A Predictive Model of Pressure Injury in Children Undergoing Living Donor Liver Transplantation Based on Machine Learning Algorithm.
Xiaomei Chen, Shi Tang, Yanwen Qin and 4 others
PMID 39253783WHAT IT FOUND
In 438 children after living donor liver transplant, 42 got pressure injuries, mostly on the back of the head.
Operation time, steroids, before surgery skin care and skin condition were the strongest risk clues in a model.
Key findings
01In children undergoing their first living donor liver transplant, 438 were examined and 42 developed pressure injuries.
02Fifty-four percent of the 50 pressure injuries were on the occiput.
03The best-performing Decision Tree model used operation time, intraoperative corticosteroids administration, preoperative skin protection measures and preoperative skin conditions, and in the 132-child testing dataset had sensitivity 0.769 and specificity 0.857.
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 retrospective and single centre, so the model may not work the same way in other hospitals. There was no prospective external validation. Only 42 children developed pressure injuries, and the testing set had 132 children, so performance estimates are based on a small number of events. Detailed preoperative skin care protocols were difficult to obtain because records were used. The paper did not test whether using the model reduced pressure injuries.
Declared interests
The authors declared no conflicts of interest.
The easy way to misread this
Do not assume this model is ready for clinical use or that the listed factors prove cause. It was developed from one centre's retrospective records, had no external validation, and did not test whether acting on the model prevented pressure injuries.