Risk factors and the potential of nomogram for predicting hospital‐acquired pressure injuries

Abstract

This 1:5 case‐control study aimed to identify the risk factors of hospital‐acquired pressure injuries (HAPIs) and to develop a mathematical model of nomogram for the risk prediction of HAPIs. Data for 370 patients with HAPIs and 1971 patients without HAPIs were extracted from the adverse events and the electronic medical systems. They were randomly divided into two sets: training (n = 1951) and validation (n = 390). Significant risk factors were identified by univariate and multivariate analyses in the training set, followed by a nomogram constructed. Age, independent movement, sensory perception and response, moisture, perfusion, use of medical devices, compulsive position, hypoalbuminaemia, an existing pressure injury or scarring from a previous pressure injury, and surgery sufferings were considered significant risk factors and were included to construct a nomogram. In both of the training and validation sets, the areas of 0.90 under the receiver operating characteristic curves showed excellent discrimination of the nomogram; calibration plots demonstrated a good consistency between the observed probability and the nomogram's prediction; decision curve analyses exhibited preferable net benefit along with the threshold probability in the nomogram. The excellent performance of the nomogram makes it a convenient and reliable tool for the risk prediction of HAPIs.

Application of an infrared thermography-based model to detect pressure injuries: a prospective cohort study

“…Our results show that the development of pressure injuries is associated with the use of diuretic drugs and with hypertension, age, BMI, consciousness, diastolic blood pressure, ADL score, haemoglobin and length of hospital stay; this is consistent with the literature 30 . However, there was no significant correlation between albumin levels, Acute Physiology and Chronic Health Evaluation II (APACHE II) scores and the risk of pressure injury, as observed previously 31 . In our study, the predictive ability of the nomogram model that was developed based on these variables was poor (AUC 0·51, 95% CI 0·42–0·59).…”

“…30 However, there was no significant correlation between albumin levels, Acute Physiology and Chronic Health Evaluation II (APACHE II) scores and the risk of pressure injury, as observed previously. 31 In our study, the predictive ability of the nomogram model that was developed based on these variables was poor (AUC 0Á51, 95% CI 0Á42-0Á59). There are discrepancies in the risk factors for developing pressure injuries in different studies, reducing the reliability and validity of predictive models based on these factors.…”

Development and validation of a nomogram for predicting the risk of pressure injury in adult patients undergoing abdominal surgery

“…The results of this study showed that the nomogram had better specificity and sensitivity than the Braden score for assessing the risk of PI in critically ill patients admitted to the ICU [ 17 ]. A Chinese study of nomograms for predicting PI in the ICU based on hospital EHR data also showed similar results [ 18 ]. Notably, in this study, surgical suffering was considered an independent risk factor for the incidence of PI.…”

Development and validation of a machine learning algorithm–based risk prediction model of pressure injury in the intensive care unit

“…11,12 Since most machine learning algorithms were not presented intuitively, previous studies held predilection for logistic regression analysis, which quantified the risk formulation for clinicians to easily evaluate the risk probabilities. 13,14 In this study, we generated fresh insight into the fusion of machine learning and risk prediction to develop a brand-new model for predicting the risk probability of PIs in ICU.…”

“…However, the Braden scale demonstrated an insufficient performance and labour‐consuming trait, so that numerous studies devoted to finding better‐performing estimates to require less from nursing resources 11,12 . Since most machine learning algorithms were not presented intuitively, previous studies held predilection for logistic regression analysis, which quantified the risk formulation for clinicians to easily evaluate the risk probabilities 13,14 …”