Wound Management System for Predicting and Treating Wounds - Patent application

Abstract

An aspect of the present disclosure provides a wound management system and method for predicting and treating wounds. The method includes collecting data related to a patient's health and applying a machine learning model to the data related to the patient's health to predict a first probability that the patient will incur a first wound type outside of a treatment setting. The method also includes, in response to determining that the first probability exceeds a threshold, determining an action to reduce the first probability and communicating a message to the patient indicating that an action should be taken to reduce the first probability that the patient will incur the first wound type.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. Patent Application No. 17 / 562,771, filed December 27, 2021, the entire contents of which are incorporated herein by reference in their entirety.

[0002] Introduction Aspects of the present disclosure relate to wound management systems for predicting and treating wounds. A focus of the healthcare industry is the treatment of wounds. However, traditional approaches to wound treatment are reactive, with the patient not receiving treatment until the patient actually suffers a wound. As a result, although techniques exist for treating and healing many different types of wounds, the incidence or occurrence of wounds has not necessarily decreased. [Background technology]

[0003] In addition, conventional processes for determining whether a patient is likely to sustain a wound outside of a treatment setting have relied on subjective human judgment and analysis of the patient's information, which has resulted in incomplete analysis of the patient's information and inaccurate predictions. Recommendations and actions made based on these inaccurate predictions may not actually improve the patient's health and well-being or reduce the incidence or occurrence of wounds. Summary of the Invention [Means for solving the problem]

[0004] A wound management system and method for predicting and treating wounds are described herein. According to an embodiment, the method includes collecting data related to a patient's health and applying a machine learning model to the data related to the patient's health to predict a first probability that the patient will incur a first wound type outside of a treatment setting. The method also includes determining an action to reduce the first probability in response to determining that the first probability exceeds a threshold, and communicating a message to the patient indicating that an action should be taken to reduce the first probability that the patient will incur the first wound type. Other embodiments include devices and processing systems that perform the method. Additional embodiments include a non-transitory computer-readable medium and computer program product that include instructions that, when executed by a processor, cause the processor to perform the method.

[0005] The following description and the annexed drawings set forth in detail certain illustrative features of the one or more embodiments. [Brief description of the drawings]

[0006] The accompanying drawings depict certain aspects of one or more embodiments and are not therefore to be considered as limiting the scope of the present disclosure.

[0007] [Figure 1] FIG. 1 illustrates an exemplary system.

[0008] [Diagram 2] FIG. 2 illustrates an exemplary wound management system in the system of FIG.

[0009] [Diagram 3] FIG. 3 illustrates exemplary health data in the system of FIG.

[0010] [Figure 4] FIG. 4 illustrates exemplary health screening data in the system of FIG.

[0011] [Diagram 5] FIG. 5 illustrates an exemplary wound management system in the system of FIG.

[0012] [Figure 6] FIG. 6 illustrates an exemplary wound management system in the system of FIG.

[0013] [Figure 7] FIG. 7 illustrates an example operation in the system of FIG.

[0014] [Figure 8] FIG. 8 is a flowchart of an exemplary method that may be implemented in the system of FIG.

[0015] [Figure 9] FIG. 9 is a flowchart of an exemplary method that may be implemented in the system of FIG.

[0016] [Figure 10] FIG. 10 is a flowchart of an exemplary method that may be implemented in the system of FIG.

[0017] [Figure 11] FIG. 11 illustrates an example device in the system of FIG.

[0018] [Figure 12] FIG. 12 illustrates an example device in the system of FIG.

[0019] [Figure 13] FIG. 13 illustrates an example device in the system of FIG.

[0020] [Figure 14] FIG. 14 is a flowchart of an exemplary method that may be implemented in the system of FIG.

[0021] [Figure 15] FIG. 15 illustrates an example device in the system of FIG.

[0022] To facilitate understanding, the same reference numerals have been used, where possible, to designate like elements common to the figures. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] Detailed Description Aspects of the present disclosure provide devices, methods, processing systems, and computer-readable media for predicting and treating wounds incurred outside of a treatment setting. Specifically, the present disclosure describes a wound management system that uses machine learning to predict whether a patient is likely to incur different wound types outside of a treatment setting based on information about the patient's life. For example, the wound management system may predict that if the patient is a chef, the patient is more likely to incur a cut or burn at work. As another example, the wound management system may predict that if the patient enjoys rock climbing, the patient is more likely to incur a wound from a fall. The wound management system may also prevent the predicted wound type from occurring by recommending actions the patient can take to reduce the likelihood of incurring the wound type. In this manner, the wound management system provides a proactive approach towards wound treatment, which in certain embodiments improves the health and well-being of the patient.

[0024] Exemplary Systems and Methods FIG. 1 illustrates an exemplary system 100. As seen in FIG. 1, the system 100 includes one or more devices 104, a network 106, a database 108, and a wound management system 110. In general, the system 100 applies one or more machine learning models to information about the patient's 102 life (e.g., the patient's 102 demographics, occupation, and habits) to predict how likely the patient 102 will be to incur different types of wounds. The system 100 proactively addresses these likelihoods by providing warnings to the patient 102 or by recommending corrective actions to be taken by the patient 102. As a result, the system 100 reduces the likelihood that the patient 102 will incur different wound types, which in certain embodiments improves the health and well-being of the patient 102 and reduces the incidence or occurrence of wounds.

[0025] Specifically, conventional processes for determining whether a patient 102 is likely to incur a wound outside of a treatment setting have relied on subjective human judgment and analysis of the patient's 102 information, which has resulted in an incomplete analysis of the patient's 102 information and inaccurate predictions. Recommendations and actions made based on these inaccurate predictions may not actually improve the health and well-being of the patient 102 or reduce the incidence or occurrence of wounds. In addition, subjective human assessments are often subject to bias, which has resulted in inconsistent predictions and recommendations. On the other hand, the wound management system 110 applies machine learning models to the patient's 102 information and performs a complete analysis of the patient's 102 information, which provides the technical advantage of a more accurate prediction of the likelihood that the patient 102 will incur a wound outside of a treatment setting. The wound management system 110 also provides recommendations based on these more accurate predictions, which result in specific treatments or prophylaxis to prevent or reduce the likelihood of incurring a wound outside of a treatment setting. By using machine learning to predict and treat wounds, the wound management system 110 significantly reduces human subjectivity, which overcomes bias and increases consistency.

[0026] The patient 102 uses the device 104 to provide information about the patient 102. For example, the patient 102 may be at a healthcare facility. During the check-in process, the patient 102 responds to a questionnaire or questionnaire that requests information about the patient 102. After this information is collected, the system 100 analyzes the information to determine the likelihood that the patient 102 will have different wound types. As another example, the patient 102 may be using a personal device 104 at home or at work to run an application. The patient 102 responds to a questionnaire or questionnaire presented by the application to provide information about the patient 102. After the information is collected, the system 100 analyzes the information to predict the likelihood that the patient 102 will have different wound types.

[0027] The device 104 is any suitable device for communicating with the components of the system 100 via the network 106. By way of example, and not limitation, the device 104 may be a computer, a laptop, a wireless or cellular phone, an electronic organizer, a personal digital assistant, a tablet, or any other device capable of receiving, processing, storing information, or communicating with other components of the system 100. The device 104 may be a wearable device, such as a virtual or augmented reality headset, a smart watch, or smart glasses. The device 104 may also include a user interface, such as a display, a microphone, a keypad, or other suitable terminal equipment usable by the patient 102. The device 104 may include a hardware processor, memory, or circuitry to perform any of the functions or actions of the device 104 described herein. For example, a software application designed using software code may be stored in memory and executed by a processor to perform the functions of the device 104.

[0028] Network 106 is any suitable network operable to facilitate communication between the components of system 100. Network 106 may include any interconnected system capable of transmitting audio, video, signals, data, messages, or any combination of the foregoing. Network 106 may include all or a portion of a local, regional, or global communications or computer network, such as a public switched telephone network (PSTN), a public or private data network, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), the Internet, a wired or wireless network, a corporate intranet, or any other suitable communications link, including any combination thereof, operable to facilitate communication between the components.

[0029] The database 108 stores information about previous wounds. As seen in FIG. 1, the database 108 stores health data 112. The health data 112 may include information about other individuals and their previous wounds. For example, the health data 112 may include information such as the demographics, home conditions, working conditions, symptoms, and habits of the other individuals. In addition, the health data 112 may include the wound types that these other individuals have sustained and the time they sustained the wound types. The system 100 uses the health data 112 to train a machine learning model to predict the likelihood that the patient 102 will sustain a wound type that is outside of the treatment setting. For example, the machine learning model may analyze the health data 112 to detect patterns or trends in the demographics and lifestyle of other individuals that may result in sustaining a particular wound type. Once trained, the machine learning model may analyze information about the patient 102 to determine whether patterns or trends also exist in the lifestyle of the patient 102. The machine learning model then predicts the likelihood that the patient 102 will suffer from different wound types based on these detected patterns or trends.

[0030] The wound management system 110 collects information about the patient 102 and applies machine learning models to the information to predict how likely the patient 102 will incur different wound types. In addition, the wound management system 110 provides warnings or corrective actions that the patient 102 may take to reduce the likelihood that the patient 102 will incur a wound type. In some embodiments, the wound management system 110 is a separate computer system (e.g., a server) from the device 104. In some embodiments, the wound management system 110 is embodied within the device 104. For example, the device 104 may implement the wound management system 110 by executing an application on the device 104. As seen in FIG. 1, the wound management system 110 includes a processor 114 and a memory 116 that may perform the actions or functions of the wound management system 110 described herein. In embodiments in which the wound management system 110 is embodied within the device 104, the processor 114 and the memory 116 may be the processor and memory of the device 104.

[0031] The processor 114 is any electronic circuitry, including, but not limited to, one or a combination of a microprocessor, a microcontroller, an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), and / or a state machine, communicatively coupled to the memory 116 and controlling the operation of the wound management system 110. The processor 114 may be 8-bit, 16-bit, 32-bit, 64-bit, or any other suitable architecture. The processor 114 may include an arithmetic logic unit (ALU) for performing arithmetic and logical operations, processor registers that provide operands to the ALU and store results of the ALU operations, and a control unit that fetches instructions from memory and executes them by directing the cooperative operation of the ALU, registers, and other components. The processor 114 may include other hardware that runs software to control and process information. The processor 114 executes software stored on the memory 116 to perform any of the functions described herein. The processor 114 controls the operation and governance of the wound management system 110 by processing information, such as information received from the device 104, the network 106, and the memory 116. The processor 114 is not limited to a single processing device, but may encompass multiple processing devices.

[0032] The memory 116 may store, either permanently or temporarily, data, operating software, or other information related to the processor 114. The memory 116 may include any one or combination of volatile or non-volatile local or remote devices suitable for storing information. For example, the memory 116 may include a random access memory (RAM), a read-only memory (ROM), a magnetic storage device, an optical storage device, or any other suitable information storage device, or a combination of these devices. Software represents any suitable set of instructions, logic, or code embodied in a computer-readable storage medium. For example, the software may be embodied in the memory 116, a disk, a CD, or a flash drive. In certain embodiments, the software may include applications executable by the processor 114 to perform one or more of the functions described herein.

[0033] The wound management system 110 collects health screening data 118 from the patient 102 or the device 104. The health screening data 118 may be provided by the patient 102, for example, in response to a questionnaire or survey. In some embodiments, the wound management system 110 communicates these questionnaires or surveys to the device 104. The patient 102 responds to the survey or survey using the device 104. The device 104 then communicates these responses back to the wound management system 110 as health screening data 118. The health screening data 118 may include any suitable information about the patient 102. For example, the health screening data 118 may include demographic information about the patient 102 (e.g., age, gender, and location). As another example, the health screening data 118 may include information about the lifestyle of the patient 102 (e.g., home conditions, work conditions, habits, or hobbies). The health screening data 118 may also include medical information (e.g., allergies, vaccinations, hospitalizations, surgeries, prescription medications, and family medical history) of the patient 102. The wound management system 110 collects and analyzes the health screening data 118 to predict the likelihood that the patient 102 will sustain various wound types.

[0034] The wound management system 110 applies the machine learning model 120 to the health screening data 118 to detect patterns or trends in the health screening data 118. The detected patterns or trends are then used to determine the likelihood that the patient 102 will suffer from different wound types. As seen in FIG. 1 , the machine learning model 120 analyzes the health screening data 118 to determine probabilities 124 that the patient 102 will suffer from different wound types 122. In the example of FIG. 1 , the machine learning model 120 analyzes the health screening data 118 to determine that the patient 102 has a probability 124A of suffering from wound type 122A, a probability 124B of suffering from wound type 122B, and a probability 124C of suffering from wound type 122C.

[0035] The wound management system 110 may implement supervised machine learning techniques, unsupervised machine learning techniques, or a combination of supervised and unsupervised learning techniques. In an embodiment, a user or administrator selects a machine learning model to apply based on knowledge or analysis of the health screening data 118 or health data 112. For example, the wound management system 110 may begin by applying a logistic regression to the health screening data 118 or health data 112. After that analysis is complete, the user or administrator may select another machine learning model to apply that the user or administrator deems more suitable for the data. In some embodiments, the wound management system 110 analyzes the health screening data 118 or health data 112 and determines the machine learning model to apply to the data based on that analysis. Regardless of whether supervised or unsupervised techniques are used, the wound management system 110 may convert the health screening data 118 or health data 112 into a numerical format, and a data conversion technique may be selected (e.g., by the wound management system 110 or by the user or administrator) based on the initial data analysis.

[0036] Each wound type 122 may be a category that encompasses many different wounds. For example, the wound type 122 of "wounds incurred from falls / tumbles" may encompass wounds such as lacerations, contusions, fractures, abrasions, and contusions. As another example, the wound type 122 of "self-inflicted wounds" may encompass wounds such as cuts, burns, and scratches. As yet another example, the wound type 122 of "wounds incurred from walking conditions" may encompass wounds such as contusions, fractures, and abrasions. The wound management system 110 may determine the likelihood that the patient 102 will develop a wound type 122 and provide warnings or recommendations to the patient to reduce the likelihood.

[0037] The wound management system 110 determines one or more actions 126 based on the probability 124. For example, if the probability 124 that the patient 102 will incur a particular wound type 122 is high, the wound management system 110 may determine corrective actions that the patient 102 may take to reduce the probability 124. As another example, if the probability 124 that the patient 102 will incur a particular wound type 122 is low, the wound management system 110 may provide the patient 102 with a general warning of the risk that the patient 102 will incur the wound type 122. In an embodiment, a database or repository may store the actions 126 that should be recommended to correct or avoid a certain wound type 122. The wound management system 110 determines the one or more actions 126 by querying a database or repository using the wound type 122. The database or repository then returns the one or more actions 126. For example, when a healthcare facility treats a patient with a wound, the healthcare facility may log in the database 108, or as part of the health data 112, the wound types the patient sustained and the treatments or corrective actions recommended for the patient 102 to avoid those wound types in the future. When the wound management system 110 queries the database 108 with the determined wound type 122, the database 108 may return one or more actions 126 based on previously recommended treatments and corrective actions for that wound type 122.

[0038] The wound management system 110 may recommend any suitable action 126. For example, the wound management system may recommend that the patient 102 wear a different type of protective clothing (e.g., gloves and boots) while working to protect against a certain wound type 122. As another example, the wound management system may recommend that the patient 102 change what and when the patient 102 eats, or that the patient 102 change his / her occupation or hobby to reduce the likelihood of acquiring a certain wound type 122. As yet another example, the wound management system may recommend that the patient 102 visit a particular healthcare facility if the patient 102 acquires a certain wound type. The wound management system 110 may use addresses in the health screening data 118 to identify healthcare facilities in the patient's 102 vicinity. The wound management system 110 may then review treatment statistics (e.g., statistics in the health data 112) for these healthcare facilities to identify and recommend the healthcare facilities that are most successful or optimal for treating the particular wound type.

[0039] The wound management system 110 communicates a message to the patient 102 or the device 104 indicating one or more actions 126 determined by the wound management system 110. If the patient 102 acknowledges the message, the patient 102 may implement a corrective action or follow a warning provided by the wound management system 110. As a result, the wound management system 110 provides a specific treatment or prophylactic method that prevents or reduces the likelihood that the patient 102 will incur the wound type 122, which in an embodiment improves the health and well-being of the patient 102 and reduces the incidence and occurrence of the wound type 122.

[0040] In some embodiments, the wound management system 110 may detect changes in the patient's 102 lifestyle or health screening data 118. For example, the wound management system 110 may detect that the patient 102 has moved to a different location associated with a different occupation or hobby based on the location of the device 104. As another example, the wound management system 110 may detect that the patient 102 has changed occupation or hobby based on the patient's 102 social media feed. As yet another example, the patient 102 may use the device 104 to inform the wound management system 110 that the patient 102 has changed occupation or hobby. In response to detecting these changes, the wound management system 110 reapplies the machine learning model 120 to the updated data and reassess the likelihood that the patient 102 will incur a certain wound type 122. The wound management system 110 may then provide updated actions 126 that the patient 102 may take to reduce these updated likelihoods.

[0041] Figure 2 illustrates an example wound management system 110 in the system 100 of Figure 1. Generally, Figure 2 shows the wound management system 110 training a machine learning model. Although the wound management system 110 is shown training the machine learning model, it is envisioned that a computer system separate from the wound management system 110 may train the machine learning model and then deploy the machine learning model to the wound management system 110.

[0042] The wound management system 110 begins by collecting health data 112 from one or more patients 202. For example, as the patient 202 sustains a wound and is treated at a healthcare facility, the healthcare facility may collect information about the patient 202. This information may include the patient's 202 demographics, the patient's 202 occupation and habits, and the patient's 202 medical history. In addition, the healthcare facility may log information about the wounds sustained by the patient 202 and the time the wounds were sustained. The healthcare facility may also log the treatments and corrective actions prescribed or recommended to the patient 202. All of this information may be encapsulated in the health data 112. The health data 112 may then be stored in the database 108 shown in FIG. 1. Once the wound management system 110 (or another computer system) is ready to train the machine learning model, the wound management system 110 may retrieve the health data 112 from the database 108. The wound management system 110 then uses the health data 112 to train a machine learning model.

[0043] The wound management system 110 subdivides or splits the health data 112 into two data sets. In the example of FIG. 2, the wound management system 110 subdivides the health data 112 into training data 204 and validation data 206. The wound management system 110 may use any suitable process to subdivide the health data 112 into training data 204 and validation data 206. For example, the wound management system 110 may analyze the health data 112 and select the data points that are most different from each other to form the training data 204. The remaining data points then form the validation data 206. As another example, the wound management system 110 may cluster the health data 112 such that data points within the health data 112 that are most similar to each other are assigned to the same cluster. The wound management system 110 then selects data points from the different clusters to form the training data 204, which may ensure that the training data 204 includes a diverse set of data points. The remaining data points then form the validation data 206. In this manner, the wound management system 110 may use a diverse set of data points to train the machine learning model, which in certain embodiments increases the robustness, generalizability, and accuracy of the machine learning model.

[0044] The wound management system 110 trains (at block 208) the machine learning model by having the machine learning model analyze the training data 204 and detect patterns or trends in the training data 204. Through this training, the machine learning model learns to predict the likelihood of incurring a particular wound type based on the detected patterns or trends. The wound management system 110 then uses the validation data 206 to validate the trained machine learning model 210. For example, the wound management system 110 may apply the trained machine learning model 210 to the validation data 206 to see if the trained machine learning model 210 makes accurate predictions. During this validation process, the wound management system 110 performs a loss calculation 209 that indicates the accuracy or loss of the machine learning model. If the loss or accuracy of the trained machine learning model 210 is not acceptable, the wound management system 110 may perform another step of training 208. This cycle of training and validation may continue until the loss or accuracy of the machine learning model is improved to an acceptable level.

[0045] In an embodiment, the loss may be calculated by applying the trained machine learning model 210 to the data points in the validation data 206. The trained machine learning model 210 may detect patterns or trends in the validation data 206 and predict the likelihood of incurring a particular wound type based on the detected patterns or trends. The wound management system 110 then compares the predicted likelihood against the actual wounds inflicted by the validation data 206. The difference in the predicted likelihood and the actual wounds inflicted represents the loss or accuracy of the trained machine learning model 210. The wound management system 110 may perform additional iterations of training until this loss or accuracy is at an acceptable level.

[0046] Figure 3 illustrates example health data 112 in the system 100 of Figure 1. As discussed above, the health data 112 may include information about previous patients 202 and wounds sustained by these previous patients 202.

[0047] 3, the health data 112 includes information that identifies the patient 202 (e.g., name and address). In an embodiment, the wound management system 110 removes or excludes this patient information (indicated by "*") from the health data 112 before using the health data 112 to train the machine learning model. In this way, the wound management system protects the privacy and security of the former patients 202.

[0048] The health data 112 also includes information about wounds sustained by previous patients 202. The health data 112 may include the date the wound was sustained and the wound type of the particular wound. As seen in Figure 3, each data point includes a data field indicating the date the wound was sustained. In addition, each data point includes a wound type, such as a wound sustained from a fall / tumble, a self-inflicted wound, or a wound sustained through walking conditions.

[0049] The health data 112 may also include information about the circumstances under which the wound was sustained. As seen in FIG. 3, the health data 112 may include events, which may indicate the actions or activities the patient 202 was engaged in when the wound was sustained. For example, the events may include cooking, climbing, running, driving, playing a sport, etc. Additionally, the health data 112 may include environments, which indicate the setting in which the wound was sustained. For example, the environments may include home, work, gym, kitchen, park, lake, mountain, etc. A machine learning model may use this information to determine the types of events and environments that led to a certain wound.

[0050] The health data 112 may also include information about the lifestyle of the patient 202. As seen in Figure 3, the health data 112 includes information about the habits and occupation of the patient 202. The habits may indicate the activities and practices that the patient 202 regularly engages in. The occupation may indicate the job that the patient 202 holds. The machine learning model may use this information to determine which habits and occupations are more likely to result in incurring certain wound types.

[0051] In some embodiments, the wound management system 110 may exclude or remove certain information from the health data 112 based on the date the wound was incurred (indicated by an "*"). For example, the wound management system 110 may compare the date from each data point in the health data 112 to the date threshold 302. If the date is earlier than the date threshold 302, the wound management system 110 may remove the data point with that date from the health data 112 so that the machine learning model is not trained using that data point. As a result, the wound management system 110 removes old data points from being used to train the machine learning model, which, in certain embodiments, may improve the accuracy of the machine learning model.

[0052] FIG. 4 illustrates example health screening data 118 in the system 100 of FIG. 1. The patient 102 may provide the health screening data 118 using the device 104 when the patient 102 checks into the healthcare facility. Additionally or alternatively, the patient 102 may provide the health screening data 118 by running an application on the patient's 102 personal device 104 (e.g., at work or at home). The patient 102 may provide the information by responding to a questionnaire or survey. The responses to the questionnaire or survey provide the information in the health screening data 118. After the device 104 collects the responses, the device 104 communicates the responses to the wound management system 110 as the health screening data 118.

[0053] 4, the health screening data 118 includes information that identifies the patient 102. For example, the health screening data 118 may include the name, address, and date of birth of the patient 102, as well as information that identifies family members of the patient 102. This information may be needed to properly store the health screening data 118 and to properly notify the patient 102 of any health or medical developments.

[0054] The health screening data 118 also includes medical information about the patient 102. For example, the health screening data 118 may indicate any allergies the patient 102 has and any vaccinations the patient 102 has received. In addition, the health screening data 118 may indicate previous hospitalizations of the patient 102 and previous surgeries the patient 102 has undergone. The health screening data 118 may also indicate prescription medications taken or being taken by the patient 102. The health screening data 118 may also include information about symptoms the patient 102 has experienced. In some instances, the health screening data 118 also includes a family medical history regarding the patient 102, indicating medical conditions (e.g., heart attack or stroke) that family members of the patient 102 have had.

[0055] The health screening data 118 also includes information about the lifestyle of the patient 102. For example, the health screening data 118 may include information about the home conditions or work conditions of the patient 102. The home conditions may indicate whether the patient 102's home is cluttered, includes stairs, or has a carbon monoxide detector. The work conditions may indicate a description of the patient 102's duties and responsibilities in the patient's 102 occupation and workplace. For example, the work conditions may indicate that the patient 102 is a cook who regularly prepares and cooks food in a large kitchen. As another example, the work conditions may indicate that the patient 102 is a utility maintenance provider who regularly climbs utility poles. The health screening data 118 may also include event information that indicates various activities or practices in which the patient 102 is engaged. For example, the health screening data 118 may indicate that the patient 102 enjoys rock climbing or driving race cars.

[0056] The health screening data 118 also includes information about the habits of the patient 102. For example, the health screening data 118 may include information indicative of whether the patient 102 smokes or drinks alcohol. In addition, the health screening data 118 may include information indicative of whether the patient 102 wears a seat belt or uses recreational drugs.

[0057] The wound management system 110 may apply the machine learning model 120 to the information in the health screening data 118 to determine the likelihood that the patient 102 will incur certain wound types. For example, the machine learning model 120 may predict that the patient 102 is more likely to incur certain types of wounds as a result of the patient's occupation. As another example, the machine learning model 120 may predict that the patient 102 is more likely to incur certain wound types due to the patient's 102 habits. Based on these predictions, the wound management system 110 may proactively warn or recommend corrective actions to the patient 102, which, in certain embodiments, may reduce the likelihood that the patient 102 will incur these wound types.

[0058] Figure 5 illustrates an example wound management system 110 in the system 100 of Figure 1. Generally, Figure 5 shows the wound management system 110 applying a machine learning model 120 to health screening data 118 of utility maintenance providers. The machine learning model 120 predicts that the utility maintenance providers are likely to incur certain wound types, and the wound management system 110 provides alerts and recommendations to the utility maintenance providers based on these predictions.

[0059] The health screening data 118 indicates that the utility maintenance provider has had previous hand and foot surgery. In addition, the health screening data 118 indicates that the utility maintenance provider not only enjoys rock climbing, but also smokes and drinks alcohol. The utility maintenance provider may provide this health screening data 118 while checking into a health care facility. Alternatively, the utility maintenance provider may provide the health screening data 118 while at home using the utility maintenance provider's personal device 104.

[0060] The wound management system 110 applies the machine learning model 120 to information in the health screening data 118 to detect patterns and trends in the health screening data 118. For example, the machine learning model 120 may identify prior patients 202 similar to the utility maintenance provider by comparing the health screening data 118 to the health data 112 of the prior patients 202. In the example of FIG. 5 , the machine learning model 120 determines, based on the health screening data 118, that the utility maintenance provider has a 60% chance of sustaining a wound from a fall, a 10% chance of sustaining a self-inflicted wound, and a 50% chance of sustaining a wound from walking conditions.

[0061] After the machine learning model 120 determines the likelihood that the utility maintenance provider will sustain a particular wound type, the wound management system 110 analyzes the predicted likelihoods and determines whether any corrective action is appropriate. The wound management system 110 compares each of the determined likelihoods to a threshold 502. If a determined likelihood exceeds the threshold 502, the wound management system 110 may determine a corrective action 126 that the utility maintenance provider may take to reduce the likelihood of sustaining the particular wound type corresponding to that likelihood. In the example of FIG. 5, the wound management system compares the likelihood that the utility maintenance provider will sustain an injury from a fall to the threshold 502. The wound management system 110 may determine that a 60% likelihood exceeds the threshold 502. In response, the wound management system 110 determines an action 126, including changing jobs or changing hobbies. In other words, the wound management system 110 may determine that a utility maintenance provider has a high likelihood of sustaining an injury from a fall due to the fact that the utility maintenance provider enjoys rock climbing or climbs utility poles for a living. The wound management system 110 may determine that this likelihood may be reduced if the utility maintenance provider changes jobs or finds a new hobby.

[0062] The wound management system 110 compares the likelihood that the utility maintenance provider will incur a self-inflicted wound to a threshold 502. The wound management system 110 may determine that the 10% likelihood is below the threshold 502. In response, the wound management system 110 may not determine a corrective action to recommend to the utility maintenance provider. In some embodiments, the wound management system 110 may still provide a warning to the utility maintenance provider that the utility maintenance provider is at risk of incurring a self-inflicted wound (e.g., while setting up climbing equipment for work or for fun).

[0063] The wound management system 110 compares the likelihood that the utility maintenance provider will incur an injury from the walking conditions to a threshold 502. The wound management system 110 may determine that a 50% likelihood exceeds the threshold 502. In response, the wound management system 110 determines an action 126 that the utility maintenance provider may take to reduce the likelihood. In the example of FIG. 5, the wound management system 110 determines that the utility maintenance provider may reduce the risk of incurring an injury due to the walking conditions by finding a new hobby. After assessing each of the predicted likelihoods, the wound management system 110 may communicate the determined action 126 to the utility maintenance provider. The utility maintenance provider may take the recommended action 126 to reduce the predicted likelihood of incurring various wound types.

[0064] Figure 6 illustrates an example wound management system 110 in the system 100 of Figure 1. Generally, Figure 6 shows the wound management system 110 applying a machine learning model 120 to a cook's health screening data 118. The machine learning model 120 predicts the likelihood that the cook will incur a particular wound type. The wound management system 110 then analyzes these predicted likelihoods and determines corrective actions 126 that the cook can take to reduce these likelihoods, which, in an embodiment, improves the health and well-being of the cook.

[0065] The wound management system 110 collects health screening data 118 from the cook. The cook may provide the health screening data 118 when checking into a healthcare facility. Alternatively, the cook may provide the health screening data 118 using the cook's personal device 104 while at work or at home. In the example of FIG. 6 , the health screening data 118 indicates the cook's occupation. Additionally, the health screening data 118 indicates that the cook has a history of suffering burns and lacerations. Additionally, the health screening data 118 indicates that the cook consumes alcohol. The wound management system 110 may collect and analyze the health screening data 118 to determine the type of wound the cook is likely to suffer.

[0066] The wound management system 110 applies the machine learning model 120 to the health screening data 118 to determine the likelihood. The machine learning model 120 may then analyze the health data 112 of these other patients 202 to determine the likelihood that the cook will sustain a certain wound type. In the example of FIG. 6, the machine learning model 120 may determine that the cook has a 30% chance of sustaining a wound from a fall, a 75% chance of sustaining a self-inflicted wound, and a 5% chance of sustaining a wound due to walking conditions. For example, the machine learning model 120 may determine that the cook has a 30% chance of slipping or falling while working on a wet floor in the kitchen. As another example, the machine learning model 120 may determine that the cook has a 75% chance of sustaining a burn or cut while working in the kitchen.

[0067] The wound management system 110 compares the predicted likelihood to a threshold 502 to determine if a corrective action 126 should be recommended. In the example of FIG. 6, the wound management system 110 compares a 30% chance of sustaining a wound due to a fall to a threshold 502. The wound management system determines that the 30% likelihood exceeds the threshold 502. In response, the wound management system 110 determines the action 126 to wear boots while working to prevent the cook from slipping and falling on a wet kitchen floor. The wound management system 110 may recommend that the cook wear boots while working to reduce the likelihood that the cook will fall while cooking in the kitchen. The wound management system 110 also compares the likelihood of sustaining a self-inflicted wound to a threshold 502. In the example of FIG. 6, the wound management system 110 determines that a 75% likelihood exceeds the threshold 502. In response, the wound management system 110 determines the corrective action 126 to wear gloves. The wound management system 110 may recommend that the cook wear protective gloves while working in the kitchen to reduce the likelihood of incurring a self-inflicted wound (e.g., a burn or cut). The wound management system 110 compares the likelihood of incurring a wound from walking conditions to a threshold 502. In the example of FIG. 6, the wound management system 110 compares a 5% likelihood to the threshold 502 and determines that the 5% likelihood does not exceed the threshold 502. In response, the wound management system 110 does not determine a corrective action 126 regarding the wound incurring due to the walking conditions. In some embodiments, the wound management system 110 may still provide a warning to the cook of the risk of incurring a wound due to the walking conditions. Thus, the wound management system can identify an action (e.g., a protective action, a prescribed medication, a medical procedure, or another action) to reduce the likelihood that the patient will incur a wound (e.g., a bedsore, a suture wound, an abrasion, an injury, or any other wound). As an example, a patient may be provided with medical treatment (e.g., a bandage, a surgical procedure, a particular prescription medication, or any other suitable treatment) to reduce the likelihood of incurring a wound. For example, a pressure sore, stitch wound, abrasion, or injury may be identified as being less likely to occur if the patient receives the identified prescription medication, bandage, or another medical procedure.

[0068] The wound management system 110 may communicate a message to the cook's device 104 indicating the determined corrective action 126. The cook may read the message and implement the corrective action 126 (e.g., by wearing boots and gloves while working) to reduce the likelihood that the cook will sustain a wound from a fall or a self-inflicted wound while working. As a result, the cook's health and well-being is improved in certain embodiments.

[0069] FIG. 7 illustrates an example operation of the system 100 of FIG. 1. In general, FIG. 7 shows the wound management system 110 communicating a determined action 126 to the cook's 102 device 104. As discussed above, the wound management system 110 determines the action 126 by applying a machine learning model 120 to the health screening data 118 provided by the patient 102 to predict the likelihood that the patient 102 will incur a certain wound type and by comparing those predicted likelihoods to a threshold 502. In some embodiments, the wound management system 110 selects the action 126 from a database or repository of corrective actions. The wound management system may make these selections based on the wound type and information in the health screening data 118.

[0070] The wound management system 110 communicates actions 126 to the device 104 using messages 702. The messages 702 may include the actions 126. When the device 104 receives the message 702, the device 104 displays the message 702 to the patient 102. The patient 102 may then read the message 702 and determine corrective actions 126 that the patient 102 can take to reduce the risk of incurring certain wound types and the likelihood of incurring those wound types. The patient 102 may take these actions 126 to reduce the likelihood, which improves the health and well-being of the patient 102.

[0071] Figure 8 is a flowchart of an exemplary method 800 implemented in the system 100 of Figure 1. In certain embodiments, the wound management system 110 implements the method 800. By implementing the method 800, the wound management system 110 trains the machine learning model 120 using health data 112 of previous patients 202.

[0072] In block 802, the wound management system 110 collects health data 112. The wound management system 110 may collect or retrieve the health data 112 from the database 108. The health data 112 may be assembled by collecting information about previous patients 202. For example, a health care facility may collect the health data 112 when it treated wounds inflicted by the previous patients 202. The health data 112 may include information about the previous patients 202 and the wound types inflicted by the previous patients 202. For example, the health data 112 may include information identifying the patient 102. The health data 112 may also include information about the wound types inflicted by the patient 202, such as the wound type and the date the wound type was inflicted. The health data 112 may also include information about the circumstances under which the wound type was inflicted, such as the environment or event under which the wound type was inflicted. The health data 112 may further include information about the lifestyle of the patient 202 , such as the patient's 202 occupation or the patient's 202 habits.

[0073] At block 804, the wound management system divides the health data 112 into training data 204 and validation data 206. The wound management system 110 may use any suitable process for dividing the health data 112. For example, the wound management system 110 may randomly divide the health data 112 into the training data 204 and the validation data 206. As another example, the wound management system 110 may select a diverse data set for the training data 204 by clustering data points in the health data 112 into clusters of similar data points and then selecting data points from the different clusters. As a result, the training data 204 includes data points from different clusters, which increases the diversity of the data points in the training data 204.

[0074] In block 806, the wound management system 110 uses the training data 204 to train a machine learning model to predict the probability that a patient will incur different wound types. For example, the wound management system 110 may have the machine learning model analyze the training data 204 to determine patterns and trends within the training data 204. The machine learning model may also determine the wound types incured that correspond to these detected patterns or trends. In this manner, the machine learning model is trained to determine the likelihood that a particular wound type will be incurred given a particular pattern or trend.

[0075] At block 808, the wound management system 110 validates the machine learning model using the validation data 206. The validation data 206 may include data points from the health data 112 that were not included in the training data 204. The wound management system 110 may apply the machine learning model to the data points in the validation data 206 to predict the likelihood that a patient represented by the data points in the validation data 206 will suffer a particular wound type. The machine learning model predicts these likelihoods, and the wound management system 110 compares these predicted likelihoods to the actual wound types shown in the validation data 206. Based on this comparison, the wound management system 110 determines a loss or accuracy of the machine learning model. If the loss or accuracy is not at an acceptable level, the wound management system 110 may perform another iteration of training on the machine learning model. If the loss or accuracy is at an acceptable level, the wound management system 110 may continue.

[0076] At block 810, the wound management system 110 deploys the machine learning model after it has been trained and validated. In other words, when the accuracy or loss of the machine learning model is at an acceptable level, the wound management system 110 deploys the machine learning model. In some embodiments, the wound management system 110 deploys the machine learning model within the wound management system 110 such that the wound management system 110 may apply the machine learning model to the health screening data 118 provided by the patient 102. In some embodiments, the wound management system 110 deploys the machine learning model to the device 104 of the patient 102. In these embodiments, the device 104 may apply the machine learning model to the health screening data 118 provided by the patient 102. By applying the machine learning model to the health screening data 118, the machine learning model predicts the likelihood that the patient 102 will suffer different wound types.

[0077] Figure 9 is a flowchart of an exemplary method 900 implemented in the system 100 of Figure 1. In certain embodiments, the wound management system 110 implements the method 900. By implementing the method 900, the wound management system 110 predicts the likelihood or probability that the patient 102 will incur various wound types.

[0078] In block 902, the wound management system 110 collects health screening data 118. The health screening data 118 may be provided by the patient 102 using the device 104. For example, the patient 102 may respond to a questionnaire or survey on the device 104. After the patient 102 provides a response, the device 104 communicates the response to the wound management system as health screening data 118. The health screening data 118 includes information about the patient 102 that may be useful in identifying the likelihood that the patient 102 will suffer from different wound types. For example, the health screening data 118 may include information that identifies the patient 102 (e.g., the name and address of the patient 102). The health screening data 118 may include medical information about the patient 102, such as symptoms experienced by the patient 102, allergies of the patient 102, vaccinations or prescription medications taken by the patient 102, previous hospitalizations or surgeries of the patient 102, and medical history of other family members of the patient 102. The health screening data 118 may also include information about the lifestyle of the patient 102. For example, the health screening data 118 may include the home conditions, work conditions, hobbies, and events of the patient 102. The health screening data 118 may also indicate whether the patient 102 smokes, drinks alcohol, wears a seat belt, or uses recreational drugs. The wound management system 110 may analyze the information in the health screening data 118 and predict the likelihood that the patient 102 will suffer from different wound types.

[0079] In block 904, the wound management system 110 applies the machine learning model 120 to the health screening data 118 to predict the probability that the patient 102 will incur a wound type outside of a treatment setting. For example, the wound management system 110 may predict the probability that the patient 102 will incur a wound type due to the patient's 102 occupation or habits. For example, the machine learning model 120 may compare the health screening data 118 to the health data 112 of other patients 202 similar to the patient 102 to determine the likelihood that the patient 102 will incur the wound type. After the wound management system 110 applies the machine learning model 120 in block 904, the wound management system 110 may determine a recommended action by implementing the method illustrated in FIG.

[0080] Figure 10 is a flowchart of an exemplary method 1000 implemented in the system 100 of Figure 1. In certain embodiments, the wound management system 110 implements the method 1000. By implementing the method 1000, the wound management system 110 determines actions 126 that the patient 102 can take to reduce the likelihood of incurring a wound type.

[0081] In block 1002, the wound management system 110 determines whether the predicted probability exceeds a threshold 502. The threshold 502 may be set at any suitable level. If the predicted probability that the patient 102 will incur a particular wound type does not exceed the threshold 502, the wound management system 110 may draw a conclusion regarding that wound type. In some embodiments, the wound management system 110 may generate a warning message for the wound type if the predicted probability for that wound type does not exceed the threshold 502.

[0082] If the predicted probability exceeds the threshold 502, the wound management system 110 determines an action 126 to reduce the probability at block 1004. In some embodiments, the wound management system 110 may determine the action 126 from a database or repository of corrective actions 126. These corrective actions 126 may be linked or tied to various wound types in the database or repository. The wound management system 110 may use information from the health screening data 118 along with the predicted wound type to query the database or repository to determine the action 126. After the wound management system 110 determines the action 126, the wound management system 110 communicates the action 126 to the user device 104 at block 1006. For example, the wound management system 110 may communicate a message 702 to the device 104. The message 702 may indicate or include the determined action 126. The device 104 may then display the message 702. When the patient 102 reads the message 702, the patient 102 is informed of the corrective action 126. The patient 102 may then implement or take the action 126 to reduce the likelihood that the patient 102 will incur the wound type. As a result, the health and well-being of the patient 102 is improved in some embodiments.

[0083] In an embodiment, by implementing the methods 900 and 1000, the wound management system 110 can predict the likelihood that the patient 102 will incur a wound outside of a treatment setting. Specifically, conventional processes for determining whether the patient 102 is likely to incur a wound outside of a treatment setting have relied on subjective human judgment and analysis of the patient 102's information, which has resulted in an incomplete analysis of the patient 102's information and inaccurate predictions. Recommendations and actions taken based on these inaccurate predictions may not actually improve the health and well-being of the patient 102 or reduce the incidence or occurrence of wounds. On the other hand, the wound management system 110 applies machine learning models to the patient 102's information and performs a complete analysis of the patient 102's information, which results in a more accurate prediction of the likelihood that the patient 102 will incur a wound outside of a treatment setting. The wound management system 110 also provides recommendations based on these more accurate predictions, which result in specific treatments or prophylactic measures to prevent or reduce the likelihood of incurring a wound outside of a treatment setting.

[0084] FIG. 11 illustrates an example device 104 in the system 100 of FIG. 1. As seen in FIG. 11, the device 104 presents an interface through which the patient 102 may provide health screening data 118. For example, the interface includes fields in which the patient 102 may provide a name and address. This information may later be used to identify the patient 102. The interface also includes a field that the patient 102 may use to indicate a job or occupation. In the example of FIG. 11, this field is a drop-down list. When the patient 102 selects this field, a list of potential jobs or occupations appears. The patient 102 may then select a job or occupation from the list. The wound management system 110 may later use the selected job or occupation to determine the likelihood that the patient 102 will incur a particular wound type. The patient 102 in the example of FIG. 11 indicates that the patient 102 is a chef.

[0085] The interface also includes fields that the patient 102 may use to indicate the patient's 102 family or home conditions. In the example of FIG. 11, the interface includes fields that the patient 102 may use to indicate whether the patient 102 is married or whether the patient 102 has children. The patient 102 in the example of FIG. 11 indicates that the patient 102 is not married and does not have children. The interface also includes fields that the patient 102 may use to indicate the patient's 102 habits. The patient 102 in the example of FIG. 11 indicates that the patient smokes and drinks alcohol.

[0086] After the device 104 collects the information from the patient 102, the device 104 communicates the collected information to the wound management system 110 as health screening data 118. The wound management system 110 may then apply machine learning models 120 to the health screening data 118 to predict the likelihood that the patient 102 will incur various wound types (e.g., due to the patient's 102 occupation or habits). The wound management system 110 may then determine actions 126 that the patient 102 can take to reduce the predicted likelihood.

[0087] Figure 12 illustrates an example device 104 in the system 100 of Figure 1. As seen in Figure 12, the device 104 displays a message received from the wound management system 110. The message indicates various wound types 122 that the wound management system 110 predicts the patient 102 is likely to incur. In addition, the message includes actions 126 that the wound management system 110 has determined will reduce the likelihood that the patient 102 will incur these wound types 122.

[0088] As seen in FIG. 12, the wound management system 110 has determined that the patient 102 is likely to sustain a self-inflicted wound (e.g., a burn) and a wound resulting from a fall. A message shown on the device 104 indicates that the patient 102 is likely to experience a burn and a fall. The wound management system 110 has also determined actions 126 that may be taken by the patient 102 to reduce the likelihood of sustaining a burn or a fall. As seen in FIG. 12, the message indicates that the patient 102 should put on protective gloves before handling hot items to reduce the likelihood of experiencing a burn. Additionally, the message indicates that the patient 102 should wear boots when walking on wet surfaces to reduce the likelihood of a fall. The device 104 displays these actions 126 to the patient 102. The patient 102 may take or implement these actions to reduce the likelihood of sustaining a burn and a fall, which, in certain embodiments, improves the health and well-being of the patient 102.

[0089] In some embodiments, the message also includes a recommendation of a healthcare facility for treating the predicted wound type. The wound management system 110 may determine the healthcare facility by first determining healthcare facilities that are in the vicinity of the patient 102 based on an address provided by the patient 102 in the health screening data 118. The wound management system 110 may then determine the healthcare facility that is best suited to treat the predicted wound type based on statistics about the healthcare facilities. The wound management system 110 then includes the healthcare facility in the message communicated to the device 104. By providing this information to the patient 102, the patient 102 may know which healthcare facility to visit if the patient 102 incurs any of the predicted wound types.

[0090] Figure 13 illustrates an example device 104 in the system 100 of Figure 1. Generally, the device 104 in the example of Figure 13 is a device 104 of a utility maintenance provider who enjoys rock climbing. The device 104 may receive a message from the wound management system 110 indicating a type of wound that the patient 102 is likely to sustain. In the example of Figure 13, the message indicates that the patient 102 is likely to sustain a wound from a fall or a wound from an electric shock.

[0091] The message also includes a corrective action 126 that the patient 102 may take to reduce the likelihood that the patient 102 will sustain an injury from a fall. As seen in FIG. 13, the action 126 includes putting on gloves and boots when climbing the utility pole. The device 104 presents a message including this action 126 to inform the patient 102 that the patient 102 should put on gloves and boots when climbing the utility pole to reduce the likelihood of sustaining an injury from a fall. The patient 102 may take or perform the action 126 to reduce the likelihood of a fall, which, in an embodiment, improves the health and well-being of the patient 102. Additionally, as seen in FIG. 13, no action 126 is associated with the electric shock wound type. As discussed above, the wound management system 110 may not have determined an action 126 corresponding to the electric shock wound type because the predicted likelihood for the electric shock wound type did not exceed the threshold 502. In response, the wound management system 110 provides a warning of the electrical shock wound type, but does not provide a corrective action 126 to reduce the likelihood of the electrical shock wound type.

[0092] The wound management system 110 also provides recommendations regarding lifestyle changes for the patient 102 that will reduce the risk of incurring the predicted wound type. In the example of FIG. 13, the wound management system 110 determined that eating a healthy meal before going to work may provide the patient 102 with more energy while climbing a utility pole, which may reduce the likelihood of falling. Eating a healthy meal may also keep the patient 102 up while working, which may reduce the likelihood of electrocution. In addition, the wound management system 110 determined that changing occupation to electrician or climbing instructor may reduce the likelihood that the patient 102 will incur the predicted wound type. As discussed above, the wound management system 110 may have determined these actions 126 or lifestyle changes by analyzing other clusters of patients 202 that have a lower likelihood of incurring the patient's 102 predicted wound type.

[0093] Figure 14 is a flowchart of an exemplary method 1400 implemented in the system 100 of Figure 1. In certain embodiments, the wound management system 110 implements the method 1400. By implementing the method 1400, the wound management system 110 updates or modifies the predicted likelihood for the patient 102.

[0094] In block 1402, the wound management system 110 determines that a change in the patient's occupation or habit has occurred. The wound management system 110 may determine the change by analyzing the patient's 102 activity when carrying the device 104. The wound management system 110 may determine that the patient 102 is moving to a different location or engaging in a different activity. For example, the wound management system 110 may track the location of the device 104 and determine that the patient 102 is moving to a different location that is not associated with the patient's 102 previous occupation or habit. As another example, the wound management system 110 may examine the patient's 102 social media feed and determine that the patient 102 is engaging in a different activity or hobby. As yet another example, the patient 102 may input the change into the device 104 such that the wound management system 110 determines that a change has occurred.

[0095] In block 1404, the wound management system 110 updates the health screening data 118 based on the changes determined in block 1402. For example, the wound management system 110 may update the occupation, condition, or habits of the patient 102 in the health screening data 118.

[0096] In block 1406, the wound management system 110 applies the machine learning model 120 to the updated health screening data 118 to predict the probability that the patient 102 will suffer a wound type 122 resulting from the changed occupation or habits. In other words, the wound management system 110 applies the machine learning model 120 to the updated data to determine the likelihood that the patient 102 will suffer a particular wound type 122. The machine learning model 120 may then determine from the health data 112 of these other patients 202 the likelihood that the patient 102 is likely to suffer the wound type 122.

[0097] At block 1408, the wound management system 110 determines whether the predicted probability exceeds the threshold 502. If the predicted probability does not exceed the threshold 502, the wound management system 110 may conclude. In some embodiments, the wound management system 110 still provides a warning message of the predicted wound type 122 when the predicted probability does not exceed the threshold 502. If the predicted probability exceeds the threshold 502, the wound management system 110 determines and communicates an action 126 to the device 104 of the patient 102 at block 1410. The action 126 may be a corrective action that, if taken by the patient 102, reduces the likelihood that the patient 102 will incur the predicted wound type 122. In this manner, the wound management system 110 takes a proactive approach to reduce the likelihood that the patient 102 will incur the predicted wound type, which in certain embodiments improves the health and safety of the patient 102.

[0098] FIG. 15 illustrates an example device 104 in the system 100 of FIG. 1. Generally, the device 104 of FIG. 15 illustrates a message that the wound management system 110 provides in response to detecting an update to the health screening data 118 of the patient 102. As seen in FIG. 15, the message indicates that a change has been detected in the occupation of the patient 102. Based on the change in occupation, the patient 102 is at risk of experiencing a cut. Because the wound management system 110 determines that a predicted likelihood of incurring a cut exceeds a threshold 502, the wound management system 110 provides a corrective action 126 that reduces the likelihood that the patient 102 will incur a cut. In the example of FIG. 15, the message indicates that the action 126 is to put on gloves while lifting a package. If the patient 102 puts on gloves while lifting a package, the patient 102 reduces the likelihood that the patient 102 will incur a cut.

[0099] In summary, the wound management system 110 uses machine learning to predict whether the patient 102 is likely to incur different wound types 122 based on information about the patient's 102 life. For example, the wound management system 110 may predict that if the patient 102 is a cook, the patient 102 is more likely to incur a cut or burn. As another example, the wound management system 110 may predict that if the patient 102 enjoys rock climbing, the patient 102 is more likely to incur a wound from a fall. The wound management system 110 may also prevent the predicted wound type 122 from occurring by recommending actions 126 that the patient 102 can take to reduce the likelihood of incurring the wound type 122. In this manner, the wound management system 110 provides a proactive approach towards wound treatment, which in certain embodiments improves the health and well-being of the patient 102.

[0100] Example notes Implementation examples are described in the numbered appendices below.

[0101] Supplementary Note 1: A method, comprising: collecting data related to a patient's health; and applying a machine learning model to the data related to the patient's health to predict a first probability that the patient will incur a first wound type outside of a treatment setting. The method also includes, in response to determining that the first probability exceeds a threshold, determining an action to reduce the first probability; and communicating a message to the patient indicating that an action should be taken to reduce the first probability that the patient will incur the first wound type.

[0102] Appendix 2: The method of Appendix 1, further comprising collecting a dataset indicating past physical wounds inflicted by different patients, splitting the dataset into a training dataset and a validation dataset, training a machine learning model using the training dataset, and validating the machine learning model using the validation dataset after the machine learning model has been trained.

[0103] Addendum 3: The method of any of Addendums 1-2, wherein the dataset indicates multiple wound types related to past physical wounds.

[0104] Appendix 4: The method of any of appendices 1-3, wherein the multiple wound types for the past physical wounds comprise wounds incurred during falls, self-inflicted wounds, and wounds from walking conditions.

[0105] Appendix 5: The method of any of appendices 1-4, wherein the data related to the patient's health comprises the patient's occupation or habit, and the first probability indicates the likelihood that the patient will suffer a first wound type due to the occupation or habit.

[0106] Clause 6: The method of any of Clauses 1-5, wherein the action includes wearing a type of clothing while engaging in an occupation or habit.

[0107] Addendum 7: The method of any of Addendums 1-6, wherein the action includes changing the patient's occupation.

[0108] Appendix 8: The method of any of Appendixes 1-7, further comprising predicting a second probability that the patient will incur a second wound type resulting from the occupation or practice, and in response to determining that the second probability does not exceed a threshold, communicating a message to the patient alerting them to the second wound type.

[0109] Appendix 9: The method of any of appendices 1-8, further comprising updating data related to the patient's health in response to determining that a change in occupation or habit has occurred to generate updated data, and applying a machine learning model to the updated data to predict a second probability that the patient will suffer a second wound type due to the change.

[0110] Addendum 10: The method of any of Addendums 1-9, wherein the message further indicates a healthcare facility for treating the first wound type.

[0111] Addendum 11: The method of any of Addendums 1-10, wherein the first wound type comprises a plurality of wounds.

[0112] Addendum 12: An apparatus comprising: a memory; and a hardware processor, communicatively coupled to the memory, configured to perform a method according to any one of Addendums 1-11.

[0113] Appendix 13: A non-transitory computer-readable medium comprising instructions that, when executed by a processor, cause the processor to perform a method according to any one of appendices 1-11.

[0114] Additional Considerations The foregoing description is provided to enable any person skilled in the art to practice the various embodiments described herein. The examples discussed herein are not limitations of the scope, applicability, or embodiments described in the claims. Various modifications of these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments. For example, changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components, as appropriate. For example, the methods described may be performed in different orders than those described, and various steps may be added, omitted, or combined. Also, features described with respect to some examples may be combined in some other examples. For example, an apparatus may be implemented, or a method may be practiced, using any number of aspects described herein. In addition, the scope of the disclosure is intended to cover such apparatus or methods practiced using other structure, functionality, or structure and functionality in addition to or other than the various aspects of the disclosure described herein. It should be understood that any aspect of the disclosure disclosed herein may be embodied by one or more elements of a claim.

[0115] As used herein, the word "exemplary" means "serving as an example, instance, or illustration." Any aspect described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects.

[0116] As used herein, phrases referring to "at least one of" a list of items refer to any combination of those items, including single members. By way of example, "at least one of a, b, or c" is intended to cover a, b, c, ab, ac, bc, and abc, and any combination with multiples of the same element (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbc, cc, and ccc, or any other permutation of a, b, and c).

[0117] As used herein, the term "determining" encompasses a wide variety of actions. For example, "determining" may include calculating, computing, processing, deriving, investigating, looking up (e.g., looking up in a table, database, or another data structure), ascertaining, and the like. "Determining" may also include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory), and the like. "Determining" may also include resolving, selecting, choosing, establishing, and the like.

[0118] The methods disclosed herein include one or more steps or actions for achieving the method. Method steps and / or actions may be interchanged with one another without departing from the scope of the claims. In other words, unless a specific order of steps or actions is specified, the order and / or use of specific steps and / or actions may be modified without departing from the scope of the claims. Furthermore, various operations of the methods described above may be performed by any suitable means capable of performing the corresponding functions. The means may include various hardware and / or software components and / or modules, including, but not limited to, circuits, application specific integrated circuits (ASICs), or processors. Generally, where operations are illustrated in a figure, those operations may have corresponding counterparts of means+function components with similar numbering.

[0119] The following claims are not intended to be limited to the embodiments set forth herein, but are to be accorded the full scope consistent with the claim language. Within the claims, reference to an element in the singular is not intended to mean "one and only one" unless specifically so recited, but rather, "one or more." Unless specifically recited otherwise, the term "some" refers to one or more. No claim element is to be construed under the provisions of 35 USC §112(f) unless the element is expressly recited using the phrase "means for," or, in the case of a method claim, the element is recited using the phrase "step for." All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later become known to those of skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Additionally, nothing disclosed herein is intended to be made available to the public, regardless of whether such disclosure is expressly recited in a claim.

[0120] In the foregoing, reference is made to the embodiments presented in this disclosure. However, the scope of the disclosure is not limited to the specific described embodiments. Instead, any combination of the described features and elements, whether related to different embodiments or not, is envisioned to implement and practice the envisioned embodiments. Furthermore, the embodiments disclosed herein may achieve advantages over other possible solutions or over the prior art, but whether a particular advantage is achieved by a given embodiment is not a limitation of the scope of the disclosure. Thus, the foregoing aspects, features, embodiments, and advantages are merely illustrative and are not considered elements or limitations of the appended claims unless expressly recited in the claims.

[0121] As will be appreciated by those skilled in the art, the embodiments disclosed herein may be embodied as a system, method, or computer program product. Thus, aspects may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be generally referred to herein as a "circuit," "module," or "system." Additionally, aspects may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.

[0122] Any combination of one or more computer readable media may be utilized. The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media may include the following: an electrical connection with one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium is any tangible medium that can contain or store a program for use by or in association with an instruction execution system, apparatus, or device.

[0123] The program code embodied on the computer readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

[0124] Computer program code for performing operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, or equivalent, and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or wide area network (WAN), or the connection may be made to an external computer (e.g., through the Internet using an Internet Service Provider).

[0125] Aspects of the present disclosure are described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments presented in the present disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions, executed via a processor of the computer or other programmable data processing apparatus, create means for implementing the function / acts defined in a block or blocks of the flowchart and / or block diagrams.

[0126] These computer program instructions may also be stored in a computer-readable medium, where the instructions stored in the computer-readable medium may instruct a computer, other programmable data processing apparatus, or other device to function in a particular manner to produce an article of manufacture, including instructions implementing the function / acts specified in a block or blocks of the flowcharts and / or block diagrams.

[0127] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, such that the instructions, which execute on a computer or other programmable apparatus, provide a process for implementing the function / acts defined in a block or blocks of the flowcharts and / or block diagrams, causing a series of operational steps to be performed on the computer, other programmable apparatus, or other device to generate a computer-implemented process.

[0128] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments. In this regard, each block in the flowcharts or block diagrams may represent a module, partition, or portion of code, which comprises one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions described in the blocks may occur out of the order described in the figures. For example, two blocks shown in succession may in fact be executed substantially in parallel, or the blocks may sometimes be executed in reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, may be implemented by a special-purpose hardware-based system that performs the specified functions or acts, or a combination of special-purpose hardware and computer instructions.

Claims

1. 1. A method comprising: Collecting data related to the patient's health; applying a machine learning model to the data related to the patient's health to predict a first probability that the patient will incur a first wound type outside of a treatment setting; in response to determining that the first probability exceeds a threshold, determining an action to reduce the first probability; communicating a message to the patient indicating that the action should be taken to reduce the first probability that the patient will incur the first wound type; A method comprising:

2. collecting a data set indicative of past physical wounds sustained by different patients; Splitting the dataset into a training dataset and a validation dataset; training the machine learning model using the training dataset; After the machine learning model has been trained, validating the machine learning model using the validation dataset. The method of claim 1 further comprising:

3. The method of claim 2 , wherein the dataset indicates a plurality of wound types for the past physical wounds.

4. The method of claim 3 , wherein the multiple wound types for the past physical wounds comprise wounds inflicted during falls, self-inflicted wounds, and wounds from walking conditions.

5. the data relating to the patient's health comprises the patient's occupation or habit; the first probability indicating a likelihood that the patient will suffer from the first wound type due to the occupation or habit; The method of claim 1.

6. The method of claim 5 , wherein the action includes wearing a type of clothing while engaging in the occupation or the habit.

7. The method of claim 5 , wherein the action includes changing the patient's occupation.

8. predicting a second probability that the patient will suffer a second wound type resulting from the occupation or practice; in response to determining that the second probability does not exceed the threshold, communicating a message to the patient alerting the patient to the second wound type. The method of claim 5 further comprising:

9. updating the data related to the patient's health in response to determining that a change in the occupation or the habit has occurred to generate updated data; applying the machine learning model to the updated data to predict a second probability that the patient will suffer a second wound type due to the change; and The method of claim 5 further comprising:

10. The method of claim 1 , wherein the message further indicates a healthcare facility for treating the first wound type.

11. The method of claim 1 , wherein the first wound type comprises a plurality of wounds.

12. An apparatus comprising: Memory, a hardware processor communicatively coupled to the memory, the hardware processor comprising: Collecting data related to the patient's health; applying a machine learning model to the data related to the patient's health to predict a first probability that the patient will incur a first wound type outside of a treatment setting; in response to determining that the first probability exceeds a threshold, determining an action to reduce the first probability; communicating a message to the patient indicating that the action should be taken to reduce the first probability that the patient will incur the first wound type; a hardware processor configured to: An apparatus comprising:

13. The hardware processor further comprises: collecting a data set indicative of past physical wounds sustained by different patients; Splitting the dataset into a training dataset and a validation dataset; training the machine learning model using the training dataset; After the machine learning model has been trained, validating the machine learning model using the validation dataset. The apparatus of claim 12 configured to:

14. The apparatus of claim 13 , wherein the dataset indicates a plurality of wound types for the past physical wounds.

15. The apparatus of claim 14 , wherein the multiple wound types for the past physical wounds comprise wounds inflicted during falls, self-inflicted wounds, and wounds from walking conditions.

16. the data relating to the patient's health comprises the patient's occupation or habit; the first probability indicating a likelihood that the patient will suffer from the first wound type due to the occupation or habit; 13. The apparatus of claim 12.

17. The apparatus of claim 16 , wherein the action includes wearing a type of clothing while engaging in the occupation or the habit.

18. The apparatus of claim 16 , wherein the action includes changing an occupation of the patient.

19. predicting a second probability that the patient will suffer a second wound type resulting from the occupation or practice; in response to determining that the second probability does not exceed the threshold, communicating a message to the patient alerting the patient to the second wound type.

20. The apparatus of claim 16, further comprising:

20. A non-transitory computer readable medium comprising instructions that, when executed by a processor, cause the processor to: Collecting data related to the patient's health; applying a machine learning model to the data related to the patient's health to predict a first probability that the patient will incur a first wound type outside of a treatment setting; in response to determining that the first probability exceeds a threshold, determining an action to reduce the first probability; communicating a message to the patient indicating that the action should be taken to reduce the first probability that the patient will incur the first wound type; A non-transitory computer readable medium for causing

Images