Pressure damage decision support system and processing method thereof

Abstract

The invention provides a pressure injury decision support system and a processing method thereof, which are used for providing a specific module configuration scheme for clinical work of pressure injury under the condition of creating an integrated and automatic decision support system. According to the method, comprehensive decision support can be provided for the risk, identification and intervention of the stress injury of the patient, accurate automatic data support work is realized, and more effective prevention and treatment of the stress injury are facilitated, so that the stress injury management level in clinical work is improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a pressure injury decision support system and a processing method thereof. Background Art

[0002] Pressure injury is a localized injury to the skin and subcutaneous soft tissue caused by severe or prolonged pressure or pressure combined with shear force. In actual situations, it usually significantly affects the patient's recovery and quality of life.

[0003] Currently, the assessment, identification and treatment of pressure injuries in medical institutions mainly rely on the experience and manual operations of medical staff. This method is inefficient and carries the risk of misdiagnosis and delayed treatment.

[0004] Therefore, there is an urgent need for an integrated and automated decision support system to provide accurate data support for medical staff in the clinical work of pressure injuries. Summary of the invention

[0005] The present application provides a pressure injury decision support system and a processing method thereof, which are used for clinical work on pressure injuries. While building an integrated and automated decision support system, a specific module configuration scheme is provided, which can provide comprehensive decision support for the risk, identification and intervention of pressure injuries for patients, realize accurate automated data support work, and contribute to more effective prevention and treatment of pressure injuries, thereby improving the level of pressure injury management in clinical work.

[0006] In a first aspect, the present application provides a pressure injury decision support system, the pressure injury risk decision support system includes a pressure injury risk assessment module, a high-risk patient identification module and a pressure injury intervention measure module;

[0007] The pressure injury risk assessment module performs pressure injury risk assessment processing based on the patient data under the preset risk assessment indicators to obtain the corresponding risk assessment results;

[0008] The high-risk patient identification module performs high-risk identification processing based on the risk assessment results output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm, obtains corresponding high-risk identification results, and issues reminders and generates corresponding preventive measures when high-risk situations exist;

[0009] The pressure injury intervention measures module performs pressure injury staging based on the input pressure injury image, obtains the corresponding pressure injury staging results, and generates corresponding intervention measures recommendations based on the pressure injury staging results.

[0010] In a second aspect, the present application provides a processing method for a pressure injury decision support system, the processing method for a pressure injury decision support system is applied to a pressure injury decision support system, the pressure injury risk decision support system includes a pressure injury risk assessment module, a high-risk patient identification module and a pressure injury intervention measure module, the processing method for the pressure injury decision support system includes:

[0011] The pressure injury risk assessment module performs pressure injury risk assessment processing based on the patient data under the preset risk assessment indicators to obtain the corresponding risk assessment results;

[0012] The high-risk patient identification module performs high-risk identification processing based on the risk assessment results output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm, obtains corresponding high-risk identification results, and issues reminders and generates corresponding preventive measures when high-risk situations exist;

[0013] The pressure injury intervention measures module performs pressure injury staging based on the input pressure injury image and obtains the corresponding pressure injury staging results;

[0014] The pressure injury intervention measures module generates corresponding intervention measures recommendations based on the pressure injury staging results, combined with historical risk assessment results and corresponding real-time risk assessment results.

[0015] In a third aspect, the present application provides a computer-readable storage medium, which stores a plurality of instructions, and the instructions are suitable for loading by a processor to execute the method provided in the second aspect of the present application.

[0016] From the above content, it can be concluded that the present application has the following beneficial effects:

[0017] For the clinical work of pressure injuries, the pressure injury risk decision support system configured in the present application is composed of a pressure injury risk assessment module, which performs pressure injury risk assessment processing based on patient data under preset risk assessment indicators to obtain corresponding risk assessment results. The high-risk patient identification module performs high-risk identification processing based on the risk assessment results output by the pressure injury risk assessment module, through a high-risk patient identification model pre-configured by a machine learning algorithm, to obtain corresponding high-risk identification results, and gives reminders when high-risk situations exist. The pressure injury intervention measures module performs pressure injury staging processing based on the input pressure injury image to obtain corresponding pressure injury staging results, and generates corresponding intervention measures recommendations based on the pressure injury staging results. In the system setting content, the present application provides a specific module configuration scheme while creating an integrated and automated decision support system, which can provide comprehensive decision support for the risk, identification and intervention of pressure injuries for patients, realize accurate automated data support work, and help to prevent and treat pressure injuries more effectively, thereby improving the level of pressure injury management in clinical work. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of a system architecture of a pressure injury decision support system for this application;

[0020] Figure 2 A flowchart of a processing method of a pressure injury decision support system of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0022] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0023] The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

[0024] First, see Figure 1 , Figure 1 A schematic diagram of the system architecture of the pressure injury decision support system of the present application is shown. Figure 1 It can be clearly seen that the pressure injury risk decision support system provided in this application can specifically include three modules: a pressure injury risk assessment module, a high-risk patient identification module and a pressure injury intervention measures module.

[0025] In specific applications, it can be understood that the pressure injury risk decision support system provided by the present application can be configured in the form of a device or a device cluster, for example, it can be configured by a server cluster consisting of a server device or multiple server devices. Of course, for the device cluster, the specific devices involved can be different types of devices. Typically, it can involve the front-end and back-end architectural design. The front end is usually different types of terminal devices such as smart phones, tablet computers, personal digital assistants (PDA), and the back end is a server device. Alternatively, it can also be divided according to the deployment scenario / location. These can obviously be flexibly configured according to the actual situation. Therefore, in terms of the specific hardware structure, this application does not make specific limitations.

[0026] In this case, it can be seen that the three modules of the pressure injury risk assessment module, the high-risk patient identification module and the pressure injury intervention measures module included in the pressure injury risk decision support system of this application are mainly considered from the perspective of functional services, rather than saying that these three modules are different hardware devices.

[0027] In specific applications, the division of the three modules, namely, the pressure injury risk assessment module, the high-risk patient identification module and the pressure injury intervention measures module, will help to achieve a good division of labor in the functional services that can be provided by the pressure injury risk decision support system of this application, thereby facilitating the development and maintenance of functional services as well as the efficient operation of functional services.

[0028] Based on the above brief description of the hardware structure, the functional services that can be provided by the pressure injury risk decision support system of the present application are further described.

[0029] In brief, the pressure injury risk decision support system provided in this application includes the following work contents:

[0030] (1) The pressure injury risk assessment module performs pressure injury risk assessment processing based on the patient data under the preset risk assessment indicators to obtain the corresponding risk assessment results.

[0031] It can be seen that the present application involves the assessment and processing of the risk of pressure injury before it occurs, so as to understand the risk of subsequent pressure injury of the current patient, which helps to prevent it before it happens. In the case of no pressure injury, preventive work can be carried out in time to avoid the occurrence of pressure injury, thereby well protecting the patient's recovery and quality of life.

[0032] Among them, the preset risk assessment indicators involved here refer to relevant indicators that can reflect or quantify the risk of pressure injuries. These indicators are usually predetermined and may involve aspects such as age, weight, specific activity ability, and specific nutritional status.

[0033] After obtaining the patient data of the current patient under the preset risk assessment indicators, the corresponding pressure injury risk assessment process can be carried out to form a corresponding risk assessment result.

[0034] It should be noted that the risk assessment result is not simply indicated by a risk quantification value or risk level, but on the basis of the risk quantification value or risk level, it also includes the content of the patient data under the original preset risk assessment indicators, so as to provide data support for the subsequent high-risk identification process. Therefore, the risk assessment results made here can also be understood as pre-processing of patient data, involving the assessment of the initial pressure injury risk, the main purpose of which is to process the patient data into input data for the subsequent high-risk identification process.

[0035] Specifically, as an example, the pressure injury risk assessment module can display an input interface to the current patient or medical staff through a web service or a local service for manual entry of patient data.

[0036] Alternatively, as another example, the pressure injury risk assessment module may provide a data import interface, which allows patients or medical staff to directly upload files carrying patient data, or directly upload patient data files.

[0037] Alternatively, as another example, the pressure injury risk assessment module can automatically extract data through a preset data interface to efficiently and automatically extract patient data from a database pre-stored in the pressure injury risk decision support system or a related business system (such as a hospital information system (HIS)).

[0038] Obviously, the specific acquisition of patient data is relatively flexible, and different acquisition methods can be configured according to actual conditions / specific application requirements. For example, the three methods listed above correspond to manual input method, data import method and interface docking method respectively.

[0039] In addition, as another example, the patient data can be configured in terms of data content and form using the Braden scale or the Norton scale, both of which are commonly used scales in clinical work. This makes it easy to operate and implement the program.

[0040] In addition, the pressure injury risk assessment module can also proactively collect patient data through relevant vital sign monitoring equipment.

[0041] Furthermore, in the process of obtaining patient data, data verification and automatic completion functions can also be supported to improve input accuracy and efficiency.

[0042] (2) The high-risk patient identification module performs high-risk identification processing based on the risk assessment results output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm, obtains the corresponding high-risk identification results, and issues reminders and generates corresponding preventive measures when high-risk situations exist.

[0043] It can be seen that the present application has designed a high-risk identification setting for the occurrence of pressure injuries. This helps to screen out patients with a high probability of developing pressure injuries in the future when no pressure injuries have occurred. These patients can be given key reminders and corresponding preventive measures can be recommended. This helps to carry out preventive work in a timely manner, avoid the occurrence of pressure injuries, and well protect the rehabilitation and quality of life of these patients.

[0044] This design involves the application of artificial intelligence (AI) technology, which uses a pre-configured machine learning algorithm to efficiently and accurately carry out high-risk identification and processing. It is worth noting that the input data for the high-risk identification and processing carried out here is specifically the risk assessment result output by the previous pressure injury risk assessment module, and the risk assessment result is the data analyzed / processed by the previous pressure injury risk assessment module for the original patient data. Therefore, when the linkage module is used to implement high-risk identification and processing, it also has a more efficient and accurate identification and processing effect.

[0045] For the high-risk patient identification model configured by a machine learning algorithm, the specific algorithm type used is obviously more flexible and can be configured according to actual needs, such as a decision tree algorithm, a support vector machine algorithm, a neural network algorithm, etc. For the neural network algorithm, a deep learning algorithm can also be used.

[0046] Among them, it is understandable that for the specific machine learning algorithm used in the high-risk patient identification model, it is possible to use existing algorithms, optimize and improve on the basis of existing algorithms, or use novel self-developed algorithms. These are all possible in actual situations.

[0047] Taking the neural network algorithm as an example, the pre-configuration process of the high-risk patient identification model mainly involves model training, and the model training architecture and loss function used in it also have the characteristics of the above machine learning algorithm.

[0048] Taking the neural network algorithm as an example, for model training, there are usually the following contents:

[0049] In each round of model training, the training samples (sample risk assessment results) are input into the model, so that the model can carry out the corresponding high-risk identification processing and realize forward propagation. Then, based on the high-risk identification results output by the model and the high-risk identification results of the samples annotated by the training samples themselves, the loss function is calculated, and the model parameters are optimized based on the loss function calculation results to realize back propagation. In this way, when the preset model training conditions such as training duration, number of trainings or prediction accuracy are met, the model training can be completed. At this time, the model is recorded as a high-risk patient identification model that can be put into practical use.

[0050] It can be understood that the high-risk identification results output by the high-risk patient identification model are mainly divided into two categories, one corresponding to low-risk situations or normal situations, and the other corresponding to high-risk situations.

[0051] When a high-risk situation occurs or is indicated, the high-risk patient identification module can provide reminders and generate corresponding preventive measures recommendations to play a good preventive function / role.

[0052] In specific operations, reminder operations may involve one or more methods, such as system alarms, SMS notifications, emails, public account push and AI voice calls, to promptly remind patients or medical staff; and preventive measures recommendations may involve recommendations on body position changes, mainly starting from the goal of preventing the occurrence of pressure injuries. When necessary, it may also involve intervention measures that can be taken when pressure injuries occur, such as drug treatment recommendations, decompression equipment use recommendations, or local wound care recommendations.

[0053] (3) The pressure injury intervention measures module performs pressure injury staging based on the input pressure injury image, obtains the corresponding pressure injury staging results, and generates corresponding intervention measures recommendations based on the pressure injury staging results.

[0054] It can be seen that the pressure injury intervention measures module in the system focuses on the situation of pressure injury in patients, and uses the corresponding image recognition model to carry out pressure injury staging processing on the pressure injury images collected at the location where the pressure injury occurs in the patient, so as to determine the specific stage of the pressure injury that occurs in the patient and form the corresponding pressure injury staging results. In addition, the corresponding intervention measures recommendations can be generated based on the analyzed pressure injury staging results, providing sufficient recommendations for the treatment of pressure injuries.

[0055] It is easy to understand that for the image recognition technology to identify the pressure injuries in the input image and to perform staging based on the identified pressure injuries, the preliminary processing of the image recognition model can refer to the content of the previous neural network model.

[0056] In this way, when a patient suffers from pressure injury, the system can achieve good decision support effects for the treatment of pressure injury through the pressure injury intervention measures module.

[0057] For the above scheme content, in short, for the clinical work of pressure injury, the pressure injury risk decision support system configured in the present application is composed of a pressure injury risk assessment module, based on the patient data under the preset risk assessment indicators, to perform pressure injury risk assessment processing to obtain the corresponding risk assessment results; a high-risk patient identification module, based on the risk assessment results output by the pressure injury risk assessment module, performs high-risk identification processing through a high-risk patient identification model pre-configured by a machine learning algorithm to obtain the corresponding high-risk identification results, and gives a reminder when a high-risk situation exists; a pressure injury intervention measure module performs pressure injury staging processing based on the input pressure injury image to obtain the corresponding pressure injury staging results, and generates corresponding intervention measure recommendations based on the pressure injury staging results. In the system setting content, the present application provides a specific module configuration scheme while creating an integrated and automated decision support system, which can provide all-round decision support for the risk, identification and intervention of pressure injuries for patients, realize accurate automated data support work, and help to prevent and treat pressure injuries more effectively, thereby improving the level of pressure injury management in clinical work.

[0058] Continue to the above Figure 1 Each step of the illustrated embodiment and possible implementation methods thereof in practical applications are described in detail.

[0059] Focusing on the situation where the patient has pressure injury, or in other words, for the pressure injury intervention measure module, as an exemplary embodiment, the pressure injury intervention measure module performs pressure injury staging based on the input pressure injury image to obtain the corresponding pressure injury staging result, which may specifically include:

[0060] The pressure injury intervention measure module analyzes the injury image features of the input pressure injury image, wherein the injury image features include injury morphology, injury color and injury area;

[0061] The pressure injury intervention measures module performs pressure injury staging based on the injury image features and obtains the corresponding pressure injury staging results.

[0062] It can be understood that in the image recognition process of pressure injuries, the present application may specifically involve the analysis and processing of injury image features including injury morphology, injury color and injury area (i.e., feature recognition processing), and then carry out accurate pressure injury staging treatment based on this.

[0063] In addition, for the staging treatment involved in the present application, as an exemplary embodiment, the staging range of the pressure injury staging results can specifically include 6 types, namely, stage 1, stage 2, stage 3, stage 4, deep tissue injury and unstageable.

[0064] Specifically, the performance and characteristics of Phase 1 are:

[0065] (1) Non-blanchable erythema, intact skin, and localized skin intact. If erythema that does not blanch under pressure appears, dark skin may show different symptoms; erythema that blanchs under pressure or changes in sensation, skin temperature, or hardness may appear before skin changes are observed. Color changes at this stage do not include purple or maroon changes, which may indicate deep tissue damage.

[0066] (2) The manifestations and characteristics of stage 2 are:

[0067] Partial skin loss with exposed dermis. The wound bed is active, pink or red, moist, or presents as intact or broken serous blisters, with no exposure of fat and deep tissue, and no granulation tissue, slough, or eschar.

[0068] (3) The manifestations and characteristics of stage 3 are:

[0069] Full-thickness skin is lost, fat is visible at the ulcer site, granulation tissue and wound curling are common, and slough, eschar, undermining or sinus tracts may be present. Fascia, muscle, tendon, ligament, cartilage or bone are not visible. Note: In this stage, the bridge of the nose, auricle, occipital area, ankles, etc. may present as superficial ulcers due to the lack of subcutaneous tissue, and will not develop stage 3 pressure injuries.

[0070] (4) The manifestations and characteristics of stage 4 are:

[0071] Full-thickness skin and tissue loss, with visible or directly palpable fascia, muscle, tendon, ligament, cartilage, or bone at the site of the ulcer, visible slough and / or eschar, and often with rolled edges, sinus tracts, and / or undermining. If slough or necrotic tissue obscures the extent of tissue loss, an indeterminate pressure injury has occurred.

[0072] (5) The manifestations and characteristics of deep tissue injury include:

[0073] A persistent, non-blanchable dark red, maroon, or purple color of intact or partially lost skin, or separation of the epidermis to reveal a dark wound bed or blood-filled blister. Pain and temperature changes usually precede color changes, and darker skin may show different color. The wound may progress rapidly, revealing the actual extent of tissue damage, or may resolve without tissue damage. If necrotic tissue, subcutaneous tissue, granulation tissue, fascia, muscle, or other deeper structures are present, it indicates full-thickness tissue damage (Unstageable, Stage 3, or Stage 4). This stage of injury is not used to describe vascular, traumatic, neuropathic wounds, and skin diseases.

[0074] (6) The manifestations and characteristics of non-stageable are:

[0075] Full-thickness skin and tissue loss, the wound bed is covered by slough and / or eschar, the extent of tissue loss cannot be identified, and the wound base is completely covered by slough and / or eschar. The slough or eschar on the surface of this stage masks the extent of tissue damage, and once the slough or necrotic tissue is removed, it will present a stage 3 or 4 pressure injury.

[0076] In addition, for the intervention measures recommendations generated based on the pressure injury staging results, it can be understood that different stages have different specific measures recommendations.

[0077] As an exemplary embodiment, the above six types of pressure injury staging results each include corresponding specific intervention measures recommendations, and the specific intervention measures recommendations include four aspects: position change recommendations, drug treatment recommendations, decompression equipment use recommendations and local wound care recommendations.

[0078] Specifically, the conventional intervention measures recommended for phase (1)1 are:

[0079] The skin tissue structure and function at this stage have not been damaged and are in a reversible change. Relieving local pressure, turning the patient over regularly, improving local blood circulation, and removing risk factors can prevent the further development of pressure injuries.

[0080] 1. Local decompression: turn over to avoid continuous pressure, and do not massage the red areas and bone protrusions; 2. Decompression equipment: use air mattress / water mattress, turning pillow, functional dressing; 3. Foot decompression, long-term bedridden patients use heel lifts, foam pads, etc. to prevent pressure injuries, and the knee joint is slightly flexed (5-10°); 4. Liquid dressing spraying: spray Sai Fu Run and other liquids on the skin red, tender or pressure prevention areas, pat gently to promote absorption, and repair damaged skin; 5. Foam dressing, hydrocolloid dressing or transparent decompression patch protection: choose a dressing that is 2-3 cm larger than the red skin to promote blood stasis absorption and soften nodules. In addition, although the intervention measures recommended in stage 1 here are aimed at relatively mild (stage 1) pressure injuries, they are also applicable to the subsequent stages 2, 3 and deep tissue injuries, that is, they can be superimposed with the conventional intervention measures recommended in the subsequent stages 2, 3 and deep tissue injuries, and the corresponding measures should be used as much as possible in actual situations.

[0081] (2) Recommendations for routine intervention measures in phase 2 include:

[0082] Local decompression protects the wound surface, prevents blisters from rupturing, and prevents infection.

[0083] For those with damaged epidermis, clean the wound with saline solution:

[0084] 1. When the exudate is small, cover with hydrocolloid dressing and change it every 2 to 3 days; 2. When the exudate is moderate or large, cover with foam dressing and change it every 3 to 5 days;

[0085] Blisters:

[0086] 1. If the diameter of the blister is less than 2cm, local disinfection should be performed and the blister should be covered with a hydrocolloid dressing to promote self-absorption. 2. If the diameter of the blister is ≥2cm, local disinfection should be performed and aspiration should be performed at the lowest point of the blister with a sterile scalp needle, and the scab should be retained and covered with a hydrocolloid dressing. When more fluid appears in the blister again, the exudate should be aspirated after disinfection on the outside of the dressing. 3. If the blister ruptures, the inactivated blister skin should be cleaned and covered with a hydrocolloid dressing. 4. Dressing change: depending on the amount of exudate, the dressing should be changed every 3 days or so. 5. If there is no exudate on the wound and the base is red, it is the process of epidermal growth and should be protected with a hydrocolloid dressing or a transparent pressure relief patch.

[0087] Note: If this stage is not treated and cared for in time, it will quickly develop into stage 3 to 4.

[0088] (3) The recommended routine intervention measures for phase 3 are:

[0089] Remove necrotic tissue, control infection, promote granulation growth, and protect new tissue.

[0090] 1. Clean the wound with normal saline; 2. Mechanical debridement: remove dead flesh under the principle of sterility and turn the wound bed red; 3. Provide an environment conducive to wound healing: alginate filling + outer foam dressing / hydrocolloid dressing; 4. Infected / suspected infected wounds: use antibacterial dressings on the inner layer, and the outer layer is prohibited from being covered with edged foam dressings. Gauze, cotton pads or edgeless foam dressings can be used to cover; 5. Apply for consultation with a wound professional team.

[0091] (4) Recommendations for routine intervention measures for stage 4 include:

[0092] 1. Clean the wound with normal saline; 2. Mechanical debridement: remove dead flesh under the principle of sterility; 3. Autolytic debridement: use hydrogel dressings on exposed bones and tendons; 4. Provide an environment conducive to wound healing: alginate filling + outer foam dressing / hydrocolloid dressing; 5. For infected / suspected infected patients: use antibacterial dressings on the inner layer, and the outer layer is prohibited from being covered with edged foam dressings. Gauze, cotton pads or edgeless foam dressings can be used for coverage; 6. Apply for consultation with a wound professional team.

[0093] (5) Recommended conventional intervention measures for deep tissue injuries include:

[0094] Handle with caution and request consultation with a wound care team.

[0095] 1. Local decompression: Pay attention to body position to avoid pressure on bony prominences that have erythema that does not turn white when pressed. Do not massage or use air rings locally. 2. Drink enough water to avoid dry skin. 3. Change the dressing under the guidance of the wound nurse.

[0096] (6) Recommendations for routine interventions that cannot be staged include:

[0097] Debridement, decompression, and infection control.

[0098] 1. Clean the wound with normal saline; 2. Mechanical debridement: conservative debridement, remove necrotic tissue, slough, and hard scab, and avoid excessive debridement; if the eschar is stable (dry, complete, without erythema or fluctuation) in the ischemic lower limbs, ankles, feet, etc., it should be retained and should not be softened or removed; 3. Autolytic debridement: hydrogel debridement glue for moisturizing; 4. Wound coverage: hydrophilic fiber silver ion dressing + foam dressing + self-adhesive bandage; 5. After debridement, stage the wound and treat the pressure injury according to the corresponding stage; 6. Apply for consultation with the wound care professional team in time.

[0099] Next, we focus on the situation where the patient has not suffered pressure injury, or focus on the high-risk patient identification module. As an exemplary embodiment, the high-risk patient identification module performs high-risk identification processing based on the risk assessment result output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm to obtain a corresponding high-risk identification result, which may specifically include:

[0100] The high-risk patient identification module performs high-risk identification processing based on historical risk assessment results and corresponding real-time risk assessment results through a high-risk patient identification model to obtain corresponding high-risk identification results.

[0101] It can be understood that the risk assessment results obtained by the current pressure injury risk assessment module based on patient data correspond to the current / real-time situation, while the present application may involve the time dimension when performing high-risk identification processing, that is, high-risk identification processing can be carried out based on the risk assessment results obtained at different times, so as to better predict whether pressure injury will occur by capturing the characteristic changes in the time dimension, and achieve a more accurate prediction effect on the occurrence of pressure injury.

[0102] Under this design mechanism, the high-risk patient identification module can obtain the historical risk assessment results obtained previously (involving one or more historical time points), and combine them with the risk assessment results of the corresponding real-time situation to carry out high-precision high-risk identification processing and obtain corresponding high-risk identification results.

[0103] Furthermore, when the time dimension is introduced, the high-risk identification result processed by the high-risk patient identification module, as an exemplary embodiment, may include not only the risk situation of whether pressure injury occurs, but also the predicted time period for the pressure injury to occur.

[0104] It can be understood that the predicted time period of pressure injury can provide more accurate preventive measures for high-risk patients when no pressure injury actually occurs. At the same time, more accurate preventive measures can also be implemented, which can obviously play a better preventive role.

[0105] In addition, when the time dimension is introduced into the high-risk identification process, the present application can also configure the module linkage setting between the high-risk patient identification module and the pressure injury intervention measures module to further optimize the processing performance of the subsequent pressure injury intervention measures module.

[0106] Specifically, according to common sense, the input data required by the pressure injury intervention measure module for staging pressure injury treatment, that is, the pressure injury image, is collected after the patient suffers a pressure injury and goes to the hospital under the guidance of medical staff in the hospital.

[0107] While the present application provides all-round decision-making support for the risk, identification and intervention of pressure injuries for patients, in terms of details, the predicted time period of pressure injuries predicted by the high-risk patient identification module can be referred to to arrange the acquisition of pressure injury images and trigger pressure injury staging treatment and other treatments.

[0108] That is, as an exemplary embodiment, the pressure injury intervention measure module may collect pressure injury images according to the pressure injury predicted occurrence time period output by the high-risk patient identification module.

[0109] The specific image acquisition operation may involve manual operation, in which the pressure injury intervention measures module reminds the patient or medical staff to perform manual image acquisition, or may involve automatic operation, in which the pressure injury intervention measures module reminds the patient or medical staff to perform automatic image acquisition (i.e., the specific image acquisition is automatically completed by the system, and the patient needs to be instructed to come to the designated address of the hospital to perform it).

[0110] It can be understood that performing image acquisition according to the predicted time period of pressure injury does not necessarily require that the image acquisition be performed entirely within the predicted time period of pressure injury. Instead, the specific acquisition time point is determined with reference to the predicted time period of pressure injury, and the specific time point can be adjusted according to actual needs.

[0111] For example, the image may be collected at a time point that is a preset time span ahead of the pressure injury prediction period. For another example, the image may be collected at the central time point of the pressure injury prediction period. For another example, the image may be collected at a time point that is a preset time span behind the pressure injury prediction period. All of these are possible. After all, under the design of this scheme, the patient has not actually suffered a pressure injury yet. Image collection is arranged in advance for high-risk patients. Although the collected images are called pressure injury images, they may only have very mild pressure injury symptoms, or even no pressure injury symptoms. These are also possible in actual situations.

[0112] Furthermore, the determination of the specific image acquisition time point may also be independently determined / adjusted by the pressure injury intervention measure module.

[0113] Specifically, based on the predicted time period of pressure injury output by the high-risk patient identification module and combined with the patient data involved in the previous pressure injury risk assessment module, the time point can be fine-tuned to determine the specific image acquisition time point.

[0114] It can be understood that for patients with poor habits or physical conditions that are prone to pressure injuries, the image acquisition time point can be appropriately set forward. As mentioned earlier, the image acquisition time point can be preset before the pressure injury prediction period to perform the acquisition; and for patients with good habits or physical conditions that are not prone to pressure injuries, the image acquisition time point can be appropriately set backward. As mentioned earlier, the image acquisition time point can be preset after the pressure injury prediction period to perform the acquisition. If the habits or physical conditions tend to be normal, as mentioned earlier, the image acquisition time point can be used at the center of the pressure injury prediction period.

[0115] Under the above-mentioned scheme setting for the image acquisition time point, it can be understood that, in actual circumstances, it is helpful to perform image acquisition of pressure injuries at the first time or in the micro-early stage in response to the subsequent high probability of pressure injuries. This can not only urge patients not to perform image acquisition at a later date after the pressure injury occurs, but also greatly avoid patients delaying image acquisition due to lack of understanding of pressure injuries or various reasons (such as work, family, personal enthusiasm for medical treatment, etc., which may lead to late or even no medical treatment), but also ensure that image acquisition is performed as early as possible, and then treatment can be carried out as early as possible through the given intervention measures, taking into account the patient user experience, pressure injury prevention cost, pressure injury prevention quality, pressure injury treatment cost and pressure loss treatment quality, and has very good application value.

[0116] In addition, similar to the above method of combining patient data to determine the specific image acquisition time point, in the process of generating intervention measures recommendations by the pressure injury intervention measures module, the risk assessment results evaluated by the previous high-risk patient identification module can also be combined to perform fine-tuning of specific intervention measures recommendations (which can be considered as adjustments to one or more specific intervention measures recommendations under the same stage conditions) to obtain more personalized and more suitable intervention measures recommendations (i.e., customized intervention measures recommendations), thereby promoting more efficient and high-quality intervention effects for the pressure injuries that occur.

[0117] In this regard, as an exemplary embodiment, the pressure injury intervention measure module generates corresponding intervention measure suggestions based on the pressure injury staging results, which may specifically include:

[0118] The pressure injury intervention measures module generates corresponding intervention measures recommendations based on the pressure injury staging results, combined with historical risk assessment results and corresponding real-time risk assessment results.

[0119] It can be understood that in the process of generating intervention measures recommendations, not only can the risk assessment results based on the current real-time situation be used, but also the historical risk assessment results obtained previously (involving one or more historical time points) can be referred to. In this way, the consideration of the time dimension can be combined to better determine the appropriate intervention measures recommendations.

[0120] In addition, in actual applications, the generation strategy / model of intervention measures can also be combined with the intervention effect on the patient's pressure injury (the effect tracking itself is also involved in the treatment of pressure injuries) to adjust / optimize, so as to achieve the effect of dynamic update and maintenance to maintain effectiveness and accuracy. Similarly, the preventive measures mentioned above can also involve such operations.

[0121] The above is an introduction to the pressure injury decision support system provided by this application. Correspondingly, this application also provides a processing method for the pressure injury decision support system from the perspective of the system workflow. The processing method for the pressure injury decision support system is applied to the pressure injury decision support system. The pressure injury risk decision support system includes a pressure injury risk assessment module, a high-risk patient identification module, and a pressure injury intervention measure module. On this basis, refer to Figure 2 A flowchart of a processing method of a pressure injury decision support system of the present application is shown. The processing method of a pressure injury decision support system provided by the present application may specifically include the following steps S201 to S204:

[0122] Step S201, the pressure injury risk assessment module performs pressure injury risk assessment processing based on patient data under preset risk assessment indicators to obtain corresponding risk assessment results;

[0123] Step S202: The high-risk patient identification module performs high-risk identification processing based on the risk assessment result output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm to obtain a corresponding high-risk identification result, and issues a reminder when a high-risk situation exists and generates corresponding preventive measures suggestions;

[0124] Step S203, the pressure injury intervention measure module performs pressure injury staging processing based on the input pressure injury image to obtain a corresponding pressure injury staging result;

[0125] Step S204: the pressure injury intervention measure module generates corresponding intervention measure suggestions based on the pressure injury staging results, combined with the historical risk assessment results and the risk assessment results of the corresponding real-time situation.

[0126] In an exemplary embodiment, the pressure injury intervention measure module performs pressure injury staging processing based on the input pressure injury image to obtain corresponding pressure injury staging results, including:

[0127] The pressure injury intervention measure module analyzes the injury image features of the input pressure injury image, wherein the injury image features include injury morphology, injury color and injury area;

[0128] The pressure injury intervention measures module performs pressure injury staging based on the injury image features and obtains the corresponding pressure injury staging results.

[0129] In yet another exemplary embodiment, the staging range of the pressure injury staging result includes 6 types, namely, stage 1, stage 2, stage 3, stage 4, deep tissue injury, and unstageable.

[0130] In another exemplary embodiment, the six types of pressure injury staging results each include corresponding specific intervention measures recommendations, and the specific intervention measures recommendations include four aspects: body position change recommendations, drug treatment recommendations, decompression equipment use recommendations, and local wound care recommendations.

[0131] In another exemplary embodiment, the high-risk patient identification module performs high-risk identification processing based on the risk assessment result output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm to obtain a corresponding high-risk identification result, including:

[0132] The high-risk patient identification module performs high-risk identification processing based on historical risk assessment results and corresponding real-time risk assessment results through a high-risk patient identification model to obtain corresponding high-risk identification results.

[0133] In yet another exemplary embodiment, the high-risk identification result includes a predicted time period for the pressure injury to occur.

[0134] In yet another exemplary embodiment, the processing method of the pressure injury decision support system further includes:

[0135] The pressure injury intervention measure module collects pressure injury images according to the predicted time period of pressure injury output by the high-risk patient identification module.

[0136] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the processing method of the pressure injury decision support system described above can refer to the following. Figure 1 The description of the pressure injury decision support system in the corresponding embodiment will not be repeated here.

[0137] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0138] To this end, the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the present application as follows: Figure 2 The steps of the processing method of the pressure injury decision support system in the corresponding embodiment, the specific operation can be referred to as follows Figure 2 The description of the processing method of the pressure injury decision support system in the corresponding embodiment will not be repeated here.

[0139] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0140] Due to the instructions stored in the computer-readable storage medium, the present application can be executed. Figure 2 The steps of the processing method of the pressure injury decision support system in the corresponding embodiment, therefore, the present application can be implemented as follows Figure 2 The beneficial effects that can be achieved by the processing method of the pressure injury decision support system in the corresponding embodiment are detailed in the previous description and will not be repeated here.

[0141] The pressure injury decision support system, the processing method of the pressure injury decision support system and the computer-readable storage medium provided by the present application are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A pressure injury decision support system, characterized in that: The pressure injury risk decision support system includes a pressure injury risk assessment module, a high-risk patient identification module and a pressure injury intervention measure module; The pressure injury risk assessment module performs pressure injury risk assessment processing based on the patient data under the preset risk assessment indicators to obtain corresponding risk assessment results; The high-risk patient identification module performs high-risk identification processing based on the risk assessment result output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm to obtain a corresponding high-risk identification result, and when a high-risk situation exists, it reminds and generates corresponding preventive measures suggestions; The pressure injury intervention measure module performs pressure injury staging processing based on the input pressure injury image, obtains corresponding pressure injury staging results, and generates corresponding intervention measure suggestions based on the pressure injury staging results.

2. The pressure injury decision support system according to claim 1, characterized in that: The pressure injury intervention measure module performs pressure injury staging processing based on the input pressure injury image to obtain corresponding pressure injury staging results, including: The pressure injury intervention measure module analyzes the injury image features of the input pressure injury image, wherein the injury image features include injury morphology, injury color and injury area; The pressure injury intervention measure module performs pressure injury staging processing based on the injury image features to obtain the corresponding pressure injury staging results.

3. The pressure injury decision support system according to claim 2, characterized in that: The staging range of the pressure injury staging results includes 6 types, namely, stage 1, stage 2, stage 3, stage 4, deep tissue injury and unstageable.

4. The pressure injury decision support system according to claim 3, characterized in that: The 6 types of pressure injury staging results each include corresponding specific intervention measures recommendations, which include four aspects: body position change recommendations, drug treatment recommendations, decompression equipment use recommendations, and local wound care recommendations.

5. The pressure injury decision support system according to claim 1, characterized in that: The high-risk patient identification module performs high-risk identification processing based on the risk assessment result output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm to obtain a corresponding high-risk identification result, including: The high-risk patient identification module performs high-risk identification processing based on historical risk assessment results and the risk assessment results corresponding to real-time situations through the high-risk patient identification model to obtain the corresponding high-risk identification results.

6. The pressure injury decision support system according to claim 5, characterized in that: The high-risk identification result includes a predicted time period for the pressure injury to occur.

7. The pressure injury decision support system according to claim 6, characterized in that: The pressure injury intervention measure module collects the pressure injury image according to the pressure injury predicted occurrence time period output by the high-risk patient identification module.

8. The pressure injury decision support system according to claim 7, characterized in that: The pressure injury intervention measure module generates corresponding intervention measure suggestions based on the pressure injury staging results, including: The pressure injury intervention measure module generates the corresponding intervention measure suggestion based on the pressure injury staging result and in combination with the historical risk assessment result and the risk assessment result of the corresponding real-time situation.

9. A processing method of a pressure injury decision support system, characterized in that: The processing method of the pressure injury decision support system is applied to the pressure injury decision support system, the pressure injury risk decision support system includes a pressure injury risk assessment module, a high-risk patient identification module and a pressure injury intervention measure module, and the processing method of the pressure injury decision support system includes: The pressure injury risk assessment module performs pressure injury risk assessment processing based on the patient data under the preset risk assessment indicators to obtain corresponding risk assessment results; The high-risk patient identification module performs high-risk identification processing based on the risk assessment result output by the pressure injury risk assessment module through a high-risk patient identification model pre-configured by a machine learning algorithm to obtain a corresponding high-risk identification result, and when a high-risk situation exists, it reminds and generates corresponding preventive measures suggestions; The pressure injury intervention measure module performs pressure injury staging processing based on the input pressure injury image to obtain the corresponding pressure injury staging result; The pressure injury intervention measure module generates corresponding intervention measure suggestions based on the pressure injury staging results, combined with historical risk assessment results and the risk assessment results corresponding to real-time situations.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor to execute the method of claim 9.

Images