AI technology for remote clinical assessment and monitoring

3D bioprinted mesenchymal stem cell laden scaffold enhances subcutaneous vascularization for delivery of cell therapy

Subcutaneous delivery of cell therapy is an appealing minimally-invasive strategy for the treatment of various diseases. However, the subdermal site is poorly vascularized making it inadequate for supporting engraftment, viability, and function of exogenous cells. In this study, we developed a 3D bioprinted scaffold composed of alginate/gelatin (Alg/Gel) embedded with mesenchymal stem cells (MSCs) to enhance vascularization and tissue ingrowth in a subcutaneous microenvironment. We identified bio-ink crosslinking conditions that optimally recapitulated the mechanical properties of subcutaneous tissue. We achieved controlled degradation of the Alg/Gel scaffold synchronous with host tissue ingrowth and remodeling. Further, in a rat model, the Alg/Gel scaffold was superior to MSC-embedded Pluronic hydrogel in supporting tissue development and vascularization of a subcutaneous site. While the scaffold alone promoted vascular tissue formation, the inclusion of MSCs in the bio-ink further enhanced angiogenesis. Our findings highlight the use of simple cell-laden degradable bioprinted structures to generate a supportive microenvironment for cell delivery.

A Scoping Review of Wearable Technologies for Use in Individuals With Intellectual Disabilities and Diabetic Peripheral Neuropathy

BACKGROUND

Individuals with intellectual disabilities (IDs) are at risk of diabetes mellitus (DM) and diabetic peripheral neuropathy (DPN), which can lead to foot ulcers and lower-extremity amputations. However, cognitive differences and communication barriers may impede some methods for screening and prevention of DPN. Wearable and mobile technologies-such as smartphone apps and pressure-sensitive insoles-could help to offset these barriers, yet little is known about the effectiveness of these technologies among individuals with ID.

METHODS

We conducted a scoping review of the databases Embase, PubMed, and Web of Science using search terms for DM, DPN, ID, and technology to diagnose or monitor DPN. Finding a lack of research in this area, we broadened our search terms to include any literature on technology to diagnose or monitor DPN and then applied these findings within the context of ID.

RESULTS

We identified 88 articles; 43 of 88 (48.9%) articles were concerned with gait mechanics or foot pressures. No articles explicitly included individuals with ID as the target population, although three articles involved individuals with other cognitive impairments (two among patients with a history of stroke, one among patients with hemodialysis-related cognitive changes).

CONCLUSIONS

Individuals with ID are not represented in studies using technology to diagnose or monitor DPN. This is a concern given the risk of DM complications among patients with ID and the potential for added benefit of such technologies to reduce barriers to screening and prevention. More studies should investigate how wearable devices can be used among patients with ID.

Machine Learning Approaches for the Image-Based Identification of Surgical Wound Infections: Scoping Review

BACKGROUND

Surgical site infections (SSIs) occur frequently and impact patients and health care systems. Remote surveillance of surgical wounds is currently limited by the need for manual assessment by clinicians. Machine learning (ML)-based methods have recently been used to address various aspects of the postoperative wound healing process and may be used to improve the scalability and cost-effectiveness of remote surgical wound assessment.

OBJECTIVE

The objective of this review was to provide an overview of the ML methods that have been used to identify surgical wound infections from images.

METHODS

We conducted a scoping review of ML approaches for visual detection of SSIs following the JBI (Joanna Briggs Institute) methodology. Reports of participants in any postoperative context focusing on identification of surgical wound infections were included. Studies that did not address SSI identification, surgical wounds, or did not use image or video data were excluded. We searched MEDLINE, Embase, CINAHL, CENTRAL, Web of Science Core Collection, IEEE Xplore, Compendex, and arXiv for relevant studies in November 2022. The records retrieved were double screened for eligibility. A data extraction tool was used to chart the relevant data, which was described narratively and presented using tables. Employment of TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) guidelines was evaluated and PROBAST (Prediction Model Risk of Bias Assessment Tool) was used to assess risk of bias (RoB).

RESULTS

In total, 10 of the 715 unique records screened met the eligibility criteria. In these studies, the clinical contexts and surgical procedures were diverse. All papers developed diagnostic models, though none performed external validation. Both traditional ML and deep learning methods were used to identify SSIs from mostly color images, and the volume of images used ranged from under 50 to thousands. Further, 10 TRIPOD items were reported in at least 4 studies, though 15 items were reported in fewer than 4 studies. PROBAST assessment led to 9 studies being identified as having an overall high RoB, with 1 study having overall unclear RoB.

CONCLUSIONS

Research on the image-based identification of surgical wound infections using ML remains novel, and there is a need for standardized reporting. Limitations related to variability in image capture, model building, and data sources should be addressed in the future.

Digital Twin in Healthcare: A Study for Chronic Wound Management

Although the concept of digital twin technology has been in existence for nearly half a century, its application in healthcare is a relatively recent development. In healthcare, the utilization of digital twin and data-driven models has proven to enhance clinical decision support, particularly in the treatment and assessment of chronic wounds, leading to improved clinical outcomes. This article proposes the implementation of a digital twin in the domain of healthcare, specifically in the management of chronic wounds, by leveraging artificial intelligence techniques. The digital twin is composed of data collection, data processing, and AI models dedicated to wound healing. A novel AI pipeline is utilized to track the healing of chronic wounds. The digital twin, serving as a virtual representation of the actual wound, simulates and replicates the healing process. Furthermore, the proposed wound-healing prediction model effectively guides the treatment of chronic wounds. Additionally, by comparing the actual wound with its digital twin, the system enables early identification of non-healing wounds, facilitating timely adjustments and modifications to the treatment plan. By incorporating a digital twin in healthcare, the proposed system enables personalized and tailored treatments, potentially playing a crucial role in proactive problem identification.

The digital future of nursing: making sense of taxonomies and key concepts

Digital technology is becoming increasingly common in routine nursing practice. The adoption of digital technologies such as video calling, and other digital communication, has been hastened by the recent COVID-19 pandemic. Use of these technologies has the potential to revolutionise nursing practice, leading to potentially more accurate patient assessment, monitoring processes and improved safety in clinical areas. This article outlines key concepts related to the digitalisation of health care and the implications for nursing practice. The aim of this article is to encourage nurses to consider the implications, opportunities and challenges associated with the move towards digitalisation and advances in technology. Specifically, this means understanding key digital developments and innovations associated with healthcare provision and appreciating the implications of digitalisation for the future of nursing practice.

What COVID-19 taught us: New opportunities and pathways from telemedicine and novel antiseptics in wound healing

The COVID-19 pandemic deeply impacted the capacity of the health systems to maintain preventive and curative services, especially for the most vulnerable populations. During the pandemic, the wound healing centres in Italy assisted a significant reduction of the frequency of their hospital admission, since only urgencies, such as severe infections or wound haemorrhagic complications, were allowed to the hospital. The aim of this multidisciplinary work is to highlight the importance of a new pathway of wound care with patient-based therapeutic approach, tailored treatments based on the characteristics of the wound and fast tracks focused on the outpatient management, reserving hospital assessment only for patients with complicated or complex wounds. This analysis highlights the point that patients with chronic wounds need to be critically evaluated in order to find the best and most appropriate care pathway, which should vary according to the patient and, especially, to the characteristics of the wound. Moreover, the most adequate topic antiseptic should be started as soon as possible. An appropriate and correct management of the wound care will allow to link the knowledge based on years of clinical practice with the new challenges and the need to visit patients remotely, when possible.

Literature Review of Machine-Learning Algorithms for Pressure Ulcer Prevention: Challenges and Opportunities

Pressure ulcers are associated with significant morbidity, resulting in a decreased quality of life for the patient, and contributing to healthcare professional burnout, as well as an increase of health service costs. Their prompt diagnosis and treatment are important, and several studies have proposed solutions to help healthcare professionals in this process. This work analyzes studies that use machine-learning algorithms for risk assessment and management of preventive treatments for pressure ulcers. More specifically, it focuses on the use of machine-learning algorithms that combine information from intrinsic and extrinsic pressure-ulcer predisposing factors to produce recommendations/alerts to healthcare professionals. The review includes articles published from January 2010 to June 2021. From 60 records screened, seven articles were analyzed in full-text form. The results show that most of the proposed algorithms do not use information related to both intrinsic and extrinsic predisposing factors and that many of the approaches separately address one of the following three components: data acquisition; data analysis, and production of complementary support to well-informed clinical decision-making. Additionally, only a few studies describe in detail the outputs of the algorithm, such as alerts and recommendations, without assessing their impacts on healthcare professionals’ activities.