The impact of machine learning on the prediction of diabetic foot ulcers - A systematic review.

INTRODUCTION: Globally, diabetes mellitus poses a significant health challenge as well as the associated complications of diabetes, such as diabetic foot ulcers (DFUs). The early detection of DFUs is important in the healing process and machine learning may be able to help inform clinical staff during the treatment process. METHODS: A PRISMA-informed search of the literature was completed via the Cochrane Library and MEDLINE (OVID), EMBASE, CINAHL Plus and Scopus databases for reports published in English and in the last ten years. The primary outcome of interest was the impact of machine learning on the prediction of DFUs. The secondary outcome was the statistical performance measures reported. Data were extracted using a predesigned data extraction tool. Quality appraisal was undertaken using the evidence-based librarianship critical appraisal tool. RESULTS: A total of 18 reports met the inclusion criteria. Nine reports proposed models to identify two classes, either healthy skin or a DFU. Nine reports proposed models to predict the progress of DFUs, for example, classing infection versus non-infection, or using wound characteristics to predict healing. A variety of machine learning techniques were proposed. Where reported, sensitivity = 74.53-98 %, accuracy = 64.6-99.32 %, precision = 62.9-99 %, and the F-measure = 52.05-99.0 %. CONCLUSIONS: A variety of machine learning models were suggested to successfully classify DFUs from healthy skin, or to inform the prediction of DFUs. The proposed machine learning models may have the potential to inform the clinical practice of managing DFUs and may help to improve outcomes for individuals with DFUs. Future research may benefit from the development of a standard device and algorithm that detects, diagnoses and predicts the progress of DFUs.

Twelve tips for developing and implementing an effective critical care simulation programme.

Simulation training in healthcare settings has become a valuable training tool. It provides an ideal formative assessment for interdisciplinary teaching. It provides a high fidelity and highly immersive environment where healthcare staff and students can practice developing their skills in a safe and controlled manner. Simulation training allows staff to practice skills that better prepare them for clinical emergencies, therefore possibly optimising clinical care. While the benefits of simulation education are well understood, establishing a programme for use by critical care staff is complex. Complexities include the highly specialised scenarios that are not typically encountered in non-critical care areas, as well as the need for advanced monitoring equipment, ventilation equipment etc. These 12 tips are intended to assist healthcare educators in navigating the complexities in the establishment of a critical care simulation programme, providing advice on selecting target audiences, learning outcomes, creating a critical care simulation environment and recommendations on evaluation and development of the programme.

Pressure ulcer risk assessment in the ICU. Is it time for a more objective measure?

BACKGROUND: The Braden scale, one of the most widely used risk assessment tools is often criticized when used in the Intensive Care Unit. Most patients in the Intensive Care Unit are at risk of pressure ulcer development meaning that the Braden score will usually indicate high risk for these patients. This study set out to determine the correlation between Sub-Epidermal Moisture measurements and Braden scores among Intensive Care Unit patients. METHODS: This study employed an observational research design. Braden score was assessed on all study days (1-5), in addition to visual skin assessment and Sub-Epidermal Moisture measurements at the sacrum and heels. Sub-Epidermal Moisture measurements were categorised as low (<0.5), borderline abnormal (≥0.5), and high (≥0.8). Correlation was assessed between Sub-Epidermal Moisture levels and Braden scores. RESULTS: A total of 53 participants were recruited. The median (interquartile range) baseline Braden score was 9 (9-10) and 81 % (n = 43) of participants were at very high/high risk of pressure ulcer development. Braden scores remained relatively constant over time with little fluctuation in scores. 19 % (n = 10) of patients had normal (<0.5) Sub-Epidermal Moisture delta measurements on enrolment, and all developed abnormal measurements by day 2. There were no significant correlations between Braden scores and Sub-Epidermal Moisture measurements. CONCLUSION: Although this was not its original intention, a missing link with the Braden scale is that it does not provide information on how patients are responding to the adverse effects of pressure and shear forces. Furthermore, in patients who are critically unwell, most patients are classified as being "at risk" of pressure ulcer development. Therefore, an objective measure of how patients are responding to pressure and shear forces at different anatomical areas is needed. IMPLICATIONS TO CLINICAL PRACTICE: Sub-Epidermal Moisture measurements can offer more information, not only on identifying those who are at risk, but also how those patients are tolerating this risk at different anatomical sites.

Ethical considerations for the nursing care of Transgender patients in the Intensive Care Unit.

There is more discussion than ever surrounding the health and care needs of Transgender communities. However, there is limited research on the care of Transgender patients in the Intensive Care Unit which can contribute to knowledge gaps, inconsistencies and uncertainties surrounding health care practices. This article is not intended to address all of the specific needs of Transgender patients in ICU, but to explore the ethical considerations for caring for a Transgender woman in the ICU. In doing so, this article will explore some specific considerations around gender affirming care, challenging discrimination, physiological changes, and systems change to enhance care.

The impact of brain tissue oxygenation monitoring on the Glasgow Outcome Scale/Glasgow Outcome Scale Extended in patients with moderate to severe traumatic brain injury: A systematic review.

BACKGROUND: Traumatic brain injuries (TBIs) are one of the leading causes of death or long-term disability around the world. As a result of improvements in supportive care, patients are surviving more severe insults with more pronounced dependency on their families, hospitals, and long-term care facilities. The introduction of brain tissue oxygenation (PbtO2) monitoring aims to recognize episodes of reduced cerebral perfusion with and without associated increased intracranial pressure (ICP). AIM: The aim of this review is to determine the impact of PbtO2 on the Glasgow Outcome Scale/Glasgow Outcome Scale Extended (GOS/GOSE) in patients with moderate to severe TBI. DESIGN: Systematic review with narrative and meta-analysis. All original research in which adult patients undergoing PbtO2 were compared with a control group of traditional ICP/cerebral perfusion pressure (CPP) monitoring. Both randomized controlled trials and observational studies were included in this review. METHODS: Databases were searched in September 2022. The primary outcome of the review was the impact of PbtO2 monitoring on GOS/GOSE, while secondary outcomes were mortality and length of stay (LOS) in the intensive care unit (ICU). RESULTS: Seven studies with a combined number of 770 patients were included in the review. These patients were adults ≥16 years of age. Only two of the studies included found a statistically significant association between PbtO2 monitoring and improved long-term neurological outcomes in patients with TBI (p = .01, p < .01). A meta-analysis of the secondary outcomes identified an associated reduction of mortality in favour of the group treated with PbtO2 monitoring (p < .0001). Results from studies examining LOS in ICU have demonstrated an associated increase of LOS in ICU in patients treated with PbtO2-guided therapy. CONCLUSION: From the studies included in this review, only two found a statistically significant association between PbtO2 monitoring and long-term outcomes. It is unclear whether PbtO2 goal-directed therapy has a positive impact on the long-term neurological functions and mortality of patients suffering from TBI. A multicentre randomized controlled trial may provide further evidence, but not necessarily conclusive. RELEVANCE TO CLINICAL PRACTICE: Further research is warranted to determine the efficacy of the introduction of this new monitoring system to guide local policy change.

The role of proinflammatory cytokines in the detection of early pressure ulcer development: a systematic review.

OBJECTIVE: Pressure ulcers (PUs) commonly occur over bony prominences and are notoriously difficult to treat. Proinflammatory cytokines are substances that initiate the inflammatory process preceding PU development. The aim of this review was to assess whether the increased presence of proinflammatory cytokines could potentially be used as an early detection system for PU development. METHOD: A systematic search of publications using MEDLINE, CINAHL, and Cochrane databases was conducted in August 2020. Data were extracted and a narrative synthesis was undertaken. The evidence-based librarianship (EBL) checklist assessed the methodological quality of the included studies. The systematic review included original research studies, prospective design, and human studies written in English. Retrospective studies, animal studies, conference papers, opinion papers and qualitative methodology were excluded. No restrictions on the date of publication and study setting were applied. RESULTS: The six studies included were conducted between 2015 and 2019, 50% (n=3) used an experimental study design. The mean sample size was 15 participants (standard deviation=1.72). A total of seven proinflammatory cytokines were analysed. Statistically significant differences were found among inflammatory mediators. Overall results showed that the concentration of interleukin (IL)-1α significantly increased in each study. The EBL score varied between 77-88%. In total, 100% (n=6) of the studies scored ≥75%, reflecting validity. CONCLUSION: It is not yet certain that monitoring proinflammatory cytokines represents a noninvasive method that could potentially direct preventative measures to those who are identified as at high risk for developing PUs. IL-1α potentially may be elevated for other health conditions, not just PUs. Future studies are therefore recommended.

Pressure ulcers in patients with COVID-19 acute respiratory distress syndrome undergoing prone positioning in the intensive care unit: A pre- and post-intervention study.

BACKGROUND: Prone positioning has been widely used to improve oxygenation and reduce ventilator-induced lung injury in patients with severe COVID-19 acute respiratory distress syndrome (ARDS). One major complication associated with prone positioning is the development of pressure ulcers (PUs). AIM: This study aimed to determine the impact of a prevention care bundle on the incidence of PUs in patients with COVID-19 ARDS undergoing prone positioning in the intensive care unit. STUDY DESIGN: This was a single-centre pre and post-test intervention study which adheres to the Standards for Reporting Implementation Studies (StaRI) guidelines. The intervention included a care bundle addressing the following: increasing frequency of head turns, use of an open gel head ring, application of prophylactic dressings to bony prominences, use of a pressure redistribution air mattress, education of staff in the early identification of evolving PUs through regular and rigorous skin inspection and engaging in bedside training sessions with nursing and medical staff. The primary outcome of interest was the incidence of PU development. The secondary outcomes of interest were severity of PU development and the anatomical location of the PUs. RESULTS: In the pre-intervention study, 20 patients were included and 80% (n = 16) of these patients developed PUs, comprising 34 ulcers in total. In the post-intervention study, a further 20 patients were included and 60% (n = 12) of these patients developed PUs, comprising 32 ulcers in total. This marks a 25% reduction in the number of patients developing a PU, and a 6% decrease in the total number of PUs observed. Grade II PUs were the most prevalent in both study groups (65%, n = 22; 88%, n = 28, respectively). In the post-intervention study, there was a reduction in the incidence of grade III and deep tissue injuries (pre-intervention 6%, n = 2 grade III, 6% n = 2 deep tissue injuries; post-intervention no grade III ulcers, grade IV ulcers, or deep tissues injuries were recorded). However, there was an increase in the number of unstageable PUs in the post-intervention group with 6% (n = 2) of PUs being classified as unstageable, meanwhile there were no unstageable PUs in the pre-intervention group. This is an important finding to consider as unstageable PUs can indicate deep tissue damage and therefore need to be considered alongside PUs of a more severe grade (grade III, grade IV, and deep tissue injuries). CONCLUSION: The use of a new evidence-based care bundle for the prevention of PUs in the management of patients in the prone position has the potential to reduce the incidence of PU development. Although improvements were observed following alterations to standard practice, further research is needed to validate these findings. RELEVANCE TO CLINICAL PRACTICE: The use of a new, evidence-based care bundle in the management of patients in the prone position has the potential to reduce the incidence of PUs.

Biomarkers for the early detection of pressure ulcers in the intensive care setting: A comparison between sub-epidermal moisture measurements and interleukin-1α.

Pressure ulcer (PU) prevention in the intensive care unit (ICU) is an important clinical issue as critically unwell patients are at high risk of developing PUs. However, current methods of PU detection are limited, especially for early detection. This study aimed to establish the correlation between Interleukin-1α (IL-1α)/total protein (TP) and sub-epidermal moisture (SEM) measurements in the early identification of PUs in ICU patients. This study employed an observational research design using the STROBE guidelines. Following ethical approval, 53 participants were recruited and sebum was obtained using Sebutape from weight-bearing areas (sacrum, heels and a control site). SEM measurements were taken from the same anatomical sites. Both measures were taken at the same time and participants were followed up for 5 days, or until discharge or death. Correlations between SEM delta measurements, IL-1α, TP and PU incidence and other demographic information were explored using Spearman's correlation for data not normally distributed, and Pearson's R correlation coefficient for normally distributed data. Mean baseline SEM delta measurements indicate abnormal readings for all anatomical sites except the control site, consistent with previous studies. Mean baseline IL-1α/TP readings were higher for the sacrum versus both heels and, on average, readings were higher for the control site versus all other anatomical locations. This is conflicting, given that the control site was non-weight bearing. There were very weak or weak correlations between SEM delta measurements and IL-1α/TP readings. SEM measurements are quick and easy to obtain and results are instant, however Sebutape sampling takes significantly longer and is challenging to conduct among haemodynamically unstable patients. Obtaining SEM measurements is more practical and feasible than Sebutape sampling to assess for the presence of inflammation.

Use of a novel "Split" ventilation system in bench and porcine modeling of acute respiratory distress syndrome.

Split ventilation (using a single ventilator to ventilate multiple patients) is technically feasible. However, connecting two patients with acute respiratory distress syndrome (ARDS) and differing lung mechanics to a single ventilator is concerning. This study aimed to: (1) determine functionality of a split ventilation system in benchtop tests, (2) determine whether standard ventilation would be superior to split ventilation in a porcine model of ARDS and (3) assess usability of a split ventilation system with minimal specific training. The functionality of a split ventilation system was assessed using test lungs. The usability of the system was assessed in simulated clinical scenarios. The feasibility of the system to provide modified lung protective ventilation was assessed in a porcine model of ARDS (n = 30). In bench testing a split ventilation system independently ventilated two test lungs under conditions of varying compliance and resistance. In usability tests, a high proportion of naïve operators could assemble and use the system. In the porcine model, modified lung protective ventilation was feasible with split ventilation and produced similar respiratory mechanics, gas exchange and biomarkers of lung injury when compared to standard ventilation. Split ventilation can provide some elements of lung protective ventilation and is feasible in bench testing and an in vivo model of ARDS.

Measuring subepidermal moisture to detect early pressure ulcer development: a systematic review.

OBJECTIVE: The aim was to assess evidence related to the measuring of subepidermal moisture (SEM) to detect early, nonvisible development of pressure ulcers (PUs). METHOD: Using systematic review methodology, all quantitative animal and human research studies written in English were considered. In January 2021, PubMed, CINAHL, SCOPUS, Cochrane and EMBASE databases were searched. The primary outcome of interest was the validity of SEM measurement to detect early PU development. The secondary outcome was time to PU detection, sensitivity and specificity of SEM measurement, and the impact of SEM measurements on PU prevention. Data analysis was undertaken using RevMan and narrative synthesis. RESULTS: A total of 17 articles met the inclusion criteria. In all studies, a consistent abnormal deviation in SEM measurements corresponded with evidence of visual PU development. Time to PU development, explored in four studies, showed earlier detection of PU development using SEM measurement. RevMan analysis identified the mean difference in time to PU development (SEM measurement versus visual skin assessment, VSA) was 4.61 days (95% confidence interval: 3.94-5.28; p=0.0001) in favour of SEM measurements. The sensitivity of SEM measurements was reported in four studies, and scores varied from 48.3% to 100.0%. Specificity was also reported in four studies and scores ranged from 24.4% to 83.0%. The impact of the detection of abnormal SEM measurements on PU prevention was explored by one study. Results showed a 93% decrease in PU rates when staff acted on the results of the SEM readings. CONCLUSION: The findings of this review identified that SEM measurement detects PU development earlier than VSA. Furthermore, when staff responded to abnormal SEM measurements, prevention strategies were enhanced, with a subsequent reduction in visible PU development. SEM measurement may therefore be a useful addition to PU prevention strategies. DECLARATION OF INTEREST: The School of Nursing & Midwifery, RCSI has a research agreement with Bruin Biometrics. Funding for the study was through an Irish Research Council PhD Enterprise Partnership Scheme with Bruin Biometrics. The authors have no other conflicts of interest.