Automated measurement of pressure injury through image processing

Application of deep learning to pressure injury staging

OBJECTIVE

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.

METHOD

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.

RESULTS

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.

CONCLUSION

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.

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).

Wound tissue segmentation by computerised image analysis of clinical pressure injury photographs: a pilot study

OBJECTIVE

Wound tissues can provide ample information about the wound development and healing process. However, the manual identification and measurement of wound tissue types is time-consuming and challenging due to the complexities of pressure injuries (PI). This study aims to develop an image analysis algorithm to automatically identify and differentiate wound tissue types from PI wound beds.

METHOD

This was a cross-sectional algorithm development study. PI photographs were obtained from a western Pennsylvania hospital. We used our previously developed wound bed segmentation tool to identify PI wound beds. We then used the k-means clustering method to classify the subzones on the wound beds. Finally, the support vector machine classifier was used to identify the classified subzones to certain types of wound tissue.

RESULTS

An image analysis algorithm was developed, using 64 selected PI photographs, to automatically identify different wound tissues for PIs.

CONCLUSION

Validation of the wound tissue identification of the PIs by image analysis algorithm demonstrated that our image analysis algorithm is a reliable and objective approach to monitoring wound healing progress through clinical PI photographs, and offers new insight into PI evaluation and documentation.

DECLARATION OF INTEREST

The authors have no conflicts of interest to declare.

Reshaping wound care: Evaluation of an artificial intelligence app to improve wound assessment and management amid the COVID-19 pandemic

Wound documentation is integral to effective wound care, health data coding and facilitating continuity of care. This study evaluated the usability and effectiveness of an artificial intelligence application for wound assessment and management from a clinician‐and‐patient user perspective. A quasi‐experimental design was conducted in four settings in an Australian health service. Data were collected from patients in the standard group (n = 166, 243 wounds) and intervention group (n = 124, 184 wounds), at baseline and post‐intervention. Clinicians participated in a survey (n = 10) and focus group interviews (n = 13) and patients were interviewed (n = 4). Wound documentation data were analysed descriptively, and bivariate statistics were used to determine between‐group differences. Thematic analysis of interviews was conducted. Compared with the standard group, wound documentation in the intervention group improved significantly (more than two items documented 24% vs 70%, P < .001). During the intervention, 101 out of 132 wounds improved (mean wound size reduction = 53.99%). Positive evaluations identified improvements such as instantaneous objective wound assessment, shared wound plans, increased patient adherence and enhanced efficiency in providing virtual care. The use of the application facilitated remote patient monitoring and reduced patient travel time while maintaining optimal wound care.

Deep learning approach based on superpixel segmentation assisted labeling for automatic pressure ulcer diagnosis

A pressure ulcer is an injury of the skin and underlying tissues adjacent to a bony eminence. Patients who suffer from this disease may have difficulty accessing medical care. Recently, the COVID-19 pandemic has exacerbated this situation. Automatic diagnosis based on machine learning (ML) brings promising solutions. Traditional ML requires complicated preprocessing steps for feature extraction. Its clinical applications are thus limited to particular datasets. Deep learning (DL), which extracts features from convolution layers, can embrace larger datasets that might be deliberately excluded in traditional algorithms. However, DL requires large sets of domain specific labeled data for training. Labeling various tissues of pressure ulcers is a challenge even for experienced plastic surgeons. We propose a superpixel-assisted, region-based method of labeling images for tissue classification. The boundary-based method is applied to create a dataset for wound and re-epithelialization (re-ep) segmentation. Five popular DL models (U-Net, DeeplabV3, PsPNet, FPN, and Mask R-CNN) with encoder (ResNet-101) were trained on the two datasets. A total of 2836 images of pressure ulcers were labeled for tissue classification, while 2893 images were labeled for wound and re-ep segmentation. All five models had satisfactory results. DeeplabV3 had the best performance on both tasks with a precision of 0.9915, recall of 0.9915 and accuracy of 0.9957 on the tissue classification; and a precision of 0.9888, recall of 0.9887 and accuracy of 0.9925 on the wound and re-ep segmentation task. Combining segmentation results with clinical data, our algorithm can detect the signs of wound healing, monitor the progress of healing, estimate the wound size, and suggest the need for surgical debridement.

Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review

Background

Artificial intelligence (AI) holds the promise of supporting nurses’ clinical decision-making in complex care situations or conducting tasks that are remote from direct patient interaction, such as documentation processes. There has been an increase in the research and development of AI applications for nursing care, but there is a persistent lack of an extensive overview covering the evidence base for promising application scenarios.

Objective

This study synthesizes literature on application scenarios for AI in nursing care settings as well as highlights adjacent aspects in the ethical, legal, and social discourse surrounding the application of AI in nursing care.

Methods

Following a rapid review design, PubMed, CINAHL, Association for Computing Machinery Digital Library, Institute of Electrical and Electronics Engineers Xplore, Digital Bibliography & Library Project, and Association for Information Systems Library, as well as the libraries of leading AI conferences, were searched in June 2020. Publications of original quantitative and qualitative research, systematic reviews, discussion papers, and essays on the ethical, legal, and social implications published in English were included. Eligible studies were analyzed on the basis of predetermined selection criteria.

Results

The titles and abstracts of 7016 publications and 704 full texts were screened, and 292 publications were included. Hospitals were the most prominent study setting, followed by independent living at home; fewer application scenarios were identified for nursing homes or home care. Most studies used machine learning algorithms, whereas expert or hybrid systems were entailed in less than every 10th publication. The application context of focusing on image and signal processing with tracking, monitoring, or the classification of activity and health followed by care coordination and communication, as well as fall detection, was the main purpose of AI applications. Few studies have reported the effects of AI applications on clinical or organizational outcomes, lacking particularly in data gathered outside laboratory conditions. In addition to technological requirements, the reporting and inclusion of certain requirements capture more overarching topics, such as data privacy, safety, and technology acceptance. Ethical, legal, and social implications reflect the discourse on technology use in health care but have mostly not been discussed in meaningful and potentially encompassing detail.

Conclusions

The results highlight the potential for the application of AI systems in different nursing care settings. Considering the lack of findings on the effectiveness and application of AI systems in real-world scenarios, future research should reflect on a more nursing care–specific perspective toward objectives, outcomes, and benefits. We identify that, crucially, an advancement in technological-societal discourse that surrounds the ethical and legal implications of AI applications in nursing care is a necessary next step. Further, we outline the need for greater participation among all of the stakeholders involved.

Using Machine Learning Technologies in Pressure Injury Management: Systematic Review

Background

Pressure injury (PI) is a common and preventable problem, yet it is a challenge for at least two reasons. First, the nurse shortage is a worldwide phenomenon. Second, the majority of nurses have insufficient PI-related knowledge. Machine learning (ML) technologies can contribute to lessening the burden on medical staff by improving the prognosis and diagnostic accuracy of PI. To the best of our knowledge, there is no existing systematic review that evaluates how the current ML technologies are being used in PI management.

Objective

The objective of this review was to synthesize and evaluate the literature regarding the use of ML technologies in PI management, and identify their strengths and weaknesses, as well as to identify improvement opportunities for future research and practice.

Methods

We conducted an extensive search on PubMed, EMBASE, Web of Science, Cumulative Index to Nursing and Allied Health Literature (CINAHL), Cochrane Library, China National Knowledge Infrastructure (CNKI), the Wanfang database, the VIP database, and the China Biomedical Literature Database (CBM) to identify relevant articles. Searches were performed in June 2020. Two independent investigators conducted study selection, data extraction, and quality appraisal. Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST).

Results

A total of 32 articles met the inclusion criteria. Twelve of those articles (38%) reported using ML technologies to develop predictive models to identify risk factors, 11 (34%) reported using them in posture detection and recognition, and 9 (28%) reported using them in image analysis for tissue classification and measurement of PI wounds. These articles presented various algorithms and measured outcomes. The overall risk of bias was judged as high.

Conclusions

There is an array of emerging ML technologies being used in PI management, and their results in the laboratory show great promise. Future research should apply these technologies on a large scale with clinical data to further verify and improve their effectiveness, as well as to improve the methodological quality.

The characteristics of pressure injury photographs from the electronic health record in clinical settings

AIMS AND OBJECTIVES

To analyse and understand the characteristics of pressure injury images stored in the electronic health record.

BACKGROUND

To improve the quality of pressure injury documentation, photographing pressure injuries and storing the images in the electronic health record are standard practices in many hospitals. As new technologies develop, the utilisation of computer-assisted image processing makes automatic measurement of pressure injury size and tissue segmentation through pressure injury images possible. The translation of new technological developments to pressure injury photography conducted in clinical environments faces obstacles such as the complexity of conditions in which photographs are taken.

DESIGN

A cross-sectional descriptive study.

METHODS

A set of 360 pressure injury images were obtained from a hospital in western Pennsylvania. These images were taken in clinical settings during daily wound care service. The authors reviewed the pressure injury images to analyse the relative position of the pressure injury in the images, the shooting angle of the digital camera and the clinical objects in the background.

RESULTS

Only 5.9% of the pressure injury images were confined to only the wound region. In 80.1% of the images, the pressure injury is located in the central part of the image. In 54.0% of the images, the lens of the digital camera was not pointed perpendicularly to the plane of the pressure injury.

CONCLUSIONS

Bedside wound assessment of pressure injuries and assessment from photographs of pressure injuries display reasonable agreement with pressure injury staging. To extract wound information (e.g., size and tissue type) from pressure injury images through novel image processing technologies, the characteristics of pressure injury images in clinical settings should be better understood during the development of tools for pressure injury image processing.

RELEVANCE TO CLINICAL PRACTICE

Our results can help image processing experts understand wound photography characteristics to shorten the gap between laboratory and clinical environments when translating new image processing technologies.