A systematic review of machine learning and automation in burn wound evaluation: A promising but developing frontier

Novel multi-spectral short-wave infrared imaging for assessment of human burn wound depth

Burn depth determination is critical for patient care but is currently lacking accuracy. Recent animal studies showed that Short Wave Infrared (SWIR) imaging can distinguish between superficial and deep burns. This is a first human study correlating reflectance of multiple SWIR bands using a SWIR assessment tool (SWAT) with burn depth classifications by surgeons and histology. Burns and adjacent normal skin in 11 patients with thermal injuries were imaged with visual and narrow bands centred at 1200, 1650, 1940 and 2250 nm and biopsies were taken from select areas. Reflectance intensities for each band in 273 regions of interest (ROI) were divided by the normal skin reflectance and combined into three Reflectance Indices (RIs). In addition, burns in ROIs and biopsies were classified by five surgeons and three pathologists, respectively, as superficial partial, deep partial, or full thickness. Results show that for burn depth increase classified by the surgeons, reflectance increased at 1200 and 2250, decreased at 1940, and didn't change at 1650 nm. In contrast, all three RIs increase with burn depth and predict the deep and full depths ROIs representing operable regions (Area Under Curve >0.6507, p < 0.0001). Pathologists' classification matched surgeons' classification of burn category only in eight of 21 biopsies (38.1%), but reflectance at all bands and one RI for all deep partial and full thickness biopsies were larger than in non-biopsy normal and superficial partial thickness ROIs (p < 0.0118). In conclusion, multi-spectral imaging with a new SWAT is a promising approach for evaluation of burn wound depth.

Progress in the application of artificial intelligence in skin wound assessment and prediction of healing time

Since the 1970s, artificial intelligence (AI) has played an increasingly pivotal role in the medical field, enhancing the efficiency of disease diagnosis and treatment. Amidst an aging population and the proliferation of chronic disease, the prevalence of complex surgeries for high-risk multimorbid patients and hard-to-heal wounds has escalated. Healthcare professionals face the challenge of delivering safe and effective care to all patients concurrently. Inadequate management of skin wounds exacerbates the risk of infection and complications, which can obstruct the healing process and diminish patients' quality of life. AI shows substantial promise in revolutionizing wound care and management, thus enhancing the treatment of hospitalized patients and enabling healthcare workers to allocate their time more effectively. This review details the advancements in applying AI for skin wound assessment and the prediction of healing timelines. It emphasizes the use of diverse algorithms to automate and streamline the measurement, classification, and identification of chronic wound healing stages, and to predict wound healing times. Moreover, the review addresses existing limitations and explores future directions.

Artificial intelligence in wound care: diagnosis, assessment and treatment of hard-to-heal wounds: a narrative review

OBJECTIVE

The effective assessment of wounds, both acute and hard-to-heal, is an important component in the delivery by wound care practitioners of efficacious wound care for patients. Improved wound diagnosis, optimising wound treatment regimens, and enhanced prevention of wounds aid in providing patients with a better quality of life (QoL). There is significant potential for the use of artificial intelligence (AI) in health-related areas such as wound care. However, AI-based systems remain to be developed to a point where they can be used clinically to deliver high-quality wound care. We have carried out a narrative review of the development and use of AI in the diagnosis, assessment and treatment of hard-to-heal wounds. We retrieved 145 articles from several online databases and other online resources, and 81 of them were included in this narrative review. Our review shows that AI application in wound care offers benefits in the assessment/diagnosis, monitoring and treatment of acute and hard-to-heal wounds. As well as offering patients the potential of improved QoL, AI may also enable better use of healthcare resources.

An in silico modeling approach to understanding the dynamics of the post-burn immune response

Introduction

Burns are characterized by a massive and prolonged acute inflammation, which persists for up to months after the initial trauma. Due to the complexity of the inflammatory process, Predicting the dynamics of wound healing process can be challenging for burn injuries. The aim of this study was to develop simulation models for the post-burn immune response based on (pre)clinical data.

Methods

The simulation domain was separated into blood and tissue compartments. Each of these compartments contained solutes and cell agents. Solutes comprise pro-inflammatory cytokines, anti-inflammatory cytokines and inflammation triggering factors. The solutes diffuse around the domain based on their concentration profiles. The cells include mast cells, neutrophils, and macrophages, and were modeled as independent agents. The cells are motile and exhibit chemotaxis based on concentrations gradients of the solutes. In addition, the cells secrete various solutes that in turn alter the dynamics and responses of the burn wound system.

Results

We developed an Glazier-Graner-Hogeweg method-based model (GGH) to capture the complexities associated with the dynamics of inflammation after burn injuries, including changes in cell counts and cytokine levels. Through simulations from day 0 - 4 post-burn, we successfully identified key factors influencing the acute inflammatory response, i.e., the initial number of endothelial cells, the chemotaxis threshold, and the level of chemoattractants.

Conclusion

Our findings highlight the pivotal role of the initial endothelial cell count as a key parameter for intensity of inflammation and progression of acute inflammation, 0 - 4 days post-burn.

Risk predictions of surgical wound complications based on a machine learning algorithm: A systematic review

Surgical wounds may arise due to harm inflicted upon soft tissue during surgical intervention, and many complications and injuries may accompany them. These complications can lead to prolonged hospitalization and poorer clinical outcomes. Also, Machine learning (ML) is a Section of artificial intelligence (AI) that has emerged in medical care and is increasingly used for diagnosis, complications, prognosis and recurrence prediction. This study aims to investigate surgical wound risk predictions and management using a ML algorithm by R programming language analysis. The systematic review, following PRISMA guidelines, spanned electronic databases using search terms like 'machine learning', 'surgical' and 'wound'. Inclusion criteria covered experimental studies from 1990 to the present on ML's application in surgical wound evaluation. Exclusion criteria included studies lacking full text, focusing on ML in all surgeries, neglecting wound assessment and duplications. Two authors rigorously assessed titles, abstracts and full texts, excluding reviews and guidelines. Ultimately, relevant articles were then analysed. The present study identified nine articles employing ML for surgical wound management. The analysis encompassed various surgical procedures, including Cardiothoracic, Caesarean total abdominal colectomy, Burn plastic surgery, facial plastic surgery, laparotomy, minimal invasive surgery, hernia repair and unspecified surgeries. ML was skillful in evaluating surgical site infections (SSI) in seven studies, while two extended its use to burn-grade diagnosis and wound classification. Support Vector Machine (SVM) and Convolutional Neural Network (CNN) were the most utilized algorithms. ANN achieved a 96% accuracy in facial plastic surgery wound management. CNN demonstrated commendable accuracies in various surgeries, and SVM exhibited high accuracy in multiple surgeries and burn plastic surgery. In sum, these findings underscore ML's potential for significant improvements in postoperative management and the development of enhanced care techniques, particularly in surgical wound management.

Systematic reviews of machine learning in healthcare: a literature review

INTRODUCTION

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

METHODS

A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted.

RESULTS

In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively).

EXPERT OPINION

The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.

Autonomous Multi-modality Burn Wound Characterization using Artificial Intelligence

INTRODUCTION

Between 5% and 20% of all combat-related casualties are attributed to burn wounds. A decrease in the mortality rate of burns by about 36% can be achieved with early treatment, but this is contingent upon accurate characterization of the burn. Precise burn injury classification is recognized as a crucial aspect of the medical artificial intelligence (AI) field. An autonomous AI system designed to analyze multiple characteristics of burns using modalities including ultrasound and RGB images is described.

MATERIALS AND METHODS

A two-part dataset is created for the training and validation of the AI: in vivo B-mode ultrasound scans collected from porcine subjects (10,085 frames), and RGB images manually collected from web sources (338 images). The framework in use leverages an explanation system to corroborate and integrate burn expert's knowledge, suggesting new features and ensuring the validity of the model. Through the utilization of this framework, it is discovered that B-mode ultrasound classifiers can be enhanced by supplying textural features. More specifically, it is confirmed that statistical texture features extracted from ultrasound frames can increase the accuracy of the burn depth classifier.

RESULTS

The system, with all included features selected using explainable AI, is capable of classifying burn depth with accuracy and F1 average above 80%. Additionally, the segmentation module has been found capable of segmenting with a mean global accuracy greater than 84%, and a mean intersection-over-union score over 0.74.

CONCLUSIONS

This work demonstrates the feasibility of accurate and automated burn characterization for AI and indicates that these systems can be improved with additional features when a human expert is combined with explainable AI. This is demonstrated on real data (human for segmentation and porcine for depth classification) and establishes the groundwork for further deep-learning thrusts in the area of burn analysis.

Holistic Approach to Burn Reconstruction and Scar Rehabilitation

More than 11 million burn injuries occur each year across the world. Many people with burn injuries, regardless of injury size, develop hypertrophic scar, contracture, unstable scar, heterotopic ossification, and disability resulting from these sequelae. Advances in trauma systems, critical care, safe surgery, and multidisciplinary burn care have markedly improved the survival of people who have experienced extensive burn injuries. Burn scar reconstruction aims to improve or restore physical function, confidence, and body image. Like acute burn care, burn scar reconstruction requires thoughtful, coordinated approaches along the continuum of burn injury, recovery, and rehabilitation.

Machine learning approach for predicting inhalation injury in patients with burns

BACKGROUND

The coronavirus disease pandemic has had a tangible impact on bronchoscopy for burn inpatients due to isolation and triage measures. We utilised the machine-learning approach to identify risk factors for predicting mild and severe inhalation injury and whether patients with burns experienced inhalation injury. We also examined the ability of two dichotomous models to predict clinical outcomes including mortality, pneumonia, and duration of hospitalisation.

METHODS

A retrospective 14-year single-centre dataset of 341 intubated patients with burns with suspected inhalation injury was established. The medical data on day one of admission and bronchoscopy-diagnosed inhalation injury grade were compiled using a gradient boosting-based machine-learning algorithm to create two prediction models: model 1, mild vs. severe inhalation injury; and model 2, no inhalation injury vs. inhalation injury.

RESULTS

The area under the curve (AUC) for model 1 was 0·883, indicating excellent discrimination. The AUC for model 2 was 0·862, indicating acceptable discrimination. In model 1, the incidence of pneumonia (P < 0·001) and mortality rate (P < 0·001), but not duration of hospitalisation (P = 0·1052), were significantly higher in patients with severe inhalation injury. In model 2, the incidence of pneumonia (P < 0·001), mortality (P < 0·001), and duration of hospitalisation (P = 0·021) were significantly higher in patients with inhalation injury.

CONCLUSIONS

We developed the first machine-learning tool for differentiating between mild and severe inhalation injury, and the absence/presence of inhalation injury in patients with burns, which is helpful when bronchoscopy is not available immediately. The dichotomous classification predicted by both models was associated with the clinical outcomes.

A Deep Learning Image-to-Image Translation Approach for a More Accessible Estimator of the Healing Time of Burns

OBJECTIVE

An accurate and timely diagnosis of burn severity is critical to ensure a positive outcome. Laser Doppler imaging (LDI) has become a very useful tool for this task. It measures the perfusion of the burn and estimates its potential healing time. LDIs generate a 6-color palette image, with each color representing a healing time. This technique has very high costs associated. In resource-limited areas, such as low- and middle-income countries or remote locations like space, where access to specialized burn care is inadequate, more affordable and portable tools are required. This study proposes a novel image-to-image translation approach to estimate burn healing times, using a digital image to approximate the LDI.

METHODS

This approach consists of a U-net architecture with a VGG-based encoder and applies the concept of ordinal classification. Paired digital and LDI images of burns were collected. The performance was evaluated with 10-fold cross-validation, mean absolute error (MAE), and color distribution differences between the ground truth and the estimated LDI.

RESULTS

Results showed a satisfactory performance in terms of low MAE ( 0.2370 ±0.0086). However, the unbalanced distribution of colors in the data affects this performance.

SIGNIFICANCE

This novel and unique approach serves as a basis for developing more accessible support tools in the burn care environment in resource-limited areas.

Implementing AI Models for Prognostic Predictions in High-Risk Burn Patients

BACKGROUND AND OBJECTIVES

Burn injuries range from minor medical issues to severe, life-threatening conditions. The severity and location of the burn dictate its treatment; while minor burns might be treatable at home, severe burns necessitate medical intervention, sometimes in specialized burn centers with extended follow-up care. This study aims to leverage artificial intelligence (AI)/machine learning (ML) to forecast potential adverse effects in burn patients.

METHODS

This retrospective analysis considered burn patients admitted to Chi Mei Medical Center from 2010 to 2019. The study employed 14 features, comprising supplementary information like prior comorbidities and laboratory results, for building models for predicting graft surgery, a prolonged hospital stay, and overall adverse effects. Overall, 70% of the data set trained the AI models, with the remaining 30% reserved for testing. Three ML algorithms of random forest, LightGBM, and logistic regression were employed with evaluation metrics of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).

RESULTS

In this research, out of 224 patients assessed, the random forest model yielded the highest AUC for predictions related to prolonged hospital stays (>14 days) at 81.1%, followed by the XGBoost (79.9%) and LightGBM (79.5%) models. Besides, the random forest model of the need for a skin graft showed the highest AUC (78.8%), while the random forest model and XGBoost model of the occurrence of adverse complications both demonstrated the highest AUC (87.2%) as well. Based on the best models with the highest AUC values, an AI prediction system is designed and integrated into hospital information systems to assist physicians in the decision-making process.

CONCLUSIONS

AI techniques showcased exceptional capabilities for predicting a prolonged hospital stay, the need for a skin graft, and the occurrence of overall adverse complications for burn patients. The insights from our study fuel optimism for the inception of a novel predictive model that can seamlessly meld with hospital information systems, enhancing clinical decisions and bolstering physician-patient dialogues.

Blank Spots in the Map of Human Skin: The Challenge for Xenotransplantation

Most of the knowledge about human skin homeostasis, development, wound healing, and diseases has been accumulated from human skin biopsy analysis by transferring from animal models and using different culture systems. Human-to-mouse xenografting is one of the fundamental approaches that allows the skin to be studied in vivo and evaluate the ongoing physiological processes in real time. Humanized animals permit the actual techniques for tracing cell fate, clonal analysis, genetic modifications, and drug discovery that could never be employed in humans. This review recapitulates the novel facts about mouse skin self-renewing, regeneration, and pathology, raises issues regarding the gaps in our understanding of the same options in human skin, and postulates the challenges for human skin xenografting.

Application of multiple deep learning models for automatic burn wound assessment

PURPOSE

Accurate assessment of the percentage of total body surface area (%TBSA) burned is crucial in managing burn injuries. It is difficult to estimate the size of an irregular shape by inspection. Many articles reported the discrepancy of estimating %TBSA burned by different doctors. We set up a system with multiple deep learning (DL) models for %TBSA estimation, as well as the segmentation of possibly poor-perfused deep burn regions from the entire wound.

METHODS

We proposed boundary-based labeling for datasets of total burn wound and palm, whereas region-based labeling for the dataset of deep burn wound. Several powerful DL models (U-Net, PSPNet, DeeplabV3+, Mask R-CNN) with encoders ResNet101 had been trained and tested from the above datasets. With the subject distances, the %TBSA burned could be calculated by the segmentation of total burn wound area with respect to the palm size. The percentage of deep burn area could be obtained from the segmentation of deep burn area from the entire wound.

RESULTS

A total of 4991 images of early burn wounds and 1050 images of palms were boundary-based labeled. 1565 out of 4994 images with deep burn were preprocessed with superpixel segmentation into small regions before labeling. DeeplabV3+ had slightly better performance in three tasks with precision: 0.90767, recall: 0.90065 for total burn wound segmentation; precision: 0.98987, recall: 0.99036 for palm segmentation; and precision: 0.90152, recall: 0.90219 for deep burn segmentation.

CONCLUSION

Combining the segmentation results and clinical data, %TBSA burned, the volume of fluid for resuscitation, and the percentage of deep burn area can be automatically diagnosed by DL models with a pixel-to-pixel method. Artificial intelligence provides consistent, accurate and rapid assessments of burn wounds.

Quantization of extraoral free flap monitoring for venous congestion with deep learning integrated iOS applications on smartphones: a diagnostic study

BACKGROUND

Free flap monitoring is essential for postmicrosurgical management and outcomes but traditionally relies on human observers; the process is subjective and qualitative and imposes a heavy burden on staffing. To scientifically monitor and quantify the condition of free flaps in a clinical scenario, we developed and validated a successful clinical transitional deep learning (DL) model integrated application.

MATERIAL AND METHODS

Patients from a single microsurgical intensive care unit between 1 April 2021 and 31 March 2022, were retrospectively analyzed for DL model development, validation, clinical transition, and quantification of free flap monitoring. An iOS application that predicted the probability of flap congestion based on computer vision was developed. The application calculated probability distribution that indicates the flap congestion risks. Accuracy, discrimination, and calibration tests were assessed for model performance evaluations.

RESULTS

From a total of 1761 photographs of 642 patients, 122 patients were included during the clinical application period. Development (photographs =328), external validation (photographs =512), and clinical application (photographs =921) cohorts were assigned to corresponding time periods. The performance measurements of the DL model indicate a 92.2% training and a 92.3% validation accuracy. The discrimination (area under the receiver operating characteristic curve) was 0.99 (95% CI: 0.98-1.0) during internal validation and 0.98 (95% CI: 0.97-0.99) under external validation. Among clinical application periods, the application demonstrates 95.3% accuracy, 95.2% sensitivity, and 95.3% specificity. The probabilities of flap congestion were significantly higher in the congested group than in the normal group (78.3 (17.1)% versus 13.2 (18.1)%; 0.8%; 95% CI, P <0.001).

CONCLUSION

The DL integrated smartphone application can accurately reflect and quantify flap condition; it is a convenient, accurate, and economical device that can improve patient safety and management and assist in monitoring flap physiology.

Inhalation Injury Grading Using Transfer Learning Based on Bronchoscopy Images and Mechanical Ventilation Period

The abbreviated injury score (AIS) is commonly used as a grading system for inhalation injuries. While inhalation injury grades have inconsistently been shown to correlate positively with the time mechanical ventilation is needed, grading is subjective and relies heavily on the clinicians' experience and expertise. Additionally, no correlation has been shown between these patients' inhalation injury grades and outcomes. In this paper, we propose a novel inhalation injury grading method which uses deep learning algorithms in bronchoscopy images to determine the injury grade from the carbonaceous deposits, blistering, and fibrin casts in the bronchoscopy images. The proposed method adopts transfer learning and data augmentation concepts to enhance the accuracy performance to avoid overfitting. We tested our proposed model on the bronchoscopy images acquired from eighteen patients who had suffered inhalation injuries, with the degree of severity 1, 2, 3, 4, 5, or 6. As performance metrics, we consider accuracy, sensitivity, specificity, F-1 score, and precision. Experimental results show that our proposed method, with both transfer learning and data augmentation components, provides an overall 86.11% accuracy. Moreover, the experimental results also show that the performance of the proposed method outperforms the method without transfer learning or data augmentation.

A Workflow for Computer-Aided Evaluation of Keloid Based on Laser Speckle Contrast Imaging and Deep Learning

A keloid results from abnormal wound healing, which has different blood perfusion and growth states among patients. Active monitoring and treatment of actively growing keloids at the initial stage can effectively inhibit keloid enlargement and has important medical and aesthetic implications. LSCI (laser speckle contrast imaging) has been developed to obtain the blood perfusion of the keloid and shows a high relationship with the severity and prognosis. However, the LSCI-based method requires manual annotation and evaluation of the keloid, which is time consuming. Although many studies have designed deep-learning networks for the detection and classification of skin lesions, there are still challenges to the assessment of keloid growth status, especially based on small samples. This retrospective study included 150 untreated keloid patients, intensity images, and blood perfusion images obtained from LSCI. A newly proposed workflow based on cascaded vision transformer architecture was proposed, reaching a dice coefficient value of 0.895 for keloid segmentation by 2% improvement, an error of 8.6 ± 5.4 perfusion units, and a relative error of 7.8% ± 6.6% for blood calculation, and an accuracy of 0.927 for growth state prediction by 1.4% improvement than baseline.

Artificial intelligence, machine learning, and deep learning for clinical outcome prediction

AI is a broad concept, grouping initiatives that use a computer to perform tasks that would usually require a human to complete. AI methods are well suited to predict clinical outcomes. In practice, AI methods can be thought of as functions that learn the outcomes accompanying standardized input data to produce accurate outcome predictions when trialed with new data. Current methods for cleaning, creating, accessing, extracting, augmenting, and representing data for training AI clinical prediction models are well defined. The use of AI to predict clinical outcomes is a dynamic and rapidly evolving arena, with new methods and applications emerging. Extraction or accession of electronic health care records and combining these with patient genetic data is an area of present attention, with tremendous potential for future growth. Machine learning approaches, including decision tree methods of Random Forest and XGBoost, and deep learning techniques including deep multi-layer and recurrent neural networks, afford unique capabilities to accurately create predictions from high dimensional, multimodal data. Furthermore, AI methods are increasing our ability to accurately predict clinical outcomes that previously were difficult to model, including time-dependent and multi-class outcomes. Barriers to robust AI-based clinical outcome model deployment include changing AI product development interfaces, the specificity of regulation requirements, and limitations in ensuring model interpretability, generalizability, and adaptability over time.