-Driven Model to Predict Delirium Based on Dynamic Patterns of Clinical Deterioration in Critically Ill Patients.
Ji-Sun Back, Yinji Jin, Taixian Jin and 2 others
PMID 41047725WHAT IT FOUND
In 3600 ICU patients, sustained worsening of vital signs and blood tests was linked to delirium.
Nurses should watch low diastolic blood pressure, high heart rate, high carbon dioxide, low albumin, high blood urea nitrogen or high sodium as possible delirium risk markers.
Key findings
01Of 3600 ICU patients, 827 had delirium and 2773 did not.
02The final model included 14 variables and had a C-statistic of 0.88; age ≥65, dependence, medical ICU, mechanical ventilation, PICC and restraints were associated with higher odds of delirium (odds ratios 2.11, 1.94, 4.02, 1.60, 1.51 and 4.58).
03Worsening or persistent diastolic BP <60 mmHg, HR >100/min, PaCO2 >48 mmHg, albumin <3 g/dL, BUN >20 mg/dL and sodium >146 mmol/L were associated with higher odds of delirium (odds ratios 2.01, 1.55, 1.45, 2.27, 1.45 and 2.06); worsening RR >25/min and HCO3 >28 mEq/L were not statistically significant.
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 analysis came from one university hospital, so it may not apply to other ICUs. 2438 of 8865 patients were excluded because research nurses could not access them, which was 28% of the total. The study only assessed delirium during ICU admission and did not include whether delirium existed before ICU or occurred after leaving ICU. The worsening or persistent group may combine different patient trajectories, such as those who worsened and never recovered and those who never worsened. CAM-ICU was performed twice daily by the nurse in charge, and no delirium protocol or prevention structure was in place during the study period.
Declared interests
Funded by the National Research Foundation of Korea and the Ministry of Education, Science and Technology; the authors declared no conflicts of interest.
The easy way to misread this
Do not read the model as a validated delirium-prevention tool. It was a retrospective single-centre analysis, 2438 of 8865 patients were excluded, and no delirium protocol or prevention structure was in place during the study period.