AI Article Synopsis

  • The study aimed to identify factors that lead to the progression of early pressure injuries in pediatric patients and develop a machine learning model for predicting these outcomes.
  • The researchers conducted a retrospective cohort study, analyzing data from pediatric patients with hospital-acquired stage I pressure injury or suspected deep tissue injury over a period from January 2015 to October 2018.
  • The best prediction model achieved high accuracy and identified key variables such as serum creatinine and red blood cell counts that influence healing outcomes, ultimately aiming to enhance care quality for children with pressure injuries.

Article Abstract

Aims: We sought to explore factors associated with early pressure injury progression and build a model for predicting these outcomes using a machine learning approach.

Design: A retrospective cohort study.

Methods: In this study, we recruited paediatric patients, with hospital-acquired stage I pressure injury or suspected deep tissue injury, who met the inclusion criteria between 1 January 2015-31 October 2018. We divided patients into two groups, namely healing or delayed healing, then followed them up for 7 days. We analysed patient pressure injury characteristics, demographics, treatment, clinical situation, vital signs, and blood test results, then build prediction models using the Random Forest and eXtreme Gradient Boosting approaches.

Results: The best prediction model, trained and tested using Random Forest with 10 variables, achieved an accuracy, sensitivity, specificity, and area under the curve of 0.82 (SD 0.06), 0.80 (SD 0.08), 0.84 (SD 0.08), and 0.89 (SD 0.06), respectively. The most contributing variables, in order of importance, included serum creatinine, red blood cell, and haematocrit.

Conclusion: An awareness of specific conditions and areas that could lead to delayed healing pressure injury in paediatric patients is needed.

Impact: This evidence-based prediction model, coupled with the aforementioned clinical indicators, is expected to enhance early prediction of outcomes in paediatric patients thereby improve the quality of care and the outcome of children with PIs.

Download full-text PDF

Source
http://dx.doi.org/10.1111/jan.14680DOI Listing

Publication Analysis

Top Keywords

pressure injury
20
paediatric patients
16
model predicting
8
outcomes paediatric
8
machine learning
8
delayed healing
8
random forest
8
prediction model
8
injury
6
pressure
5

Similar Publications

Background: To investigate the effect of Midnight-noon Ebb-flow combined with five-element music therapy in the continuous nursing of patients with chronic wounds.

Methods: From March 2022 to November 2023, we recruited 50 eligible chronic wound patients and randomly divided them into two groups according to a random number table: the experimental group (n = 25) and the control group (n = 25). The control group was treated with conventional nursing measures.

View Article and Find Full Text PDF

We report a case of a 45-year-old gentleman who presented to our major trauma centre after sustaining a penetrating high-pressure paint injection injury to the neck. This rare mechanism of injury is most commonly reported to affect the non-dominant hand, occurring due to the malfunction or misuse of industrial paint machines, causing a piercing soft tissue injury with high-pressure fluid. The unique challenges faced in managing penetrating injuries to the neck are due to the density of vital visceral structures in the region, including major blood vessels and the upper aerodigestive tract.

View Article and Find Full Text PDF

Only skull-deep? Headbutting adaptations may not extend to the brain cavity.

Anat Rec (Hoboken)

January 2025

Center for Anatomy and Functional Morphology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.

High-impact headbutting behavior makes the muskox (Ovibos moschatus) a charismatic species. While many theorize how these headbutting bovids might protect their brain during such encounters, few have investigated their claims anatomically. We investigated the anatomical function of digitiform impressions in the bovid brain cavity and their relationship to headbutting.

View Article and Find Full Text PDF

In patients with acute brain injury (ABI), optimizing cerebral perfusion parameters relies on multimodal monitoring. This include data from systemic monitoring-mean arterial pressure (MAP), arterial carbon dioxide tension (PaCO), arterial oxygen saturation (SaO), hemoglobin levels (Hb), and temperature-as well as neurological monitoring-intracranial pressure (ICP), cerebral perfusion pressure (CPP), and transcranial Doppler (TCD) velocities. We hypothesized that these parameters alone were not sufficient to assess the risk of cerebral ischemia.

View Article and Find Full Text PDF

Blood coagulation is a highly regulated injury response that features polymerization of fibrin fibers to prevent the passage of blood from a damaged vascular endothelium. A growing body of research seeks to monitor coagulation in microfluidic systems but fails to capture coagulation as a response to disruption of the vascular endothelium. Here we present a device that allows compression injury of a defined segment of a microfluidic vascular endothelium and the assessment of coagulation at the injury site.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!