WO2025181763A1

WO2025181763A1 - System and method for monitoring wound healing

Info

Publication number: WO2025181763A1
Application number: PCT/IB2025/052213
Authority: WO
Inventors: Chindu KABIR; Marlene LOBO
Original assignee: Post OP Ltd
Current assignee: Post OP Ltd
Priority date: 2024-03-01
Filing date: 2025-02-28
Publication date: 2025-09-04
Anticipated expiration: 2026-09-01

Abstract

Disclosed is a system (100) for monitoring wound healing. The system comprises: an imaging unit (102) for capturing wound images over a predefined period of time; and a software application comprising a user interface (104) and a processing arrangement (106). The processing arrangement is configured to: receive, via the user interface, wound images captured by the imaging unit; analyse the received wound images using an artificial intelligence (AI) algorithm; generate a wound assessment report based on the analysis by the AI algorithm; and transmit, via the user interface, the wound assessment report. Disclosed also is a method for monitoring wound healing.

Description

SYSTEM AND METHOD FOR. MONITORING WOUND HEALING

TECHNICAL FIELD

The present disclosure relates to systems for monitoring wound healing. Moreover, the present disclosure relates to methods for monitoring wound healing. Furthermore, the present disclosure relates to non- transitory computer-readable storage mediums having computer- readable instructions stored thereon, that being executable by a computerized device comprising processing hardware to execute the aforementioned methods.

BACKGROUND

Effective wound monitoring is critical for ensuring proper healing and preventing complications such as infections. However, traditional methods of wound assessment are often manual, subjective, and timeconsuming, leading to inconsistencies in evaluations. Additionally, the lack of accessible, non-invasive, and rapid diagnostic tools for detecting bacterial infections in wounds poses significant challenges for both healthcare providers and patients. These challenges are further exacerbated in remote or resource-limited settings, where access to specialized medical equipment and expertise is limited.

Existing solutions for wound monitoring and infection detection include traditional laboratory-based methods, biosensor technologies, and manual clinical assessments. Laboratory methods, such as bacterial cultures, Gram staining, and polymerase chain reaction (PCR), are effective but require specialized equipment and settings, trained personnel, and significant time, making them unsuitable for point-of-care applications. Biosensor technologies, such as electronic noses and surface-enhanced Raman spectroscopy, aim to provide faster results but face challenges in terms of accuracy, reliability, and clinical adoption. Moreover, manual clinical assessments, which rely on visual inspection and subjective judgment, often lack standardization and can lead to delayed detection of complications.

Therefore, in light of the foregoing discussion, there exists a need to overcome the aforementioned drawbacks.

SUMMARY

The aim of the present disclosure is to provide a system and a method for post-operative wound care, leveraging cutting-edge Al algorithms to enhance the accuracy, efficiency, and comprehensiveness of wound monitoring and assessment. The aim of the present disclosure is achieved by a system and a method for monitoring wound healing as defined in the appended independent claims to which reference is made to. Advantageous features are set out in the appended dependent claims.

Throughout the description and claims of this specification, the words "comprise" , "include", "have", and "contain" and variations of these words, for example "comprising" and "comprises" , mean "including but not limited to", and do not exclude other components, items, integers or steps not explicitly disclosed also to be present. Moreover, the singular encompasses the plural unless the context otherwise requires. In particular, where the indefinite article is used, the specification is to be understood as contemplating plurality as well as singularity, unless the context requires otherwise.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is an illustration of a system for monitoring wound healing, in accordance with an embodiment of the present disclosure; and FIG. 2 is an illustration of a flowchart depicting steps of a method for monitoring wound healing, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS

The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practising the present disclosure are also possible.

In a first aspect, the present disclosure provides a system for monitoring wound healing, the system comprising : an imaging unit for capturing wound images over a predefined period of time; and a software application comprising a user interface and a processing arrangement, wherein the processing arrangement is configured to: receive, via the user interface, wound images captured by the imaging unit; analyse the received wound images using an artificial intelligence (Al) algorithm; generate a wound assessment report based on the analysis by the Al algorithm; and transmit, via the user interface, the wound assessment report.

In a second aspect, the present disclosure provides a method for monitoring wound healing, the method comprising : capturing wound images using an imaging unit; initiating a software application comprising a user interface and a processing arrangement; receiving, via the user interface, by the processing arrangement, wound images captured by the imaging unit; analysing, using an artificial intelligence (Al) algorithm executed by the processing arrangement, the received wound images; generating, by the processing arrangement, a wound assessment report based on the analysis by the Al algorithm; and transmitting, by the user interface, the wound assessment report.

The present disclosure provides a system and method that focuses on post-operative wound care and management. The disclosed system and method provide improved solutions that are accurate, non-invasive, and accessible for timely wound assessment and infection detection. In this regard, the present disclosure leverages an objective, Al-driven analysis of wound images (and/or videos), enhancing the accuracy and reliability of post-operative wound monitoring. Moreover, automated wound monitoring leads to better patient outcomes by enabling more timely and appropriate interventions, and reduces workload on healthcare professionals and effectively streamline post-operative care processes.

In a third aspect, the present disclosure provides a non-transitory computer-readable storage medium having computer-readable instructions stored thereon, the computer-readable instructions being executable by a computerized device comprising processing hardware to execute the aforementioned method of the second aspect.

Throughout the present disclosure, the phrase "system for monitoring wound healing" or "system" refers to a comprehensive arrangement designed to facilitate the assessment and management of wound healing over a predefined period of time. The system integrates various components, including an imaging unit, a software application, and a processing arrangement, to capture, analyse, and report wound-related data. The system is configured to utilize artificial intelligence (Al) algorithms to process wound images and generate a wound assessment report. The system is further capable of transmitting the wound assessment report to relevant stakeholders, such as healthcare professionals, for subsequent analysis and decision-making. The healthcare professional refers to the medical practitioner who reviews the wound assessment report and provides treatment recommendations. The system supports healthcare professionals by providing accurate and timely wound assessments. Herein, the term "user" refers to a patient. In some embodiment, the user may also be a caregiver of the patient who is authorized to provide the wound images and the self-assessment data, on behalf of the patient (such as an incapacitated patient).

The term "wound" refers to a disruption or break in the integrity of the skin or underlying tissues, typically caused by physical, chemical, or biological factors. Wounds can result from external trauma, surgical procedures, or underlying medical conditions. Wounds vary in severity, depth, and healing characteristics, and their classification often depends on the cause, duration, and extent of tissue damage.

In an embodiment, the wound is selected from at least one of: an acute wound, a chronic wound. Typically, the acute wounds occur suddenly and typically heal within a predictable timeframe. For example, cuts, abrasions, burns, and surgical incisions. Chronic wounds are wounds that fail to heal within the expected timeframe, often persisting for weeks or months. For example, diabetic ulcers, pressure ulcers (bedsores), and venous leg ulcers, that are often associated with underlying medical conditions such as diabetes, poor circulation, or prolonged pressure on the skin. Moreover, wounds may be classified as infected wounds, surgical wounds, traumatic wounds, burn wounds and post-operative wounds. Infected wounds show signs of infection, such as redness, swelling, pus, or an unpleasant odour. Infected wounds may result from bacterial, fungal, or other microbial contamination and require prompt medical attention. Surgical wounds are wounds that are intentionally created during surgical procedures, and require careful monitoring to ensure proper healing and to detect any signs of infection or complications. Traumatic wounds are wounds caused by external trauma, such as accidents, falls, or injuries. Traumatic wounds can vary in severity and may involve damage to deeper tissues. Burn wounds are wounds caused by thermal, chemical, or electrical burns, and may vary based on their depth (e.g., first-degree, second-degree, or third-degree burns). Post-operative wounds are wounds resulting from surgical interventions and require close monitoring to ensure proper healing and prevent complications. Furthermore, wounds can also be classified based on their depth and severity, such as superficial wounds (affecting only the outermost layer of skin), partial-thickness wounds (involving the epidermis and dermis), and full-thickness wounds (extending into deeper tissues, such as muscle or bone). Therefore, proper wound care and monitoring are essential to promote healing, prevent infection, and minimize complications.

The system comprises the imaging unit for capturing wound images over a predefined period of time. The term "imaging unit" refers to a hardware component that is configured to capture wound images. The imaging unit works in conjunction with the software application to ensure that the captured wound images are suitable for analysis. The imaging unit is essential for providing the raw data required for the processing arrangement to perform Al-driven analysis.

In an embodiment, the wound images are captured using an imaging unit associated with any of: a mobile device, the software application, and wherein the imaging unit is implemented as an Al-aided imaging unit, and wherein the wound images include a corresponding wound area and surrounding tissues. Herein, the imaging unit could be integrated into a mobile device, such as a smartphone or tablet, or it could be a standalone device that works in conjunction with the software application. The imaging unit may include a mobile device camera or any other Al-aided imaging unit capable of capturing high-resolution images of the wound area and surrounding tissues. The "mobile device" refers to the hardware platform, such as a smartphone or tablet, that hosts the software application and serves as the imaging unit. The mobile device enables the system for monitoring wound healing to be portable and accessible. Optionally, the mobile device is any device associated with a user that comprises an imaging unit or camera, namely, devices with a camera. Herein, it may be appreciated that the mobile device is not just restricted to a smartphone or a tablet, as mentioned above.

Typically, the Al-aided imaging unit incorporates artificial intelligence capabilities to enhance the image capture process. Such Al capabilities may include, but not limit to, features such as automatic focus adjustment, positional corrections, optimization of lighting conditions, or real-time preprocessing of the captured images to ensure high-quality and consistent results. Beneficially, said implementation ensures that the imaging unit can adapt to varying conditions, such as different lighting environments or user proficiency, to produce images suitable for analysis.

The wound images captured by the imaging unit include not only the wound area but also the surrounding tissues. This ensures that the images provide a comprehensive view of the wound and its immediate environment, which is critical for accurate analysis. The inclusion of surrounding tissues allows the system to assess additional factors, such as inflammation, discoloration, or other signs of complications that may extend beyond the wound itself. This comprehensive imaging approach enhances the system's ability to provide detailed and reliable wound assessments.

In an embodiment, the system further comprises an image processing module for maintaining image quality in varying lighting conditions, wherein the image processing module is implemented as an Al-aided image processing module. The term "image processing module" refers to a software component that is designed to enhance and maintain the quality of wound images captured by the imaging unit. These modules are responsible for correcting issues such as poor lighting, shadows, glare, or noise that may arise during image capture. The image processing module ensures that the wound images are clear, consistent, and suitable for further analysis by the system's processing arrangement. Specifically, the Al-aided image processing modules utilize artificial intelligence techniques to enhance and optimize the captured images. In this regard, the image processing module functions by analysing the captured wound images and applying Al-driven adjustments to correct issues such as poor lighting, shadows, glare, positioning object(s) of interest, or other inconsistencies that may arise due to environmental factors or user error during image capture. This ensures that the images are of sufficient quality for accurate analysis by the system's processing arrangement and artificial intelligence algorithm. Beneficially, the Al- aided image processing module allows the system to dynamically adapt to different lighting conditions and user environments. For example, the Al-aided image processing modules can automatically adjust brightness, contrast, and colour balance or remove noise from the images, thus ensuring that the wound images remain consistent and reliable, regardless of the conditions in which they are captured.

The term "wound image" refers to visual data captured by the imaging unit, representing the wound area and surrounding tissues. A wound image is required to enable accurate, objective, and consistent monitoring of wound healing. It serves as the primary input for systems which use artificial intelligence (Al) algorithms to analyse the wound's condition. It may be appreciated that the wound images are captured and analysed for a predefined period of time, to monitor the wound's condition. This period may vary depending on the type of wound, such as an acute wound or a chronic wound, the user's medical condition, and the specific requirements of the healthcare professional overseeing the treatment. Beneficially, the predefined period of time ensures that the wound images and associated data are captured and analysed consistently to monitor the healing process effectively. Moreover, the system comprises the software application comprising a user interface and a processing arrangement. The term "software application" is a digital platform within the system that facilitates the interaction between the user and the system for monitoring wound healing. The user interface is a component of the software application that facilitates interaction between the user and the system for monitoring wound healing. The user interface is configured to receive inputs and transmit output. The user interface ensures that the system is user-friendly and accessible to both patients and healthcare professionals.

The processing arrangement is a computational component of the software application that is configured to analyse the wound images using an artificial intelligence algorithm. The term "processing arrangement" refers to programmable and/or non-programmable components configured to execute one or more software applications for storing, processing, sharing data and/or set of instructions. It will be appreciated that the "processing arrangement" refers to "one processing arrangement" in some implementations, and "a plurality of processing arrangements" in other implementations. In cases where the processing arrangement is a plurality of processing arrangements, the plurality of processing arrangements is communicably coupled to each other via a communication network. Optionally, the processing arrangement is a set of one or more hardware components or a multi-processor system, depending on a particular implementation. More optionally, the processing arrangement includes, for example, a component included within an electronic communications network. Additionally, the processing arrangement includes one or more data processing facilities for storing, processing, sharing data and/or a set of instructions. Optionally, the processing arrangement includes functional components, for example, a processor, a memory, a network adapter and so forth. Throughout the present disclosure, the term "communication network" refers to a network of interconnected programmable and/or nonprogrammable components that are configured to facilitate data communication between one or more electronic devices and/or databases, such as the imaging unit and the processing arrangement or software application, whether available or known at the time of filing or as later developed. Furthermore, the communication network may include, but is not limited to, one or more peer-to-peer network, a hybrid peer-to-peer network, local area networks (LANs), radio access networks (RANs), metropolitan area networks (MANS), wide area networks (WANs), all or a portion of a public network such as the global computer network known as the Internet, a private network, a cellular network and any other communication system or systems at one or more locations. Furthermore, the processing arrangement facilitates communication between the imaging unit or user device and the software application over the communication network, likely to execute tasks related to the system's function.

The processing arrangement is configured to receive, via the user interface, wound images captured by the imaging unit, by communicably coupling therewith. In other words, the processing arrangement is communicably coupled to the imaging unit, and configured to receive wound images captured by the imaging unit. In this regard, the processing arrangement is configured to receive wound images captured by the imaging unit through the user interface. The user interface acts as the intermediary between the user and the system, allowing the user to upload or input the wound images or videos. These wound images or videos are then transferred to the processing arrangement for further analysis.

Moreover, the processing arrangement is configured to analyse the received wound images using an artificial intelligence (Al) algorithm. The artificial intelligence algorithm is embedded within the processing arrangement. The Al algorithm enhances the system's ability to provide precise and consistent wound assessments. The use of an Al algorithm ensures that the wound is assessed objectively, eliminating the variability and subjectivity associated with manual evaluations by healthcare professionals. This consistency improves the reliability of wound monitoring.

In an embodiment, the processing arrangement is configured to analyse the wound images for identifying key indicators selected from at least one of: margins, colour, size, inflammation, and signs of healing, infection or complications in the wound. The term "key indicators" refers to the specific attributes of the wound analysed by the processing arrangement, including margins, colour, size, inflammation, and signs of healing, infection, or complications. The identification of key indicators is critical for an accurate wound assessment. The margins are key indicators that help to assess the boundaries of the wound and detect changes over time. The colour of the wound and its surrounding tissue is used to evaluate the presence of redness, discoloration, or other signs of inflammation or infection. For example, for an open wound a pink colour of the granulation tissue may be associated with a desired healing, while a white or pale-yellow colour may be associated with pus or infection in the wound, and redness of the surrounding tissue may be associated with inflammation in the wound. The size of the wound may be used to monitor the wound's progression, including reduction or expansion in size, wherein reduction in size of wound is indicative of a healing wound, while expansion in size of wound is indicative of worsening or spreading of wound. Level of inflammation is a sign indicative of healing or complications, such as infection or delayed recovery, in the wound. Beneficially, by analysing the key indicators, the healthcare professionals can make informed decisions about treatment, detect complications early, and track the healing process over time. Additionally, wound images reduce the need for frequent in-person clinical visits by allowing remote monitoring and telehealth integration.

In an embodiment, the processing arrangement is further configured to detect and identify specific microbial species associated with the inflammation and/or infection in the wound. The term "microbial species" refers to the types of microorganisms that may be present or cause infection in the wound. In an embodiment, the microbial species includes any of: bacterial, fungi, protozoa, virus, archaea. It may be appreciated that each of these microbial species represents a distinct category of microorganisms, and their identification is critical for accurate diagnosis and effective wound management. Bacteria are one of the most common causes of wound infections. Pathogenic bacteria such as Enterococcus faecium, Staphylococcus aureus, Clostridium difficile, Acinetobacter species (for example Acinetobacter baumanni), Pseudomonas aeruginosa, and Enterobacteriaceae species (for example, Escherichia coll), often referred to as the ESKAPE pathogens, are the most important multi-drug resistant (MDR) threats as recognised by the World Health Organization (WHO). The ESKAPE pathogens can delay wound healing and lead to complications such as abscesses, cellulitis, or sepsis. The system is capable of identifying specific bacterial species by analysing fluorescence patterns or other visual indicators in the wound images. Early detection of bacterial infections allows for timely intervention, such as the administration of targeted antibiotics. It may be appreciated that by knowing the type of bacteria, Gram-positive or Gram-negative, the strain and if it is an MDR. strain, are critical in prescribing antibiotics to an infected patient. Notably, an inappropriate initial use of antibiotics is known to lead to a five-fold increase in mortality in sepsis patients. Fungal infections in wounds, though less common than bacterial infections, can occur, particularly in immunocompromised patients or in chronic wounds. Fungi such as Candida albicans or Aspergillus species can colonize wounds and impede healing. The system's ability to detect fungal species ensures that antifungal treatments can be initiated promptly, reducing the risk of further complications. Protozoan infections in wounds are rare but can occur in specific circumstances, such as in tropical regions or in wounds exposed to contaminated water or soil. Protozoa such as the Leishmania species (causing cutaneous leishmaniasis) can infect wounds and lead to chronic, non-healing ulcers. The system's capability to identify protozoan species ensures that such infections are not overlooked, enabling appropriate treatment. Viral infections in wounds are less common but can complicate wound healing. For example, the presence of herpes simplex virus (HSV) in wounds can cause delayed healing and increased pain. The system's ability to detect viral species ensures that antiviral therapies can be considered as part of the treatment plan. Archaea are a group of microorganisms that are less commonly associated with wound infections but may play a role in certain environments, such as biofilms. Biofilms are complex microbial communities that can form on wound surfaces and protect pathogens from the immune system and antibiotics. The system's ability to detect archaea contributes to a comprehensive understanding of the microbial ecosystem within the wound. Beneficially, by including the capability to detect bacterial, fungal, protozoan, viral, and archaeal species, the system provides a holistic approach to identifying the microbial causes of inflammation and infection in wounds. This broad-spectrum detection ensures that all potential pathogens are accounted for, enabling precise and effective wound care management.

The processing arrangement, using the artificial intelligence algorithm, detects and identifies these microbial species based on specific key indicators, such as fluorescence emission spectrum , biomarkers (such as C-reactive protein (CR.P), procalcitonin, bacterial protease activity), visual indicators (such as discolouration, abnormal granulation tissue, purulent exudate), odour and gas production, biofilm formation, delayed healing and tissue damage, and so on), captured in the wound images. In an example, specific microbial species may cause discoloration of the wound bed or exudate. For example, Pseudomonas aeruginosa often produces a greenish hue due to pyocyanin production. In another example, presence of biofilms, which are protective layers formed by microbial communities, is a hallmark of chronic wound infections. Biofilms can be identified through imaging techniques or by detecting specific extracellular polymeric substances (EPS) produced by the microbes.

In an embodiment, the system further comprises a light source configured to illuminate the wound to emit fluorescence patterns in the microbial species in the wound, prior to capturing the wound images. The term "light source" refers to a component of the imaging unit that illuminates the wound area to induce fluorescence patterns in the microbial species. In this regard, the light source illuminates the wound with specific wavelengths of light, such as ultraviolet (UV), blue, or nearinfrared (NIR.) light, causing certain microbial species to emit fluorescence patterns which are then captured in the wound images by the imaging unit. In an example, the specific wavelengths of light may be 405 nm, 458 nm, 488 nm, 514 nm, 561 nm, 594 nm and 633 nm. Notably, the wavelengths of light are selected based on their ability to excite fluorescence in microbial species. Optionally, the light source may be part of the imaging unit (e.g., a smartphone flashlight with filters) or a separate component within the system. Beneficially, the light source ensures that the captured wound images contain the necessary data for the processing arrangement to analyse and identify specific microbial species.

The term "fluorescence patterns" refers to the light emissions induced in the microbial species by the light source as a response to the excitation light. The emitted fluorescence is captured by the imaging unit, which is equipped with sensors capable of detecting these fluorescence patterns. Optionally, the imaging unit may further comprise filters or specialized optics to enhance the detection of fluorescence patterns while minimizing background noise.

In an embodiment, the processing arrangement is configured to analyse fluorescence patterns captured in the wound image, for detecting at least one microbial species associated with the inflammation and/or infection in the wound. The fluorescence patterns exhibited by the wound may be used to identify specific microbial species associated with infection, when fluorescence-based imaging is used. The emitted fluorescence patterns are analysed by the system's Al algorithm to detect and identify the specific microbial species associated with inflammation or infection in the wound. Specifically, the Al algorithm analyses the intensity, distribution, and spectral characteristics of the fluorescence patterns to identify the microbial species present in the wound. In an example, Pseudomonas aeruginosa fluoresces green under UV light due to the production of pyoverdine, while other bacteria or fungi may emit different fluorescence patterns or colours depending on their metabolic byproducts or structural components. In another example, Staphylococcus aureus may exhibit red fluorescence and other colours, or fluorescence patterns may correspond to fungi or other microbial species.

Moreover, the processing arrangement is configured to generate the wound assessment report based on the analysis by the Al algorithm. In this regard, the processing arrangement combines the fluorescence pattern analysis with other wound image data (e.g., size, margins, colour, inflammation) to provide the comprehensive wound assessment report. The term "wound assessment report" refers to an output generated by the processing arrangement after analysing the wound images using the artificial intelligence algorithm. The wound assessment report includes information on the wound's condition, such as the identified key indicators, the presence of specific microbial species, and so on. Additionally, optionally, the wound assessment report includes information on the medical condition of the user, any surgical intervention or external factors that resulted in the wound development, and so on.

Furthermore, the processing arrangement is configured to transmit, via the user interface, the wound assessment report. Herein, the transmission of the wound assessment report refers to the process by which the processing arrangement sends the generated wound assessment report to the user interface or other connected systems, for access by the user or their healthcare professionals or other stakeholders for further analysis and decision-making. It may be appreciated that the wound assessment report is transmitted over the communication network existing between the various components of the system, namely, processing arrangement, user interface, and user device. Beneficially, the transmission capability of the system is essential for enabling remote monitoring and telehealth applications.

In an embodiment, the user interface is further configured to: receive inputs associated with at least one of: self-assessment of the wound healing, and customisation of one or more analysis parameters based on a wound type and user needs; and transmit at least one of: recommendations for wound care and management, guidance for capturing and uploading wound images, and alert notifications for potential complications.

In this regard, the user interface collects data from the user related to wound healing and customize the system's analysis parameters. Such user input is subsequently processed by the processing arrangement to tailor the analysis and reporting to the specific needs of the wound type and user requirements.

Optionally, the self-assessment of the wound healing may include inputs related to pain levels, exudate (or wound discharge), swelling or redness, healing progress, and other symptoms associated with wound's condition, as observed by the user (namely, patients or caregivers in case the patient is incapacitated). Pain is a critical indicator of wound healing or potential complications, such as infection or inflammation. Herein, users can rate their pain on a scale (e.g., 1 to 10) or describe the type of pain (e.g., sharp, throbbing, or dull). Users can describe the amount, colour, and consistency of any discharge from the wound. For example, clear or slightly yellow discharge may indicate normal healing, while green or foul-smelling discharge could suggest infection. Users can report visible changes in the wound area, such as increased redness, swelling, or warmth, which may indicate inflammation or infection. Users can provide their perception of the wound's healing progress, such as whether the wound appears to be closing, scabbing, or worsening. Users can report additional symptoms, such as fever, chills, or general discomfort, which may be associated with systemic infection or delayed healing. Optionally, mental health, and factors affecting their quality of life too could be added to monitor complete recovery. This feature is particularly useful for capturing subjective observations that may not be fully reflected in the wound images.

Moreover, the user interface also allows for the customization of analysis parameters, enabling the system to adapt to different wound types and individual user requirements. This feature is particularly important because wounds vary significantly in terms of their nature, healing process, and care requirements. Optionally, customizations may be done by the user or the healthcare professional based on the wound characteristics. Optionally, customizations may include, but not limited to, a wound type selection (such as acute wounds or chronic wounds); a healing stage (e.g., inflammatory, proliferative, or remodelling phase); user-specific needs (such as sensitivity of the Al algorithm; frequency of monitoring; language preferences, environmental factors, custom alerts and notifications). For example, chronic wounds may require more detailed analysis of biofilm formation or prolonged inflammation as compared to the acute wounds. In this regard, the customization of frequency of monitoring may be frequent and the customization of custom alerts and notifications may require reminders or schedules for at least one of: capturing wound images, potential complications (e.g., infection or delayed healing), wound care activities (e.g., dressing changes or follow-up appointment). Moreover, customizations may include input details about the environment, such as lighting conditions or camera quality, to optimize the system's image processing modules. For example, the system may apply additional image enhancement techniques if the user indicates poor lighting during image capture.

Beneficially, by allowing users to input self-assessment data and customize analysis parameters, the system provides a tailored approach to wound monitoring, addressing the unique needs of each patient. Moreover, said functionality enhances the overall effectiveness of the wound monitoring system, improving patient outcomes and streamlining wound care management.

Moreover, the user interface is configured to transmit outputs comprising personalized recommendations for wound care and management based on the analysis performed by the system's Al algorithm, guidance to ensure that users capture high-quality wound images suitable for accurate analysis, and alert notifications when the system detects potential complications in the wound, to the user or connected platforms. This functionality ensures that the system provides actionable insights and guidance to support effective wound management. Moreover, this functionality ensures that the system is not only a diagnostic tool but also a comprehensive recovery support system for wound care. This functionality enhances the system's effectiveness, usability, and impact on patient outcomes. Optionally, the recommendations include, but do not limit to, wound cleaning instructions (e.g., use of saline solution), dressing suggestions (such as hydrocolloid, foam, or antimicrobial dressings, depending on the wound's healing stage, moisture level, and risk of infection), frequency of dressing changes (to maintain an optimal healing environment), medication or topical treatments (such as applying specific ointments, creams, or antibiotics if signs of infection or inflammation are detected), and lifestyle adjustments (e.g., avoiding excessive movement or pressure on the wound area or maintaining proper hydration and nutrition).

Optionally, the guidance may include, but not limited to, imaging using positioning instructions relative to the wound, lighting recommendations (such as using natural light or the smartphone's flashlight, to avoid shadows or glare that could obscure details), focus and stability tips (to capture clear and sharp images), angle and perspective (capturing images from multiple angles or perspectives to provide a comprehensive view of the wound), and uploading instructions (ensuring that the images are securely transmitted for analysis). Beneficially, guidance ensures that users, regardless of their technical proficiency, can easily capture and upload images that meet the system's requirements, enabling accurate and reliable wound assessments.

Optionally, the alerts are designed to prompt timely action and may include, but not limited to, signs of infection (such as increased redness, swelling, or abnormal discharge; and the alert may recommend contacting a healthcare provider immediately); delayed healing (wound's healing progress is slower than expected, suggesting the need for further evaluation or changes in the care plan); risk of complications (such as necrosis, excessive inflammation, or the presence of biofilms, which may require medical intervention); critical thresholds (such as wound size, colour changes, or microbial activity exceeding predefined thresholds, indicating a need for urgent attention); and reminders for follow-up actions (such as capturing new wound images, changing dressings, or attending follow-up appointments with their healthcare provider). Beneficially, the alert notifications ensure that users are promptly informed of any issues that may require immediate attention, reducing the risk of complications and improving overall wound care outcomes.

In an embodiment, the Al algorithm is trained on a dataset of wound images and a dataset of microbial species. The Al algorithm is trained on a dataset of wound images and a dataset of microbial species to analyse the received wound images. The dataset of wound images and the dataset of microbial species are the training data used by the artificial intelligence algorithm. These datasets enable the Al algorithm to learn and improve its ability to analyse wound images and identify specific microbial species.

The dataset of wound images comprises high-resolution images of various types of wounds, captured under different conditions. The images are labelled with information about wound type, healing stage, key indicators, complications, and so on. The dataset of wound images is diverse, including images from patients with different skin tones, wound locations, and lighting conditions. This diversity ensures that the algorithm can generalize well and provide accurate assessments across a wide range of scenarios.

Moreover, the dataset of microbial species comprises information about various microbial species that may be present in wounds, such as bacteria, fungi, protozoa, viruses, and archaea. The data is labelled with fluorescence patterns, microbial species identification, association with wound conditions, and so on. Optionally, the dataset of microbial species may also include metadata, such as the environmental conditions under which the microbes are detected, to improve the algorithm's ability to identify pathogens in varying contexts. It may be appreciated that the metadata is collected irrespective of the wound images or the dataset of wound images. As mentioned above, the metadata provides additional data about the specific microbial species. Optionally, such metadata is obtained from published data.

The training process involves feeding the Al algorithm with labelled data so it can identify and classify specific characteristics in new, unseen data. With regards to training, the wound images and microbial species data are pre-processed to ensure consistency and quality. Optionally, said preprocessing includes resizing the wound images to a standard resolution, normalizing colour and brightness to account for variations in lighting, annotating images with labels for wound features and microbial species, and so on. Subsequently, Al algorithms are trained to extract relevant features from the datasets. For example, from wound images, the Al algorithm learns to identify edges, textures, and colour patterns that indicate wound margins, inflammation, or exudate; and from microbial species data, the Al algorithm learns to recognize fluorescence patterns and spectral characteristics unique to specific pathogens. Then the Al algorithm employs supervised learning, where it is trained on labelled data to associate specific features with corresponding labels (e.g., "infection present" or "microbial species: Pseudomonas aeruginosa"). Optionally, the trained Al algorithm is validated and tested on separate datasets to evaluate its accuracy, precision, and ability to generalize to new data. By training on a dataset of wound images, the Al algorithm can accurately assess wound healing progress, detect complications, and provide actionable insights. For example, it can identify whether a wound is healing normally or if there are signs of delayed healing or infection. Additionally, training on a dataset of microbial species enables the Al algorithm to detect and identify pathogens associated with wound infections. This is particularly important for early intervention, as different pathogens require different treatments (e.g., antibiotics for bacteria, antifungals for fungi). Moreover, combining data from both datasets allows the algorithm to correlate visual indicators in the wound (e.g., redness, swelling) with microbial activity (e.g., fluorescence patterns). This holistic approach improves the accuracy and reliability of the wound assessment. In other words, training the Al algorithm on a dataset of wound images and a dataset of microbial species ensures developing a robust, accurate, and versatile wound monitoring system that provides comprehensive assessments, detect infections early, and support personalized wound care management.

In an embodiment, the Al algorithm employs deep learning techniques to compare the received wound images against a dataset of wound images and a dataset of microbial species. The Al algorithm is developed using machine learning and deep learning techniques, or multimodal techniques, which require large datasets to "learn" patterns, features, and relationships. The deep learning techniques refer to the advanced machine learning methods employed by the artificial intelligence algorithm to analyse the wound images. These techniques enable the Al algorithm to compare the received wound images against the datasets and identify key indicators (such as wound margins, size, colour, inflammation, and signs of infection), specific microbial species (using fluorescence patterns), and categorize wounds based on their healing stage, severity, or the presence of complications. Deep learning techniques, such as convolutional neural networks (CNNs), may be used to analyse wound images, while spectral analysis models may be used for microbial fluorescence data. Deep learning techniques enable accurate, automated wound assessments and early detection of infections, significantly improving the quality and efficiency of wound care management.

In an embodiment, the software application is further configured to provide an interactive platform for multiple users to connect for advice and support in wound care and management. The term "interactive platform" is a feature of the software application that enables multiple users to connect and share advice and support in wound care and management. The interactive platform fosters community engagement and knowledge sharing, enhancing the overall user experience. Herein, the multiple users may include, the user (patient and/or caregiver), healthcare professional (nurse or physician), superuser (administrator or a third party). Via the interactive platform, the patients can connect with healthcare professionals or wound care specialists to receive personalized advice and recommendations. Moreover, patients can share their experiences, challenges, and tips with others who are going through similar situations, creating a sense of community and emotional support (peer support group). Furthermore, healthcare providers can exchange insights, discuss complex cases, and collaborate on best practices for wound care that may be accessible to all the registered stakeholders of the interactive platform. Optionally, the interactive platform leverages communication tools such as chat functionality (to engage in real-time text-based conversations with healthcare providers or other patients), video/audio calls (for consultations, enabling remote discussions about wound care), discussion forums (to share experiences and learn from others), and so on. Moreover, the interactive platform provides access to educational materials, such as articles, videos, and tutorials on wound care best practices; FAQs addressing common concerns about wound healing and management; and guidelines for recognizing signs of infection or complications, to registered users and other stakeholders. It may be appreciated that users and other stakeholders are required to create profiles with relevant information, such as their role (patient, caregiver, or healthcare provider), wound type, and care needs. Additionally, healthcare providers may include their credentials and areas of expertise. Moreover, healthcare providers can invite patients to join the platform for ongoing monitoring and advice. Furthermore, healthcare providers can host virtual Q&A sessions or webinars on wound care topics. Moreover, healthcare providers can collaborate with colleagues to refine treatment plans or address challenging cases. In an embodiment, the software application is further configured to be operated in multiple languages, and wherein the wound assessment report is accessible in multiple languages. By supporting multiple languages, the software application ensures that both the user interface (III) and the wound assessment report can be understood and utilized effectively by users who speak different languages and ensures accessibility for diverse users. This includes translating all aspects of the user interface and functionality into multiple languages. In this regard, users can select their preferred language during the initial setup of the application or change it later in the settings. Alternatively, the software application may automatically detect the user's language based on their device settings or location and provide a default option. In this regard, the software application leverages a GPS or related functionality. Additionally, all elements of the user interface, such as menus, buttons, instructions, and notifications, are translated into the selected language. For example, instructions for capturing wound images (e.g., "Hold your phone steady and ensure good lighting") are displayed in the user's chosen language. The wound assessment report, which is generated by the Al algorithm, is also accessible in multiple languages. This ensures that both patients and healthcare providers can understand the report, regardless of their linguistic background. For example, if the report includes a recommendation like "Signs of infection detected. Consult a healthcare provider immediately," it will be translated into the user's preferred language. Similarly, healthcare providers who speak different languages can access the report in their preferred language, ensuring clear communication and understanding of the wound's condition. This is particularly useful in multilingual healthcare settings or when patients and healthcare providers speak different languages.

In this regard, advanced language processing technologies and translation frameworks are employed by the software application. The multilingual translation process involves employing a database of translations for all III elements, instructions, and report content in multiple languages. This database is regularly updated to ensure accuracy and consistency. Moreover, the software application employs dynamic translation modules to dynamically translate content based on the user's selected language. Furthermore, the software application employs integration with Al-powered translation tools, such as neural machine translation (NMT) systems, to provide high-quality translations for complex or context-specific content. Furthermore, the software application leverages customization for regional variations in language. For example, English may be customized for US, UK, or Australian users. Spanish may be adapted for users in Spain, Mexico, or Latin America. Beneficially, by allowing users to operate the application and access wound assessment reports in their preferred language, this feature enhances patient engagement, improves communication in multilingual healthcare settings, and promotes inclusivity.

In an embodiment, the processing arrangement is further configured to integrate with at least one of: electronic health records (EHR.), telehealth platforms, for transmitting the wound assessment report with a healthcare professional for subsequent analysis. The processing arrangement generates the wound assessment report based on the analysis and transmits the wound assessment report to the user interface or integrated platforms, such as electronic health records or telehealth platforms, for review by healthcare professionals, facilitating further analysis, decision-making, and treatment planning.

Electronic Health Records (EHR) are digital systems used by healthcare providers to store and manage patient medical information, including medical history, diagnoses, treatments, and test results. Integration with EHR allows the wound assessment report to be automatically uploaded to the patient's medical record. Optionally, the integration may use standardized protocols such as HL7 (Health Level Seven) or FHIR (Fast Healthcare Interoperability Resources) to ensure compatibility with various EHR systems.

Telehealth platforms enable remote communication between patients and healthcare providers through video calls, messaging, and data sharing. Integration with telehealth platforms allows the wound assessment report to be shared with healthcare professionals during remote consultations. The integration may include real-time data sharing, allowing the provider to review it during a telehealth session. Moreover, integration may include a two-way communication, wherein the patient uploads wound images, and the healthcare providers can send feedback, additional instructions, or treatment recommendations to the patient through the integrated platform.

In this regard, the processing arrangement uses secure communication protocols (e.g., HTTPS, TLS) to transmit the wound assessment report to EHR or telehealth systems. Optionally, data in the wound assessment report is encrypted to ensure patient privacy and compliance with regulations such as HIPAA (Health Insurance Portability and Accountability Act) or GDPR (General Data Protection Regulation).

Beneficially, by automating data transmission and supporting remote monitoring, the integration improves patient outcomes, enhances provider efficiency, and reduces healthcare costs.

In an embodiment, the processing arrangement is configured to analyse the wound images irrespective of the user's base colour. The term "base colour" refers to the natural pigmentation of a user's skin, which can vary widely across individuals due to factors such as ethnicity, melanin levels, and environmental exposure. It may be appreciated that variations in skin pigmentation can affect the appearance of wounds in images, making it difficult for traditional diagnostic tools to accurately assess wound conditions. For example, redness or erythema, a common indicator of inflammation, may appear less pronounced on darker skin tones compared to lighter skin tones. Similarly, discoloration or changes in wound margins may be harder to detect on highly pigmented skin. In other words, subtle changes in wound colour or texture may be obscured by the underlying skin tone.

The processing arrangement is specifically designed to analyse wound images accurately, irrespective of the user's base skin colour, by, optionally, leveraging advanced Al techniques and diverse training datasets. In this regard, the Al algorithm is trained to focus on woundspecific features rather than being influenced by the surrounding skin tone. Such wound-specific features include, but do not limit to, wound margins, texture changes, colour variations within the wound itself (e.g., redness, necrosis, or exudate), and fluorescence patterns (if applicable, such as in case of identifying specific microbial species). Beneficially, by isolating the wound-specific features, the Al algorithm minimizes the impact of skin pigmentation on its analysis.

Diverse training datasets include wound images from individuals with a wide range of skin tones and in variations in lighting conditions and image quality, for training the Al algorithm; as well as microbial data set, ensuring that it learns to recognize wound characteristics across all pigmentation levels. The inclusion of diverse wound images and microbial species ensures that the algorithm can handle variations in skin tone, wound type, and environmental conditions. This makes the system more inclusive and effective for a wide range of users.

Optionally, to ensure inclusivity and minimize bias related to skin tone, established classification scales such as the Fitzpatrick scale, Monk scale, and so on may be utilized. Additionally, a customized Al-driven classification system leveraging computer vision may be utilized to accurately assess wounds across diverse skin tones. In this regard, the custom Al-driven classification system can further improve inclusivity by automatically detecting skin tone from images instead of relying on manual classification. Moreover, the custom Al-driven classification system can enhance wound contrast based on skin pigmentation, using adaptive image processing techniques (e.g., color normalization, contrast adjustments). Furthermore, the custom Al-driven classification system may leverage deep learning to compare wounds across different tones, learning from a large dataset of diverse wound images.

Moreover, the processing arrangement may leverage image preprocessing techniques, namely, image normalization and colour correction techniques, to standardize the appearance of wound images before analysis. Furthermore, the processing arrangement may leverage advanced feature extraction methods to identify wound-specific characteristics, such as edges and contours of the wound, changes in texture or surface irregularities, colour gradients within the wound area, and so on. Furthermore, the system undergoes thorough validation and testing to ensure its accuracy across diverse skin tones. Such validation and testing include comparative studies to evaluate performance on different skin tones, receiving feedback from healthcare professionals to refine the algorithm, and so on.

Beneficially, by leveraging diverse training datasets, advanced Al techniques, and image preprocessing methods, the system eliminates bias and promotes equitable healthcare outcomes.

In an embodiment, the system further comprises a memory unit to store at least one of: the captured wound images, the wound assessment report, the recommendations for wound care and management. The memory unit serves as a data storage component that enables the system to store and manage critical information related to wound monitoring and care. The memory unit ensures that the system can retain and manage essential information, such as wound images, wound assessment reports, and care recommendations, for future reference, analysis, and sharing. Optionally, the memory unit can be implemented using various storage technologies, depending on the system's design and requirements. For example, the memory unit can be implemented as a local storage (data stored directly on the users device (e.g., smartphone or tablet) or on a dedicated hardware component within the system); cloud storage (data is uploaded to a secure cloud server, enabling remote access and scalability); or hybrid storage (combination of local and cloud storage, where critical data is stored locally for quick access, and backups are maintained in the cloud).

Optionally, the memory unit organizes data into structured categories, such as patient profiles, chronological records of wound images and reports, or recommendations and alerts, to ensure efficient retrieval and management of data.

Optionally, the data stored in the memory unit is encrypted to prevent unauthorized access. The memory unit is provided with access control to restrict its access only to authorized users, such as the patient and their healthcare provider. The memory unit is compliant with data privacy regulations, such as HIPAA (Health Insurance Portability and Accountability Act) or GDPR (General Data Protection Regulation). Optionally, the system includes mechanisms for regular data backups to prevent loss due to hardware failure or other issues. Recovery protocols ensure that data can be restored in case of accidental deletion or corruption.

The present disclosure also relates to the method as described above. Various embodiments and variants disclosed above, with respect to the aforementioned system, apply mutatis mutandis to the method.

In an embodiment, the step of analysing the wound images comprises identifying key indicators selected from at least one of: margins, colour, size, inflammation, and signs of healing, infection or complications in the wound, detecting and identifying specific microbial species associated with the inflammation and/or infection in the wound.

In an embodiment, the method further comprises illuminating the wound, using a light source, to emit fluorescence patterns in the microbial species in the wound, prior to capturing the wound images.

In an embodiment, the method further comprises analysing fluorescence patterns captured in the wound image, for detecting at least one microbial species associated with the inflammation and/or infection in the wound.

In an embodiment, the method further comprises training the Al algorithm on a dataset of wound images and a dataset of microbial species.

In an embodiment, the Al algorithm employs deep learning techniques to compare the received wound images against a dataset of wound images and a dataset of microbial species.

In an embodiment, the method further comprises integrating with at least one of: electronic health records (EHR.), telehealth platforms, for transmitting the wound assessment report with a healthcare professional for subsequent analysis.

In an embodiment, the method further comprises storing in a memory unit at least one of: the captured wound images, the wound assessment report, the recommendations for wound care and management.

The present disclosure also relates to the non-transitory computer- readable storage medium as described above. Various embodiments and variants disclosed above, with respect to the aforementioned system and the aforementioned method, apply mutatis mutandis to the non- transitory computer-readable storage medium. EXPERIMENTAL PART

The disclosed system and method are versatile and applicable in various settings, including hospitals for post-surgical monitoring, outpatient clinics, and at-home patient care. It is particularly beneficial for patients who have limited mobility or live in remote areas. The system is also crucial in situations like the COVID-19 pandemic, where minimizing in- person contact is vital. It enables healthcare providers to remotely monitor wound healing, promptly identify any complications, and adjust treatment plans accordingly.

Post-Surgical Monitoring in Hospitals: In an implementation, the disclosed system and method was used by patients recovering from surgery to regularly monitor their wound healing progress and detect any signs of infection. This was particularly useful in reducing the risk of postoperative complications.

Home Care for Chronic Wounds: In another implementation, the disclosed system and method was beneficial for patients with chronic wounds, such as diabetic ulcers, who required regular monitoring. The system allowed them to keep track of their wound status at home, reducing frequent visits to healthcare providers.

Remote Area Healthcare: In yet another implementation, the disclosed system and method was used in rural or remote areas where access to healthcare facilities is limited. The system provided crucial support in wound management, enabling local healthcare workers or patients themselves to monitor wound healing and detect infections early.

Telemedicine Applications: In still another implementation, the disclosed system and method was integrated with telehealth platforms, to be used by healthcare providers to remotely assess a patient's wound condition and make informed decisions about treatment, enhancing the efficiency and reach of telemedicine services. DETAILED DESCRIPTION OF THE DRAWINGS

Referring to FIG. 1, illustrated is a system 100 for monitoring wound healing, in accordance with an embodiment of the present disclosure. The system 100 comprises an imaging unit 102 for capturing wound images over a predefined period of time; and a software application comprising a user interface 104 and a processing arrangement 106, wherein the processing arrangement 106 is configured to: receive, via the user interface, wound images captured by the imaging unit 102; analyse the received wound images using an artificial intelligence (Al) algorithm; generate a wound assessment report based on the analysis by the Al algorithm; and transmit, via the user interface, the wound assessment report. The user interface 104 is further configured to: receive inputs associated with at least one of: self-assessment of the wound healing, and customisation of one or more analysis parameters based on a wound type and user needs; and transmit at least one of: recommendations for wound care and management, guidance for capturing and uploading wound images, and alert notifications for potential complications. As shown, the user interface is hosted on a user device implemented as a mobile device 108. As shown, the processing arrangement 106 and the imaging unit 102 and the user interface 104 are communicably coupled over a communication network 110.

Referring to FIG. 2, illustrated is a method for monitoring wound healing, in accordance with an embodiment of the present disclosure. At step 202, wound images are captured using an imaging unit. At step 204, a software application comprising a user interface and a processing arrangement is initiated. At step 206, wound images captured by the imaging unit are received, via the user interface, by the processing arrangement. At step 208, the received wound images are analysed, using an artificial intelligence (Al) algorithm executed by the processing arrangement. At step 210, a wound assessment report is generated, by the processing arrangement, based on the analysis by the Al algorithm. At step 212, the wound assessment report is transmitted, by the user interface.

Claims

1. A system (100) for monitoring wound healing, the system comprising: an imaging unit (102) for capturing wound images over a predefined period of time; and a software application comprising a user interface (14) and a processing arrangement (106), wherein the processing arrangement is configured to: receive, via the user interface, wound images captured by the imaging unit; analyse the received wound images using an artificial intelligence (Al) algorithm; generating generate a wound assessment report based on the analysis by the Al algorithm; and transmit, via the user interface, the wound assessment report.

2. A system (100) of claim 1, wherein the user interface (104) is further configured to: receive inputs associated with at least one of: self-assessment of the wound healing, and customisation customization of one or more analysis parameters based on a wound type and user needs; and transmit at least one of: recommendations for wound care and management, guidance for capturing and uploading wound images, and alert notifications for potential complications.

3. A system (100) of claim 1 or 2, wherein the software application is further configured to provide an interactive platform for multiple users to connect for advice and support in wound care and management.

4. A system (100) of any of the preceding claims, wherein the software application is further configured to be operated in multiple languages, and wherein the wound assessment report is accessible in multiple languages.

5. A system (100) of any of the preceding claims, wherein the processing arrangement (106) is configured to analyse the wound images for identifying key indicators selected from at least one of: margins, colour, size, inflammation, and signs of healing, infection or complications in the wound.

6. A system (100) of claim 5, wherein the processing arrangement (106) is further configured to detect and identify specific microbial species associated with the inflammation and/or infection in the wound.

7. A system (100) of claim 6, wherein the microbial species includes any of: bacterial, fungi, protozoa, virus, archaea.

8. A system (100) of claim 5 to 7, further comprising a light source configured to illuminate the wound to emit fluorescence patterns in the microbial species in the wound, prior to capturing the wound images.

9. A system (100) of claim 5 to 8, wherein the processing arrangement (106) is configured to analyse fluorescence patterns captured in the wound image, for detecting at least one microbial species associated with the inflammation and/or infection in the wound.

10. A system (100) of claim 5 to 9, further comprising an image processing modules for maintaining image quality in varying lighting conditions, wherein the image processing module is implemented as an Al-aided image processing module.

11. A system (100) of claims 5-8, wherein the Al algorithm is trained on a dataset of wound images and a dataset of microbial species.

12. A system (100) of claim 9, wherein the Al algorithm employs deep learning techniques to compare the received wound images against a dataset of wound images and a dataset of microbial species.

13. A system (100) of any of the preceding claims, wherein the processing arrangement (106) is further configured to integrate with at least one of: electronic health records (EHR.), telehealth platforms, for transmitting the wound assessment report with a healthcare professional for subsequent analysis.

14. A system (100) of any of the preceding claims, wherein the processing arrangement is configured to analyse the wound images irrespective of the user's base colour.

15. A system (100) of claim 2-12, further comprising a memory unit (112) to store at least one of: the captured wound images, the wound assessment report, the recommendations for wound care and management.

16. A system (100) of any of the preceding claims, wherein the wound images are captured using an imaging unit (102) associated with any of: a mobile device (108), the software application, and wherein the imaging unit is implemented as an Al-aided imaging unit, and wherein the wound images include a corresponding wound area and surrounding tissues.

17. A system (100) of any of the preceding claims, wherein the wound is selected from at least one of: an acute wound, a chronic wound.

18. A method for monitoring wound healing, the method comprising : capturing wound images using an imaging unit; initiating a software application comprising a user interface and a processing arrangement; receiving, via the user interface, by the processing arrangement, wound images captured by the imaging unit; analysing, using an artificial intelligence (Al) algorithm executed by the processing arrangement, the received wound images; generating, by the processing arrangement, a wound assessment report based on the analysis by the Al algorithm; and transmitting, by the user interface, the wound assessment report.

19. A method of claim 18, wherein the step of analysing the wound images comprises identifying key indicators selected from at least one of: margins, colour, size, inflammation, and signs of healing, infection or complications in the wound, detecting and identifying specific microbial species associated with the inflammation and/or infection in the wound.

20. A method of claim 19, further comprising illuminating the wound, using a light source, to emit fluorescence patterns in the microbial species in the wound, prior to capturing the wound images.

21. A method of claim 20, further comprising analysing fluorescence patterns captured in the wound image, for detecting at least one microbial species associated with the inflammation and/or infection in the wound.

22 A method of claims 18-21, further comprising training the Al algorithm on a dataset of wound images and a dataset of microbial species.

23. A method of claim 22, wherein the Al algorithm employs deep learning techniques to compare the received wound images against a dataset of wound images and a dataset of microbial species.

24. A method of claims 18-25, further comprising integrating with at least one of: electronic health records (EHR.), telehealth platforms, for transmitting the wound assessment report with a healthcare professional for subsequent analysis.

25. A method of claim 19-24, further comprising storing in a memory unit at least one of: the captured wound images, the wound assessment report, the recommendations for wound care and management.

26. A non-transitory computer-readable storage medium having computer-readable instructions stored thereon, the computer-readable instructions being executable by a computerized device comprising processing hardware to execute a method as claimed in any one of claims 18 to 25.