A nomogram prediction of pressure injury in critical ill patients: A retrospective cohort study

Psychometric properties of the Braden scale to assess pressure injury risk in intensive care: A systematic review

OBJECTIVE

To analyse the psychometric properties of the Braden scale to assess pressure injury risk in adults in intensive care.

DESIGN

A systematic review was conducted, with literature searches undertaken in five electronic databases. No date limits were applied. Selection, data extraction and risk of bias assessment were completed by two reviewers independently. A customised data extraction template was used, with risk of bias conducted using the COSMIN Risk of Bias checklist. Data were analysed using narrative synthesis.

RESULTS

Thirty-four studies met inclusion criteria. Two studies reported internal consistency with Cronbach's alpha ranging from poor (0.43) to good (0.85). For interrater reliability, only four studies reported intraclass correlation, ranging from 0.66 to 0.96 for Braden sum score. Three studies reported convergent validity, with strong associations found between the COMHON Index (r = 0.70), Cubbin-Jackson scale (r = 0.80), and Norton scale (r = 0.77), but contrasting associations with the Waterlow score (r = 0.22 to 0.72). A large majority of studies reported predictive validity (n = 29), with wide variability. Several studies investigated optimal cut-off scores, with the majority indicating this was in the range of 12-14.

CONCLUSIONS

This review demonstrates inconsistency in the psychometric properties of the Braden scale in ICU settings. Further research is needed to determine suitability of the Braden scale for ICU before it can be recommended as standard for clinical practice, including comparison with other ICU-specific risk assessment tools.

IMPLICATIONS FOR CLINICAL PRACTICE

When used in ICU, the reliability, validity and reported cut-off scores of the Braden scale are variable. As a predictive tool, the scale should be used cautiously. In ICU, the value of the Braden scale resides in its ability to identify patients that are most at risk of developing a pressure injury and to implement preventative measures to mitigate identified risk factors.

A nomogram to predict the risk of surgery-related pressure ulcers in patients undergoing cardiovascular surgery

OBJECTIVE

In this study, we aimed to establish a new nomogram score to predict the occurrence of surgery-related pressure ulcers (SRPU) in patients undergoing cardiovascular surgery.

METHODS

We conducted a retrospective study among patients who underwent cardiovascular surgery between February 2016 and November 2020.

RESULTS

We established a prediction model based on a logistic regression model and tested the calibration and discrimination. We included 1163 patients who had undergone cardiovascular surgery. We formulated the logistic regression model, with Logit(P) = -11.745 + 0.024 preoperative hemoglobin value + 0.118 serum sodium value - 0.014 prealbumin value - 0.213 intraoperative mean temperature - 0.058 minimum mean arterial pressure + 0.646 preoperative blood potassium value + 0.264 smoking frequency + 0.760 hypertension history + 0.536 age ≥70 years. In this model ,"+" indicates that the factor is positively related to the occurrence risk of SRPU and "-" indicates that the factor is negatively associated with SRPU risk. The predictive model and nomogram had good accuracy in estimating the risk of SRPU, with a C-index of 0.755 (95% confidence interval: 0.719-0.792).

CONCLUSIONS

The present model can be used to effectively screen patients with a high risk of SRPU to devise targeted nursing intervention strategies and ultimately reduce the incidence rate of SRPU.

Nomogram model on estimating the risk of pressure injuries for hospitalized patients in the intensive care unit

OBJECTIVES

This study aimed to build and validate a nomogram model to estimate the risk of pressure injuries in intensive care unit patients.

DESIGN

Multicenter prospective cohort study.

SETTING

33 tertiary hospitals in the Gansu Province, China.

MEASUREMENTS AND MAIN RESULTS

This study included 6420 patients between April 2021 to October 2022 from an information platform of pressure injury risk management called the "Long Hu Hui." Univariate and multivariate logistic regression analyses identified pressure injury risk factors to be included in the nomogram. The resulting nomogram was tested for calibration discrimination, and clinical usefulness. Of the included patients, 77 developed pressure injuries, representing an incidence rate of 1.2 %. Analysis of binary logistic regression revealed that the estimation nomogram included weight loss greater than 5 kg in the last three months, pneumotomy cannula, thoracic catheter, isoproterenol, norepinephrine, abnormal skin color, ruptured erythema, stroke, increased body temperature and nonspecific patients (specific patients include paralysis, unconsciousness, dementia, forced body position). The area under the receiver operating characteristic curve for the training cohort was 0.806 (95 % CI 0.755-0.857), and the AUC of the text cohort was 0.737 (95 % CI 0.574-0.901). The model has excellent calibration in both the training cohort (H-L test: χ2 = 6.34, P = 0.61) and the text cohort (H-L test: χ2 = 4.50, P = 0.81). Furthermore, the decision curve analysis revealed the preferred net benefit and the threshold probability in the estimation nomogram.

CONCLUSIONS

The nomogram model accurately estimated the risk of pressure injuries among intensive care patients, it should be used to inform risk assessment and facilitate early intervention strategies in future practice.

IMPLICATIONS FOR CLINICAL PRACTICE

The nomogram allows intensive care providers to dynamically assess the patient's risk of pressure injuries and to implement more targeted interventions accordingly.

Risk factors and the nomogram model for intraoperatively acquired pressure injuries in children with brain tumours: A retrospective study

This study aimed to investigate the clinical features and incidence of Intraoperatively Acquired Pressure Injuries (IAPIs) of brain tumours in children, to screen the risk factors and to establish a nomogram model for making prevention strategies against the development of IAPIs. Clinical data of 628 children undergoing brain tumour surgery from August 2019 to August 2021 were extracted from the adverse events and the electronic medical systems. They were randomly divided into a training cohort(n = 471) and a validation cohort(n = 157). The univariate and multivariate analysis was performed to identify the risk factors in training cohort; R software was used to construct a nomogram model; the area under the receiver operator characteristic curve (AUC) and calibration plots were used to judge the predictive performance of the nomogram model; decision curve analysis (DCA) was used to assess the clinical usefulness of the nomogram model. Age, haemorrhage, use of vasopressor, temperature, operation time and operation position were considered as significant risk factors, and enrolled to construct a nomogram model. The results of AUC showed satisfactory discrimination of the nomogram; the calibration plots indicated favourable consistency between the prediction of the nomogram and actual observations in both the training and validation cohorts; DCA showed better net benefit and threshold probability of the nomogram model. The nomogram model illustrates significant predictive ability, which can provide scientific and individual guidance for preventing development of IAPIs.

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

The study aimed to establish a machine learning-based scoring nomogram for early recognition of likely pressure injuries in an intensive care unit (ICU) using large-scale clinical data. A retrospective cohort study design was employed to develop and validate a top-performing clinical feature panel accessibly in the electronic medical records (EMRs), which was in the mode of a quantifiable nomogram. Clinical factors regarding demographics, admission cause, clinical laboratory index, medical history and nursing scales were extracted as risk candidates. The performance improvement was based on the application of the machine learning technique, comprising logistic regression, decision tree and random forest algorithm with five-fold cross-validation (CV) technique. The comprehensive assessment of sensitivity, specificity and the area under the receiver operating characteristic curve (AUROC) was considered in the evaluation of predictive performance. The receiver operating characteristic curves revealed the top performance for the logistic regression model in respect to machine learning improvement, achieving the highest sensitivity and AUC among three types of classifiers. Compared against the 23-point Braden scale routinely recorded online, an incorporated nomogram of logistic regression model and Braden scale achieved the best performance with an AUC of 0.87 ± 0.07 and 0.84 ± 0.05 in training and test cohort, respectively. Our findings suggest that the machine learning technique potentiated the limited predictive validity of routinely recorded clinical data on pressure injury development during ICU hospitalisation. Easily accessible electronic records held the potentials to substitute the traditional Braden score in the prediction of pressure injury in intensive care unit. Preoperative prediction of pressure injury facilitates the exemption from the severe consequences.