Methods for diagnosing and treating deep tissue injury using subepidermal water measurement - Patents.com

Abstract

The present disclosure provides methods, devices, and computer readable media for measuring subepidermal moisture in a patient to determine deep tissue damage for clinical intervention. The present disclosure also provides methods for detecting and predicting deep tissue damage. The present disclosure further provides methods for determining appropriate clinical interventions, including preventative measures and treatments for deep tissue damage.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Application No. 63 / 158,713, filed March 9, 2021, and U.S. Provisional Application No. 63 / 316,218, filed March 3, 2022, each of which is incorporated by reference in its entirety herein.

[0002] The present disclosure provides systems, devices, and computer readable media for measuring subepidermal water in a patient to determine damaged tissue for clinical intervention. The present disclosure also provides methods for determining damaged tissue. The present disclosure further provides methods for determining appropriate clinical intervention, including preventative measures and treatments for deep tissue damage. [Background technology]

[0003] Skin is the largest organ in the human body and is subject to many types of damage and injury. When the skin and surrounding tissues are unable to redistribute external pressure and mechanical forces, pressure ulcers (also known as pressure injuries or bed sores) can form. Pressure ulcers pose a significant health and economic concern internationally across both acute and long-term care settings. Pressure ulcers affect approximately 2.5 million people annually in the United States and a similar number in Europe. In long-term and critical care settings, up to 25% of elderly and bedridden patients develop pressure ulcers. Approximately 60,000 U.S. patients die each year from infections and other complications from pressure ulcers.

[0004] Most pressure ulcers develop over bony prominences where there is less tissue to compress and pressure gradients within the vascular network change. Pressure ulcers are classified into one of four stages ranging from an early stage (stage 1), where the skin remains intact but may appear red over the bony prominence, to a final stage (stage 4), where the tissue breaks down and bone, tendon, or muscle is exposed. In addition to the four stages of pressure ulcers, there are also unique forms of ulcers known as deep tissue injuries (DTIs) or deep tissue pressure injuries (DTPIs). See, for example, "Deep Tissue Injury," National Pressure Ulcer Advisory Panel (NPUAP) White Paper, available at npiap.com (2004). DTIs are pressure-related injuries to the subcutaneous tissue beneath the intact skin. These injuries have the appearance of a deep bruise and begin in the muscle layer next to the bony prominence and develop outward toward the epidermis layer. Due to the etiology of DTI, it is often difficult to precisely classify DTI into one of the four stages above. DTI can also develop over a relatively short period of time and often rapidly deteriorate into stage 3 and stage 4 ulcers.

[0005] Currently, DTI is diagnosed through visual inspection of localized areas of purple or maroon coloration of discolored intact skin or blisters containing blood due to damage to the underlying soft tissue. Therefore, DTI can be difficult to detect in individuals with darker skin tones. Furthermore, visual inspection of DTI can also lead to misclassification under stage 1 or stage 2 ulcers that do not represent the true and dangerous potential of the damage.

[0006] To treat pressure ulcers in a timely and effective manner, clinicians need to be able to precisely identify the presence of DTI and distinguish it from the early stages of ulceration. However, the current standard for detecting pressure ulcers is by visual inspection, which is subjective, unreliable, untimely, and lacking specificity. Summary of the Invention

[0007] The present disclosure provides and includes systems, devices, and methods for detecting deep tissue injury (DTI). In one aspect, the present disclosure provides a method for 1) detecting deep tissue injury (DTI) before it becomes visible on a patient's skin, the method comprising: a) acquiring a set of SEM delta values ​​at a location on the patient's skin at a predetermined frequency; b) applying a predetermined weight to each of the acquired set of SEM delta values; c) calculating a first average SEM delta value of the N oldest weighted SEM delta values; d) calculating a second average SEM delta value of the M most recent weighted SEM delta values; e) comparing a difference between the first average SEM delta value and the second average SEM delta value to a predetermined threshold; and f) determining that a DTI is present at the location on the patient's skin when the difference exceeds the predetermined threshold. In one aspect, the acquired set of SEM delta values ​​includes at least five SEM delta values, each taken at one-day intervals. In one aspect, the predetermined weight is in the range of 0 to 2. In some embodiments, the predetermined weights increase monotonically over time. In some embodiments, N>M. In some embodiments, N is 4 and M is 2. In some embodiments, the predetermined threshold is a real number in the range of 0 to 1. In some embodiments, the most recent SEM delta value is obtained by linear extrapolation of the K most recent SEM delta values. In some embodiments, K is 3. In some embodiments, the predetermined threshold is 0.7. In some embodiments, the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the coccyx, the buttocks, the lower back, the inner knees, the heels, and combinations thereof.

[0008] The present disclosure also provides a computer-implemented method for training a neural network to detect deep tissue injury (DTI) before the injury is visible on a patient's skin, the computer-implemented method including: a) acquiring, for each patient of a first plurality of patients who have been diagnosed with a DTI, a first set of subepidermal moisture (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency before and until the formation of the DTI; b) acquiring, for each patient of a second plurality of patients who have not been diagnosed with a DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency; c) applying a set of weights to each of the acquired first and second set of SEM delta values; d) creating a training set including the first set of weighted SEM delta values ​​and the second set of weighted SEM delta values ​​for all patients of the first and second plurality of patients; and e) training the neural network using the training set. In an embodiment, the trained neural network outputs a set of optimized weights, including optimized weights for each time point prior to formation of the DTI, and the optimized weights monotonically increase over time. In an embodiment, the method further includes a) for each patient of the first plurality of patients and the second plurality of patients, i) calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set of SEM delta values, ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values, iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value, iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold, b) creating a training set including the first set of difference values ​​for the first plurality of patients and the second set of difference values ​​for the second plurality of patients, and c) training the neural network using the training set. In an embodiment, the predetermined frequency is once a day. In some embodiments, the first and second sets of SEM delta values ​​comprise at least six SEM delta values, each taken at one-day intervals. In some embodiments, N+M=6.In some embodiments, N = 4 and M = 2. In some embodiments, the location on the patient's skin is selected from the group consisting of the back of the head, sacrum, shoulders, elbows, lower back, tailbone, buttocks, lower back, inner knees, heels, and combinations thereof.

[0009] The present disclosure also provides a computer-implemented method for training a neural network to detect deep tissue injury (DTI) before the injury is visible on a patient's skin, comprising: a) acquiring, for each patient of a first plurality of patients experiencing a DTI, a first set of subepidermal moisture (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency prior to and until the formation of the DTI; b) acquiring, for each patient of a second plurality of patients not experiencing a DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency; c) applying a set of weights to each of the acquired first and second set of SEM delta values; and d) for each patient of the first and second plurality of patients, acquiring a first set of subepidermal moisture (SEM) delta values ​​at a predetermined frequency prior to and until the formation of the DTI. i) calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set of SEM delta values, ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values, iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value, iv) comparing a difference between the first average SEM delta value and the second average SEM delta value to a threshold, e) creating a training set including a first set of difference values ​​in a first plurality of patients and a second set of difference values ​​in a second plurality of patients, and f) training a neural network using the training set. In one embodiment, the trained neural network outputs a) a set of optimized weights including optimized weights for each time point prior to formation of the DTI, the optimized weights increasing monotonically over time, b) an optimized threshold, c) a value of N, and d) a value of M. In one embodiment, the predetermined frequency is once a day. In some embodiments, the first and second sets of SEM delta values ​​include at least six SEM delta values, each taken one day apart. In some embodiments, N+M=6. In some embodiments, N=4 and M=2. In some embodiments, the location on the patient's skin is selected from the group consisting of the back of the head, sacrum, shoulders, elbows, lower back, coccyx, buttocks, lower back, inner knees, heels, and combinations thereof.In one aspect, the optimized set of weights and the optimized threshold are used to predict the occurrence of deep tissue damage.

[0010] The present disclosure provides and includes a non-transitory computer readable medium for identifying DTI tissue. The non-transitory computer readable medium may include instructions stored thereon that, when executed on a processor, may perform the steps of: a) acquiring a set of SEM delta values ​​at a location on a patient's skin at a predetermined frequency; b) applying a predetermined weight to each of the acquired set of SEM delta values; c) calculating a first average SEM delta value of the N oldest weighted SEM delta values; d) calculating a second average SEM delta value of the M most recent weighted SEM delta values; e) comparing a difference between the first average SEM delta value and the second average SEM delta value to a predetermined threshold; and f) determining that DTI is present at the location on the patient's skin when the difference exceeds the predetermined threshold. In an embodiment, the acquired set of SEM delta values ​​includes at least five SEM delta values, the SEM delta values ​​each taken at one-day intervals. In an embodiment, the predetermined weight is in the range of 0 to 2. In some embodiments, the predetermined weights increase monotonically over time. In some embodiments, N>M. In some embodiments, N is 4 and M is 2. In some embodiments, the predetermined threshold is a real number in the range of 0 to 1. In some embodiments, the most recent SEM delta value is obtained by linear extrapolation of the K most recent SEM delta values. In some embodiments, K is 3. In some embodiments, the predetermined threshold is 0.7. In some embodiments, the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the coccyx, the buttocks, the lower back, the inner knees, the heels, and combinations thereof.

[0011] The present disclosure provides and includes a non-transitory computer readable medium for identifying DTI tissue, which may include instructions stored thereon that, when executed on a processor, may perform the steps of: a) acquiring, for each patient of a first plurality of patients diagnosed with DTI, a first set of subepidermal moisture (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency prior to and until the formation of the DTI, b) acquiring, for each patient of a second plurality of patients not diagnosed with DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency, c) applying a set of weights to each of the acquired first and second set of SEM delta values, d) creating a training set including the first and second set of weighted SEM delta values ​​for all patients of the first and second plurality of patients, and e) training a neural network using the training set. In an embodiment, the trained neural network outputs a set of optimized weights, including optimized weights for each time point prior to formation of the DTI, and the optimized weights monotonically increase over time. In an embodiment, the method further includes a) for each patient of the first plurality of patients and the second plurality of patients, i) calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set of SEM delta values, ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values, iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value, iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold, b) creating a training set including the first set of difference values ​​for the first plurality of patients and the second set of difference values ​​for the second plurality of patients, and c) training the neural network using the training set. In an embodiment, the predetermined frequency is once a day. In one embodiment, the first and second sets of SEM delta values ​​comprise at least six SEM delta values, the SEM delta values ​​each taken at one-day intervals.In some embodiments, N+M = 6. In some embodiments, N = 4 and M = 2. In some embodiments, the location on the patient's skin is selected from the group consisting of the back of the head, sacrum, shoulders, elbows, lower back, tailbone, buttocks, lower back, inner knees, heels, and combinations thereof.

[0012] The present disclosure provides and includes a non-transitory computer readable medium for identifying DTI tissue, which may include instructions stored thereon that, when executed on a processor, include the steps of: a) acquiring, for each patient of a first plurality of patients experiencing a DTI, a first set of subepidermal hydration (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency prior to and until the formation of the DTI, b) acquiring, for each patient of a second plurality of patients not experiencing a DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency, c) applying a set of weights to each of the acquired first and second set of SEM delta values, and d) for each patient of the first and second plurality of patients: i) calculating a weight of the SEM delta values ​​from the weights of ... The method may include the steps of: calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set; ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values; iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value; iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold; e) creating a training set including a first set of difference values ​​for a first plurality of patients and a second set of difference values ​​for a second plurality of patients; and f) training the neural network using the training set. In one embodiment, the trained neural network outputs: a) a set of optimized weights including optimized weights for each time point prior to formation of the DTI, the optimized weights increasing monotonically over time; b) an optimized threshold; c) a value of N; and d) a value of M. In one embodiment, the predetermined frequency is once a day. In some embodiments, the first and second sets of SEM delta values ​​include at least six SEM delta values, each taken at one-day intervals. In some embodiments, N+M=6. In some embodiments, N=4 and M=2.In some aspects, the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the tailbone, the hips, the lower back, the inner knees, the heels, and combinations thereof. In some aspects, the optimized set of weights and the optimized thresholds are used to predict the occurrence of deep tissue damage.

[0013] The present disclosure provides and includes a computer-implemented method for predicting deep tissue injury (DTI), the method including: receiving, via an input device, a plurality of subepidermal moisture (SEM) delta values ​​associated with a patient; automatically inputting, via a processor, the plurality of SEM delta values ​​into a trained model to receive a probability value, the model being configured to predict a probability value corresponding to a future occurrence of the patient developing a DTI, the model being trained based on a set of training data including SEM delta data from a set of patients; and outputting, via an output device, a prediction of the future occurrence of the patient developing a DTI based on the probability value. In one aspect, training the model includes receiving, via an input device, a set of training data, the set of training data including: 1) a plurality of subepidermal moisture (SEM) delta values ​​associated with a set of patients, and 2) a threshold value, where each patient in the set of patients has a known deep tissue injury (DTI) status, the threshold value being a number between 0 and 1; automatically inputting, via a processor, the training data into an optimization algorithm to receive a plurality of optimal weight values; and automatically updating, via the processor, the model with the plurality of optimal weight values.In one aspect, the optimization algorithm is configured to generate a plurality of increasing random numbers between 0 and 2 as a plurality of weight values; input the training data and the plurality of weight values ​​into a model to receive a set of predicted deep tissue injury (DTI) statuses associated with a set of patients; compare the predicted DTI statuses to known DTI statuses associated with the set of patients; and calculate a true positive rate (TPR) and a false positive rate (FPR) based on the comparison, where the TPR is calculated as a percentage of patients in the set of patients whose predicted DTI statuses match their known DTI statuses and the FPR is calculated as a percentage of patients in the set of patients whose predicted DTI statuses do not match their known DTI statuses; repeat steps a) to d) for a predetermined number of iterations; identify an optimal TPR and FPR from all calculated TPRs and FPRs from the iterations; and output a plurality of optimal weight values ​​associated with the identified optimal TPRs and FPRs. In one embodiment, the plurality of SEM delta values ​​includes SEM delta readings from a predetermined number of days prior to the date predicting deep tissue injury (DTI). In one embodiment, identifying the optimal TPR and FPR includes minimizing an objective function of 1-TPR+FPR and satisfying the constraint TPR>>FPR. In one embodiment, the input device is a SEM scanner. In one embodiment, the SEM scanner is connected to the computer by cable or wireless technology. In one embodiment, the DTI occurs at a location selected from the group consisting of the back of the head, sacrum, shoulders, elbows, lower back, coccyx, hips, lower back, inner knees, heels, and combinations thereof.

[0014] The present disclosure provides and includes a method for assessing a risk of deep tissue injury (DTI) in a patient, the method including: receiving a plurality of subepidermal moisture (SEM) delta values ​​associated with the patient; inputting the plurality of SEM delta values ​​into a trained model to receive a probability value, the model configured to predict a probability value corresponding to a future occurrence of the patient developing a DTI, the model being trained based on a set of training data including SEM delta data of a set of patients; outputting a prediction of a likelihood of the patient's future DTI occurrence based on the probability value; and assessing the risk of the patient developing a DTI based on the predicted likelihood of the future DTI occurrence. In an aspect, the predicted future occurrence is classified as no DTI, low probability of DTI, high probability of DTI, or suspected DTI. In an aspect, the method further includes selecting an intervention for the patient based on the assessed risk of DTI. In some aspects, the intervention includes at least one of reducing pressure, repositioning the patient, changing the patient's support surface, providing a mattress with low friction padding, providing a silicone pad, providing a heel boot, cleaning and dressing the wound, removing damaged tissue, applying a topical cream, applying a barrier cream, applying neuromuscular stimulation, administering medication, and surgery. In some aspects, the DTI occurs at a location selected from the group consisting of the occipital region, sacrum, shoulder, elbow, lower back, coccyx, buttocks, lower back, inner knee, heel, and combinations thereof. In some aspects, the method further includes generating or updating a report from performing the method. In some aspects, the method further includes communicating the report to the patient or clinician. In some aspects, the method further includes storing the report in a non-transitory computer readable storage medium. In some aspects, the method further includes displaying the report on a computer display.

[0015] The present disclosure provides and includes a non-transitory computer-readable storage medium comprising one or more programs for execution by one or more processors of a device, the one or more programs including instructions that, when executed by the one or more processors, cause the device to perform a method of any one of the above embodiments. In an aspect, the non-transitory computer-readable storage medium further includes a report generated from performing the method of any one of the above embodiments.

[0016] The present disclosure provides and includes an electronic device comprising one or more processors, a memory, and one or more programs, the one or more programs including instructions that, when executed by the one or more processors, cause the device to perform the method of any one of the above embodiments. In an aspect, the electronic device further comprises one or more displays for presenting a report generated from performing the method of any one of the above embodiments. [Brief description of the drawings]

[0017] Some aspects of the present disclosure are described herein, by way of example only, with reference to the accompanying drawings. Now, with specific reference to the drawings in detail, it is emphasized that the details shown are by way of example and for purposes of illustrative discussion of embodiments of the present disclosure. In this regard, the description taken together with the drawings will make apparent to those skilled in the art how aspects of the present disclosure may be practiced.

[0018] [Figure 1A] 1 is an exemplary device according to the present disclosure comprising one coaxial electrode. [Figure 1B] 13 is an illustration of an exemplary method of using an exemplary apparatus according to the present disclosure for measuring SEM delta values ​​to detect potential DTI. [Figure 2A] Sample SEM delta values ​​taken from patients diagnosed with DTI (left) and patients not diagnosed with DTI (right). [Figure 2B] 1 illustrates an exemplary method for detecting DTI according to the present disclosure. [Diagram 3] Sample SEM delta values ​​taken from patients. [Figure 4] 1 is an exemplary manner of partitioning data for processing. [Figure 5A] 1 is a flow chart illustrating an example method for predicting DTI according to the present disclosure. [Figure 5B] 4 is a flow chart illustrating an example method for optimizing weights according to the present disclosure. [Figure 6] Optimized weights and thresholds for samples according to the present disclosure. [Figure 7] 1 is an exemplary method for predicting the formation of a DTI according to the present disclosure. [Figure 8] 13 shows the results of an exemplary prediction and detection method according to the present disclosure. [Figure 9] 1 illustrates an exemplary system according to certain aspects of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] This description is not intended to be a detailed listing of all the different ways in which the disclosure may be implemented or all the features that may be added to the disclosure. For example, features illustrated with respect to one embodiment may be incorporated in other embodiments, and features illustrated with respect to a particular embodiment may be deleted from that embodiment. Thus, the disclosure contemplates that in some embodiments of the disclosure, any feature or combination of features described herein may be excluded or omitted. In addition, modifications and additions to the various embodiments suggested herein will be apparent to those skilled in the art in light of the disclosure, and do not depart from the disclosure. In other instances, well-known structures, interfaces, and processes have not been shown in detail so as not to unnecessarily obscure the invention. No part of this specification is intended to result in a denial of any portion of the full scope of the invention. Thus, the following description is intended to illustrate some specific embodiments of the disclosure, without exhaustively specifying all rearrangements, combinations, and modifications thereof.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terms used in the description of the present disclosure herein are for the purpose of describing particular embodiments only and are not intended to be limiting of the present disclosure.

[0021] All publications, patent applications, patents, and other references cited herein are incorporated by reference in their entirety for the teachings related to the sentence and / or paragraph in which the reference is presented. References to techniques employed herein are intended to refer to techniques as commonly understood in the art, including variations of those techniques or substitutions of equivalent techniques that would be apparent to one of ordinary skill in the art.

[0022] Unless the context indicates otherwise, it is specifically contemplated that the various features of the present disclosure described herein can be used in any combination. Further, the present disclosure also contemplates that in some embodiments of the present disclosure, any feature or combination of features described herein can be excluded or omitted.

[0023] The methods disclosed herein include one or more steps or actions for achieving the described method. The steps and / or actions of the methods may be interchanged with one another without departing from the scope of the invention. In other words, unless a specific order of steps or actions is required for proper operation of an embodiment, the order and / or use of specific steps and / or actions may be modified without departing from the scope of the invention.

[0024] As used in the description of this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0025] As used herein, "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items, as well as the lack of a combination if interpreted otherwise ("or").

[0026] The terms "about" and "approximately" when used herein when referring to a measurable value such as length, frequency, or SEM delta value are intended to encompass variations of as much as ±20%, ±10%, ±5%, ±1%, ±0.5%, or ±0.1% of the specified amount.

[0027] As used herein, phrases such as "between X and Y" and "between about X and Y" should be interpreted to include X and Y. As used herein, phrases such as "between about X and Y" mean "between about X and about Y," and phrases such as "about X to Y" mean "about X to about Y."

[0028] As used herein, the term "exemplary" is used herein to mean serving as an example, instance, or illustration. Any aspect or aspects described as "exemplary" should not necessarily be construed as preferred or advantageous over other aspects or aspects, nor is it meant to exclude equivalent structures and techniques known to those skilled in the art. Rather, use of the word exemplary is intended to present concepts in a specific manner, and the disclosed subject matter is not limited by such examples.

[0029] As used herein, the term "subepidermal moisture" or "SEM" refers to the amount of water in skin tissue below the epidermis. SEM can include intracellular and extracellular fluid. Without being bound by theory, when skin tissue is injured, inflammation at the injured site can dilate blood vessels and increase blood flow into the skin tissue. There is also an increase in vascular permeability, allowing fluid, proteins, and white blood cells to migrate from the circulation to the skin tissue injury site. The intense influx of fluid, cells, and other substances into the injured site results in swelling and redness, increasing the amount of SEM in the injured skin tissue. Processes such as apoptosis and necrosis can also increase the amount of fluid in the injured area. SEM can be measured, for example, by measuring biocapacitance. In some aspects, the methods described herein include obtaining SEM values ​​in tissue. In some aspects, the methods described herein include obtaining SEM values ​​in skin. In some aspects, the methods described herein include obtaining SEM values ​​in the subepidermal layer of skin. In some aspects, the methods described herein include obtaining SEM delta values ​​in tissue. In some aspects, the methods described herein include obtaining SEM delta values ​​at skin. In some aspects, the methods described herein include obtaining a set of SEM values ​​at tissue. In some aspects, the methods described herein include obtaining a set of SEM values ​​at skin. In some aspects, the methods described herein include obtaining a set of SEM delta values ​​at tissue. In some aspects, the methods described herein include obtaining a set of SEM delta values ​​at skin. In some aspects, the set of SEM delta values ​​includes multiple SEM delta values ​​taken at different times. In some aspects, the set of SEM delta values ​​includes multiple SEM delta values ​​taken simultaneously.

[0030] As used herein, "SEM delta value" or "SEM-Δ value" refers to the calculated difference between two values ​​derived from SEM measurements taken at the same tissue location or at approximately the same time regardless of tissue location.

[0031] In some embodiments, each of the two values ​​is a SEM measurement taken at approximately the same time as the other. In some embodiments, each of the two values ​​is an average value determined from a subset of multiple SEM measurements taken at approximately the same time. In some embodiments, the two values ​​are a SEM measurement and an average value determined from multiple SEM measurements taken at approximately the same time. In some embodiments, the two values ​​are a maximum SEM measurement and a SEM measurement taken at approximately the same time. In some embodiments, the two values ​​are a maximum SEM measurement and an average value determined from multiple SEM measurements taken at approximately the same time. In some embodiments, the two values ​​are a maximum SEM measurement and a minimum SEM measurement determined from multiple SEM measurements taken at approximately the same time.

[0032] In some embodiments, each of the two values ​​is a SEM measurement taken at the same tissue location. In some embodiments, each of the two values ​​is an average SEM value determined from a subset of multiple SEM measurements taken at the same tissue location. In some embodiments, the two values ​​are SEM measurements and an average value determined from multiple SEM measurements taken at the same tissue location. In some embodiments, the two values ​​are a maximum SEM measurement and a SEM measurement taken at the same tissue location. In some embodiments, the two values ​​are a maximum SEM measurement and an average value determined from multiple SEM measurements taken at the same tissue location. In some embodiments, the two values ​​are a maximum SEM measurement and a minimum SEM measurement determined from multiple SEM measurements taken at the same tissue location. In some embodiments, the two SEM measurements taken at the same tissue location are measurements taken at spatially distinct locations on the tissue. In some embodiments, the two SEM measurements taken at the same tissue location are measurements taken at overlapping locations on the tissue. In some embodiments, the tissue location is centered on an anatomical site, including, but not limited to, the sternum, sacrum, heel, scapula, elbow, ear, or other fleshy tissue. In some embodiments, taking multiple SEM measurements at the same tissue location includes taking measurements at and around the anatomical location. In some embodiments, taking multiple SEM measurements at the same tissue location includes taking measurements at and around the anatomical location based on a measurement map. Exemplary measurement maps can be found, for example, in U.S. Patent Application Serial No. 17 / 591,139 or U.S. Patent No. 9,763,596, which are incorporated herein in their entireties.

[0033] In some embodiments, the average SEM value is determined for several SEM values ​​measured at approximately the same time at each spatial location surrounding the anatomical site. In some embodiments, the SEM delta value is the difference between each of the maximum average SEM value and the average SEM value measured around the anatomical site at approximately the same time. In some embodiments, the SEM delta value is the difference between the maximum average SEM value and the minimum average SEM value measured around the anatomical site at approximately the same time. In some embodiments, the "SEM delta value" may also refer to the calculated difference between two values ​​derived from measurements taken around the same tissue location at different times. In some embodiments, two measurements are taken approximately simultaneously when they are taken about 10 hours or less apart, about 8 hours or less apart, about 6 hours or less apart, about 5 hours or less apart, about 4 hours or less apart, about 3 hours or less apart, about 2 hours or less apart, or about 1 hour or less apart.

[0034] As used herein, the term "tissue biocapacitance" refers to a biophysical marker for detecting early tissue damage based on increased levels of fluid accumulating in the interstitial space. Without being bound by theory, the greater the fluid content in the tissue, the higher the biocapacitance value. In some aspects, the methods described herein include measuring biocapacitance in tissue. In some aspects, the methods described herein include measuring biocapacitance of skin. In some aspects, the biocapacitance measured by the methods described herein varies linearly with the SEM in the tissue. In some aspects, the biocapacitance measured by the methods described herein varies non-linearly with the SEM in the tissue.

[0035] As used herein, a "system" may be a collection of devices in wired or wireless communication with each other.

[0036] As used herein, "probing" refers to the use of radio frequency energy to penetrate the skin of a patient.

[0037] As used herein, a "patient" may be a human or animal subject.

[0038] As used herein, a "weight" is a numerical coefficient assigned to a SEM delta value to express its relative importance in the distribution of SEM delta values. Without being bound by theory, a weight may adjust the contribution of SEM measurements on different days compared to the present.

[0039] As used herein, a "neural network" is an artificial neural network that includes artificial neurons or nodes that use a mathematical or computational model for information processing based on a connectionist approach to computation. A neural network may perform supervised learning of a function that maps inputs to outputs based on exemplary input-output pairs. The exemplary input-output pairs may be provided to the neural network as a "training set."

[0040] As used herein, an "electrode sensor" is an electrode that detects an electrical property. In some embodiments, the electrode sensor comprises one electrode. In some embodiments, the electrode sensor comprises two electrodes. In some embodiments, the electrode sensor comprises two electrodes arranged in a coaxial configuration. In some embodiments, the electrode sensor comprises two electrodes arranged in close proximity to each other.

[0041] As used herein, "prevention" or "preventing" in reference to a condition or disease is an approach to reduce the risk of developing a condition or disease before it manifests in a patient, or to slow or stop the progression of a condition or disease once it has manifested. Preventive approaches include, but are not limited to, identifying a disease at an early stage of the disease so that prompt and appropriate management can be initiated, protecting the condition or tissues susceptible to the disease before it manifests, reducing or minimizing the consequences of the disease, and combinations thereof. In some embodiments, DTIs are prevented when DTIs are not formed. In some embodiments, DTIs are prevented when formed DTIs are not worsened.

[0042] As used herein, "treatment" or "treating" with respect to a condition or disease is an approach to obtain a beneficial or desired result, preferably including clinical results after the condition or disease appears in a patient. Beneficial or desired results with respect to a disease include, but are not limited to, one or more of improving a condition associated with the disease, curing the disease, reducing the severity of the disease, slowing the progression of the disease, alleviating one or more symptoms associated with the disease, improving the quality of life of a person suffering from the disease, prolonging survival, and combinations thereof. Similarly, for purposes of this disclosure, beneficial or desired results with respect to a disease include, but are not limited to, one or more of improving a condition, curing the disease, reducing the severity of the condition, slowing the progression of the condition, alleviating one or more symptoms associated with the condition, improving the quality of life of a person suffering from the condition, prolonging survival, and combinations thereof.

[0043] Exemplary devices according to the present disclosure are shown in Figures 1A and 1B. It will be understood that these are examples of devices for measuring subepidermal moisture. In some embodiments, devices according to the present disclosure can be handheld devices, portable devices, wired devices, wireless devices, or devices that are fixed to measure a portion of a human patient. U.S. Patent Nos. 9,220,455 and 9,398,879 to Sarrafzadeh et al. and 10,182,740 to Tonar et al. are directed to different SEM scanning devices. U.S. Patent Nos. 9,220,455, 9,398,879, and 10,182,740 are all incorporated herein by reference in their entirety.

[0044] Method of detection In an embodiment, the present disclosure provides a method for detecting deep tissue injury (DTI) before it becomes visible on a patient's skin, the method comprising: a) acquiring a set of SEM delta values ​​at a location on the patient's skin at a predetermined frequency; b) applying a predetermined weight to each of the acquired set of SEM delta values; c) calculating a first average SEM delta value of the N oldest weighted SEM delta values; d) calculating a second average SEM delta value of the M most recent weighted SEM delta values; e) comparing a difference between the first average SEM delta value and the second average SEM delta value to a predetermined threshold; and f) determining that a DTI is present at the location on the patient's skin when the difference exceeds the predetermined threshold. In an embodiment, the acquired set of SEM delta values ​​includes at least five SEM delta values, each taken at one-day intervals. In an embodiment, the predetermined weight is in the range of 0 to 2. In an embodiment, the predetermined weight increases monotonically over time. In an embodiment, N>M. In some embodiments, N is 4 and M is 2. In some embodiments, the predetermined threshold is a real number in the range of 0 to 1. In some embodiments, the most recent SEM delta value is obtained by linear extrapolation of the K most recent SEM delta values. In some embodiments, K is 3. In some embodiments, the predetermined threshold is 0.7.

[0045] In some embodiments, the set of SEM delta values ​​includes a plurality of SEM delta values ​​taken at different times, hi some embodiments, the set of SEM delta values ​​includes a plurality of SEM delta values ​​taken at a predetermined frequency. In certain embodiments, the predetermined frequency is once a month, once every two weeks, once a week, once every five days, once every four days, once every three days, once every two days, once a day, once every 24 hours, once every 23 hours, once every 22 hours, once every 21 hours, once every 19 hours, once every 18 hours, once every 17 hours, once every 16 hours, once every 15 hours, once every 14 hours, once every 13 hours, once every 12 hours, once every 11 hours, once every 10 hours, once every 9 hours, once every 8 hours, once every 7 hours, once every 6 hours, once every 5 hours, once every 4 hours, once every 3 hours, once every 2 hours, once every hour, once every 60 minutes, once every 30 minutes, once every 15 minutes, once every 10 minutes, once every 5 minutes, once every 2 minutes. In some embodiments, the set of SEM delta values ​​includes 10 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 9 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 8 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 7 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 6 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 5 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 4 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 3 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 2 SEM delta values ​​obtained once every 24 hours.

[0046] In an embodiment, a set of weights is applied to each SEM delta value in the set of SEM delta values. In an embodiment, the set of weights is predetermined. In an embodiment, a first predetermined weight is applied to a first SEM delta value in the set of SEM delta values. In an embodiment, a second predetermined weight is applied to a second SEM delta value in the set of SEM delta values. In an embodiment, the predetermined weights applied to SEM delta values ​​in the set of SEM delta values ​​are determined by the time at which the SEM delta value is obtained compared to the current time. In an embodiment, a larger weight is applied to a more recently obtained SEM delta value than a SEM delta value obtained at an earlier time. In an embodiment, a smaller weight is applied to a SEM delta value obtained at an earlier time compared to a more recently obtained SEM delta value. In an embodiment, the predetermined weights increase monotonically with time. In an embodiment, the predetermined weights are in the range of 0 to 2. In some aspects, the predetermined weights are about 2, about 1.9, about 1.8, about 1.7, about 1.6, about 1.5, about 1.4, about 1.3, about 1.2, about 1.1, about 1.0, about 0.9, about 0.8, about 0.7, about 0.6, about 0.5, about 0.4, about 0.3, about 0.2, about 0.1, or about 0.0. In some aspects, the predetermined weights are obtained from the results of a supervised learning algorithm. In some aspects, the predetermined weights are obtained from the results of an unsupervised learning algorithm.

[0047] In an embodiment, an average SEM delta value is calculated from a set of SEM delta values. In an embodiment, an average SEM delta value is calculated from a subset of the SEM delta values. In an embodiment, a first average SEM delta value is calculated from the N oldest weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the M newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the five oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the four oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the two newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the three oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the three newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the two oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the four most recent weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the one oldest weighted SEM delta value and a second average SEM delta value is calculated from the five most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the most recent weighted SEM delta value and a first average SEM delta value is calculated from the next five most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the two most recent weighted SEM delta values ​​and a first average SEM delta value is calculated from the next four most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the three most recent weighted SEM delta values ​​and a first average SEM delta value is calculated from the next three most recent weighted SEM delta values. In one embodiment, the second average SEM delta value is calculated from the four most recent weighted SEM delta values, and the first average SEM delta value is calculated from the next two most recent weighted SEM delta values.In some embodiments, the second average SEM delta value is calculated from the 5 most recent weighted SEM delta values ​​and the first average SEM delta value is calculated from the next most recent weighted SEM delta value. In some embodiments, N+M=3. In some embodiments, N+M=4. In some embodiments, N+M=5. In some embodiments, N+M=6. In some embodiments, N+M=7. In some embodiments, N+M=8. In some embodiments, N+M=9. In some embodiments, N+M=10. In some embodiments, N=1, 2, 3, 4, 5, 6, 7, 8, 9, or 10. In some embodiments, M=1, 2, 3, 4, 5, 6, 7, 8, 9, or 10. In some embodiments, multiple SEM delta values ​​associated with a patient are obtained periodically over a predetermined time interval prior to risk assessment. In certain embodiments, the predetermined time interval prior to risk assessment is 1 day, 2 days, 3 days, 4 days, 5 days, 6 days, 7 days, 8 days, 9 days, or 10 days.

[0048] In some embodiments, a difference between the first average SEM delta value and the second average SEM delta value is calculated. In some embodiments, the difference between the first average SEM delta value and the second average SEM delta value is compared to a predetermined threshold. In some embodiments, the predetermined threshold is zero. In some embodiments, the predetermined threshold is a positive value. In some embodiments, the predetermined threshold is a negative value. In some embodiments, a positive difference between the first average SEM delta value and the second average SEM delta value indicates deep tissue damage. In some embodiments, a non-positive or zero difference between the first average SEM delta value and the second average SEM delta value indicates no deep tissue damage. In some embodiments, a positive difference between the average of the most recent SEM delta value and the average of the oldest SEM delta value indicates deep tissue damage. In some embodiments, a non-positive or zero difference between the average of the most recent SEM delta value and the average of the oldest SEM delta value indicates no deep tissue damage. In some embodiments, the predetermined threshold is a real number in the range of 0 to 1. In some embodiments, the pre-defined threshold is about 0.1, about 0.2, about 0.3, about 0.4, about 0.5, about 0.6, about 0.7, about 0.8, about 0.9, about 1.0, In some embodiments, a DTI is determined to be present at a location on the patient's skin when the difference exceeds the pre-defined threshold.

[0049] Training Methods In an aspect, the disclosure provides a computer-implemented method for training a neural network to detect deep tissue injury (DTI) before the injury is visible on a patient's skin, the computer-implemented method including: a) acquiring, for each patient of a first plurality of patients diagnosed with a DTI, a first set of subepidermal moisture (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency before and until the formation of the DTI; b) acquiring, for each patient of a second plurality of patients not diagnosed with a DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency; c) applying a set of weights to each of the acquired first and second set of SEM delta values; d) creating a training set including the first set of weighted SEM delta values ​​and the second set of weighted SEM delta values ​​for all patients of the first and second plurality of patients; and e) training the neural network using the training set.

[0050] In some embodiments, the neural network is a single layer neural network. In some embodiments, the neural network is a multi-layer neural network. In some embodiments, the neural network includes at least one hidden layer, at least two hidden layers, at least three hidden layers, at least four hidden layers, or at least five hidden layers. In some embodiments, the neural network uses a supervised learning algorithm. In some embodiments, the neural network uses an unsupervised learning algorithm.

[0051] In an embodiment, the first plurality of patients has been diagnosed with a DTI. In an embodiment, for each patient of the first plurality of patients, a first set of SEM delta values ​​is acquired at a location on the patient's skin. In an embodiment, the first set of SEM delta values ​​is acquired at a predetermined frequency prior to and until the formation of a DTI. In an embodiment, the second plurality of patients has not been diagnosed with a DTI. In an embodiment, for each patient of the second plurality of patients, a second set of SEM delta values ​​is acquired at a location on the patient's skin. In an embodiment, the second set of SEM delta values ​​is acquired at the same predetermined frequency as the first set of SEM delta values. In an embodiment, the set of SEM delta values ​​includes a plurality of SEM delta values ​​acquired at different times. In an embodiment, the set of SEM delta values ​​includes a plurality of SEM delta values ​​acquired at a predetermined frequency. In one embodiment, the predetermined frequency is once a month, once every two weeks, once a week, once every five days, once every four days, once every three days, once every two days, once a day, once every 24 hours, once every 23 hours, once every 22 hours, once every 21 hours, once every 19 hours, once every 18 hours, once every 17 hours, once every 16 hours, once every 15 hours, once every 14 hours, once every 13 hours, once every 12 hours ... The SEM delta values ​​may be taken once every 24 hours, once every 11 hours, once every 10 hours, once every 9 hours, once every 8 hours, once every 7 hours, once every 6 hours, once every 5 hours, once every 4 hours, once every 3 hours, once every 2 hours, once every hour, once every 60 minutes, once every 30 minutes, once every 15 minutes, once every 10 minutes, once every 5 minutes, once every 2 minutes, once every minute, or once every 30 seconds. In one embodiment, the set of SEM delta values ​​includes 10 SEM delta values ​​taken once every 24 hours. In one embodiment, the set of SEM delta values ​​includes 9 SEM delta values ​​taken once every 24 hours. In one embodiment, the set of SEM delta values ​​includes 8 SEM delta values ​​taken once every 24 hours. In one embodiment, the set of SEM delta values ​​includes 7 SEM delta values ​​taken once every 24 hours. In one embodiment, the set of SEM delta values ​​includes six SEM delta values ​​taken once every 24 hours.In some embodiments, the set of SEM delta values ​​includes 5 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 4 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 3 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 2 SEM delta values ​​obtained once every 24 hours. In some embodiments, the location on the patient's skin is an area at risk for developing DTI, including, but not limited to, the heel, knee, elbow, sacrum, thigh, back of the head, shoulder, base of the spine, buttocks, toes, ear, lower back, leg, or rib cage.

[0052] In an embodiment, a set of weights is applied to each SEM delta value in the set of SEM delta values. In an embodiment, the set of weights is random. In an embodiment, a first random weight is applied to a first SEM delta value in the set of SEM delta values. In an embodiment, a second random weight is applied to a second SEM delta value in the set of SEM delta values. In an embodiment, the random weights applied to SEM delta values ​​in the set of SEM delta values ​​are determined by the time at which the SEM delta value is obtained relative to the current time. In an embodiment, a larger random weight is applied to a more recently obtained SEM delta value than a SEM delta value obtained at an earlier time. In an embodiment, a smaller random weight is applied to a SEM delta value obtained at an earlier time compared to a more recently obtained SEM delta value. In an embodiment, the random weights increase monotonically with time.

[0053] In one embodiment, a training set is created that includes a first set of weighted SEM delta values ​​and a second set of weighted SEM delta values ​​for all patients of the first plurality of patients and the second plurality of patients, hi one embodiment, a neural network is trained using the training set.

[0054] In an aspect, the method further includes: a) for each patient of the first plurality of patients and the second plurality of patients, i) calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set of SEM delta values; ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values; iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value; and iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold; b) creating a training set including the first set of difference values ​​for the first plurality of patients and the second set of difference values ​​for the second plurality of patients; and c) training the neural network using the training set.

[0055] In an embodiment, an average SEM delta value is calculated from a set of SEM delta values. In an embodiment, an average SEM delta value is calculated from a subset of the SEM delta values. In an embodiment, a first average SEM delta value is calculated from the N oldest weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the M newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the five oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the four oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the two newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the three oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the three newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the two oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the four most recent weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the one oldest weighted SEM delta value and a second average SEM delta value is calculated from the five most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the most recent weighted SEM delta value and a first average SEM delta value is calculated from the next five most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the two most recent weighted SEM delta values ​​and a first average SEM delta value is calculated from the next four most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the three most recent weighted SEM delta values ​​and a first average SEM delta value is calculated from the next three most recent weighted SEM delta values. In one embodiment, the second average SEM delta value is calculated from the four most recent weighted SEM delta values, and the first average SEM delta value is calculated from the next two most recent weighted SEM delta values.In one embodiment, the second average SEM delta value is calculated from the five most recent weighted SEM delta values ​​and the first average SEM delta value is calculated from the next most recent weighted SEM delta value. In one embodiment, the plurality of SEM delta values ​​associated with the patient are obtained periodically over a predetermined time interval prior to risk assessment. In one embodiment, the predetermined time interval prior to risk assessment is 1 day, 2 days, 3 days, 4 days, 5 days, 6 days, 7 days, 8 days, 9 days, or 10 days.

[0056] In some embodiments, a difference between the first average SEM delta value and the second average SEM delta value is calculated. In some embodiments, the difference between the first average SEM delta value and the second average SEM delta value is compared to a threshold value. In some embodiments, the threshold value is zero. In some embodiments, the threshold value is a positive value. In some embodiments, the threshold value is a negative value. In some embodiments, a positive difference between the first average SEM delta value and the second average SEM delta value indicates deep tissue damage. In some embodiments, a non-positive or zero difference between the first average SEM delta value and the second average SEM delta value indicates no deep tissue damage. In some embodiments, a positive difference between the average of the most recent SEM delta value and the average of the oldest SEM delta value indicates deep tissue damage. In some embodiments, a non-positive or zero difference between the average of the most recent SEM delta value and the average of the oldest SEM delta value indicates no deep tissue damage. In some embodiments, the threshold value is a real number in the range of 0 to 1. In some embodiments, the threshold value is about 0.1, about 0.2, about 0.3, about 0.4, about 0.5, about 0.6, about 0.7, about 0.8, about 0.9, about 1.0, In some embodiments, a DTI is determined to be present at a location on the patient's skin when the difference exceeds a predetermined threshold value.

[0057] In one embodiment, a training set is created that includes a first set of difference values ​​for a first plurality of patients and a second set of difference values ​​for a second plurality of patients. In one embodiment, the training set is used to train a neural network.

[0058] In some embodiments, the trained neural network outputs a set of optimized weights, including optimized weights for each time point prior to formation of the DTI. In some embodiments, the optimized weights increase monotonically with time. In some embodiments, the optimized weights are in the range of 0 to 2. In some embodiments, the optimized weights are about 2, about 1.9, about 1.8, about 1.7, about 1.6, about 1.5, about 1.4, about 1.3, about 1.2, about 1.1, about 1.0, about 0.9, about 0.8, about 0.7, about 0.6, about 0.5, about 0.4, about 0.3, about 0.2, about 0.1, or about 0.0. In some embodiments, the trained neural network outputs an optimized threshold. In certain embodiments, the optimized threshold is about 0.1, about 0.2, about 0.3, about 0.4, about 0.5, about 0.6, about 0.7, about 0.8, about 0.9, about 1.0.

[0059] In an aspect, the present disclosure provides a computer-implemented method for training a neural network to detect deep tissue injury (DTI) before the injury is visible on a patient's skin, comprising: a) acquiring, for each patient of a first plurality of patients experiencing a DTI, a first set of subepidermal moisture (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency prior to and until the formation of the DTI; b) acquiring, for each patient of a second plurality of patients not experiencing a DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency; c) applying a set of weights to each of the acquired first and second set of SEM delta values; and d) calculating a weight for each patient of the first and second plurality of patients. the first and second average SEM delta values; iv) comparing the difference between the first and second average SEM delta values ​​to a threshold; e) creating a training set including a first set of difference values ​​for a first plurality of patients and a second set of difference values ​​for a second plurality of patients; and f) training a neural network using the training set.

[0060] In some embodiments, the neural network is a single layer neural network. In some embodiments, the neural network is a multi-layer neural network. In some embodiments, the neural network includes at least one hidden layer, at least two hidden layers, at least three hidden layers, at least four hidden layers, or at least five hidden layers. In some embodiments, the neural network uses a supervised learning algorithm. In some embodiments, the neural network uses an unsupervised learning algorithm.

[0061] In an embodiment, the first plurality of patients has been diagnosed with a DTI. In an embodiment, for each patient of the first plurality of patients, a first set of SEM delta values ​​is acquired at a location on the patient's skin. In an embodiment, the first set of SEM delta values ​​is acquired at a predetermined frequency prior to and until the formation of a DTI. In an embodiment, the second plurality of patients has not been diagnosed with a DTI. In an embodiment, for each patient of the second plurality of patients, a second set of SEM delta values ​​is acquired at a location on the patient's skin. In an embodiment, the second set of SEM delta values ​​is acquired at the same predetermined frequency as the first set of SEM delta values. In an embodiment, the set of SEM delta values ​​includes a plurality of SEM delta values ​​acquired at different times. In an embodiment, the set of SEM delta values ​​includes a plurality of SEM delta values ​​acquired at a predetermined frequency. In certain embodiments, the predetermined frequency is once a month, once every two weeks, once a week, once every five days, once every four days, once every three days, once every two days, once a day, once every 24 hours, once every 23 hours, once every 22 hours, once every 21 hours, once every 19 hours, once every 18 hours, once every 17 hours, once every 16 hours, once every 15 hours, once every 14 hours, once every 13 hours, once every 12 hours, once every 11 hours, once every 10 hours, once every 9 hours, once every 8 hours, once every 7 hours, once every 6 hours, once every 5 hours, once every 4 hours, once every 3 hours, once every 2 hours, once every hour, once every 60 minutes, once every 30 minutes, once every 15 minutes, once every 10 minutes, once every 5 minutes, once every 2 minutes. In some embodiments, the set of SEM delta values ​​includes 10 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 9 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 8 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 7 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 6 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 5 SEM delta values ​​obtained once every 24 hours.In some embodiments, the set of SEM delta values ​​includes 4 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 3 SEM delta values ​​obtained once every 24 hours. In some embodiments, the set of SEM delta values ​​includes 2 SEM delta values ​​obtained once every 24 hours. In some embodiments, the location on the patient's skin is an area at risk for developing DTI, including, but not limited to, the heel, knee, elbow, sacrum, thigh, back of the head, shoulder, base of the spine, buttocks, toes, ear, lower back, leg, or rib cage.

[0062] In an embodiment, a set of weights is applied to each SEM delta value in the set of SEM delta values. In an embodiment, the set of weights is random. In an embodiment, a first random weight is applied to a first SEM delta value in the set of SEM delta values. In an embodiment, a second random weight is applied to a second SEM delta value in the set of SEM delta values. In an embodiment, the random weights applied to SEM delta values ​​in the set of SEM delta values ​​are determined by the time at which the SEM delta value is obtained relative to the current time. In an embodiment, a larger random weight is applied to a more recently obtained SEM delta value than a SEM delta value obtained at an earlier time. In an embodiment, a smaller random weight is applied to a SEM delta value obtained at an earlier time compared to a more recently obtained SEM delta value. In an embodiment, the random weights increase monotonically with time.

[0063] In one embodiment, a training set is created that includes a first set of weighted SEM delta values ​​and a second set of weighted SEM delta values ​​for all patients of the first plurality of patients and the second plurality of patients, hi one embodiment, a neural network is trained using the training set.

[0064] In an embodiment, an average SEM delta value is calculated from a set of SEM delta values. In an embodiment, an average SEM delta value is calculated from a subset of the SEM delta values. In an embodiment, a first average SEM delta value is calculated from the N oldest weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the M newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the five oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the four oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the two newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the three oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the three newest weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the two oldest weighted SEM delta values ​​and a second average SEM delta value is calculated from the four most recent weighted SEM delta values. In an embodiment, a first average SEM delta value is calculated from the one oldest weighted SEM delta value and a second average SEM delta value is calculated from the five most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the most recent weighted SEM delta value and a first average SEM delta value is calculated from the next five most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the two most recent weighted SEM delta values ​​and a first average SEM delta value is calculated from the next four most recent weighted SEM delta values. In an embodiment, a second average SEM delta value is calculated from the three most recent weighted SEM delta values ​​and a first average SEM delta value is calculated from the next three most recent weighted SEM delta values. In one embodiment, the second average SEM delta value is calculated from the four most recent weighted SEM delta values, and the first average SEM delta value is calculated from the next two most recent weighted SEM delta values.In one embodiment, the second average SEM delta value is calculated from the five most recent weighted SEM delta values, and the first average SEM delta value is calculated from the next most recent weighted SEM delta value.

[0065] In some embodiments, a difference between the first average SEM delta value and the second average SEM delta value is calculated. In some embodiments, the difference between the first average SEM delta value and the second average SEM delta value is compared to a threshold value. In some embodiments, the threshold value is zero. In some embodiments, the threshold value is a positive value. In some embodiments, the threshold value is a negative value. In some embodiments, a positive difference between the first average SEM delta value and the second average SEM delta value indicates deep tissue damage. In some embodiments, a non-positive or zero difference between the first average SEM delta value and the second average SEM delta value indicates no deep tissue damage. In some embodiments, a positive difference between the average of the most recent SEM delta value and the average of the oldest SEM delta value indicates deep tissue damage. In some embodiments, a non-positive or zero difference between the average of the most recent SEM delta value and the average of the oldest SEM delta value indicates no deep tissue damage. In some embodiments, the threshold value is a real number in the range of 0 to 1. In some embodiments, the threshold value is about 0.1, about 0.2, about 0.3, about 0.4, about 0.5, about 0.6, about 0.7, about 0.8, about 0.9, about 1.0, In some embodiments, a DTI is determined to be present at a location on the patient's skin when the difference exceeds a predetermined threshold value.

[0066] In one embodiment, a training set is created that includes a first set of difference values ​​for a first plurality of patients and a second set of difference values ​​for a second plurality of patients. In one embodiment, the training set is used to train a neural network.

[0067] In one embodiment, the trained neural network outputs: a) a set of optimized weights, including optimized weights for each time point prior to formation of the DTI, where the optimized weights monotonically increase with time; b) an optimized threshold; c) a value of N; and d) a value of M. In one embodiment, the set of optimized weights and the optimized threshold are used to predict the occurrence of deep tissue damage. In one embodiment, the optimized weights monotonically increase with time. In one embodiment, the optimized weights are in the range of 0 to 2. In one embodiment, the optimized weights are about 2, about 1.9, about 1.8, about 1.7, about 1.6, about 1.5, about 1.4, about 1.3, about 1.2, about 1.1, about 1.0, about 0.9, about 0.8, about 0.7, about 0.6, about 0.5, about 0.4, about 0.3, about 0.2, about 0.1, or about 0.0. In some embodiments, the trained neural network outputs an optimized threshold. In some embodiments, the optimized threshold is about 0.1, about 0.2, about 0.3, about 0.4, about 0.5, about 0.6, about 0.7, about 0.8, about 0.9, about 1.0. In some embodiments, N+M=3. In some embodiments, N+M=4. In some embodiments, N+M=5. In some embodiments, N+M=6. In some embodiments, N+M=7. In some embodiments, N+M=8. In some embodiments, N+M=9. In some embodiments, N+M=10. In some embodiments, N=1, 2, 3, 4, 5, 6, 7, 8, 9, or 10. In some embodiments, M=1, 2, 3, 4, 5, 6, 7, 8, 9, or 10.

[0068] In one aspect, the optimized set of weights and the optimized threshold are used to predict the occurrence of deep tissue damage.

[0069] Computer-readable medium (software) Any of the above-described methods of the present disclosure may be implemented as a computer program process specified as a set of instructions recorded on a non-transitory computer-readable storage medium or computer readable medium (CRM).

[0070] In an aspect, the present disclosure provides a non-transitory computer-readable storage medium comprising one or more programs for execution by one or more processors of a device, the one or more programs including instructions that, when executed by the one or more processors, cause the device to perform any of the methods disclosed herein.

[0071] Also provided herein is a non-transitory computer-readable storage medium comprising a report generated from performing any of the methods disclosed herein.

[0072] Examples of computer-readable storage media include random access memory (RAM), read-only memory (ROM), read-only compact disks (CD-ROM), recordable compact disks (CD-R), rewritable compact disks (CD-RW), read-only digital versatile disks (e.g., DVD-ROM, dual-layer DVD-ROM), various recordable / rewritable DVDs (e.g., DVD-RAM, DVD-RW, DVD+RW, etc.), flash memory (e.g., SD cards, mini SD cards, micro SD cards, etc.), magnetic and / or solid-state hard drives, ultra-high density optical disks, any other optical or magnetic media, and floppy disks. In some embodiments, the computer-readable storage medium is a solid-state device, a hard disk, a CD-ROM, or any other non-volatile computer-readable storage medium.

[0073] A computer-readable storage medium may store a set of computer-executable instructions (eg, a "computer program") that is executable by at least one processing unit and includes a set of instructions for performing various operations.

[0074] A computer program (also known as a program, software, software application, script, or code) may be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it may be deployed in any form, including as a stand-alone program or as modules, components, or subroutines, objects, or other components suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program may be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, subprograms, or portions of code). A computer program may be deployed to run on one computer or multiple computers located at one site or distributed across multiple sites and interconnected by a communication network. Examples of computer programs or computer code include machine code, such as produced by a compiler, and files containing higher level code that is executed by a computer, electronic component, or microprocessor using an interpreter.

[0075] In some embodiments, software aspects of the disclosure may be implemented as sub-portions of a larger program while remaining separate software aspects of the disclosure. In some implementations, software aspects may also be implemented as separate programs. Any combination of separate programs that together implement the software aspects described herein is within the scope of the subject disclosure. In some implementations, the software programs, when installed to operate on one or more electronic systems, define one or more specific machine implementations that execute and perform the operations of the software programs.

[0076] The present disclosure provides and includes a non-transitory computer readable medium for identifying DTI tissue. The non-transitory computer readable medium may include instructions stored thereon that, when executed on a processor, may perform the steps of: a) acquiring a set of SEM delta values ​​at a location on a patient's skin at a predetermined frequency; b) applying a predetermined weight to each of the acquired set of SEM delta values; c) calculating a first average SEM delta value of the N oldest weighted SEM delta values; d) calculating a second average SEM delta value of the M most recent weighted SEM delta values; e) comparing a difference between the first average SEM delta value and the second average SEM delta value to a predetermined threshold; and f) determining that DTI is present at the location on the patient's skin when the difference exceeds the predetermined threshold. In an embodiment, the acquired set of SEM delta values ​​includes at least five SEM delta values, the SEM delta values ​​each taken at one-day intervals. In an embodiment, the predetermined weight is in the range of 0 to 2. In some embodiments, the predetermined weights increase monotonically over time. In some embodiments, N>M. In some embodiments, N is 4 and M is 2. In some embodiments, the predetermined threshold is a real number in the range of 0 to 1. In some embodiments, the most recent SEM delta value is obtained by linear extrapolation of the K most recent SEM delta values. In some embodiments, K is 3. In some embodiments, the predetermined threshold is 0.7. In some embodiments, the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the coccyx, the buttocks, the lower back, the inner knees, the heels, and combinations thereof.

[0077] The present disclosure provides and includes a non-transitory computer readable medium for identifying DTI tissue, which may include instructions stored thereon that, when executed on a processor, may perform the steps of: a) acquiring, for each patient of a first plurality of patients diagnosed with DTI, a first set of subepidermal moisture (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency prior to and until the formation of the DTI, b) acquiring, for each patient of a second plurality of patients not diagnosed with DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency, c) applying a set of weights to each of the acquired first and second set of SEM delta values, d) creating a training set including the first and second set of weighted SEM delta values ​​for all patients of the first and second plurality of patients, and e) training a neural network using the training set. In an embodiment, the trained neural network outputs a set of optimized weights, including optimized weights for each time point prior to formation of the DTI, and the optimized weights monotonically increase over time. In an embodiment, the method further includes a) for each patient of the first plurality of patients and the second plurality of patients, i) calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set of SEM delta values, ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values, iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value, iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold, b) creating a training set including the first set of difference values ​​for the first plurality of patients and the second set of difference values ​​for the second plurality of patients, and c) training the neural network using the training set. In an embodiment, the predetermined frequency is once a day. In one embodiment, the first and second sets of SEM delta values ​​comprise at least six SEM delta values, the SEM delta values ​​each taken at one-day intervals.In some embodiments, N+M = 6. In some embodiments, N = 4 and M = 2. In some embodiments, the location on the patient's skin is selected from the group consisting of the back of the head, sacrum, shoulders, elbows, lower back, tailbone, buttocks, lower back, inner knees, heels, and combinations thereof.

[0078] The present disclosure provides and includes a non-transitory computer readable medium for identifying DTI tissue, which may include instructions stored thereon that, when executed on a processor, include the steps of: a) acquiring, for each patient of a first plurality of patients experiencing a DTI, a first set of subepidermal hydration (SEM) delta values ​​at a location on the patient's skin at a predetermined frequency prior to and until the formation of the DTI, b) acquiring, for each patient of a second plurality of patients not experiencing a DTI, a second set of SEM delta values ​​at the same location on the patient's skin at a predetermined frequency, c) applying a set of weights to each of the acquired first and second set of SEM delta values, and d) for each patient of the first and second plurality of patients: i) calculating a weight of the SEM delta values ​​from the weights of ... The method may include the steps of: calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set; ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values; iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value; iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold; e) creating a training set including a first set of difference values ​​for a first plurality of patients and a second set of difference values ​​for a second plurality of patients; and f) training the neural network using the training set. In one embodiment, the trained neural network outputs: a) a set of optimized weights including optimized weights for each time point prior to formation of the DTI, the optimized weights increasing monotonically over time; b) an optimized threshold; c) a value of N; and d) a value of M. In one embodiment, the predetermined frequency is once a day. In some embodiments, the first and second sets of SEM delta values ​​comprise at least six SEM delta values, each taken at one-day intervals. In some embodiments, N+M=6. In some embodiments, N=4 and M=2.In some aspects, the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the tailbone, the hips, the lower back, the inner knees, the heels, and combinations thereof. In some aspects, the optimized set of weights and the optimized thresholds are used to predict the occurrence of deep tissue damage.

[0079] In some embodiments, the location on the patient's skin can be a bony prominence. In some embodiments, the location on the patient's skin is the sternum, sacrum, heel, shoulder blade, elbow, ear, or other fleshy tissue. In some embodiments, one SEM value is measured at the anatomical site. In some embodiments, the average SEM value at a location on the patient's skin is taken from 2, 3, 4, 5, 6, 7, 8, 9, 10 or more SEM values ​​measured at that location.

[0080] system Any of the above-described methods and devices of the present disclosure may be implemented in a system or a collection of devices.

[0081] The present disclosure provides a system for predicting DTI. In an embodiment, the system comprises a device capable of performing SEM measurements, including but not limited to those described in U.S. Pat. No. 9,398,879. In an embodiment, the system comprises a device capable of performing SEM measurements, including but not limited to those described in U.S. Pat. No. 10,182,740. Both U.S. Pat. Nos. 9,398,879 and 10,182,740 are incorporated herein by reference in their entirety. In an embodiment, the system comprises a device capable of performing SEM measurements, including but not limited to SEM Scanner Model 200 (Bruin Biometrics, LLC, Los Angeles, CA). In an embodiment, the system comprises a device capable of performing biocapacitance measurements. In an embodiment, the system is configured to perform the methods described herein. In an embodiment, the system comprises a processor. In one aspect, the system includes a non-transitory computer-readable medium electrically coupled to the processor and instructions stored on the non-transitory computer-readable medium that, when executed on the processor, perform the steps of the methods described herein.

[0082] In an embodiment, the system includes a device capable of performing SEM or biocapacitance measurements, the device including a coverlay. In an embodiment, the coverlay may be a double-sided copper clad laminate of polyimide film bonded to copper foil and an all-polyimide composite. In an embodiment, the coverlay may include Pyralux 5 mil FR0150. Without being limited by theory, the use of this coverlay may avoid parasitic charges naturally present on the skin surface from interfering with the accuracy and precision of the SEM measurements.

[0083] In some aspects, the methods disclosed herein are implemented in one or more electronic devices, the one or more electronic devices including one or more processors, memory, and one or more programs, the one or more programs including instructions that, when executed by the one or more processors, cause the device to implement the method of any one of the above embodiments. Examples of devices further include, but are not limited to, computers, tablet personal computers, personal digital assistants, and mobile phones.

[0084] In some embodiments, the electronic device may further include one or more displays. In some embodiments, the electronic device includes one or more displays for presenting a report generated from performing the method of any one of the above embodiments.

[0085] In some embodiments, the electronic device may be a server computer, a client computer, a personal computer (PC), a user device, a tablet PC, a laptop computer, a personal digital assistant (PDA), a mobile phone, or any machine capable of executing a set of instructions, sequential or otherwise, that specify actions to be taken by the machine. In some embodiments, the electronic device may further include a keyboard and pointing device, a touch device, a barcode scanner, a display device, and a network device.

[0086] To provide for interaction with a user, implementations of the subject matter described herein may be implemented on a computer having a display device as described herein for displaying information to a user, a virtual or physical keyboard, and a pointing device such as a finger, pencil, mouse, or trackball with which the user can provide input to the computer. Other types of devices may also be used to provide interaction with a user, for example, feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or haptic feedback, and input from the user may be received in any form including acoustic, velocity, or tactile input.

[0087] FIG. 9 illustrates an exemplary system 900 according to one embodiment. In an aspect, the system 900 includes a host computer connected to a network. In an aspect, the system 900 includes a client computer or a server. In an aspect, the system 900 may include any suitable type of microprocessor-based device, such as a personal computer, a workstation, a server, or a handheld computing device (portable electronic device) such as a mobile phone or tablet. As shown in FIG. 9, in an aspect, the system 900 includes one or more of a processor 910, an input device 920, an output device 930, a storage medium 940, and a communication device 960. The input device 920 and the output device 930 may generally correspond to those described above and may be connectable to or integrated with the computer.

[0088] In one embodiment, input device 920 is any suitable device that provides input, such as a touch screen, a keyboard or keypad, a mouse, or a voice recognition device. In one embodiment, input device 920 is a SEM measurement device. In one embodiment, output device 930 is any suitable device that provides output, such as a display, a touch screen, a tactile device, or a speaker.

[0089] In an aspect, storage device 940 is any suitable device providing storage, such as electrical, magnetic, or optical memory, including but not limited to RAM, ROM, cache, hard drives, and removable storage disks. In an aspect, communication device 960 includes any suitable device capable of transmitting and receiving signals over a network, including but not limited to network interface chips or devices, routers, wireless cards, and Bluetooth signal emitters and receivers. In an aspect, the components of system 900 are individually connected in any suitable manner, including but not limited to a physical bus, wired, wireless, Bluetooth connections, infrared, and radio signals.

[0090] In an aspect, the software 950 that may be stored in the memory device 940 and executed by the processor 910 includes, for example, programming that embodies functionality of the present disclosure (e.g., embodied in a device described above). In an aspect, the software 950 is stored and / or transferred in any non-transitory computer-readable storage medium for use by or in association with an instruction execution system, apparatus, or device, such as those described above, that may fetch instructions associated with the software from the instruction execution system, apparatus, or device and execute the instructions. In an aspect, a computer-readable storage medium is any medium, such as the memory device 940, that may contain or store programming for use by or in association with an instruction execution system, apparatus, or device.

[0091] In an aspect, the software 950 may be propagated in any transfer medium for use by or in connection with an instruction execution system, apparatus, or device, such as those described herein, that may fetch instructions associated with the software from the instruction execution system, apparatus, or device and execute the instructions. In an aspect, a transfer medium is any medium that may communicate, propagate, or transport programming for use by or in connection with an instruction execution system, apparatus, or device. Transfer-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, or infrared wired or wireless propagation media.

[0092] In an aspect, the system 900 may be connected to a network, which is any suitable type of interconnected communication system. In an aspect, the network may implement any suitable communication protocol and may be protected by any suitable security protocol. In an aspect, the network comprises any suitable configuration of network links that may implement the transmission and reception of network signals, including, but not limited to, wireless network connections, T1 or T3 lines, cable networks, DSL, and telephone lines.

[0093] In an aspect, the system 900 implements an operating system suitable for operating over a network. In an aspect, the software 950 is written in any suitable programming language, including, but not limited to, C, C++, Java, or Python. In an aspect, application software embodying functionality of the present disclosure may be deployed in different configurations, such as, for example, in a client / server arrangement, or through a web browser as a web-based application or web service.

[0094] Methods for preventing and treating DTI formation The methods according to the present disclosure may prevent DTI formation in a patient. These preventative methods may be applied to a patient prior to diagnosis of DTI based on the methods described herein. In an embodiment, at least five SEM delta measurements may be obtained around a location on the patient's skin using an apparatus according to the present disclosure. In an embodiment, linear interpolation is used to obtain the value of the most recent SEM delta value. In an embodiment, direct measurement is used to obtain the value of the most recent SEM delta value. In an embodiment, the methods disclosed herein are used to determine whether there is deep tissue damage at a location on the patient's skin. In an embodiment, if the methods disclosed herein determine that there is deep tissue damage at the location, preventative measures are taken. In an embodiment, the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the coccyx, the buttocks, the lower back, the inner knee, the heel, and combinations thereof.

[0095] In certain aspects, preventative measures against DTI formation may be administered to the patient upon admission to the hospital, immediately following a surgical procedure, prior to discharge of the patient, or any combination of the above. The surgical procedure may be invasive or non-invasive, but may require the patient to remain in the same position for some period of time, such as, for example, at least one hour.

[0096] In certain aspects, preventative measures may be selected from the group consisting of turning and repositioning the patient at least every two hours, protecting bony prominences with padding, instituting a specific rotation and repositioning schedule, providing a wedge device for lateral positioning, providing a pressure redistribution support surface, managing fluids, nutrition, friction, and shear, reducing pressure on bony prominences, increasing frequency of rotation including small weight shifts, reassessing SEM levels every two hours, and any combination thereof.

[0097] The methods according to the present disclosure may be used to treat a patient's PI detected by the methods described herein. These treatment methods may be applied to the patient after detection of DTI based on the methods described herein. In an embodiment, at least five SEM delta measurements are obtained around a location of the patient's skin using an apparatus according to the present disclosure. In an embodiment, linear interpolation is used to obtain the value of the most recent SEM delta value. In an embodiment, direct measurement is used to obtain the value of the most recent SEM delta value. In an embodiment, the methods disclosed herein are used to determine whether there is deep tissue damage at a location of the patient's skin. In an embodiment, if the methods disclosed herein determine that there is deep tissue damage at the location, a treatment method is implemented.

[0098] Methods according to the present disclosure may treat existing DTIs. In some embodiments, the treatment method is selected from the group consisting of protecting the skin, eliminating excessive pressure points, managing exudate, closing and re-growing damaged skin, keeping wounds clean, reducing wound size, and any combination thereof.

[0099] Having now generally described the invention, the same will be more readily understood through reference to the following examples, which are provided by way of illustration and are not intended to limit the disclosure unless otherwise specified. EXAMPLES

[0100] Example 1: Obtaining SEM delta values ​​for patients with and without DTI in the heel A blinded clinical trial is conducted to measure SEM delta values ​​in patients with skin and tissues at increased risk of developing pressure injuries. SEM delta values ​​are measured on the heel in patients over time, at a frequency of once a day. Patients are visually assessed daily for deep tissue injury (DTI). As shown in Figure 2A, patient data is classified into two groups: patients diagnosed with DTI (left panel) and patients not yet diagnosed with DTI (right panel). For patients diagnosed with DTI, SEM delta value data for the 5 days leading up to diagnosis is aligned to the date of diagnosis (days aligned to the date of diagnosis (day 0)). As shown in Figure 2B, data from patients is used to build a classification algorithm to detect and predict the formation of DTI.

[0101] Example 2: Averaging the most recent SEM delta value with the oldest SEM delta value As shown in Figure 3, the mean SEM delta value on the day before the formation of DTI is larger than the mean SEM delta value on the previous day, whereas when DTI is not diagnosed, the mean SEM delta value is similar on all days.

[0102] Therefore, the average SEM delta values ​​for the days immediately prior to and not immediately prior to the DTI diagnosis can be used as a basis for classification. In particular, the following inequality is used to classify: Mean (SEM Delta last_days )-Mean(SEM Delta first_days )>0 Mean (SEM Delta last_days )-Mean(SEM Delta first_days )>Threshold

[0103] When the obtained SEM delta value satisfies the above inequality, the model assumes that DTI is formed. This is then compared with the actual data to determine the true positive rate (TPR) and false positive rate (FPR) of whether DTI is diagnosed.

[0104] As shown in Figure 4, when there are six data points, there are five possible ways to split the data to determine the most recent data (last day) and the oldest data (first day). The most recent SEM delta value (or last day) can be the average of the most recent day, the most recent two days, the most recent three days, the most recent four days, and the most recent five days. Conversely, the oldest SEM delta value (or first day) can be the average of the oldest day, the oldest two days, the oldest three days, the oldest four days, and the oldest five days.

[0105] The best classification, as determined by the highest true positive rate and lowest false positive rate, is achieved using the two most recent (last day) SEM delta values ​​with the four oldest (first day) SEM delta values.

[0106] Example 3: Determining Weights and Thresholds Before calculating the average SEM delta value, the days were assigned monotonically increasing weights (w i ) is assigned. Thus, the inequality becomes: Average (w day(i) ×SEM Delta day(i) )-Average(w day(j) ×SEM Delta day(j) )>Threshold As shown in FIG. 7, where i=last day and j=first day.

[0107] An optimization algorithm is used to find the optimal set of weights that provide the best classification performance, as determined by the true positive rate and false positive rate. In particular, the algorithm seeks to minimize (1-TPR+FPR)→0 with the constraint TPR>>FPR. Figure 5 illustrates a flow chart of the steps of the algorithm, while Figure 6 shows the weights and thresholds that yield the best classification results.

[0108] Example 4: Predicting the formation of DTI The optimized weights and thresholds obtained from Example 3 are used to evaluate the predictive ability of the method. For the 5-day SEM delta values, the data for the 6th day (day 0) is predicted using linear interpolation of the data from 3 days prior. The SEM delta values ​​are weighted appropriately and used to calculate the inequality, as shown in Figure 7.

[0109] Example 5: Detection and prediction of DTI The method can detect DTI with 79% accuracy, with a true positive rate of 90% and a false positive rate of 21%. The method can also predict the formation of DTI with 77% accuracy, with a true positive rate of 80% and a false positive rate of 23%.

[0110] While the invention has been described in terms of specific embodiments, those skilled in the art will recognize that various modifications may be made and equivalents may be substituted for the elements thereof without departing from the scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from its scope.

[0111] Therefore, it is intended that the invention not be limited to the particular embodiment disclosed as the best mode contemplated for carrying out this invention, but that the invention will include all embodiments falling within the scope and spirit of the appended claims.

[0112] Example 6: Obtaining SEM delta values ​​for patients with and without DTI at the sacrum A blinded clinical trial is conducted to measure SEM delta values ​​in patients with skin and tissues at increased risk of developing pressure injuries. SEM delta values ​​are measured at the sacrum in patients over time, at a frequency of once a day. Patients are visually assessed daily for deep tissue injury (DTI). Patient data is classified into two groups: patients diagnosed with DTI and patients not yet diagnosed with DTI. For patients diagnosed with DTI, SEM delta value data on days leading up to diagnosis is aligned with the date of diagnosis, which is day 0. As shown in Figure 2B, data from patients with suspected DTI (Table 1) is used to build a classification algorithm to detect and predict the formation of DTI. [Table 1]

Claims

1. 1. A system for detecting deep tissue injury (DTI) before it becomes visible on a patient's skin, comprising: a) a SEM scanner configured to perform subepidermal moisture (SEM) measurements; b) a processor configured to receive the SEM measurements; and c) a non-transitory computer-readable medium electrically coupled to the processor and containing instructions stored thereon, the instructions, when executed on the processor, i) calculating a set of subepidermal moisture (SEM) delta values ​​at locations on the patient's skin at a predetermined frequency; ii) applying a predefined weight to each of the obtained set of SEM delta values; iii) calculating a first average SEM delta value of the N oldest weighted SEM delta values; iv) calculating a second average SEM delta value of the M most recent weighted SEM delta values; v) comparing a difference between the first average SEM delta value and the second average SEM delta value with a predetermined threshold; vi) determining that a DTI is present at the location on the patient's skin when the difference exceeds the predetermined threshold.

2. 2. The system of claim 1, wherein the set of obtained SEM delta values ​​comprises at least five SEM delta values, each SEM delta value taken at one-day intervals.

3. The system of claim 1 , wherein the predetermined frequency is once a day.

4. The system of claim 1 , wherein the predetermined weight is in the range of 0 to 2.

5. The system of claim 1 , wherein the predetermined weights increase monotonically over time.

6. The system of claim 1 , wherein N>M.

7. 7. The system of claim 6, wherein N is 4 and M is 2.

8. The system of claim 1 , wherein the predetermined threshold is a real number in the range of 0 to 1.

9. The system of claim 1 , wherein the most recent SEM delta value is obtained by linear extrapolation of the K most recent SEM delta values.

10. 10. The system of claim 9, wherein K is 3.

11. The system of claim 1 , wherein the predetermined threshold is 0.

7.

12. 12. The system of claim 1, wherein the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the tailbone, the buttocks, the lower back, the inner knees, the heels, and combinations thereof.

13. 1. A computer-implemented method for training a neural network to detect deep tissue injury (DTI) before said injury is visible on a patient's skin, comprising: a) for each patient of a first plurality of patients diagnosed with a DTI, obtaining a first set of subepidermal moisture (SEM) delta values ​​at locations on the patient's skin at a predetermined frequency prior to and until the formation of the DTI; b) for each patient of a second plurality of patients not diagnosed with a DTI, obtaining a second set of SEM delta values ​​at the same location on the patient's skin at the predetermined frequency; c) applying a set of weights to each of the SEM delta values ​​of the obtained first and second sets of SEM delta values; d) creating a training set including the first set of weighted SEM delta values ​​and the second set of weighted SEM delta values ​​for all patients of the first plurality of patients and the second plurality of patients; e) training the neural network using the training set.

14. 14. The method of claim 13, wherein the trained neural network outputs a set of optimized weights, including an optimized weight for each time point prior to the formation of a DTI, and the optimized weights increase monotonically over time.

15. a) for each patient of the first plurality of patients and the second plurality of patients, i) calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set of SEM delta values; ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values; iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value; iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold value; b) creating a training set comprising a first set of difference values ​​for the first plurality of patients and a second set of difference values ​​for the second plurality of patients; c) training the neural network using the training set.

16. 16. The method of claim 15, wherein the predetermined frequency is once a day.

17. 16. The method of claim 15, wherein the first and second sets of SEM delta values ​​include at least six SEM delta values, the SEM delta values ​​each taken at one-day intervals.

18. 16. The method of claim 15, wherein N+M=6.

19. 16. The method of claim 15, wherein N=4 and M=2.

20. 16. The method of claim 15, wherein the location on the patient's skin is selected from the group consisting of the back of the head, sacrum, shoulders, elbows, lower back, tailbone, buttocks, lower back, inner knees, heels, and combinations thereof.

21. 1. A computer-implemented method for training a neural network to detect deep tissue injury (DTI) before said injury is visible on a patient's skin, comprising: a) for each patient of a first plurality of patients experiencing a DTI, obtaining a first set of subepidermal moisture (SEM) delta values ​​at locations on the patient's skin at a predetermined frequency prior to and until the formation of said DTI; b) for each patient of a second plurality of patients not experiencing a DTI, obtaining a second set of SEM delta values ​​at the same location on the patient's skin at the predetermined frequency; c) applying a set of weights to each of the SEM delta values ​​of the obtained first and second sets of SEM delta values; d) for each patient of the first plurality of patients and the second plurality of patients, i) calculating a first average SEM delta value of the N oldest weighted SEM delta values ​​in the set of SEM delta values; ii) calculating a second average SEM delta value of the M most recent weighted SEM delta values ​​in the set of SEM delta values; iii) calculating a difference value between the first average SEM delta value and the second average SEM delta value; iv) comparing the difference between the first average SEM delta value and the second average SEM delta value to a threshold value; e) creating a training set comprising a first set of difference values ​​for the first plurality of patients and a second set of difference values ​​for the second plurality of patients; f) training the neural network using the training set.

22. The trained neural network comprises: a) a set of optimized weights including an optimized weight for each time point prior to the formation of the DTI, the optimized weights increasing monotonically with time; b) an optimized threshold; and c) the value of N; and d) outputting the value of M.

23. 22. The method of claim 21, wherein the predetermined frequency is once a day.

24. 22. The method of claim 21, wherein the first and second sets of SEM delta values ​​include at least six SEM values, the SEM delta values ​​each taken at one-day intervals.

25. 22. The method of claim 21, wherein N+M=6.

26. 22. The method of claim 21, wherein N=4 and M=2.

27. 22. The method of claim 21, wherein the optimized set of weights and the optimized threshold are used to predict the occurrence of deep tissue damage.

28. 28. The method of any one of claims 21 to 27, wherein the location on the patient's skin is selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the tailbone, the buttocks, the lower back, the inner knees, the heels, and combinations thereof.

29. 1. A system for predicting deep tissue injury (DTI), comprising: a) a SEM scanner configured to perform subepidermal moisture (SEM) measurements; b) a processor configured to receive the SEM measurements; and c) a non-transitory computer-readable medium electrically coupled to the processor and containing instructions stored thereon, the instructions, when executed on the processor, i) calculating a number of SEM delta values ​​from said SEM measurements; ii) automatically inputting, via the processor, the plurality of SEM delta values ​​into a trained model to receive a probability value, the trained model being configured to predict a probability value corresponding to a future occurrence of a patient developing a DTI, the trained model being trained based on a set of training data including a plurality of SEM delta values ​​associated with a set of patients; and iii) outputting via an output device a prediction of a future occurrence of the patient developing a DTI based on the probability value.

30. Training the trained model a) receiving, via an input device, said set of training data, said set of training data comprising: i) a number of SEM delta values ​​associated with a set of patients; and ii) a threshold value, where each patient in the set of patients has a known DTI status, the threshold value being a number between 0 and 1; b) automatically inputting the training data into an optimization algorithm via the processor to receive a plurality of optimal weight values; and c) automatically updating, via the processor, the trained model with the plurality of optimal weight values.

31. The optimization algorithm comprises: a) generating a plurality of ascending random numbers from 0 to 2 as a plurality of weight values; b) inputting the training data and the plurality of weights into the model to receive a set of predicted DTI statuses associated with the set of patients; c) comparing the predicted DTI status to the known DTI status associated with the set of patients; d) calculating a true positive rate (TPR) and a false positive rate (FPR) based on said comparison, wherein said TPR is calculated as the percentage of patients in said patient set whose predicted DTI status matches their known DTI status, and said FPR is calculated as the percentage of patients in said patient set whose predicted DTI status does not match their known DTI status; e) repeating steps a) through d) a predetermined number of times as the number of iterations; f) identifying optimal TPRs and FPRs from all calculated TPRs and FPRs from the iterations; g) outputting the plurality of optimal weight values ​​associated with the identified optimal TPRs and FPRs.

32. 32. The system of claim 31, wherein the plurality of SEM delta values ​​comprises SEM delta values ​​from a predetermined number of days prior to a date for predicting PI.

33. 32. The system of claim 31, wherein identifying optimal TPR and FPR comprises minimizing an objective function of 1-TPR+FPR and satisfying a constraint of TPR>>FPR.

34. The system of any one of claims 30 to 33, wherein the input device is the SEM scanner.

35. The system of any one of claims 30 to 33, wherein the input device is a database or a computer.

36. 34. The system of any one of claims 29 to 33, wherein the DTI occurs at a location selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the tailbone, the buttocks, the lower back, the inner knees, the heels, and combinations thereof.

37. 34. The system of any one of claims 29 to 33, wherein the prediction of the future occurrence of the patient developing a DTI comprises a high likelihood of developing a DTI and a low likelihood of developing a PI.

38. 1. A system for assessing risk of deep tissue injury (DTI), comprising: a) a SEM scanner configured to perform subepidermal moisture (SEM) measurements; b) a processor configured to receive the SEM measurements; and c) a non-transitory computer-readable medium electrically coupled to the processor and containing instructions stored thereon, the instructions, when executed on the processor, i) calculating a number of SEM delta values ​​from said SEM measurements; ii) automatically inputting, via the processor, the plurality of SEM delta values ​​into a trained model to receive a probability value, the trained model being configured to predict a probability value corresponding to a future occurrence of a patient developing a DTI, the trained model being trained based on a set of training data including a plurality of SEM delta values ​​associated with a set of patients; d) outputting via an output device a likelihood of a future occurrence of a DTI based on said probability value.

39. 40. The system of claim 38, wherein the likelihood of future occurrence of a DTI is classified as no DTI, low likelihood of a DTI, high likelihood of a DTI, or suspected PI.

40. 40. The system of claim 38, wherein the likelihood of future occurrence of a DTI is a calculated probability of developing a PI.

41. The non-transitory computer readable medium comprises: a) selecting, via the processor, a treatment for the patient based on the likelihood of a future occurrence of the DTI; 40. The system of claim 38, further comprising the step of: b) outputting a notification of the selected treatment via the output device.

42. 42. The system of claim 41, wherein the selected treatment is selected from the group consisting of reducing pressure, cleaning and dressing the wound, removing damaged tissue, administering medication, and surgery.

43. 42. The system of claim 41, wherein the DTI is a deep tissue compression injury (DTPI).

44. 44. The system of any one of claims 38-43, wherein the DTI occurs at a location selected from the group consisting of the back of the head, the sacrum, the shoulders, the elbows, the lower back, the tailbone, the buttocks, the lower back, the inner knees, the heels, and combinations thereof.

45. 40. The system of claim 38, wherein the non-transitory computer readable medium further performs the steps of generating or updating a report from performing the method of assessing risk and storing the report.

46. 40. The system of claim 38, further comprising communicating the report to the patient or clinician.

47. 40. The system of claim 38, wherein the output device is a computer display.

Images