Predicting the Risk for Hospital-Acquired Pressure Ulcers in Critical Care Patients

Hospital-acquired pressure ulcers among adult ICU patients in tertiary hospitals in Oman: a one-year prevalence study

BACKGROUND

Hospital-acquired pressure ulcer (HAPU) is a significant problem in healthcare settings and is associated with negative impacts on patient health. Although monitoring of pressure ulcers (PUs) among hospitalised patients was started more than a decade ago in Oman, no previous studies have been completed to estimate the prevalence and risk factors of HAPUs among patients in the intensive care unit (ICU). The aim of this study was to estimate the prevalence and identify risk factors for HAPUs among adult ICU patients in selected tertiary hospitals in Oman.

METHOD

A retrospective, cross-sectional, nested, case-control design was used to identify the prevalence rate of HAPUs and risk factors for a cohort of adult ICU patients over one calendar year (1 January-31 December 2019) in two tertiary hospitals in Oman.

RESULTS

The prevalence rate for HAPU among ICU patients in Oman was 36.4%. However, when excluding cases of stage 1 ulcer, the rate was 30.37%. The most prevalent location was the sacrum (64.1%), and the most common stage was stage 2 (73.1%). The risk factors for HAPU included male sex (odds ratio (OR): 0.37; p=0.023), organ failure (OR: 3.2; p=0.033), cancer (OR: 3.41; p=0.049), cerebrovascular accident (OR: 12.33; p=0.001), mechanical ventilator (OR: 9.64; p=0.025) and ICU length of stay (OR: 1.24; p<0.001).

CONCLUSION

HAPUs among ICU patients constitute a significant problem associated with severe clinical consequences and result in substantial adverse healthcare outcomes worldwide, including in Oman. Identifying the risk factors and the impact on the healthcare system is the foundation for preventing and managing HAPUs.

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.

Evaluation of the risk prediction model of pressure injuries in hospitalized patient: A systematic review and meta-analysis

AIMS AND OBJECTIVES

The main aim of this study is to synthesize the prevalent predictive models for pressure injuries in hospitalized patients, with the goal of identifying common predictive factors linked to pressure injuries in hospitalized patients. This endeavour holds the potential to provide clinical nurses with a valuable reference for providing targeted care to high-risk patients.

BACKGROUND

Pressure injuries (PIs) are a frequently occurring health problem throughout the world. There are mounting studies about risk prediction model of PIs reported and published. However, the prediction performance of the models is still unclear.

DESIGN

Systematic review and meta-analysis: The Cochrane Library, PubMed, Embase, CINAHL, Web of Science and Chinese databases including CNKI (China National Knowledge Infrastructure), Wanfang Database, Weipu Database and CBM (China Biology Medicine).

METHODS

This systematic review was conducted following PRISMA recommendations. The databases of Cochrane Library, PubMed, Embase, CINAHL, Web of Science, and CNKI, Weipu Database, Wanfang Database and CBM were searched for all studies published before September 2023. We included studies with cohort, case-control designs, reporting the development of risk model and have been validated externally and internally among the hospitalized patients. Two researchers selected the retrieved studies according to the inclusion and exclusion criteria, and critically evaluated the quality of studies based on the CHARMS checklist. The PRISMA guideline was used to report the systematic review and meta-analysis.

RESULTS

Sixty-two studies were included, which contained 99 pressure injuries risk prediction models. The AUC (area under ROC curve) of modelling in 32 prediction models were reported ranged from .70 to .99, while the AUC of verification in 38 models were reported ranged from .70 to .98. Gender (OR = 1.41, CI: .99 ~ 1.31), age (WMD = 8.81, CI: 8.11 ~ 9.57), diabetes mellitus (OR = 1.64, CI: 1.36 ~ 1.99), mechanical ventilation (OR = 2.71, CI: 2.05 ~ 3.57), length of hospital stay (WMD = 7.65, CI: 7.24 ~ 8.05) were the most common predictors of pressure injuries.

CONCLUSION

Studies of PIs risk prediction model in hospitalized patients had high research quality, and the risk prediction models also had good predictive performance. However, some of the included studies lacked of internal or external validation in modelling, which affected the stability and extendibility. The aged, male patient in ICU, albumin, haematocrit, low haemoglobin level, diabetes, mechanical ventilation and length of stay in hospital were high-risk factors for pressure injuries in hospitalized patients. In the future, it is recommended that clinical nurses, in practice, select predictive models with better performance to identify high-risk patients based on the actual situation and provide care targeting the high-risk factors to prevent the occurrence of diseases.

RELEVANCE TO CLINICAL PRACTICE

The risk prediction model is an effective tool for identifying patients at the risk of developing PIs. With the help of risk prediction tool, nurses can identify the high-risk patients and common predictive factors, predict the probability of developing PIs, then provide specific preventive measures to improve the outcomes of these patients.

REGISTRATION NUMBER (PROSPERO)

CRD42023445258.

Differentiating Pressure Ulcer Risk Levels through Interpretable Classification Models Based on Readily Measurable Indicators

Pressure ulcers carry a significant risk in clinical practice. This paper proposes a practical and interpretable approach to estimate the risk levels of pressure ulcers using decision tree models. In order to address the common problem of imbalanced learning in nursing classification datasets, various oversampling configurations are analyzed to improve the data quality prior to modeling. The decision trees built are based on three easily identifiable and clinically relevant pressure ulcer risk indicators: mobility, activity, and skin moisture. Additionally, this research introduces a novel tabular visualization method to enhance the usability of the decision trees in clinical practice. Thus, the primary aim of this approach is to provide nursing professionals with valuable insights for assessing the potential risk levels of pressure ulcers, which could support their decision-making and allow, for example, the application of suitable preventive measures tailored to each patient's requirements. The interpretability of the models proposed and their performance, evaluated through stratified cross-validation, make them a helpful tool for nursing care in estimating the pressure ulcer risk level.

Relationship between nutritional goals and pressure injuries in critical care patients receiving enteral nutrition

OBJECTIVE

To examine the relationship between pressure injury (PI) development and achievement of nutritional goals (protein and caloric), as well as consider the clinical conditions, hospitalisation factors, and risk assessment for PI development in patients who are critically ill and receiving enteral nutrition (EN) in the intensive care unit (ICU).

METHOD

An observational cohort study was conducted in the ICU of the University Hospital in São Paulo, Brazil. Inclusion criteria were as follows: age ≥18 years; length of ICU stay ≥24 hours; without PI at ICU admission; and receiving EN exclusively during ICU stay. The development of PI was considered the dependent variable. The Chi-squared test was applied to compare categorical variables, and the Mann-Whitney U test was used to compare continuous variables between groups of patients with and without a PI. The analysis of the achievement of nutritional goals was performed using Fisher's exact test. A significance level of 5% (p-value<0.05) and a confidence interval (CI) of 95% was adopted in all statistical tests.

RESULTS

A total of 181 patients met the inclusion criteria, of whom 102 (56.4%) were male and 79 (43.6%) were female. Mean age was 55.1 years, and mean length of ICU stay was 17.5 days. PI development was associated with not achieving nutritional goals. There was a higher percentage (65.3%) of patients without a PI when both protein and caloric goals were achieved. In contrast, 45.6% of patients developed a PI when the goals were not achieved. The mean days for sedation, vasoactive drugs and mechanical ventilation were all significantly higher in patients who developed a PI (p<0.001).

CONCLUSION

There was a significant association between patients developing a PI and deficits in caloric and protein intake. Patients who did not develop PIs had a greater calorie and protein intake compared with those who developed a PI.

Risk factors predicting hospital-acquired pressure injury in adult patients: An overview of reviews

BACKGROUND

Hospital-acquired pressure injuries remain a significant patient safety threat. Current well-known pressure injury risk assessment tools have many limitations and therefore do not accurately predict the risk of pressure injury development over diverse populations. A contemporary understanding of the risk factors predicting pressure injury in adult hospitalised patients will inform pressure injury prevention and future researchers considering risk assessment tool development may benefit from our summary and synthesis of risk factors.

OBJECTIVE

To summarise and synthesise systematic reviews that identify risk factors for hospital-acquired pressure injury development in adult patients.

DESIGN

An overview of systematic reviews.

METHODS

Cochrane and the Joanna Briggs Institute methodologies guided this overview. The Cochrane library, CINAHL, MEDLINE, and Embase databases were searched for relevant articles published in English from January 2008 to September 2022. Two researchers independently screened articles against the predefined inclusion and exclusion criteria, extracted data and assessed the quality of the included reviews using "a measurement tool to assess systematic reviews" (AMSTAR version 2). Data were categorised using an inductive approach and synthesised according to the recent pressure injury conceptual frameworks.

RESULTS

From 11 eligible reviews, 37 risk factors were categorised inductively into 14 groups of risk factors. From these, six groups were classified into two domains: four to mechanical boundary conditions and two to susceptibility and tolerance of the individual. The remaining eight groups were evident across both domains. Four main risk factors, including diabetes, length of surgery or intensive care unit stay, vasopressor use, and low haemoglobin level were synthesised. The overall quality of the included reviews was low in five studies (45 %) and critically low in six studies (55 %).

CONCLUSIONS

Our findings highlighted the limitations in the methodological quality of the included reviews that may have influenced our results regarding risk factors. Current risk assessment tools and conceptual frameworks do not fully explain the complex and changing interactions amongst risk factors. This may warrant the need for more high-quality research, such as cohort studies, focussing on predicting hospital-acquired pressure injury in adult patients, to reconsider these risk factors we synthesised.

REGISTRATION

This overview was registered with the PROSPERO (CRD42022362218) on 27 September 2022.

Risk assessment instruments for pressure ulcer in adults in critical situation: a scoping review

OBJECTIVE

to map the instruments for risk assessment of pressure ulcers in adults in critical situation in intensive care units; identify performance indicators of the instrument, and the appreciation of users regarding the instruments' use/limitations.

METHOD

a scoping review. We used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews in the writing of the study. We carried out the searches in the EBSCOhost search tool for 8 databases, resulting in 1846 studies, of which 22 studies compose the sample.

RESULTS

we identified two big instrument groups: generalist [Braden, Braden (ALB), Emina, Norton-MI, RAPS, and Waterlow]; and specific (CALCULATE, Cubbin & Jackson, EVARUCI, RAPS-ICU, Song & Choi, Suriaidi and Sanada, and COMHON index). Regarding the predictive value, EVARUCI and CALCULATE presented better results for performance indicators. Concerning appreciation/limitations indicated by users, we highlight the CALCULATE scale, followed by EVARUCI and RAPS-ICU, although they still need future adjustments.

CONCLUSION

the mapping of the literature showed that the evidence is sufficient to indicate one or more instruments for the risk assessment of pressure ulcers for adults in critical situation in intensive care units. (1) The risk assessment instrument must be applied to the patient's specificities. (2) The instruments are divided into two groups: generalist and specific. (3) The EVARUCI and CALCULATE instruments presented better results. (4) The EVARACI presented better results in terms of performance indicators. (5) The CALCULATE highlights itself for being recent scale, appropriate, simple, and easy to use.

Developing the Baptist Health Injury Risk Assessment Phase 1: Exploring Risk Factors

OBJECTIVES

The aim of this study was to explore risk factors for developing hospital-acquired pressure injuries (HAPIs) among critically ill adult inpatients.

BACKGROUND

Hospital-acquired pressure injuries remain a priority quality focus for Magnet ® organizations. Recent studies cite medical devices as a primary cause, yet published risk assessments lack inclusion of those threats.

METHODS

Nurses at a 434-bed, 4-time Magnet ® -designated hospital led a retrospective study acros 9 American Nurses Credentialing Center-designated facilities. Using a chart review tool, data were collected within 48 hours of a confirmed HAPI.

RESULTS

Of 207 HAPIs reported, 54% (n = 113) involved deep tissue pressure injuries and 50.2% (n = 104) involved 19 medical devices. Individuals with a HAPI also used 1 or more of 7 distinct types of mobility-limiting medical equipment.

CONCLUSIONS

Study findings support the development of a critical care risk assessment with inclusion of a medical device and mobility-limiting medical equipment as risk factors. A secondary study is underway for specificity and sensitivity testing of this assessment.

Predictive validity of the EVARUCI scale to evaluate risk for pressure injury in critical care patients

OBJECTIVE

To compare the predictive capacity of the current risk assessment scale for pressure ulcers in intensive care (EVARUCI), translated into Brazilian Portuguese, using the Braden scale.

METHOD

This cross-sectional study collected prospective data from adult patients in three intensive care units. The receiver operating characteristic (ROC) and precision-recall curve (PR curve) were used to analyse the predictive capacity for pressure injury (PI) using both predictive values and odds ratios (ORs).

RESULTS

The incidence of PIs in the study sample of 324 patients was 14.2%. The area under the ROC curve was 0.807 for EVARUCI and 0.798 for the Braden scale. At a cutoff point of 10 on the EVARUCI scale, sensitivity was 69.6%; specificity 78.4%; positive predictive value 34.8%; and OR 8.3. At a cutoff point of 11 on the Braden scale, sensitivity was 76.1%; specificity 75.9%; positive predictive value 34.3%; and OR 10. The area under the PR curve was 0.396 for the EVARUCI scale and 0.348 for the Braden scale, reflecting a smaller area for both. The F1 score value was 0.476 with 37.5% precision and 65.2% recall for the EVARUCI scale, and 0.473 with 34.3% precision and 76.1% recall for the Braden scale.

CONCLUSION

The EVARUCI scale predictive capacity was similar to that of the Braden scale. However, the precision of both scales was low for the accurate prediction of patients at risk of developing PIs.

An Integrated System of Braden Scale and Random Forest Using Real-Time Diagnoses to Predict When Hospital-Acquired Pressure Injuries (Bedsores) Occur

BACKGROUND AND OBJECTIVES

Bedsores/Pressure Injuries (PIs) are the second most common diagnosis in healthcare system billing records in the United States and account for 60,000 deaths annually. Hospital-Acquired Pressure Injuries (HAPIs) are one classification of PIs and indicate injuries that occurred while the patient was cared for within the hospital. Until now, all studies have predicted who will develop HAPI using classic machine algorithms, which provides incomplete information for the clinical team. Knowing who will develop HAPI does not help differentiate at which point those predicted patients will develop HAPIs; no studies have investigated when HAPI develops for predicted at-risk patients. This research aims to develop a hybrid system of Random Forest (RF) and Braden Scale to predict HAPI time by considering the changes in patients' diagnoses from admission until HAPI occurrence.

METHODS

Real-time diagnoses and risk factors were collected daily for 485 patients from admission until HAPI occurrence, which resulted in 4619 records. Then for each record, HAPI time was calculated from the day of diagnosis until HAPI occurrence. Recursive Feature Elimination (RFE) selected the best factors among the 60 factors. The dataset was separated into 80% training (10-fold cross-validation) and 20% testing. Grid Search (GS) with RF (GS-RF) was adopted to predict HAPI time using collected risk factors, including Braden Scale. Then, the proposed model was compared with the seven most common algorithms used to predict HAPI; each was replicated for 50 different experiments.

RESULTS

GS-RF achieved the best Area Under the Curve (AUC) (91.20 ± 0.26) and Geometric Mean (G-mean) (91.17 ± 0.26) compared to the seven algorithms. RFE selected 43 factors. The most dominant interactable risk factors in predicting HAPI time were visiting ICU during hospitalization, Braden subscales, BMI, Stimuli Anesthesia, patient refusal to change position, and another lab diagnosis.

CONCLUSION

Identifying when the patient is likely to develop HAPI can target early intervention when it is needed most and reduces unnecessary burden on patients and care teams when patients are at lower risk, which further individualizes the plan of care.

Is caring for pressure ulcers in the intensive care unit in Spain still a challenge? A qualitative study on nurses' perceptions

BACKGROUND

The incidence of pressure ulcers is an indicator of quality in intensive care units. Due to their frequency and severity, they are identified as a problem of great importance, where the well-being of patients and relatives is compromised, also generating a high healthcare cost. Nurses are primarily responsible for the care of pressure ulcers, however, the existing literature exposes a clear lack of knowledge regarding its prevention and treatment.

OBJECTIVES

To explore the attitudes, knowledge and perceived barriers by intensive care nurses regarding pressure ulcers treatment and prevention in a critical care setting.

DESIGN

A descriptive qualitative study has been carried out through semi-structured interviews with 22 intensive care nurses from two tertiary university hospitals in Spain. The consolidated criteria for reporting qualitative research (COREQ) guidelines were used to reinforce the methodological approach of the study.

FINDINGS

From the collected data, 4 main themes emerged: "lack of specific knowledge about pressure ulcers in intensive care", "continuity of care: the main problem to solve", "teamwork and pressure ulcers: gasping for improvement" and "Skin care as another vital sign".

CONCLUSION

Most intensive care nurses consider that they do not have sufficient knowledge regarding pressure ulcers. The nurses' attitudes are positive, however, an ineffective transmission of information and registration regarding ulcers is perceived. Regarding the treatment of pressure ulcers, the lack of continuity of care and updated knowledge/training have been the main barriers. In terms of prevention, the most mentioned barriers have been the clinical condition of the patient and the lack of personnel, despite the level of knowledge.

Incidence and Predictors of Pressure Ulcers among Adult Patients in Intensive Care Units at Arba Minch and Jinka Hospitals, Southern Ethiopia

Introduction

The incidence of a pressure ulcer in intensive care units (ICU) is significantly higher than in noncritical care settings. The patients in the ICU are the most vulnerable group to disruption of the skin's integrity. Prior studies in Ethiopia failed to evaluate pressure ulcers in intensive care units and were limited to general wards. The purpose of this study was to identify the incidence and predictors of pressure ulcers in adult patients admitted to intensive care units in Southern Ethiopia.

Methods

A single-arm prospective open cohort of 216 patients was used to determine the presence of a pressure ulcer in the intensive care units from June 2021 to April 2022. A consecutive sampling was used until the sample size was reached. The data were collected using a structured questionnaire and analyzed using Stata 14. A cumulative incidence of a pressure ulcer was computed. The life table was used to estimate the cumulative survival. A multivariable Cox proportional hazard regression was used to identify independent predictors of a pressure ulcer. An adjusted hazard ratio with a 95% CI was used to measure the degree of association; a P value ≤ 0.05 was considered significant.

Results

Twenty-five patients developed a pressure ulcer (PU), making a cumulative incidence of 11.57%. Out of 25 incident cases of pressure ulcers, four-fifths (80%) of the study patients developed PU within 6 days of their admission to the ICUs. The incidence rate was 32.98 PU per 1000 person-days of ICU stay. Pressure ulcers were most commonly found on the sacrum, followed by the shoulder. Among the incident cases, 52% were stage 2 ulcers. The presence of friction or shearing forces, as well as being 40 years of age or older, was independently associated with pressure ulcers.

Conclusion

The overall cumulative incidence of the pressure ulcer was lower than that in other studies but occurred at a faster rate. Age (40 years of age or older) and the presence of friction or shearing forces were the main predictors of pressure ulcers in the intensive care units. Therefore, nurses working in ICUs should continually anticipate the risk of a pressure ulcer. Moreover, special attention should be given to patients of advanced ages. Furthermore, monitoring the installation of a mattress, keeping bed linens unwrinkled, and keeping patients in a proper position on a bed to prevent or reduce friction or shearing forces are very crucial in the prevention of pressure ulcers.

An Integrated System of Multifaceted Machine Learning Models to Predict If and When Hospital-Acquired Pressure Injuries (Bedsores) Occur

Hospital-Acquired Pressure Injury (HAPI), known as bedsore or decubitus ulcer, is one of the most common health conditions in the United States. Machine learning has been used to predict HAPI. This is insufficient information for the clinical team because knowing who would develop HAPI in the future does not help differentiate the severity of those predicted cases. This research develops an integrated system of multifaceted machine learning models to predict if and when HAPI occurs. Phase 1 integrates Genetic Algorithm with Cost-Sensitive Support Vector Machine (GA-CS-SVM) to handle the high imbalance HAPI dataset to predict if patients will develop HAPI. Phase 2 adopts Grid Search with SVM (GS-SVM) to predict when HAPI will occur for at-risk patients. This helps to prioritize who is at the highest risk and when that risk will be highest. The performance of the developed models is compared with state-of-the-art models in the literature. GA-CS-SVM achieved the best Area Under the Curve (AUC) (75.79 ± 0.58) and G-mean (75.73 ± 0.59), while GS-SVM achieved the best AUC (75.06) and G-mean (75.06). The research outcomes will help prioritize at-risk patients, allocate targeted resources and aid with better medical staff planning to provide intervention to those patients.

Machine Learning Techniques, Applications, and Potential Future Opportunities in Pressure Injuries (Bedsores) Management: A Systematic Review

Pressure Injuries (PI) are one of the most common health conditions in the United States. Most acute or long-term care patients are at risk of developing PI. Machine Learning (ML) has been utilized to manage patients with PI, in which one systematic review describes how ML is used in PI management in 32 studies. This research, different from the previous systematic review, summarizes the previous contributions of ML in PI from January 2007 to July 2022, categorizes the studies according to medical specialties, analyzes gaps, and identifies opportunities for future research directions. PRISMA guidelines were adopted using the four most common databases (PubMed, Web of Science, Scopus, and Science Direct) and other resources, which result in 90 eligible studies. The reviewed articles are divided into three categories based on PI time of occurrence: before occurrence (48%); at time of occurrence (16%); and after occurrence (36%). Each category is further broken down into sub-fields based on medical specialties, which result in sixteen specialties. Each specialty is analyzed in terms of methods, inputs, and outputs. The most relevant and potentially useful applications and methods in PI management are outlined and discussed. This includes deep learning techniques and hybrid models, integration of existing risk assessment tools with ML that leads to a partnership between provider assessment and patients' Electronic Health Records (EHR).

A Hybrid System of Braden Scale and Machine Learning to Predict Hospital-Acquired Pressure Injuries (Bedsores): A Retrospective Observational Cohort Study

Background: The Braden Scale is commonly used to determine Hospital-Acquired Pressure Injuries (HAPI). However, the volume of patients who are identified as being at risk stretches already limited resources, and caregivers are limited by the number of factors that can reasonably assess during patient care. In the last decade, machine learning techniques have been used to predict HAPI by utilizing related risk factors. Nevertheless, none of these studies consider the change in patient status from admission until discharge. Objectives: To develop an integrated system of Braden and machine learning to predict HAPI and assist with resource allocation for early interventions. The proposed approach captures the change in patients' risk by assessing factors three times across hospitalization. Design: Retrospective observational cohort study. Setting(s): This research was conducted at ChristianaCare hospital in Delaware, United States. Participants: Patients discharged between May 2020 and February 2022. Patients with HAPI were identified from Nursing documents (N = 15,889). Methods: Support Vector Machine (SVM) was adopted to predict patients' risk for developing HAPI using multiple risk factors in addition to Braden. Multiple performance metrics were used to compare the results of the integrated system versus Braden alone. Results: The HAPI rate is 3%. The integrated system achieved better sensitivity (74.29 ± 1.23) and detection prevalence (24.27 ± 0.16) than the Braden scale alone (sensitivity (66.90 ± 4.66) and detection prevalence (41.96 ± 1.35)). The most important risk factors to predict HAPI were Braden sub-factors, overall Braden, visiting ICU during hospitalization, and Glasgow coma score. Conclusions: The integrated system which combines SVM with Braden offers better performance than Braden and reduces the number of patients identified as at-risk. Furthermore, it allows for better allocation of resources to high-risk patients. It will result in cost savings and better utilization of resources. Relevance to clinical practice: The developed model provides an automated system to predict HAPI patients in real time and allows for ongoing intervention for patients identified as at-risk. Moreover, the integrated system is used to determine the number of nurses needed for early interventions. Reporting Method: EQUATOR guidelines (TRIPOD) were adopted in this research to develop the prediction model. Patient or Public Contribution: This research was based on a secondary analysis of patients' Electronic Health Records. The dataset was de-identified and patient identifiers were removed before processing and modeling.

A systematic review of predictive models for hospital-acquired pressure injury using machine learning

AIMS AND OBJECTIVES

To summarize the use of machine learning (ML) for hospital-acquired pressure injury (HAPI) prediction and to systematically assess the performance and construction process of ML models to provide references for establishing high-quality ML predictive models.

BACKGROUND

As an adverse event, HAPI seriously affects patient prognosis and quality of life, and causes unnecessary medical investment. At present, the performance of various scales used to predict HAPIs is still unsatisfactory. As a new statistical tool, ML has been applied to predict HAPIs. However, its performance has varied in different studies; moreover, some deficiencies in the model construction process were observed in each study.

DESIGN

Systematic review.

METHODS

Relevant articles published between 2010-2021 were identified in the PubMed, Web of Science, Scopus, Embase and CINHAL databases. Study selection was performed in accordance with the preferred reporting items for systematic reviews and meta-analysis guidelines. The quality of the included articles was assessed using the prediction model risk of bias assessment tool.

RESULTS

Twenty-three studies out of 1793 articles were considered in this systematic review. The sample size of each study ranged from 149-75353; the prevalence of pressure injuries ranged from 0.5%-49.8%. ML showed good performance for HAPI prediction. However, some deficiencies were observed in terms of data management, data pre-processing and model validation.

CONCLUSIONS

ML, as a powerful decision-making assistance tool, is helpful for the prediction of HAPIs. However, existing studies have been insufficient in terms of data management, data pre-processing and model validation. Future studies should address these issues to establish ML models for HAPI prediction that can be widely used in clinical practice.

RELEVANCE TO CLINICAL PRACTICE

This review highlights that ML is helpful in predicting HAPI; however, in the process of data management, data pre-processing and model validation, some deficiencies still need to be addressed. The ultimate goal of integrating ML into HAPI prediction is to develop a practical clinical decision-making tool. A complete and rigorous model construction process should be followed in future studies to develop high-quality ML models that can be applied in clinical practice.

Impact of Nutrition on the Prevention and Treatment of Pressure Injuries in Critically Ill Patients: An Integrative Review

OBJECTIVE

To review the main scientific evidence on nutrition in the prevention and treatment of pressure injuries (PIs) in critically ill adult patients.

DATA SOURCES

The searches were carried out in several scientific databases, namely, Scientific Electronic Library Online (SciELO), Public MEDLINE (PubMed), Latin American and Caribbean Literature in Health Sciences (LILACS), and Web of Science. The MeSH terms used were "pressure injury", "nutrition", and "intensive care".

STUDY SELECTION

Studies published between January 1, 2005, and July 1, 2020, were included. Seven studies met the eligibility criteria and were included in this review. The searches were carried out in August 2020. The authors selected studies available in Portuguese, English, and Spanish.

DATA EXTRACTION

Two independent researchers conducted the searches and read the article titles and abstracts. The studies that met the inclusion criteria were fully evaluated. Disagreements between reviewers were resolved by consensus, and when there was no consensus, a senior researcher was consulted. Data extraction was performed using a standardized form.

DATA SYNTHESIS

Level-of-evidence analysis according to the type of study followed the classification proposed by the Oxford Center Evidence-Based Medicine. The evidence available on the use of standard enteral nutrition therapy and enteral nutrition therapy enriched with hyperprotein and hypercaloric nutrition supplements as well as the addition of zinc, eicosapentaenoic acid, γ-linolenic acid, and vitamins (A, C, D, and E) is limited in terms of supporting a specific nutrition support modality in the prevention and treatment of PI in the intensive care population.

CONCLUSIONS

Malnutrition negatively impacts both the prevention and healing of PIs. The evidence available on the use of standard enteral nutrition therapy versus enrichment with nutrition supplements is too limited to support a specific nutrition modality in the prevention and treatment of PI in the intensive care population.

Decision-Tree-Based Approach for Pressure Ulcer Risk Assessment in Immobilized Patients

Applications where data mining tools are used in the fields of medicine and nursing are becoming more and more frequent. Among them, decision trees have been applied to different health data, such as those associated with pressure ulcers. Pressure ulcers represent a health problem with a significant impact on the morbidity and mortality of immobilized patients and on the quality of life of affected people and their families. Nurses provide comprehensive care to immobilized patients. This fact results in an increased workload that can be a risk factor for the development of serious health problems. Healthcare work with evidence-based practice with an objective criterion for a nursing professional is an essential addition for the application of preventive measures. In this work, two ways for conducting a pressure ulcer risk assessment based on a decision tree approach are provided. The first way is based on the activity and mobility characteristics of the Braden scale, whilst the second way is based on the activity, mobility and skin moisture characteristics. The results provided in this study endow nursing professionals with a foundation in relation to the use of their experience and objective criteria for quick decision making regarding the risk of a patient to develop a pressure ulcer.

Malnutrition and Pressure Injury Risk in Vulnerable Populations: Application of the 2019 International Clinical Practice Guideline

ABSTRACT

Nutrition plays a vital role in promoting skin integrity and supporting tissue repair in the presence of chronic wounds such as pressure injuries (PIs). Individuals who are malnourished are at greater risk of polymorbid conditions, adverse clinical outcomes, longer hospital lengths of stay, PI development, and mortality, and incur increased healthcare costs compared with patients who are adequately nourished. In addition, some patient populations tend to be more vulnerable to PI formation, such as neonates, patients with obesity, older adults, and individuals who are critically ill. Accordingly, this article aims to review the latest nutrition care recommendations for the prevention and treatment of PIs, including those recommendations tailored to special populations. A secondary objective is to translate nutrition recommendations into actionable steps for the healthcare professional to implement as part of a patient plan of care.Implementing an evidence-based plan of care built around individualized nutrition interventions is an essential step supporting skin integrity for these populations. The 2019 Prevention and Treatment of Pressure Ulcers/Injuries: Clinical Practice Guideline (CPG) affirms that meeting nutrient requirements is essential for growth, development, maintenance, and repair of body tissues. Many macronutrients and micronutrients work synergistically to heal PIs. Registered dietitian nutritionists play an important role in helping patients identify the most nutrient dense foods, protein supplements, and oral nutrition supplements to meet their unique requirements.

Construction of Xinjiang metabolic syndrome risk prediction model based on interpretable models

Background

We aimed to construct simple and practical metabolic syndrome (MetS) risk prediction models based on the data of inhabitants of Urumqi and to provide a methodological reference for the prevention and control of MetS.

Methods

This is a cross-sectional study conducted in the Xinjiang Uygur Autonomous Region of China. We collected data from inhabitants of Urumqi from 2018 to 2019, including demographic characteristics, anthropometric indicators, living habits and family history. Resampling technology was used to preprocess the data imbalance problems, and then MetS risk prediction models were constructed based on logistic regression (LR) and decision tree (DT). In addition, nomograms and tree diagrams of DT were used to explain and visualize the model.

Results

Of the 25,542 participants included in the study, 3,267 (12.8%) were diagnosed with MetS, and 22,275 (87.2%) were diagnosed with non-MetS. Both the LR and DT models based on the random undersampling dataset had good AUROC values (0.846 and 0.913, respectively). The accuracy, sensitivity, specificity, and AUROC values of the DT model were higher than those of the LR model. Based on a random undersampling dataset, the LR model showed that exercises such as walking (OR=0.769) and running (OR= 0.736) were protective factors against MetS. Age 60 ~ 74 years (OR=1.388), previous diabetes (OR=8.902), previous hypertension (OR=2.830), fatty liver (OR=3.306), smoking (OR=1.541), high systolic blood pressure (OR=1.044), and high diastolic blood pressure (OR=1.072) were risk factors for MetS; the DT model had 7 depth layers and 18 leaves, with BMI as the root node of the DT being the most important factor affecting MetS, and the other variables in descending order of importance: SBP, previous diabetes, previous hypertension, DBP, fatty liver, smoking, and exercise.

Conclusions

Both DT and LR MetS risk prediction models have good prediction performance and their respective characteristics. Combining these two methods to construct an interpretable risk prediction model of MetS can provide methodological references for the prevention and control of MetS.

Pressure Injuries in Critical Care Patients in US Hospitals: Results of the International Pressure Ulcer Prevalence Survey

PURPOSE

The purpose of this secondary analysis was to examine pressure injury (PI) prevalence, PI risk factors, and prevention practices among adult critically ill patients in critical care units in the United States using the International Pressure Ulcer Prevalence™ (IPUP) Survey database from 2018 to 2019.

DESIGN

Observational, cohort study with cross-sectional data collection and retrospective data analysis.

SUBJECTS AND SETTING

The sample comprised 41,866 critical care patients drawn from a sample of 296,014 patients in US acute care facilities who participated in the 2018 and/or 2019 IPUP surveys. The mean age among critical care patients was 63.5 years (16.3) and 55% were male. All geographic regions of the United States were represented in this sample, with the greatest percentages from the Southeast (47.5%) and Midwest (17.5%) regions.

METHODS

Overall critical care PI prevalence and hospital-acquired PI (HAPI) rates were obtained and analyzed using the 2018/2019 IPUP survey database. Critical care PI risk factors included in the database were analyzed using frequency distributions. Prevention practices among critically ill patients were analyzed to evaluate differences in practices between patients with no PIs, superficial PIs (stage 1, stage 2), and severe PIs (stage 3, stage 4, unstageable, deep tissue pressure injury).

RESULTS

The overall PI prevalence for critical care patients was 14.3% (n = 5995) and the overall HAPI prevalence was 5.85% (n = 2451). In patients with severe HAPIs, the most common risk factors were diabetes mellitus (29.5%), mechanical ventilation (27.6%), and vasopressor agents (18.9%). Significant differences between patients with no PIs as compared to those with superficial or severe HAPIs (P = .000) for all prevention practices were found.

CONCLUSIONS

Study findings support the gaps elucidated in previous critical care studies on PI development in this population. The 2 most persistent gaps currently challenging critical care practitioners are (1) accurate risk quantification in this population and (2) the potential for unavoidability in PI development among critically ill patients.

Pressure wounds in a cohort of critical patients: incidence and associated factors

AIM

To assess the incidence and factors associated with pressure wounds in patients of a Brazilian clinical and surgical Intensive Care Center (composed of three Intensive Care Units).

METHOD

Cohort monitored for clinical and therapeutic variables in an Intensive Care Center. Cox's Multiple Regression was employed, establishing the number of days until the first pressure injury as a time variable; the omnibus test was also performed.

RESULTS

178 patients, 64 (36%) developed at least one pressure wound. The independent variables for the risk of pressure wounds were: Braden <13 (HR: 10.6; 95% CI: 2.5-43.7), history of previous stroke (HR: 2.6; 95% CI: 1.3-5.0), age> 60 years (HR: 2.0; 95% CI: 1.2-3.5), nothing by mouth time (HR: 1.06; 95% CI 1.02 -1.10) and physical therapy days (HR: 0.81; 95% CI: 0.73-0.91).

CONCLUSION

Pressure wounds were incident. Braden <13 points, history of previous strokes, being elderly, and time in nothing by mouth were shown to be independent risk factors for pressure wounds. The days of exposure to physical therapy were protective. These findings corroborate recommendations to monitor the frequency of pressure wounds and to establish protective measures based on local indicators.

Risk Factors for Pressure Injury Development Among Critical Care Patients

Identification of the appropriate pressure injury (PI) risk factors is the first step in successful PI prevention. Measuring PI risk through formalized PI risk assessment is an essential component of any PI prevention program. Major PI risk factors identified in the empirical literature in the critical care population include age, diabetes, hypotension, mobility, prolonged intensive care unit admission, mechanical ventilation and vasopressor administration. Future risk assessment using sophisticated data analytics available in the electronic medical record may result in earlier, targeted PI prevention and will improve our understanding of risk factors that may contribute to unavoidable PIs.

Value of pressure injury assessment scales for patients in the intensive care unit: Systematic review and diagnostic test accuracy meta-analysis

OBJECTIVES

To review and examine the evidence of the value of pressure injury risk assessment scales in intensive care patients.

RESEARCH METHODOLOGY

We searched MEDLINE, Embase, CINAHL, Web of Science, the Cochrane Library, China Biomedical Literature Service System, VIP Database and CNIK from inception to February 2019. Two reviewers independently assessed articles' eligibility and risk of bias using the Quality Assessment of Diagnostic Accuracy Studies-II (QUADAS-2). We used a hierarchical summary receiver operating characteristics (HSROC) model to conduct the meta-analysis of diagnostic accuracy.

RESULT

Twenty-four studies were included, involving 16 scales and 15,199 patients in intensive care settings. Results indicated that the top four risk assessment scales were the Cubbin & Jackson Index (SEN = 0.84, SPE = 0.84, AUC = 0.90), the EVRUCI scale (SEN = 0.84, SPE = 0.68, AUC = 0.82), the Braden scale (SEN = 0.78, SPE = 0.61, AUC = 0.78), the Waterlow scale (SEN = 0.63, SPE = 0.46, AUC = 0.56). The Norton scale and the other eleven scales were tested in less than two studies and need to be further researched.

CONCLUSION

The Braden scale, most frequently used in hospitals, is not the best risk assessment tool for critically ill patients. The Cubbin & Jackson Index has good diagnostic test accuracy. However, low quality of evidence and important heterogeneity were observed.

Pressure Injuries in Critical Care Patients: A Conceptual Schema

GENERAL PURPOSE

To outline a conceptual schema describing the relationships among the empirically supported risk factors, the etiologic factors, and the mitigating measures that influence pressure injury (PI) development in the critical care population.

TARGET AUDIENCE

This continuing education activity is intended for physicians, physician assistants, nurse practitioners, and nurses with an interest in skin and wound care.

LEARNING OBJECTIVES/OUTCOMES

After participating in this educational activity, the participant will: 1. Choose a static intrinsic factor that increases the risk for the development of PI. 2. List several dynamic intrinsic risk factors for developing a PI. 3. Identify dynamic extrinsic risk factors that may predispose a patient to developing a PI. 4. Explain the pathophysiology of PI development.

Predictive Validity of the Cubbin-Jackson and Braden Skin Risk Tools in Critical Care Patients: A Multisite Project

BACKGROUND

Patients in intensive care units are 5 times more likely to have skin integrity issues develop than patients in other units. Identifying the most appropriate assessment tool may be critical to preventing pressure injuries in intensive care patients.

OBJECTIVES

To validate the Cubbin-Jackson skin risk assessment in the critical care setting and to compare the predictive accuracy of the Cubbin-Jackson and Braden scales for the same patients.

METHODS

In 5 intensive care units, the Cubbin-Jackson and Braden assessments were completed by different clinicians within 61 minutes of each other for 4137 patients between October 2017 and March 2018. Bivariate correlations and the Fisher exact test were used to check for associations between the scores.

RESULTS

The Cubbin-Jackson and Braden scores were significantly and positively correlated (r = 0.80, P < .001). Both tools were significant predictors of skin changes and identified as "at risk" 100% of the patients who had a change in skin integrity occur. The specificity was 18.4% for the Cubbin-Jackson scale and 27.9% for the Braden scale, and the area under the curve was 0.75 (P < .001) for the Cubbin-Jackson scale and 0.76 (P < .001) for the Braden scale. These findings show acceptable construct validity for both scales.

CONCLUSIONS

The predictive validities of the Cubbin-Jackson and Braden scales are similar, but both are sub-optimal because of poor specificity and positive predictive value. Change in practice may not be warranted, because there are no differences between the 2 scales of practical benefit to bedside nurses.

Predictive validity of the braden scale for pressure injury risk assessment in adults: A systematic review and meta-analysis

AIM

Pressure injuries are common adverse events in clinical practice, affecting the well-being of patients and causing considerable financial burden to healthcare systems. It is therefore essential to use reliable assessment tools to identify pressure injuries for early prevention. The Braden Scale is a widely used tool to assess pressure injury risk, but the literature is currently lacking in determining its accuracy. This study aimed to evaluate the accuracy of the Braden Scale in assessing pressure injury risk.

DESIGN

Systematic review and meta-analysis.

METHODS

Articles published between 1973-2020 from periodicals indexed in the PubMed, EMBASE, CINAHL, Web of Science and the Cochrane Library were selected. Two reviewers independently selected the relevant studies for inclusion. Data were analysed by the STATA 15.0 and the RevMan 5.3 software.

RESULTS

In total, 60 studies involving 49,326 individuals were eligible for this meta-analysis. The pooled SEN, SPE, PLR, NLR, DOR and AUC were 0.78 (95% CI: 0.74 to 0.82), 0.72 (95% CI: 0.66 to 0.78), 2.80 (95% CI: 2.30 to 3.50), 0.30 (95% CI: 0.26 to 0.35), 9.00 (95% CI: 7.00 to 13.00) and 0.82 (95% CI: 0.79 to 0.85), respectively. Subgroup analyses indicated that the AUC was higher for prospective design (0.84, 95% CI: 0.81 to 0.87), mean age <60 years (0.87, 95% CI: 0.84 to 0.90), hospital (0.82, 95% CI: 0.79 to 0.86) and Caucasian population (0.86, 95% CI: 0.82 to 0.88). In addition, 18 was found to be the optimal cut-off value.

CONCLUSION

The evidence indicated that the Braden Scale had a moderate predictive validity. It was more suitable for mean age <60 years, hospitalized patients and the Caucasian population, and the cut-off value of 18 might be used for the risk assessment of pressure injuries in clinical practice. However, due to the different cut-off values used among included studies, the results had a significant heterogeneity. Future studies should explore the optimal cut-off value in the same clinical environment.

Evaluation of a Modified Version of the Norton Scale for Use as a Pressure Injury Risk Assessment Instrument in Critical Care: A Quality Improvement Project

PURPOSE

No risk assessment scale exists in the United States specifically designed for use among patients with critical illness. The aim of this project was to modify the Norton Scale for Pressure Sore Risk to improve its predictive power when used in the critical care setting.

PARTICIPANTS AND SETTING

The setting for this quality improvement project was a 1157-bed academic medical center in the Southeast United States. Data were collected from 114 clinicians; 111 were critical care nurses and 3 were certified wound care nurses.

METHODS

Participants assessed the pressure injury risks of a video-simulated critical care patient using the optimized Norton Scale (oNS); this instrument was modified from the Norton Scale. Data were collected on reliability, validity, usability, and preference.

OUTCOMES

All 114 participants accurately predicted a patient's severe high risk for pressure injury using the oNS. Predictive validity and reliability of the oNS were excellent based on a correlation coefficient of more than 0.6 and a Cronbach α = 0.944, respectively. The intraclass correlation coefficient (ICC) was 0.933 (95% confidence interval, 0.911-0.950). From 71.2% to 84.9% of the participants agreed that the oNS represented the desired characteristics for optimal usability in the critical-care setting. Preference for the oNS was associated with perceptions that it was easier, quicker, and more critical-care-specific than the Braden Scale for Pressure Sore Risk currently used in critical care units in the project facility.

IMPLICATIONS FOR PRACTICE

The oNS offered critical care nurses in our facility a quick, easy-to-use, critical care- specific risk assessment tool that focused on the unique vulnerabilities of patients with critical illness.

Comparing the Braden and Jackson/Cubbin Pressure Injury Risk Scales in Trauma-Surgery ICU Patients

BACKGROUND

The occurrence of pressure injury in the critical care environment has multiple risk factors. Prevention requires reliable assessment tools to help predict injury risk. The Braden scale, a commonly used risk assessment tool, has been shown to have poor predictive properties in critical care patients. The Jackson/Cubbin scale was developed specifically for pressure injury risk stratification in critically ill patients and has demonstrated acceptable predictive properties in the general critical care population but has not been examined in critically ill trauma-surgical patients.

OBJECTIVE

To compare the predictive properties of the Braden and Jackson/Cubbin scales in a trauma-surgical critical care population.

METHODS

A retrospective medical records review was performed to evaluate the clinical characteristics of 366 trauma-surgical critical care patients. Additionally, the negative predictive value, positive predictive value, sensitivity, specificity, and receiver operating characteristic curve with area under the curve of the Braden and Jackson/Cubbin scales were determined.

RESULTS

The sample consisted of primarily middle-aged (mean [SD], 56 [19] years) men (64%) admitted after trauma (71%). The participants who developed pressure injuries were older, more often required vasopressors and mechanical ventilation, and were less mobile. Predictive properties for the Braden and Jackson/Cubbin scales, respectively, were as follows: negative predictive value, 78% versus 87%; positive predictive value, 53% versus 66%; sensitivity, 17% versus 54%; specificity, 95% versus 92%; and area under the curve, 0.710 versus 0.793.

CONCLUSION

The Jackson/Cubbin scale demonstrated superior predictive properties and discrimination compared with the Braden scale for pressure injury risk prediction in critically ill trauma-surgical patients.

Applying Skin Barrier Film for Skin Tear Management in Patients with Central Venous Catheterization

OBJECTIVE

To examine and compare different methods of dressing change on skin tears at the periductal wound for ICU patients with central venous catheterization (CVC).

METHODS

This research used a quasi-experimental design. Participants included 98 patients from the ICU of a medical center in Taiwan using a convenience sampling technique from April 1, 2017 to March 31, 2018.

RESULTS

Applying skin barrier film at the CVC insertion site effectively protected the skin and significantly reduced the risk of skin tears among ICU patients (P < .01).

CONCLUSIONS

This study showed that use of skin barrier film at the site of CVC insertion can increase skin strength, maintain skin integrity, and decrease the incidence of skin tears. Skin barrier film is thus recommended for routine use in peripheral skin care for patients receiving CVC.

The Incidence of Pressure Ulcers and its Associations in Different Wards of the Hospital: A Systematic Review and Meta-Analysis

Pressure ulcer is a health problem worldwide that is common among inpatients and elderly people with physical-motor limitations. To deliver nursing care and prevent the development of pressure ulcers, it is essential to identify the factors that affect it. This global systematic review and meta-analysis was conducted with the aim of evaluating the incidence of pressure ulcers in observational studies. In this study, databases including Web of Science, Embase, PubMed, Scopus, and Google Scholar were searched to collect data. Articles published from 1997 to 2017 about the factors influencing the incidence of pressure ulcers were retrieved and their results were analyzed using meta-analysis according to the Random-Effects Model. The heterogeneity of studies was investigated using the I2 statistic. Data were analyzed using the R and Stata software (version 14). In this study, 35 studies were included in the final analysis. The results showed that the pooled estimate of the incidence rate of pressure ulcer was 12% (95% CI: 10-14). The incidence rates of the pressure ulcers of the first, second, third, and fourth stages were 45% (95% CI: 34-56), 45% (95% CI: 34-56), 4% (95% CI: 3-5), and 4% (95% CI: 2-6), respectively. The highest incidence of pressure ulcers was observed among inpatients in orthopedic surgery ward (18.5%) (95% CI: 11.5-25). According to the final results, better conditions should be provided to decrease the incidence of pressure ulcers in different wards, especially orthopedics, and in patients with diabetes.

Artificial intelligence and computer simulation models in critical illness

Widespread implementation of electronic health records has led to the increased use of artificial intelligence (AI) and computer modeling in clinical medicine. The early recognition and treatment of critical illness are central to good outcomes but are made difficult by, among other things, the complexity of the environment and the often non-specific nature of the clinical presentation. Increasingly, AI applications are being proposed as decision supports for busy or distracted clinicians, to address this challenge. Data driven "associative" AI models are built from retrospective data registries with missing data and imprecise timing. Associative AI models lack transparency, often ignore causal mechanisms, and, while potentially useful in improved prognostication, have thus far had limited clinical applicability. To be clinically useful, AI tools need to provide bedside clinicians with actionable knowledge. Explicitly addressing causal mechanisms not only increases validity and replicability of the model, but also adds transparency and helps gain trust from the bedside clinicians for real world use of AI models in teaching and patient care.

Comparison of four pressure ulcer risk assessment tools in critically ill patients

BACKGROUND

Critically ill patients are at a higher risk of developing pressure ulcers (PUs) than non-critically ill patients. Tools that aid in the early identification of those who are most at risk of PUs could help health care providers deliver early interventions and reduce unfavourable outcomes.

AIMS

To compare the validity of four PU risk tools (the Braden scale, the Braden [ALB] scale, the CALCULATE, and the COMHON index) and to demonstrate the optimal cut-off points for each tool in critically ill patients.

DESIGN

This was a prospective descriptive study.

METHOD

This study was conducted in the intensive care units (ICUs) of a tertiary care hospital in Thailand from January to April 2019. Baseline characteristics were collected at admission to the ICUs. Skin assessment was evaluated every 24 hours. PU assessment scores were collected every 72 hours. Receiver operating characteristic curves were used to compare the performance of the tests in predicting PUs.

RESULTS

A total of 288 patients were recruited. The incidence of PUs was 11.1%. The Braden (ALB) scale performed the best based on the area under the receiver operating characteristic curves (area under curve 0.74), followed by the CALCULATE (area under curve 0.71), the Braden (area under curve 0.67) scale, and the COMHON (area under curve 0.61) index. At the optimal cut-off point, the Braden (ALB) scale (≤13)) and the CALCULATE (≥3) were similar in terms of performance with an area under the curve of 0.69.

CONCLUSION

The Braden (ALB) performed the best at predicting PU development in ICU patients.

RELEVANCE TO CLINICAL PRACTICE

The validity of all four PU risk tools was limited in Thai patients. The scales should thus be used in conjunction with clinical judgement to provide optimal outcomes. The development of better assessment tools for the prediction of PUs is required.

A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models

OBJECTIVES

The objective of this study was to compare performance of logistic regression (LR) with machine learning (ML) for clinical prediction modeling in the literature.

STUDY DESIGN AND SETTING

We conducted a Medline literature search (1/2016 to 8/2017) and extracted comparisons between LR and ML models for binary outcomes.

RESULTS

We included 71 of 927 studies. The median sample size was 1,250 (range 72-3,994,872), with 19 predictors considered (range 5-563) and eight events per predictor (range 0.3-6,697). The most common ML methods were classification trees, random forests, artificial neural networks, and support vector machines. In 48 (68%) studies, we observed potential bias in the validation procedures. Sixty-four (90%) studies used the area under the receiver operating characteristic curve (AUC) to assess discrimination. Calibration was not addressed in 56 (79%) studies. We identified 282 comparisons between an LR and ML model (AUC range, 0.52-0.99). For 145 comparisons at low risk of bias, the difference in logit(AUC) between LR and ML was 0.00 (95% confidence interval, -0.18 to 0.18). For 137 comparisons at high risk of bias, logit(AUC) was 0.34 (0.20-0.47) higher for ML.

CONCLUSION

We found no evidence of superior performance of ML over LR. Improvements in methodology and reporting are needed for studies that compare modeling algorithms.

Developing a Health Risk Evaluation Method for Triple H

The development of a health evaluation system from human-related data is an important issue in preventive medicine. Previously, most studies have focused on disease assessment and prevention in patients. However, even if certain risk factors are all within normal ranges, individuals may not necessarily be completely healthy. This study focused on healthy individuals to develop a new index to assess health risks; this index can be used for the prevention of multiple diseases in healthy people. The kernel density technique was proposed to estimate the distribution of common risk factors and to develop a health risk index. A dataset of hypertension, hyperlipidemia, and hyperglycemia (Triple H) data from the National Health Insurance Research Database in Taiwan was used to demonstrate the proposed analytical process. The results of risk factor changes after six weeks of exercise were used to calculate the health risk index. The results showed that the subjects experienced a 7.29% reduction in their health risk index after the exercise intervention. This finding demonstrates the potential impact of an important reference index on quantifying the effect of maintenance in healthy people.

Risco de lesão por pressão em UTI: adaptação transcultural e confiabilidade da EVARUCI

Resumo Objetivo Realizar a adaptação transcultural da Escala de Valoración Actual del riesgo de desarrollar Úlceras por presión en Cuidados Intensivos (EVARUCI) para a língua portuguesa do Brasil e analisar sua confiabilidade em pacientes de Unidade de Terapia Intensiva (UTI). Métodos Pesquisa metodológica para adaptação transcultural e análise da confiabilidade da EVARUCI. A consistência interna foi verificada utilizando-se o Coeficiente Alfa de Cronbach. A concordância interobservadores foi verificada pela aplicação simultânea da versão final da EVARUCI por 3 enfermeiros e analisada pelo Coeficiente de Correlação Intraclasse (CCI). Resultados Na tradução e retrotradução, as discordâncias relacionaram-se ao uso de sinônimos e estilo de redação. Na avaliação do comitê de especialistas os termos, consciente, decúbito supino e turno não alcançaram a concordância de 90,0%. A consistência interna da EVARUCI mostrou-se aceitável (α=0,782). A concordância interobservadores foi excelente entre os avaliadores (CCI=0,980). Conclusão A adaptação transcultural da EVARUCI para o português do Brasil foi satisfatória quanto à consistência interna e à concordância interobservadores, indicando ser um instrumento específico para UTI, de fácil e rápida aplicação para avaliação de risco para lesão por pressão em pacientes críticos.