Application of Artificial Intelligence Methodologies to Chronic Wound Care and Management: A Scoping Review.

Significance: As the number of hard-to-heal wound cases rises with the aging of the population and the spread of chronic diseases, health care professionals struggle to provide safe and effective care to all their patients simultaneously. This study aimed at providing an in-depth overview of the relevant methodologies of artificial intelligence (AI) and their potential implementation to support these growing needs of wound care and management. Recent Advances: MEDLINE, Compendex, Scopus, Web of Science, and IEEE databases were all searched for new AI methods or novel uses of existing AI methods for the diagnosis or management of hard-to-heal wounds. We only included English peer-reviewed original articles, conference proceedings, published patent applications, or granted patents (not older than 2010) where the performance of the utilized AI algorithms was reported. Based on these criteria, a total of 75 studies were eligible for inclusion. These varied by the type of the utilized AI methodology, the wound type, the medical record/database configuration, and the research goal. Critical Issues: AI methodologies appear to have a strong positive impact and prospects in the wound care and management arena. Another important development that emerged from the findings is AI-based remote consultation systems utilizing smartphones and tablets for data collection and connectivity. Future Directions: The implementation of machine-learning algorithms in the diagnosis and managements of hard-to-heal wounds is a promising approach for improving the wound care delivered to hospitalized patients, while allowing health care professionals to manage their working time more efficiently.

Gait Detection from a Wrist-Worn Sensor Using Machine Learning Methods: A Daily Living Study in Older Adults and People with Parkinson's Disease.

Remote assessment of the gait of older adults (OAs) during daily living using wrist-worn sensors has the potential to augment clinical care and mobility research. However, hand movements can degrade gait detection from wrist-sensor recordings. To address this challenge, we developed an anomaly detection algorithm and compared its performance to four previously published gait detection algorithms. Multiday accelerometer recordings from a wrist-worn and lower-back sensor (i.e., the "gold-standard" reference) were obtained in 30 OAs, 60% with Parkinson's disease (PD). The area under the receiver operator curve (AUC) and the area under the precision−recall curve (AUPRC) were used to evaluate the performance of the algorithms. The anomaly detection algorithm obtained AUCs of 0.80 and 0.74 for OAs and PD, respectively, but AUPRCs of 0.23 and 0.31 for OAs and PD, respectively. The best performing detection algorithm, a deep convolutional neural network (DCNN), exhibited high AUCs (i.e., 0.94 for OAs and 0.89 for PD) but lower AUPRCs (i.e., 0.66 for OAs and 0.60 for PD), indicating trade-offs between precision and recall. When choosing a classification threshold of 0.9 (i.e., opting for high precision) for the DCNN algorithm, strong correlations (r > 0.8) were observed between daily living walking time estimates based on the lower-back (reference) sensor and the wrist sensor. Further, gait quality measures were significantly different in OAs and PD compared to healthy adults. These results demonstrate that daily living gait can be quantified using a wrist-worn sensor.

A machine learning algorithm for early detection of heel deep tissue injuries based on a daily history of sub-epidermal moisture measurements.

Sub-epidermal moisture is an established biophysical marker of pressure ulcer formation based on biocapacitance changes in affected soft tissues, which has been shown to facilitate early detection of these injuries. Artificial intelligence shows great promise in wound prevention and care, including in automated analyses of quantitative measures of tissue health such as sub-epidermal moisture readings acquired over time for effective, patient-specific, and anatomical-site-specific pressure ulcer prophylaxis. Here, we developed a novel machine learning algorithm for early detection of heel deep tissue injuries, which was trained using a database comprising six consecutive daily sub-epidermal moisture measurements recorded from 173 patients in acute and post-acute care settings. This algorithm was able to achieve strong predictive power in forecasting heel deep tissue injury events the next day, with sensitivity and specificity of 77% and 80%, respectively, revealing the clinical potential of artificial intelligence-powered technology for hospital-acquired pressure ulcer prevention. The current work forms the scientific basis for clinical implementation of machine learning algorithms that provide effective, early, and anatomy-specific preventive interventions to minimise the occurrence of hospital-acquired pressure ulcers based on routine tissue health status measurements.

An integrated experimental-computational study of the microclimate under dressings applied to intact weight-bearing skin.

Pressure ulcers (PUs) are one of the most prevalent adverse events in acute and chronic care. The root aetiological cause of PUs is sustained cell and tissue deformations, which triggers a synergistic tissue damage cascade that accelerates over relatively short time periods. Changes in skin microclimate conditions are known to indirectly contribute to PU-risk levels or to exacerbation of existing wounds. It is therefore surprising that information concerning heat accumulation under dressings is poor. Here, we aimed to investigate the effects of dressings on the microclimate of weight-bearing buttocks skin in 1-hour supine lying sessions. Using a novel and originally developed experimental-computational approach, we compared the combined influence of the mechanical and thermal properties of a polymeric membrane dressing (PolyMem, Ferris Mfg. Corp., Fort Worth, TX) on skin microclimate under and near the dressings with those of a standard placebo foam dressing. We specifically identified the thermal conductivity properties of dressings as being highly important in the context of protective dressing performances, given its association with potential heat accumulation under dressings. Accordingly, this article highlights, for the first time in the literature, the relevance of thermal properties of a dressing in effectively mitigating the risk of developing PUs or aggravating an injury, and offers a systematic, methodological bioengineering process for assessing the thermal performances of dressings.

The biomechanical protective effects of a treatment dressing on the soft tissues surrounding a non-offloaded sacral pressure ulcer.

Patients who are immobile endure prolonged bodyweight-related compressive, tensional and shear loads at their body-support contact areas that over time may lead to the onset of pressure ulcers (PUs). Approximately, one-third of the common sacral PUs are severe and classified as category 3 or 4. If a PU has occurred, off-loading is the basic, commonly accepted clinical intervention; however, in many situations, complete off-loading of sacral PUs is not possible. Minimising the exposure of wounds and their surroundings to elevated mechanical loads is crucial for healing. Accordingly, in the present study, we aimed to investigate the biomechanical effects of the structural and mechanical properties of different treatment dressings on stresses in soft tissues surrounding a non-offloaded sacral PU in a supine patient. Using a novel three-dimensional anatomically realistic finite element modelling framework, we have compared performances of three dressing designs: (a) The Mepilex Border Sacrum (MBS) multilayer anisotropic silicone foam dressing (Mölnlycke Health Care), (b) an isotropic stiff dressing, and (c) an isotropic flexible dressing. Using our newly developed protective efficacy index (PEI) and aggravation index (AI) for assessing prophylactic and treatment dressings, we identified the anisotropic stiffness feature of the MBS dressing as a key design element.

A Computer Modeling Study to Assess the Durability of Prophylactic Dressings Subjected to Moisture in Biomechanical Pressure Injury Prevention.

The sacral area is the most common site for pressure injuries (PIs) associated with prolonged supine bedrest. In previous studies, an anisotropic multilayer prophylactic dressing was found to reduce the incidence of PIs and redistribute pressure. The purpose of the current study was to further investigate relationships between design features and biomechanical efficacy of sacral prophylactic dressings. Using computer modeling, the anisotropic multilayer dressing and a hypothetical dressing with different mechanical properties were tested under dry and 3 levels of moist/wet conditions. Sixteen (16) finite element model variants representing the buttocks were developed. The model variants utilized slices of the weight-bearing buttocks of a 28-year-old healthy woman for segmentation of the pelvic bones and soft tissues. Effective stresses and maximal shear stresses in a volume of interest of soft tissues surrounding the sacrum were calculated from the simulations, and a protective endurance (PE) index was further calculated. Resistance to deformations along the direction of the spine when wet was determined by rating simulation outcomes (volumetric exposures to effective stress) for the different dressing conditions. Based on this analysis, the anisotropic multilayer prophylactic dressing exhibited superior PE (80%), which was approximately 4 times that of the hypothetical dressing (22%). This study provides additional important insights regarding the optimal design of prophylactic dressings, especially when exposed to moisture. A next step in research would be to optimize the extent of the anisotropy, particularly the property ratio of stiffnesses (elastic moduli).

The contribution of a directional preference of stiffness to the efficacy of prophylactic sacral dressings in protecting healthy and diabetic tissues from pressure injury: computational modelling studies.

The sacral region is the most common site for pressure injuries (PIs) associated with lying in bed, and such sacral PIs often commence as deep tissue injuries (DTIs) that later present as open wounds. In complex patients, diabetes is common. Because, among other factors, diabetes affects connective tissue stiffness properties, making these tissues less able to dissipate mechanical loads through physiological deformations, diabetes is an additional biomechanical risk factor for PIs and DTIs. A preventive measure with established successful clinical outcomes is the use of sacral prophylactic dressings. The objective of this study has been to expand our previous work regarding the modes of action and biomechanical efficacy of prophylactic dressings in protecting the soft tissues adjacent to the sacrum by specifically examining the role of a directional stiffness preference (anisotropy) of the dressing while further accounting for diabetic tissue conditions. Multiple three-dimensional anatomically detailed finite element (FE) model variants representing diabetic tissue conditions were used, and tissue loading state data were compared with healthy tissue simulations. We specifically compared soft tissue exposures to elevated internal shear stresses and strain energy densities (SED) near the sacrum during supine weight bearing on a standard (foam) hospital mattress without a dressing, with a prophylactic dressing lacking directional stiffness preferences and with an anisotropic dressing. Our results have clearly shown that an anisotropic dressing design reduces the peak tissue stresses and exposure to sustained tissue deformations in both healthy and diabetic cases. The present study provides additional important insights regarding the optimal structural and material design of prophylactic dressings, which in turn, informs clinicians and decision makers regarding beneficial features.