Introduction
Wound treatment is a critical component of the healthcare system. Consequently, innovative ways to predict, prevent, and find more personalised medicine are essential to modern healthcare systems. This literature review analyses how Artificial Intelligence (AI) contributes to effectively assessing wounds and their management. Allmayer (2022) highlights that in the US, $25 billion is spent yearly on treating chronic wounds for almost six million patients. Treatments are largely personalised and emanate from suboptimal health conditions and severe illnesses, such as diabetes. Nevertheless, chronic wounds are influenced by risk factors that cannot be predicted. Thus, personalised treatment and prevention are critical for a successful wound-healing process (Allmayer, 2022). This situation is highly time-consuming, and there is always a lack of a qualified wound expert to handle such issues. In today’s world of increased digitalisation, it is clear that digital tools and processes support wound management and documentation.
Such digital tools include Artificial Intelligence, which might be effective when it comes to the management of chronic wounds. For personal and time-consuming wound care, practitioners use systems medicine, preventive processes, predictive mechanisms, and treatments designed for that individual. To optimise such a systematic approach, AI provides an opportunity to change the healthcare systems and reshape them globally. Allmayer (2022) argues that the significant contributions in biomedical data analysis with AI only affirm that using AI to get predictions in the healthcare practice will enhance patient assistance and care in the coming years. With the evolution of technology and its resources, AI is now being used to guarantee better evaluation and diagnosis of patients using medical imaging. Similarly, Guler et al. (2019) opine that the increasing computational power and AI algorithms that are clinically significant are driving continuous improvements and development. For instance, mental computers can scan billions of unstructured data and obtain relevant information while identifying sophisticated patterns and relationships.
The Need for Effective Wound Care Solutions
While conducting a diagnostic study across two independent wound centres, Howell et al. (2021) affirm that chronic wounds result in many cases of morbidity and mortality, and in the US, they cost the healthcare system around $25 billion each year. In a study by Frosy and Sullivan (2021), the findings indicate that the wound care sector is investing highly in interventions and technologies that need little or no medical action, as well as those that can be utilised by patients, caregivers, and family members. Majorly added by advanced and basic wound care interventions, international wound care is projected to make $30.5 billion in terms of income by 2026, up from $20 billion in 2020, an annual growth rate of 6.7% (Frost & Sullivan, 2021).
With technological advances and a wide range of conventional and modern wound care interventions, such as apps, software, devices, wearables, and services, North America is expected to control the wound market by 2026 (Frost & Sullivan, 2021). Moreover, the European wound care market will also experience constant expansion as it becomes flooded due to advances. Frost and Sullivan (2021) note that Asia-Pacific will experience an optimum growth rate as nations in the region embrace wound care interventions quickly. In the same case, increased demand for quicker and more effective wound healing and advanced wound dressing in Latin America and the Middle East will boost the wound care interventions market in other parts of the globe with time.
The need for quicker, less-invasive wound recovery is increasing the necessity of the advanced wound care interventions (Berthet et al., 2017). In line with what Berthet et al. (2017) call a “migration” to advanced healthcare, Barakat-Johnson et al. (2022) indicate that the resumption of postponed surgeries that were postponed during the COVID-19 outbreak further increased the post-pandemic need for surgical wound interventions. Moreover, as final-users growing switch to “at-home” interventions, easy and reliable wound-tracking gadgets and interventions requiring less clinician engagement are becoming popular (Frost & Sullivan, 2021). Moreover, AI-enabled interventions, sensor-based gadgets or wearables, and wound evaluation gadgets help caregivers with medical decision advice for quicker evaluation of sophisticated or chronic wounds (Barakat-Johnson et al., 2022), resulting in effective care procedures. State and corporation financing for designing next-generation wound care interventions that mainly allow for timely wound detection and intervention is set to rise, providing an opportunity for AI-supported wound care interventions for quicker and more precise diagnosis.
Value of AI Wound Care Solutions
Net Health, one of the leading providers of software and analytics for medical care, presented a copy of their research reviewing the application of AI-based mobile wound care apps designed by the organisation. The study indicated that the apps offered effective documentation, were easy to utilise, engaged patients, and drove enhancements in wound measurements and care (Net Health, 2022). Undertaken by New South Wales Health sector, the research evaluated the effectiveness of the organisation’s Tissue Analytics’ wound photos and analysis in various areas, including a care ward and a primary care facility. Other than highlighting the apps’ value in clinical setup, the study’s results offer critical insight for scholars seeking to undertake decentralised and hybrid clinical tests about visible skin conditions, skin lesions, and wounds in the post-pandemic era.
The e-clinical approach was tried on 124 participants with 184 injuries against a standard category of 166 people with 243 injuries (Net Health, 2022). The findings indicated various statistically meaningful results linked to these apps, such as the effectiveness of documentation using the amount of dressing changes compared to the standard group, pain, measurements, and odour as criteria. This study’s findings show the apps’ positive effects on usability, patient adherence, and proof of clinical endpoints. Notably, these results match what was found by Ohura et al. (2019), who found that in e-health practice, the use of convolutional neural networks that are constructed using highly supervised data would give segmentation with high accuracy. The study concluded that such an application of AI in eHealth wound assessment would be practical in the future.
In the Net Health (2022) study, 10 out of 13 involved clinicians and nurses answered a questionnaire and strongly agreed that the AI-based apps were valuable and advantageous to communication. The interviewed patients broadly noted that the apps offered benefits to their wound recovery and communication with specialists. Net Health (2022) posits that other than showing value for mobile wound analysis in clinical setups, the results of the study will also increase the attention to Tissue Analytics for wound and skin medical studies. Results from the analysis linked to medical tests include the capacity of the wound analysis app to put patients in active positions in their care, enhance the precision of injury measurements, and yield more reliability in care and patient satisfaction.
The research findings also indicate the AI-enabled app’s value in retaining participants. Based on each interview, participants noted that they were “strongly” satisfied by the health potential of the app (Net Health, 2022). The authors of this study also indicated that utilising the app saved participants time and expenses, particularly for travel, a major element in motivating respondents to stay in the study. Notably, sponsors of advanced wound care solutions, such as corporations and states, are in search of instruments that are easy to apply, consult clients, permit virtual injury care visits and consultations, as well as offer real-time and actual insights into a patient’s situation (Net Health, 2022). Therefore, the study shows that mobile wound solutions can give the attributes that today’s practitioners, sponsors, and researchers want and need. The research concludes that looking ahead, there are many gains for this advanced wound care solution which can be applied to other skin conditions.
AI-Enabled Wound Care Assessment and Management is More Effective than Traditional Means
In a diagnostic study conducted across two independent sites using wound photographs identified for routine care, Howell et al. (2021) note that while many approaches can be applied to quantify a wound size, most healthcare facilities still apply traditional ruler measurements, which, unlike the AI-based solutions, are subject to the high variability and can overstate the actual area by as much as 40% (Rogers et al., 2010). Another popular approach to injury measurement is contact acetate tracing. However, Hammond and Nixon (2011) ascertained contact with an injury can change the borders, lead to contamination in patients with a higher risk of infection, and increase pain. Another wound assessment and management method is the manual digital planimetry of wound images. It enhances precision but is still affected by clinical variability and can be time-intensive to incorporate into high-demand injury care facilities (Bilgin & Gunes, 2013). Therefore, its reliability in a high-demand environment is limited as it will consume much time.
Besides the wound surface area, the proportion of healthy granulation in the injury is critical for evaluating if a will heal or is ready for grafting. While undertaking the diagnostic study, Howell et al. (2021) found that practitioners project the proportion of granulation tissue depending on colour as a healing indicator. Exuberant red granulation might mean contamination, while pale tissue might mean poor angiogenesis and blood distribution in the injury (Hampton, 2017). However, this approach to estimating the per cent of granulation tissue is inaccurate and faced with high clinical variability.
AI algorithms that precisely measure granulation could enhance wound recovery decisions. For instance, works by Iizaka et al. (2011) and Iizaka et al. (2013) have shown that colour study of granulation tissue can project recovery outcomes for ulcer wounds. Currently, there is no standard for the wound evaluation method. However, as He et al. (2019) posit, promising steps in Artificial Intelligence have allowed the automated study of diagnostic photos. Technological advancement in wound assessment and management gadgets and software, such as the Silhouette by Aranz Medical and insight by Ekare, have helped practitioners assess wounds quickly, accurately, and reproducibly, allowing for better wound management and patient outcomes (Kieser & Hammond, 2011). These advances prove that AI-enabled wound care solutions are far better than the traditional methods that have long been used by clinicians in wound care.
Laforet et al. (2019) focused on the role of machine learning, a subset of AI that can be described as software that uses historical information to inform future decisions. In their study, Laforet et al. (2019) assert that technological advances allow people to collect, store, and analyse more Big Data than ever as the world moves into the information era. Data science tools have shown the capacity to use medical datasets to guide medication (Dorman et al., 2016), present new clinical insights (Coudray et al., 2018), and project results. In the practice of wound care, access to unprecedented data amount will have significant implications, as noted by the authors. In their study, Laforet et al. (2019) used data science tools for wound care databases. Their study does offer not only a current picture but also offer a window of opportunities to adjust how care is delivered.
Laforet et al. (2019) have shown the ability to use complicated wound care workflow like automatically identifying types of tissues, measuring wound depth, and developing new clinical insights, such as marking and highlighting high-risk wounds. Their approach has successfully been used in other clinical settings to streamline clinical procedures and enhance patient outcomes. In summary, Laforet et al. (2019) find that these techniques based on machine learning can be used to affect positive change in the wound care practice. Laforet et al. (2019) conclude that machine learning and AI have tremendous potential to enhance wound care by bringing together clinical workflows and directing treatments that will improve patient outcomes. Notably, the study also found that embracing AI in this practice will not replace clinicians but leave those who do not adopt it disadvantaged (Laforet et al., 2019). The authors recommend that technology affects our daily lives, and much of it is based on AI or machine learning; therefore, people should accept its effects willingly and help to apply the same to human health positively.
AI-Based Wound Care Solutions Are Good at Wound Documentation
Gillespie et al. (2015) note that managing all wounds needs a good assessment and handover. Therefore, their assessment must be detailed and accurate for wounds to be effectively managed. One way of assessing wounds is through wound documentation. Inaccurate recording can impact the use of the ideal treatment and the injury recovery procedure (Coleman et al., 2017). Accurate documentation of wounds must include all factors like location of the wound, surface area, surrounding skin, tunnelling presence, and the amount of odour, pain, or exudate.
The Australian Standards for Wound Management mention the significance of precise recording to offer a valid, detailed, and systematic record of one’s wound evaluation, control, and plan for prevention (Wounds Australia, 2016). In a study by Barakat-Johnson et al. (2022), the authors highlight a shortage of research focusing on wound records. Only a few works have been provided that show the inadequacies in the area (Gillespie et al., 2020). Hansen and Fossum (2016) conducted a small Norwegian and Australian research using an analysis of wound documentation in five healthcare centres and noted that nearly half (45%) of the clinical records on wounds, particularly pressure wounds, did not have critical information on assessment and actions taken. Wound care practices were not discussed in detail.
Gillespie et al. (2014) analysed wound documentation in 200 medical recordings in hospitals in Australia. They realised that below half (41.4%) of the recordings had finished wound evaluation documentation, and that wound care recording did not align with evidence-based standards. The same outcomes have been found in the US and other nations. In a pilot study by Li and Korniewicz (2013), the authors found that wound assessment and management recording in electronic medical records (EMR) was worse than in written records. Therefore, today’s wound recording in EMR does not incorporate sophisticated patient needs and does not show evidence-based actions.
A recent forum analysis by a group of experts in Australia noted that there was no integration of patient records and wound data in the healthcare field (Pacella et al., (2018). The significance of wound imaging for comprehensive, effective wound assessment, tracking, and management has been shown in several studies, such as Wang et al. (2014) and Khoo and Jansen (2016). Health services increasingly use photos to evaluate, manage, and record wounds (Wang et al., 2014). Wound photos can be analysed immediately, are available for viewing on-screen, and can be communicated among practitioners and printed if needed in hard copies.
Various challenges are linked with injury assessment and the use of imaging for assessment. Firstly, the assessment procedure is subjective, given that it is determined by a practitioner’s experience (Barakat-Johnson et al., 2022). The evaluation of wound measurements differs between practitioners even when a definitive measure is applied due to the lack of a clear wound edge, and the decision on the point from which to determine the length or depth is subjective. Secondly, the camera type used to take wound photos, and how the camera is placed can influence the wound image, resulting in more differences in wound measurements or how the wound appears. Finally, Stevenson et al. (2016) believe the steps needed to post and share the pictures can violate hospital privacy regulations and policies. Therefore, entirely depending on this modern way of wound care assessment and management might result in legal action against healthcare facilities if a patient realises their medical records regarding wound images have been shared illegally.
However, recent advancements in wound imaging, such as wound apps, have enhanced the precision of documentation when it comes to wound care, resulting in better wound control and patient outcomes (Khoo & Jansen, 2016; Wang et al., 2017). Digital wound apps downloaded to smartphones can perform real-time wound studies and monitor through image capture. Some apps have AI algorithms and medical decision-support mechanisms to help determine the ideal treatment choices, the wound product types to be used, the monitoring of the wound recovery process, and the subsequent measures to be taken. These advancements in wound care have been designed and used for years in the US, Europe, and the UK (Do Khac et al., 2021). Notably, the use of these technologies is also understood to be in the Australian setting, and their positive impacts have been felt in the wound care practice.
Opportunities for AI-Based Wound Care Solutions
Sen (2019) analysed Medicare beneficiaries in the US and showed that 8.2 million individuals had acute and serious wounds at a yearly expense ranging from $28.1 billion to $96.8 billion. Due to the limited number of well-trained wound experts in primary and local healthcare facilities, many wound patients lack access to specialised wound care and the latest guidelines. Therefore, developing remote telemedicine networks that use AI can benefit patients in remote locations, particularly in rural areas, with better medical advice (Bowling et al., 2011). With the rising use of Artificial Intelligence and portable devices like smartphones, it is time to design remote and intelligent diagnosis and prognosis systems used in wound care. An intelligent system can benefit wound care in various ways, including higher precision, reduced workload and financial costs, definitive diagnosis and management, and improved patient care quality.
Comstock (2018) indicates that one promising area where AI is rapidly advancing is computer vision algorithms that process images. Healthcare entrepreneurs are in the middle of turning AI technology towards healthcare, where algorithms can determine lesions and rashes, measure and analyse wounds and bring testing into homes–all using short clips and images taken by smartphones (Comstock, 2018). The rise of this new approach to wound care that is happening today has been influenced by the intersection of smartphones, their prevalence, the power of these mobile devices being able to present AI services and computer vision at the bedside, as well as the developments in frameworks mainly revolving around AI.
Advantages of AI-Supported Apps in Wound Care Management
AI-based applications perform sophisticated roles that are typically done by experts. AI has significant potential, particularly in wound treatment and management. For instance, AI-based solutions offer a range of benefits, such as enhancing diagnostic accuracy, imaging, and solutions, enhancing efficiency and workflow, undertaking complex tasks, as well as improving the learning process (Allmayer, 2022). Moreover, AI helps experts in wound treatment and healing. Among the biggest challenges in wound treatment is healing prediction. This is important in achieving wound closure. In chronic wounds, Cho et al. (2020) assert that their complex nature makes prediction challenging. This issue results from the sophisticated interaction of most interrelated elements. Moreover, this complexity also incorporates a patient’s health status besides the wound, thus dominating the whole healing process. To successfully use AI in wound treatment, apps and devices should be equipped with adequate information, allowing medical practitioners to apply it as a scientific tool.
Today, a full computer diagnosis is still under development, and collaboration between humans and technological tools is indispensable. However, the current wound care practice is adapting to digitalisation based on the existing digital opportunities (Allmayer, 2022). For instance, new wound measurement and clinical apps, such as the imitoWound-App, are already helping many medical practitioners. The application and possibility of such technologies are shifting how wounds are assessed and treated, thus significantly reducing the time needed for patient care. Furthermore, practitioners can optimise preventive treatment through AI (Allmayer, 2022). Wound treatment always needs preventive measures by healthcare experts. To allow this to happen on time, constant wound assessment and observation are essential. Identifying risk patterns and factors is a time-intensive practice for experts and needs relevant knowledge and years of experience. However, with the help of AI, it is now possible to determine sophisticated interaction patterns at an early age, treat wounds at their onset, treat wounds individually, and adapt medical intervention (Allmayer, 2022). These benefits of AI to wound care make it easier for experts in this area.
Regardless of the benefits of AI, engineers and people with experience in such AI-based apps can face some setbacks. Particularly, data protection is vital in such systems. Moreover, it is essential to eliminate old or poorly processed data from the system so that no inaccurate conclusions are made during the research. However, these and other setbacks are regularly managed thanks to the constant improvement of algorithms and the collected data, which is crucial in producing accurate outcomes and the most optimised results (Allmayer, 2022). Wound treatment using AI has enormous potential and is, at the same time, the outcome of increasing digitalisation. From treatment to prevention, this approach has already adjusted wound care assessment and management in a novel way and continues to evolve.
AI Wound Care Solutions and Reduced Healthcare Expenses
AI wound care solutions and telemedicine can play a significant role in offering continuous care to society using prediction and assessment. Embracing this technology will also allow more patients to link with trained wound care specialists (Barakat-Johnson et al., 2022). With phones equipped with camera apps, AI allows patients and caregivers to capture images of their chronic wounds, which are used in wound assessment and management (Allmayer, 2022). Such images can also be shared immediately through an app allowing specialists to study the image in real-time. This approach would allow wound care experts to track the status of the wound even when patients cannot visit the healthcare facilities. The easy accessibility to telemedicine is important as some individuals with serious wounds could be bedridden and incapable of visiting their healthcare providers physically. Without an AI-enabled app, Allmayer (2022) postulates that such patients would have difficulty accessing critical healthcare systems. Due to these reasons, AI can change how wound care is offered to patients, and importantly, it can help reduce costs incurred by patients and healthcare providers.
Conclusion and Research Gap
The increasing digitalisation and information era has significantly impacted several industries and how they operate. They have resulted in technological advancements that have made numerous processes easier. Among the new technologies is AI, which uses collected data to predict future outcomes in various processes. In healthcare, the use of AI has been widespread, and medical specialists are now using it to perform complex tasks in a short period of time. The literature review has specifically focused on the application of AI in wound care assessment and management. While conducting relevant research in clinical settings, the literature agrees that this technology has resulted in new ways of assessing, measuring, treating, and managing wounds. The sources used in this literature review are current and offer a clear picture of current developments in wound care and AI application. Although the sources highlight how AI can help in treating, assessing, and managing wounds, there is no study or information about a full AI-based system that can facilitate the healing process without a clinician’s intervention. Therefore, future studies should focus on the new developments and publish their research on fully AI-supported diagnosis and treatment solutions.
Reference List
Allmayer, S. (2022). Wound treatment with the use of Artificial Intelligence. imito AG. https://imito.io/en/blog/news/wound-treatment-with-the-use-of-artificial-intelligence
Barakat‐Johnson, M., Jones, A., Burger, M., Leong, T., Frotjold, A., Randall, S., & Coyer, F. (2022). Reshaping wound care: Evaluation of an artificial intelligence app to improve wound assessment and management amid the COVID‐19 pandemic. International Wound Journal, 19(6), 1561-1577.
Berthet, M., Gauthier, Y., Lacroix, C., Verrier, B., & Monge, C. (2017). Nanoparticle-based dressing: The future of wound treatment? Trends in Biotechnology, 35(8), 770-784.
Bilgin, M., & Günes, Ü. Y. (2013). A comparison of 3 wound measurement techniques: Effects of pressure ulcer size and shape. Journal of Wound Ostomy & Continence Nursing, 40(6), 590-593.
Bowling, F. L., King, L., Paterson, J. A., Hu, J., Lipsky, B. A., Matthews, D. R., & Boulton, A. J. (2011). Remote assessment of diabetic foot ulcers using a novel wound imaging system. Wound Repair and Regeneration, 19(1), 25-30.
Cho, S. K., Mattke, S., Gordon, H., Sheridan, M., & Ennis, W. (2020). Development of a model to predict the healing of chronic wounds within 12 weeks. Advances in Wound Care, 9(9), 516-524.
Comstock, J. (2018). How AI and Computer Vision are reinventing wound care. MobiHealthNews. https://www.mobihealthnews.com/content/how-ai-and-computer-vision-are-reinventing-wound-care
Coleman, S., Nelson, E. A., Vowden, P., Vowden, K., Adderley, U., Sunderland, L., & Nixon, J. (2017). Development of a generic wound care assessment minimum data set. Journal of Tissue Viability, 26(4), 226-240.
Do Khac, A., Jourdan, C., Fazilleau, S., Palayer, C., Laffont, I., Dupeyron, A., & Gelis, A. (2021). mHealth app for pressure ulcer wound assessment in patients with spinal cord injury: Clinical validation study. JMIR mHealth and uHealth, 9(2), e26443.
Frost & Sullivan. (2021). Artificial Intelligence to boost the global wound care market by 2026 with minimal intervention solutions. PR Newswire: News Distribution, Targeting and Monitoring. https://www.prnewswire.com/in/news-releases/artificial-intelligence-to-boost-the-global-wound-care-market-by-2026-with-minimal-intervention-solutions-867200921.html
Gillespie, B. M., Chaboyer, W., St John, W., Morley, N., & Nieuwenhoven, P. (2015). Health professionals’ decision‐making in wound management: A grounded theory. Journal of Advanced Nursing, 71(6), 1238-1248.
Gillespie, B. M., Chaboyer, W., Kang, E., Hewitt, J., Nieuwenhoven, P., & Morley, N. (2014). Postsurgery wound assessment and management practices: A chart audit. Journal of Clinical Nursing, 23(21-22), 3250-3261.
Gillespie, B. M., Walker, R., Lin, F., Roberts, S., Eskes, A., Perry, J., & Chaboyer, W. (2020). Wound care practices across two acute care settings: A comparative study. Journal of Clinical Nursing, 29(5-6), 831-839. doi:10.1111/jocn.15135
Guler, O., Cheng, P., Wilson, E., Wu, K.L. (2019). Using Artificial Intelligence (AI) to model wound healing prediction – a preliminary study. Hmpgloballearningnetwork.com. https://www.hmpgloballearningnetwork.com/site/woundcare/poster/using-artificial-intelligence-ai-model-wound-healing-prediction-preliminary-study
Hammond, C. E., & Nixon, M. A. (2011). The reliability of a handheld wound measurement and documentation device in clinical practice. Journal of Wound Ostomy & Continence Nursing, 38(3), 260-264.
Hampton, S. (2017). Understanding overgranulation in tissue viability practice. British Journal of Community Nursing, 12(Sup4), S24-S30.
Hansen, R. L., & Fossum, M. (2016). Nursing documentation of pressure ulcers in nursing homes: Comparison of record content and patient examinations. Nursing Open, 3(3), 159-167.
He, J., Baxter, S. L., Xu, J., Xu, J., Zhou, X., & Zhang, K. (2019). The practical implementation of artificial intelligence technologies in medicine. Nature Medicine, 25(1), 30-36.
Howell, R. S., Liu, H. H., Khan, A. A., Woods, J. S., Lin, L. J., Saxena, M., & Gorenstein, S. A. (2021). Development of a method for clinical evaluation of Artificial Intelligence–based digital wound assessment tools. JAMA Network Open, 4(5), e217234-e217234.
Khoo, R., & Jansen, S. (2016). The evolving field of wound measurement techniques: a literature review. Wounds: A Compendium of Clinical Research and Practice, 28(6), 175-181.
Kieser, D. C., & Hammond, C. (2011). Leading wound care technology: The ARANZ medical silhouette. Advances in Skin & Wound Care, 24(2), 68-70.
Laforet, M., Gupta, R., Allport, J., & Perez, C. (2019). Is Artificial Intelligence the future of wound care? Hmpgloballearningnetwork.com. https://www.hmpgloballearningnetwork.com/site/woundcare/poster/artificial-intelligence-future-wound-care
Li, D., & Korniewicz, D. M. (2013). Determination of the effectiveness of electronic health records to document pressure ulcers. Medsurg Nursing, 22(1), n.p.
Iizaka, S., Sugama, J., Nakagami, G., Kaitani, T., Naito, A., Koyanagi, H., & Sanada, H. (2011). Concurrent validation and reliability of digital image analysis of granulation tissue colour for clinical pressure ulcers. Wound Repair and Regeneration, 19(4), 455-463.
Iizaka, S., Kaitani, T., Sugama, J., Nakagami, G., Naito, A., Koyanagi, H., & Sanada, H. (2013). Predictive validity of granulation tissue colour measured by digital image analysis for deep pressure ulcer healing: A multicenter prospective cohort study. Wound Repair and Regeneration, 21(1), 25-34.
Net Health. (2022). Australian study highlights the value of tissue analytics wound care platform. PR Newswire: Press Release Distribution, Targeting, Monitoring and Marketing. https://www.prnewswire.com/news-releases/australian-study-highlights-value-of-tissue-analytics-wound-care-platform-301526316.html
Ohura, N., Mitsuno, R., Sakisaka, M., Terabe, Y., Morishige, Y., Uchiyama, A., & Takushima, A. (2019). Convolutional neural networks for wound detection: The role of artificial intelligence in wound care. Journal of Wound Care, 28(Sup10), S13-S24.
Pacella, R. E., Tulleners, R., Cheng, Q., Burkett, E., Edwards, H., Yelland, S., … & Graves, N. (2018). Solutions to the chronic wounds problem in Australia: A call to action. Wound Practice & Research: Journal of the Australian Wound Management Association, 26(2), 84-98.
Rogers, L. C., Bevilacqua, N. J., Armstrong, D. G., & Andros, G. (2010). Digital planimetry results in more accurate wound measurements: A comparison to standard ruler measurements. Journal of Diabetes Science and Technology, 4(4), 799-802.
Sen, C. K. (2019). Human wounds and its burden: An updated compendium of estimates. Advances in Wound Care, 8(2), 39-48.
Stevenson, P., Finnane, A. R., & Soyer, H. P. (2016). Teledermatology and clinical photography: Safeguarding patient privacy and mitigating medico-legal risk. The Medical Journal of Australia,204(5), 198-200e1.
Wang, L., Pedersen, P. C., Strong, D. M., Tulu, B., Agu, E., & Ignotz, R. (2014). Smartphone-based wound assessment system for patients with diabetes. IEEE Transactions on Biomedical Engineering, 62(2), 477-488.
Wounds Australia. (2016). Standards for wound prevention and management. 3rd ed. Cambridge Media on Behalf of Wounds Australia.
write