Pressure Injury Stage Research Articles

A randomised controlled phase II trial to examine the feasibility of using hyper-oxygenated fatty acids (HOFA) to prevent facial pressure injuries from medical devices among adults admitted to intensive care-A research protocol.

One in three patients admitted to intensive care will sustain a pressure injury (PI) from a medical device. These injuries are painful and when on the face, head or neck they can result in permanent disfigurement. Preliminary evidence of the efficacy of hyper-oxygenated fatty acids (HOFAs) to prevent facial pressure injuries from medical devices is promising; however, the feasibility of incorporating HOFAs into current standard care to prevent PI from a medical device of the face, head and neck has not been extensively explored. It is intended that the findings from this phase II feasibility study will inform the design of a larger phase III trial, by addressing two primary aims: (1) to assess the feasibility of incorporating HOFAs into standard care to prevent device-related pressure ulcers of the skin associated with the face, head and neck assess the feasibility and (2) efficacy preliminary effectiveness of HOFA. This feasibility study is an investigator-initiated mixed method study incorporating a multi-centre randomised controlled trial of using HOFAs as an adjunct to standard pressure injury prevention and care, compared with standard care alone to prevent facial, head or neck from medical devices among adults admitted to intensive care. The primary outcome of interest is the incidence of facial, head or neck pressure injuries during the first 14 days in intensive care. Secondary outcomes include PI staging, medical device exposure and intensive care and hospital outcomes. The primary analysis will be undertaken using Cox's Proportional Hazards model, and due to the exploratory nature of this phase II trial, efficacy will be based on a one-sided p-value for superiority set at 0.10. Type I and Type II error rates are set at 20%; therefore, a total sample size of 196 study participants is planned. To explore the feasibility of incorporating HOFA into usual care and to design a larger phase III trial, we will aim to interview between 10 and 20 nurses across participating intensive care unit sites. Pressure injuries of the face, head or neck from medical devices, among adults admitted to intensive care, are considered preventable. This phase II study will investigate the feasibility and efficacy of HOFAs as an adjunct to standard care. Importantly, we aim to inform the development of a larger phase III trial.

Prevalence and Risk Factors of Pressure Injury in Home Care Patients

The present study aimed to determine the prevalence of pressure injury in home care patients and the risk factors that affected its occurrence. The study was conducted in a descriptive-cross-sectional design to 6 months between November 2021 and May 2022 with 170 home care patients who were registered to the Home Health Care Service at a public hospital a city western in Turkey and met the inclusion criteria. The data were collected with the in-person interview method by using the investigator-created Patient Evaluation Form, National Pressure Injury Advisory Panel (NPIAP) Pressure Injury Staging System, and Glasgow Coma Scale (GCS). The prevalence of pressure injury was found to be 33.5% in the study. The prevalence of pressure injury was statistically and significantly higher in the patients younger than 75 years of age ( p = .043), underweight, and with normal Body Mass Index (BMI) ( p = .009). The prevalence of pressure injury was found to be lower in those who were oriented according to GCS ( p = .000). No statistically significant differences were detected between the presence of pressure injury and gender, education levels, marital status, income status, presence of systemic or chronic disease, continuous medication use, type of medication used, and duration of receiving home care services ( p > .05). The results of the present study showed that the prevalence of pressure injury was high in home care patients and that age, BMI, and level of consciousness variables were factors that influenced the development of pressure injury.

Incidence and Risk Factors for Perioperative Pressure Injuries: Prospective Descriptive Study

PurposePressure injuries can often occur in patients undergoing surgical, diagnostic, or other invasive procedures, so it is important to assess patients in the perioperative period. This study was conducted to determine the incidence and risk factors of perioperative pressure injury. DesignA cross-sectional, prospective, and descriptive study. MethodsThis study involved 158 patients who met the study's eligibility criteria between May 2022 and July 2022. The data were collected using the Patient Information Form, Munro Scale, Braden Scale, and pressure injury staging form. The patients were monitored postoperatively or for 3 days. FindingsPressure injury developed in 13.9% of the patients. Perioperative risk factors were age, edema, mobilization time, parenteral nutrition, blood transfusion, and glucose level, while preoperative albumin level was lower in patients with pressure injury. In the postoperative period, the risk factors were duration of mobilization and transition to oral feeding, length of intensive care unit stay, and low Braden score. In multivariate analysis, the variables that showed significance with the risk of pressure injury were postoperative Munro score and edema. ConclusionsIt is crucial to evaluate the risk factors for pressure injury in patients who have undergone surgical procedures.

An inter-assessor reliability study on the categorization and staging of pressure injuries

BackgroundThe first step in effective management of pressure injuries (PIs) is to assess, categorize and stage correctly. PurposeThis study aims to examine the agreement regarding the classification and staging of PIs among nurse academicians working on chronic wounds and with different stage of expertise. MethodsThree nurse academicians were assigned as assessors according to Benner's stages of clinical competence (Competent, Proficient, and Expert). The assessors independently evaluated PIs photographs (n = 694). The assessors then met for the wounds where there was disagreement, and a Consensus agreement was reached. Kappa Statistics analysed the agreement between two assessors; Fleiss Kappa Statistics analysed the agreement between Competent, Proficient, Expert, and Consensus. ResultsStatistically, almost perfect agreement was obtained between Competent, Proficient, Expert, and Consensus assessments, respectively (Ƙ = 0.871; p < 0.001, Ƙ = 0.842; p < 0.001, Ƙ = 0.937; p < 0.001). The highest agreement between the assessors were Unstageable PIs, Deep Tissue PIs, and Stage 3 PIs respectively. The most common disagreements were between Deep Tissue PIs and Stage 1 PIs, and between Deep Tissue PIs and Stage 2 PIs. ConclusionIn the study, it was found that the categorization, and staging of PIs had varying degrees of reliability among the assesors, although at a statistically acceptable level.

Altered serum transferrin levels are associated with pressure injury and its stages: A case-control study

Abstract Background: Despite the measures taken to the traditional risk factors for pressure injury (PI), there is still a great residual risk. Therefore, on the basis of managing traditional risk factors, it is necessary to find and interpret interventionable factors for predicting and treating PI. Objective: To investigate the relationship between serum transferrin level and the severity of PI. Methods: PI patients from The Affiliated Hospital of Qingdao University between July 2020 and June 2021 were selected as the case group, which was further divided into stage 1 (30 patients), stage 2 (59 patients), stage 3 (64 patients), and stage 4 (43 patients) according to PI stage. The control group consisted of 196 bedridden patients of similar age who did not have a PI and were matched to the cases by sex and age. This study evaluated the serum transferrin level between the case and control groups. Results: The serum transferrin levels were statistically significant between the control and case groups (P&lt;0.001). The serum transferrin level of PI patients with stages 3 and 4 was significantly lower than that of patients with stages 1 and 2 (P&lt;0.05). After adjusting for covariates, serum transferrin remained negatively associated with PI occurrence (B=−0.045, adjusted OR=0.956, P&lt;0.001) and stage (B=−2.266, adjusted OR=0.104, P&lt;0.001). Conclusions: The serum transferrin level was decreased with the progression of PI. This study suggests that serum transferrin can serve as positive evidence for treating PI patients.

Application of deep learning to pressure injury staging.

Accurate assessment of pressure injuries (PIs) is necessary for a good outcome. Junior and non-specialist nurses have less experience with PIs and lack clinical practice, and so have difficulty staging them accurately. In this work, a deep learning-based system for PI staging and tissue classification is proposed to help improve its accuracy and efficiency in clinical practice, and save healthcare costs. A total of 1610 cases of PI and their corresponding photographs were collected from clinical practice, and each sample was accurately staged and the tissues labelled by experts for training a Mask Region-based Convolutional Neural Network (Mask R-CNN, Facebook Artificial Intelligence Research, Meta, US) object detection and instance segmentation network. A recognition system was set up to automatically stage and classify the tissues of the remotely uploaded PI photographs. On a test set of 100 samples, the average precision of this model for stage recognition reached 0.603, which exceeded that of the medical personnel involved in the comparative evaluation, including an enterostomal therapist. In this study, the deep learning-based PI staging system achieved the evaluation performance of a nurse with professional training in wound care. This low-cost system could help overcome the difficulty of identifying PIs by junior and non-specialist nurses, and provide valuable auxiliary clinical information.

NURSES ROLES IN THE MANAGEMENT OF PRESSURE INJURY

Pressure injury, also referred to as pressure ulcers or bedsores, are debilitating wounds that develop when prolonged pressure is applied to the skin, resulting in localized tissue damage and compromised blood flow. These injuries often occur in areas where bony prominence come into contact with surfaces such as beds, chairs, or medical devices. The National Pressure Injury Advisory Panel (NPIAP) defines pressure injury as "localized injury to the skin and/or underlying tissue usually over a bony prominence, as a result of pressure, or pressure in combination with shear and/or friction." This definition highlights the multi-factorial nature of pressure injury development, which can involve not only pressure but also shear forces and friction. The importance of managing pressure injury cannot be overstated, as they pose significant health risks and can lead to serious complications if left untreated.More importantly, pressure injury can impair mobility, hinder rehabilitation efforts, and prolong hospitalization, resulting in increased healthcare costs and diminished quality of life. Pressure injury is the third most expensive disorder after cardiovascular diseases and cancer (Agrawal &amp; Chauhan, 2012 as cited in Nkor M.M.,2022). Objectives : the objectives of this study includes , identification of various risk factors influencing the development of pressure injury, outlining assessment techniques for pressure injury, standardized tools used for pressure injury assessment, stages of pressure injury, nursing interventions for pressure injury and evidence base wound care techniques for various stages. Summary: In summary, pressure injuries remain a significant healthcare challenge, particularly for individuals with limited mobility or underlying health conditions. Effective prevention, assessment, and management of pressure injuries require a multifaceted approach that incorporates evidence-based practices, interdisciplinary collaboration, and patient-centered care.

Applying Object Detection and Large Language Model to Establish a Smart Telemedicine Diagnosis System with Chatbot: A Case Study of Pressure Injuries Diagnosis System.

Background: The scarcity of medical resources and personnel has worsened due to COVID-19. Telemedicine faces challenges in assessing wounds without physical examination. Evaluating pressure injuries is time consuming, energy intensive, and inconsistent. Most of today's telemedicine platforms utilize graphical user interfaces with complex operational procedures and limited channels for information dissemination. The study aims to establish a smart telemedicine diagnosis system based on YOLOv7 and large language model. Methods: The YOLOv7 model is trained using a clinical data set, with data augmentation techniques employed to enhance the data set to identify six types of pressure injury images. The established system features a front-end interface that includes responsive web design and a chatbot with ChatGPT, and it is integrated with a database for personal information management. Results: This research provides a practical pressure injury staging classification model with an average F1 score of 0.9238. The system remotely provides real-time accurate diagnoses and prescriptions, guiding patients to seek various medical help levels based on symptom severity. Conclusions: This study establishes a smart telemedicine auxiliary diagnosis system based on the YOLOv7 model, which possesses capabilities for classification and real-time detection. During teleconsultations, it provides immediate and accurate diagnostic information and prescription recommendations and seeks various medical assistance based on the severity of symptoms. Through the setup of a chatbot with ChatGPT, different users can quickly achieve their respective objectives.

Medical device-related pressure injuries prevention practices of intensive care unit nurses: A cross‐sectional study in Turkey

AimMedical device-related pressure injuries (MDRPIs) are becoming increasingly common across all healthcare services and age groups in terms of both incidence and severity. It is crucial for nurses to be aware that MDRPI is a potential complication of healthcare services. This study aimed to assess the preventive practices of intensive care unit (ICU) nurses in relation to MDRPIs. Materials and methodsThis cross-sectional and descriptive study was conducted with 96 nurses between March 10 and April 31, 2021. The “Nurse Information Form” and the “MDRPIs Prevention Practices Questionnaire” form were used for the data collection. ResultsThe overall practice scores of ICU nurses in preventing MDRPIs were 50.83 ± 12.93. Out of the participants, 57.3% (n = 55) achieved a total practice score of 51 and above out of 68 (considered an acceptable score indicating proficiency in positive practice). The items with the most negative practice levels among nurses were related to statements such as ‘I apply hydrocolloid, thin foam, or a silicone-type dressing to prevent MDPRI’ (2.86 ± 0.85) and ‘I use the normal pressure injury staging when staging the MDRPI’ (2.88 ± 0.86). No significant difference was observed between the mean scores of MDRPI prevention practices and the characteristics of ICU nurses, such as education level, years working in the unit, and years of experience in the profession (p > 0.05). Furthermore, a positive correlation was found between age and practice levels in preventing MDRPIs (p < 0.05). ConclusionThe study results indicate that the practice levels of ICU nurses in preventing MDRPIs were insufficient. We believe that regular in-service training programs, grounded in clinical practice, are necessary to enhance nurses' awareness and management of MDRPIs.

Pressure injury prevalence in critical care settings: An observational pre-post intervention study.

To explore pressure injury prevention practices and evaluate the impact of an educational intervention on PI prevalence before and after an educational intervention. A multi-centre observational study. Data were collected at two time points in May 2021 and April 2022 using a Qualtrics® online form. Two Registered Nurses at each site collected observational data at each time point by diagnosing and staging any identified pressure injuries as part of a prevalence study. Patients admitted to participating units were included. A total of 181 patients in critical care units were included at the two-time points. Pressure injury prevalence was 60.9% at the outset, with 52.9% hospital-acquired, 37.9% unit-acquired and 23.0% medical device-related. Post-intervention prevalence decreased significantly to 28.7%, including 21.3% hospital-acquired, 14.9% unit-acquired, and 8.5% medical device-related. Pressure injuries were prominent in the sacral region, head area, and heels. Stages I and II pressure injuries were the most common. Increased age and longer ICU stays are linked to a heightened risk of pressure injury development in critically ill patients, whereas higher haemoglobin levels show an inverse relationship with the development of both pressure injury and severe stages in the univariate analysis. The predictive models revealed that increased age and longer ICU stays are predictors for both pressure injury development and progression to severe stages, while Braden scores predict the likelihood of developing severe stages of pressure injuries. This study has identified a benchmark for pressure injury prevalence in critical care units in Saudi Arabia. The results demonstrate that pressure injuries can be prevented in critically ill patients when evidence-based education strategies are implemented. Pressure injuries are an important issue for critically ill patients and can be prevented with proper investments. Strategies to prevent pressure injuries from admission will result in fewer pressure injuries. Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) guidelines and the Template for Intervention Description and Replication (TIDieR) checklist. No patient or public contribution.

Socio-economic and environmental factors associated with community-acquired pressure injuries: A mixed method study

AimsTo: (1) report on the prevalence of community-acquired pressure injuries (CAPIs) in patients admitted into the acute care setting; (2) examine the socio-economic and home environment associated with CAPIs; and (3) understand the challenges of caring for patients with CAPIs at home. MethodsThis mixed-method study recruited patients admitted with CAPIs in the acute care hospital between March 2021 to June 2022. The hospital's pressure injury (PI) database was used to screen patients admitted with CAPIs. A purposive sample of CAPI patients and their caregivers participated in this study. A cross-sectional survey study was first performed to examine the prevalence of CAPIs and the socio-economic and home environment factors. Semi-structured interviews were conducted to understand the caregivers' challenges in caring for patients with CAPIs at home. ResultsThe CAPI prevalence was reported at 1.1 % during the study period (1039 had CAPIs out of 97 912 patients admitted to the hospital). A total of 70 caregivers and patients consented to participate in the study. The mean age of patients was 84.2 (SD = 10.4) years old; 68.6 % (n = 48) were females. Majority presented with a deep tissue injury (DTI) (37.1 %; n = 26) or unstageable PI (31.4 %; n = 22). More than half of the patients had alternating air mattresses at home (54.3 %; n = 38), and only 10 % (n = 7) had positioning wedges and used a sliding sheet for turning. The mean age of the caregivers was 43.4 years old (SD = 13.1), and 84.3 % (n = 59) were female. Continuous data were summarised using means and standard deviations, and categorical data were summarised using frequencies and percentages. Logistic regression found no significant socio-demographic and clinical predictors of patients having PI stages 2, 3, and 4 compared to patients with DTI and unstageable PI. Challenges to caring for PI at home included high financial burden, physical limitations, and personal challenges in CAPIs management. ConclusionCAPIs are prevalent among older patients admitted to the acute care setting. Understanding the influence of socio-economic factors is crucial for developing comprehensive strategies to mitigate the occurrence and impact of PIs. Ongoing support and education to the caregivers in the community is essential to address the reported challenges in PI care.

Comparing the Efficacy of Zinc Oxide Versus Barrier Creams for Pressure Injury Prevention: A Retrospective Cross-sectional Study.

To compare the efficacy of zinc oxide versus barrier creams for the maintenance of skin integrity in intensive care patients with a risk of pressure injury (PI). This was a retrospective and cross-sectional study. The authors included data from 95 patients treated in the neurology and respiratory ICUs of a training and research hospital between January and June 2022. Patients in the neurology ICU were treated with zinc oxide cream (group 1, n = 48), and patients in the respiratory ICU received classic barrier cream (group 2, n = 47). Sociodemographic characteristics and PI data (Braden Scale score, Pressure Ulcer Healing Assessment Scale [PUSH] score, and PI stage) were obtained from each patient's file. The mean PUSH score of the patients who received zinc oxide cream was 3.83 ± 4.39 at discharge versus 6.79 ± 4.40 for the group who received barrier cream. When PUSH scores and PI stages during hospitalization and discharge were compared, the authors found a statistically significant between-group difference in mean discharge scores (P < .05). Within the limitations of this retrospective study based on patient records, zinc oxide creams had more positive effects on the prevention of PIs than barrier creams.

Mucosal membrane pressure injury in intensive care units: A scoping review

AimTo describe published work on the current situation of mucosal membrane pressure injury of patients in the intensive care unit. BackgroundDevice-related pressure injuries in critically ill patients are mostly focused on skin surface injuries, and less attention is paid to mucosal membrane pressure injury. MethodsWe searched PubMed, Embase, Web of Science, CINAHL, and Cochrane Library from database construction until March 1, 2023. Two researchers independently screened and extracted data. ResultsEighteen articles met our criteria and were published in 2014–2023. The included studies showed that the incidence of mucosal membrane pressure injury in critically ill patients ranged from 0.83% to 88.2%, and the prevalence ranged from 0.16% to 55.6%. The most frequently reported site of mucosal injury is the oral mucosa, followed by the nasal mucosa. Ten studies used Braden to assess the risk of mucosal membrane pressure injury, and only six studies reported specific stages of mucosal membrane pressure injury. Thirteen studies described 30 risk factors for mucosal membrane pressure injury, with albumin being the most frequently reported risk factor, followed by the vasoconstrictive drugs use. Thirty risk factors were summarized in six aspects: medical device-related factors, disease-related factors, treatment- related factors, physiological and biochemical parameters, demographic-related factors, and microbial colonisation. ConclusionsThe incidence or prevalence of mucosal membrane pressure injury varies widely, and specific risk assessment tools and standardized staging criteria need to be further determined. The risk factors of mucosal membrane pressure injury involve multiple aspects, and some risk factors have only been explored in few studies and need to be further verified, in order to detect the risk group of mucosal membrane pressure injury early and take targeted preventive measures. Implications for Clinical PracticeWe synthesized the current research status of mucosal membrane pressure injury in critically ill patients, which can provide a valuable reference for the clinical staff to develop preventive and management measures for such patients.

Augmented Decision-Making in wound Care: Evaluating the clinical utility of a Deep-Learning model for pressure injury staging

BackgroundPrecise categorization of pressure injury (PI) stages is critical in determining the appropriate treatment for wound care. However, the expertise necessary for PI staging is frequently unavailable in residential care settings. ObjectiveThis study aimed to develop a convolutional neural network (CNN) model for classifying PIs and investigate whether its implementation can allow physicians to make better decisions for PI staging. MethodsUsing 3,098 clinical images (2,614 and 484 from internal and external datasets, respectively), a CNN was trained and validated to classify PIs and other related dermatoses. A two-part survey was conducted with 24 dermatology residents, ward nurses, and medical students to determine whether the implementation of the CNN improved initial PI classification decisions. ResultsThe top-1 accuracy of the model was 0.793 (95% confidence interval [CI], 0.778–0.808) and 0.717 (95% CI, 0.676–0.758) over the internal and external testing sets, respectively. The accuracy of PI staging among participants was 0.501 (95% CI, 0.487–0.515) in Part I, improving by 17.1% to 0.672 (95% CI, 0.660–0.684) in Part II. Furthermore, the concordance between participants increased significantly with the use of the CNN model, with Fleiss’ κ of 0.414 (95% CI, 0.410–0.417) and 0.641 (95% CI, 0.638–0.644) in Parts I and II, respectively. ConclusionsThe proposed CNN model can help classify PIs and relevant dermatoses. In addition, augmented decision-making can improve consultation accuracy while ensuring concordance between the clinical decisions made by a diverse group of health professionals.

Current Perspectives on Pressure Injuries in Persons with Dark Skin Tones from the National Pressure Injury Advisory Panel.

Pressure injury (PI) development is multifactorial. In patients with dark skin tones, identifying impending PIs by visual skin assessment can be especially challenging. The need for improved skin assessment techniques, especially for persons with dark skin tones, continues to increase. Similarly, greater awareness of the need for inclusivity with regard to representation of diverse skin colors/tones in education materials is apparent. To provide current perspectives from the literature surrounding skin assessment and PI development in patients with dark skin tones. The following elements will be discussed through the lens of skin tone: (1) historical perspectives of PI staging from the National Pressure Injury Advisory Panel, (2) epidemiology of PI, (3) anatomy and physiology of the skin, (3) skin tone assessment and measurement, (4) augmented visual assessment modalities, (5) PI prevention, (6) PI healing, (7) social determinants of health, and (8) gaps in clinician education. This article highlights the gap in our clinical knowledge regarding PIs in patients with dark skin tones. Racial disparities with regard to PI development and healing are especially clear among patients with dark skin tones. Skin tone color assessment must be standardized and quantifiable in clinical education, practice, and research. This work is urgently needed, and support from private and governmental agencies is essential.

Incidence of medical device-related pressure injuries in the intensive care unit and related risk factors

AimAt present, physicians employ medical devices extensively in the treatment of numerous diseases and in the care and follow-up of patients. However, these medical devices are a potential cause of pressure injuries.The study aimed to investigate the incidence and affecting risk factors of medical device-related pressure injuries (MDRPIs) in an adult intensive care unit. Materials and methodsThis is a longitudinal descriptive/analytical and cross-sectional study. The researchers conducted this study with 213 intensive care patients between 15.06.2021 and 15.12.2021. The skin and mucosa under and around each medical device were observed once a day for MDRPIs during the stay of patients who had been hospitalized in the intensive care unit for at least 24 h. The data were collected using Patient Information Form developed by the researchers based on the literature, Medical Device-Related Pressure Injury Monitoring Form, the Jackson/Cubbin Pressure Area Risk Calculator (Jackson/Cubbin BARHATr)-Turkish Version, the National Pressure Injury Advisory Panel (NPIAP) Pressure Injury Staging System and the Glasgow Coma Scale. ResultsThe incidence of MDRPIs was 28.6% (61/213). The study revealed that 48.4% (46/95) of these injuries were caused by medical devices for respiratory system, 26.3% (25/95) by devices for gastrointestinal and genitourinary system. The study also revealed that 70.5% of MDRPIs occurred on the skin and 29.5% on the mucosal membrane, and that 82.1% of the MDRPIs occurring on the skin were at Stage 1. In terms of anatomical location, 21.1% of these injuries developed on the fingers and 13.7% on the mouth/lip. In multivariate analysis, parenteral + enteral (p = 0.006, OR = 0.083, 95%CI = [0.014–0.497]) and oral nutrition (p = 0.037, OR = 0.210, 95%CI = [0.049–0.908]), a higher number of devices (nine or more) (p = 0.002, OR = 5.387, 95%CI = [1.840–15.772]) and the duration of device wear (p < 0.05) were identified as independent risk factors for the occurrence of MDRPIs. ConclusionsThe study showed that the incidence of MDRPIs was relatively high and was associated with various factors. It is critical for intensive care nurses, who encounter MDRPIs more frequently, to consider these factors while caring for their patients and to take appropriate preventive measures to reduce the incidence of these injuries.

Wagner Grading of Diabetic Foot Ulcers and National Pressure Injury Advisory Panel Staging of Pressure Injuries: A Comparison for Clinical Use

Wagner Grading of Diabetic Foot Ulcers and National Pressure Injury Advisory Panel Staging of Pressure Injuries: A Comparison for Clinical Use

Factors influencing the severity of medical device-related pressure injuries: Pressure injury staging comparison.

Medical device-related pressure injuries are receiving increased attention because their social and economic costs are increasing. This study aimed to analyse the stages for each risk factor, and to assess which has a greater impact on severity. We performed a retrospective analysis of 237 patients. Severity was evaluated by pressure injury stages, and the following categories were considered as risk factors: perceptual functioning, malnutrition, reduced mobility, comorbidities, extrinsic factors, medical devices, anatomical areas, and hospital stay. The stages of pressure injury stages were more for vascular access devices than for respiratory devices. The following were related to severity: mental deterioration-related diseases, mental status, albumin level, haemoglobin level, total cholesterol level, intensive care unit care, days of hospitalisation, and time to develop pressure injuries after admission. Decreased mental status, anaemia, hypoalbuminemia, and low total cholesterol levels were particularly critical. However, factors such as anatomical areas, age, malignancy, diabetes mellitus, diseases related to malnutrition, abnormal body mass index, immobility-related diseases, physical restraints, and Braden scale scores were not. A different approach to the management of medical device-related pressure injuries is necessary because they have distinctive characteristics and causative factors than other pressure injury types.

Effect of a Team Approach to Pressure Injury Management over 5 Years in a Tertiary Hospital.

The authors' facility established a novel integrated wound care team (IWCT), which included the implementation of a strict treatment algorithm by the patients' attending providers and a specialized wound care team led by a plastic surgeon. Investigators then retrospectively analyzed clinical outcomes of pressure injury (PI) management by the IWCT over 5 years. The authors performed a retrospective chart review and periodic statistical analysis of the data for all patients with PI referred to the IWCT in the authors' center from May 2015 to April 2019. Data including patients' demographic information, first and last consultation dates, referring department, PI stage, site of PI, and Braden Scale scores were collected and analyzed. Patients (N = 15,556) did not differ significantly in age, sex, or Braden Scale score. A preimplementation/postimplementation analysis of PI data before and after establishing the IWCT showed that the incidence of stage 3 or 4 PIs had significantly decreased during the study period (19.1% vs 15.2%, P < .05). Conversely, the incidence of stage 1 PIs significantly increased in the same period (38.0% vs 57.4%, P < .05). The proportion of completely healed PIs also increased, and the median treatment period was significantly shortened (P < .05). Implementation of the IWCT in a tertiary hospital setting led to a significant increase in early-stage PI detection and a decrease in severe PIs.

Simultaneous Segmentation and Classification of Pressure Injury Image Data Using Mask-R-CNN.

Pressure injuries (PIs) impose a substantial burden on patients, caregivers, and healthcare systems, affecting an estimated 3 million Americans and costing nearly $18 billion annually. Accurate pressure injury staging remains clinically challenging. Over the last decade, object detection and semantic segmentation have evolved quickly with new methods invented and new application areas emerging. Simultaneous object detection and segmentation paved the way to segment and classify anatomical structures. In this study, we utilize the Mask-R-CNN algorithm for segmentation and classification of stage 1-4 pressure injuries. Images from the eKare Inc. pressure injury wound data repository were segmented and classified manually by two study authors with medical training. The Mask-R-CNN model was implemented using the Keras deep learning and TensorFlow libraries with Python. We split 969 pressure injury images into training (87.5%) and validation (12.5%) subsets for Mask-R-CNN training. We included 121 random pressure injury images in our test set. The Mask-R-CNN model showed overall classification accuracy of 92.6%, and the segmentation demonstrated 93.0% accuracy. Our F1 scores for stages 1-4 were 0.842, 0.947, 0.907, and 0.944, respectively. Our Dice coefficients for stages 1-4 were 0.92, 0.85, 0.93, and 0.91, respectively. Our Mask-R-CNN model provides levels of accuracy considerably greater than the average healthcare professional who works with pressure injury patients. This tool can be easily incorporated into the clinician's workflow to aid in the hospital setting.