Systems and methods for assessing blood perfusion

Abstract

Systems and methods for assessing blood perfusion include a wearable garment having a fixed plurality of sensors, a processor communicatively coupled to the sensors, a memory component communicatively coupled to the processor, and machine readable instructions that cause the processor to perform operations, the operations include: receiving, from a plurality of sensors, a first set of blood perfusion metrics associated with an individual wearing the wearable garment; generating a first reading based on the first set of blood perfusion metrics; receiving, from the plurality of sensors, a second set of blood perfusion metrics associated with an individual wearing the wearable garment; generating a second reading based on the second set of blood perfusion metrics; determining an intervened perfusion status based on the first reading and the second reading; and generating an intervention suggestion based on the first reading, the second reading, the intervention perfusion status, or a combination thereof, using a machine learning model.

Description

Technical Field

[0001] The present disclosure relates to systems and methods for assessing blood perfusion, and more particularly, to systems and methods including a wearable garment for assessing blood perfusion of a body part wearing the wearable garment. Background Art

[0002] Blood perfusion refers to the flow of blood through the vascular system, which is responsible for transporting oxygen, nutrients, waste products, etc. throughout the body. Although commonly associated with blood flow, proper blood perfusion through the body's periphery is important for the body's normal functioning. For example, peripheral arterial disease (PAD) may reduce blood perfusion to the legs, and sometimes to the arms. Due to reduced blood perfusion to the extremities, PAD may cause complications in the extremities, and in extreme cases, may lead to gangrene and amputation.

[0003] Treating PAD is often not straightforward. The ankle-brachial index (ABI) can help diagnose PAD, but it does not provide spatial resolution of areas of potential perfusion problems. In addition, vasospasm associated with PAD may hinder initial angiography. When treating PAD, the success of PAD intervention is a subjective decision, which may lead to inappropriate or missed subsequent interventions. Moreover, current equipment for determining blood perfusion is expensive, complex, and provides limited follow-up measures for monitoring perfusion success after medical intervention. Therefore, it is desirable to have devices, systems, and methods for quantifying blood perfusion in the limbs of patients undergoing limb revascularization to provide improved intervention success metrics. Summary of the invention

[0004] According to one embodiment of the present disclosure, a system for assessing blood perfusion includes a wearable garment, a plurality of sensors fixed to the wearable garment, a processor communicatively coupled to the plurality of sensors, a memory component communicatively coupled to the processor, a machine learning model stored in the memory component, and machine readable instructions stored in the memory component. The machine readable instructions cause the processor to perform operations including: receiving a first set of blood perfusion metrics associated with an individual wearing the wearable garment from the plurality of sensors, generating a first reading based on the first set of blood perfusion metrics, receiving a second set of blood perfusion metrics associated with the individual wearing the wearable garment from the plurality of sensors, generating a second reading based on the second set of blood perfusion metrics, determining an intervention perfusion state for a medical intervention for improving blood perfusion of the individual and indicating a level of improvement in blood perfusion based on the first reading and the second reading, and generating an intervention recommendation indicating whether to recommend an additional intervention based on the first reading, the second reading, the intervention perfusion state, or a combination thereof using the machine learning model.

[0005] According to another embodiment of the present disclosure, a system for assessing blood perfusion includes a processor, a memory component communicatively coupled to the processor, a machine learning model stored in the memory component, and machine readable instructions stored in the memory component. The machine readable instructions cause the processor to perform operations including: receiving a first set of blood perfusion metrics associated with an individual from a wearable device having a plurality of sensors for assessing blood perfusion when the individual wears the wearable device, generating a first reading based on the first set of blood perfusion metrics, receiving a second set of blood perfusion metrics associated with the individual from the wearable device when the individual wears the wearable device, generating a second reading based on the second set of blood perfusion metrics, determining an intervention perfusion state for improving blood perfusion of the individual and indicating a level of improvement in blood perfusion based on the first reading and the second reading, and generating an intervention recommendation indicating whether to recommend an additional intervention based on the first reading, the second reading, the intervention perfusion state, or a combination thereof using the machine learning model.

[0006] According to another embodiment of the present disclosure, a method for assessing blood perfusion includes: receiving, using a processor, a first set of blood perfusion metrics associated with an individual wearing the wearable device from a wearable device having multiple sensors for assessing blood perfusion, generating, using the processor, a first reading based on the first set of blood perfusion metrics, receiving, using the processor, a second set of blood perfusion metrics associated with the individual wearing the wearable device from the wearable device, generating, using the processor, a second intervention reading based on the first set of blood perfusion metrics, determining, based on the first reading and the second reading, an intervention perfusion state for improving the individual's blood perfusion and indicating a level of improvement in blood perfusion, and generating, using a machine learning model, an intervention recommendation indicating whether an additional intervention is recommended based on the first reading, the second reading, the intervention perfusion state, or a combination thereof.

[0007] Although the concepts of the present disclosure are described herein primarily with reference to the foot, it is contemplated that these concepts may be applicable to any body part. For example, but not limited to, it is contemplated that the concepts of the present disclosure may be applicable to the hand. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The following detailed description of specific embodiments of the present disclosure may be best understood when read in conjunction with the following drawings, in which like structures are designated by like reference numerals, and in which:

[0009] Figure 1 schematically shows an illustrative system including an illustrative wearable device and system modules according to one or more embodiments described and illustrated herein;

[0010] Figure 2 Schematically illustrates a device according to one or more embodiments described and illustrated herein. Figure 1 illustrative wearable device with multiple sensors;

[0011] Figure 3 The present invention illustrates the use of one or more embodiments described and illustrated herein. Figure 1 A flow chart of a method for providing blood perfusion assessment in a system;

[0012] Figure 4 An illustrative method for strengthening a machine learning model according to one or more embodiments described and illustrated herein is shown; and

[0013] Figure 5 An illustrative scenario showing a subject wearing a wearable device for using a wearable device according to one or more embodiments described and illustrated herein Figure 1 The system provides blood perfusion assessment. DETAILED DESCRIPTION

[0014] Embodiments disclosed herein are generally directed to systems and methods for providing blood perfusion assessment, which is the local fluid flow through the capillary network and extracellular space of living tissue at a living tissue site, such as an individual, characterized as a volumetric flow rate per tissue volume at the site. Blood perfusion helps to provide nutrients and remove cellular waste, and a measured low oxygen saturation level can indicate low blood perfusion. The system includes a wearable device, which can be a wearable garment including multiple sensors that can help determine the spatial resolution of potential perfusion problem areas by determining at least the oxygen saturation level without the need for a medical procedure. The wearable device also includes or communicates with a computing system for analyzing data collected by the multiple sensors. The wearable device and / or the system can have machine-readable instructions for quantifying the perfusion of a body part wearing the wearable garment based on the collected data. This in turn can make the determination of the success of a PAD intervention more objective. The machine-readable instructions can also include a machine learning model that is trained on sensor data of multiple patients with different degrees of success in PAD interventions. The machine learning model may also provide follow-up monitoring for determining perfusion success following an intervention. Thus, the systems and methods as described herein provide an intuitive means of determining and / or monitoring blood perfusion.

[0015] Reference now Figure 1, schematically illustrates a system 100 including a wearable device 102 that includes one or more sensors 103. The wearable device 102 may include a sock, a glove, a sleeve, and / or any other wearable garment for assessing blood perfusion. For example, the wearable device 102 may be configured to be worn on a limb (e.g., an arm, a hand, a leg, or a foot) of a subject. The system 100 may also include a system control module 105 communicatively coupled to the wearable device 102. One or more modules in the system control module 105 may be deployed in the wearable device 102 or remote from the wearable device 102. The system control module 105 may include at least a processor 106, a memory 108, an input / output interface (I / O interface 109), a sensor module 110, a perfusion module 112, and a network interface 114. The system control module 105 may also include a communication path 104 for communicatively coupling various components of the system control module 105.

[0016] Processor 106 may include one or more processors, which may be any device capable of executing machine-readable and executable instructions. Thus, each of the one or more processors in processor 106 may be a controller, an integrated circuit, a microchip, or any other computing device. Processor 106 is coupled to communication path 104, which provides signal connectivity between various components of wearable device 102 and system control module 105. Thus, communication path 104 may communicatively couple any number of processors in processor 106 to each other and allow them to operate in a distributed computing environment. Specifically, each processor may operate as a node that can send and / or receive data. As used herein, the phrase "communicatively coupled" means that coupled components are able to exchange data signals with each other, such as, for example, exchanging electrical signals via a conductive medium, exchanging electromagnetic signals via air, exchanging optical signals via optical waveguides, and the like.

[0017] The communication path 104 can be formed from any medium capable of transmitting a signal, such as, for example, a conductive wire, a conductive trace, an optical waveguide, etc. In some embodiments, the communication path 104 can facilitate the transmission of wireless signals such as Wi-Fi, Bluetooth, near field communication (NFC), etc. In addition, the communication path 104 can be formed from a combination of media capable of transmitting a signal. In one embodiment, the communication path 104 includes a combination of conductive traces, conductive lines, connectors, and buses that cooperate to allow electrical data signals to be transmitted to components such as processors, memories, sensors, input devices, output devices, and communication devices. In addition, it is noted that the term "signal" refers to a waveform (e.g., electrical, optical, magnetic, mechanical, or electromagnetic) capable of propagating through a medium, such as DC, AC, sine waves, triangle waves, square waves, vibrations, etc.

[0018] The memory 108 is communicatively coupled to the communication path 104 and may include one or more memory modules including RAM, ROM, flash memory, a hard drive, or any device capable of storing machine-readable and executable instructions so that the processor 106 can access the machine-readable and executable instructions. The machine-readable and executable instructions may include logic or algorithms written in any programming language of any generation (e.g., 1GL, 2GL, 3GL, 4GL, or 5GL) (such as, for example, machine language that can be directly executed by the processor, or assembly language, object-oriented language, scripting language, microcode, etc. that can be compiled or assembled into machine-readable and executable instructions and stored on the memory 108). Alternatively, the machine-readable and executable instructions may be written in a hardware description language (HDL), such as logic implemented via a field programmable gate array (FPGA) configuration or an application-specific integrated circuit (ASIC), or their equivalents. Thus, the methods described herein may be implemented in any conventional computer programming language, as pre-programmed hardware elements, or as a combination of hardware and software components.

[0019] I / O interface 109 is coupled to communication path 104 and may include hardware for receiving input and / or providing output. Hardware for receiving input may include devices that send information to processor 106. For example, a keyboard, mouse, scanner, touch screen, and camera are all I / O devices because they provide input to processor 106. Hardware for providing output may include devices from which data is sent. For example, an electronic display, indicator light, speaker, and printer are all I / O devices because they output data from processor 106.

[0020] The sensor module 110 is coupled to the communication path 104 and is communicatively coupled to the processor 106. The sensor module 110 can be communicatively coupled to one or more sensors 103, which can include a plurality of sensors for measuring pulse oximetry (for, for example, measuring oxygen saturation (SpO2) levels as the percentage of hemoglobin binding sites in the bloodstream at the measurement site occupied by oxygen as the ratio of oxygen-saturated hemoglobin to total hemoglobin), heart rate, temperature, bioimpedance, and / or other vital signs, as well as a statistical confidence percentage of blood perfusion levels. Thus, the one or more sensors 103 of the wearable device 102 can include a blood pressure monitor, a pulse oximeter, an optical heart sensor, a thermometer, a bioimpedance sensor, and / or the like. The one or more sensors 103 can include any suitable sensor configured to measure and quantify a patient's blood perfusion, or any metric related to a patient's blood perfusion, at the location where the sensor 103 is placed.

[0021] The perfusion module 112 can be a hardware module coupled to the communication path 104 and communicatively coupled to the processor 106. The perfusion module 112 can also be or instead be a set of instructions contained in the memory 108. The perfusion module 112 can be configured to receive blood perfusion metrics, generate blood perfusion readings, determine intervention states (e.g., intervention perfusion states), predict intervention states (e.g., predict intervention perfusion states), and / or recommend further treatment courses. The perfusion module 112 can also be configured to train and utilize machine learning models to generate predictions of blood perfusion and / or recommendations for treatment courses (e.g., interventions such as medical interventions or surgical interventions). The perfusion module 112 can utilize supervised methods to train machine learning models as artificial intelligence (AI) model components deployed in the memory 108 based on annotated training sets, wherein the machine learning model is a decision tree, a Bayesian classifier, a support vector machine, a convolutional neural network, and / or the like. In some embodiments, unsupervised machine learning algorithms such as k-means clustering, hierarchical clustering, and / or the like can be used. The perfusion module 112 may also be configured to perform methods as described herein.

[0022] As described above, the system control module 105 may also include a network interface 114 that is communicatively coupled to the communication path 104. The network interface 114 may be any device that is capable of transmitting and / or receiving data via a network or other communication mechanism. Thus, the network interface 114 may include a communication transceiver for sending and / or receiving any wired or wireless communication. For example, the network interface 114 may include an antenna, a modem, an Ethernet port, a Wi-Fi card, a WiMAX card, a cellular modem, near field communication hardware, satellite communication hardware, and / or any other wired or wireless hardware for communicating with other networks and / or devices. The network interface 114 communicatively connects the system control module 105 to an external system such as an external computing device 120 via a network 116. The network 116 may be a wide area network, a local area network, a personal area network, a cellular network, a satellite network, etc.

[0023] The system control module 105 of the system 100 can be communicatively connected to one or more external computing devices 120. The external computing device 120 can be one or more computing devices that can be in remote communication with the wearable device 102 and the system control module 105 via the network 116. In an embodiment, the system control module 105 can be a computing device that includes one or more modules as described herein that are remote from the wearable device 102 or integrated within the wearable device 102. The external computing device 120 can include a device that operates outside of the wearable device 102, such as a desktop computer, a laptop computer, a smart phone, and any other type of computing device that communicates with the wearable device 102 and / or the system control module 105. The external computing device 120 can send information to the wearable device 102 and / or the system control module 105 and / or receive information from the wearable device 102 and / or the system control module 105, such as sensor information from the sensor module 110.

[0024] The wearable device 102 and the system control module 105 of the system 100 can be communicatively connected to one or more remote services 118. The remote services 118 can include services that operate outside of the wearable device 102 and can be utilized by or can utilize the wearable device 102, such as external databases, storage devices, servers, computing platforms, and any other type of service. For example, the external database can store sensor information collected by the sensor module 110.

[0025] It should be understood that Figure 2 The components illustrated in the figure are merely illustrative and are not intended to limit the scope of the present disclosure. More specifically, although Figure 2 The components in the embodiment are illustrated as being located within the wearable device 102, but this is a non-limiting example. In some embodiments, one or more of the components may be located external to the wearable device 102. It should also be understood that the components of the wearable device 102 and / or the system control module 105 described herein are exemplary and may include more than one embodiment. Figure 1 For example, to reduce the cost of the wearable device 102, some embodiments of the wearable device 102 may include a sensor module 110 for capturing perfusion metrics to be sent to an external computing device 120 to perform operations and / or methods of one or more system control module 105 components described herein.

[0026] Reference now Figure 2 , shows a wearable device 102 of the system 100. The wearable device 102 may include a wearable garment, a plurality of sensors 202, 204, 206, 208, 210, Figure 1One or more sensors 103, and in some embodiments may include Figure 1 . The cost of the wearable device 102 can be reduced by limiting the wearable device 102 to include a wearable garment and a plurality of sensors 202, 204, 206, 208, 210, wherein the external computing device 120 includes components of the system control module 105 and performs the methods described herein. In these embodiments, the wearable device 102 can be communicatively coupled to the external computing device via a transmitter deployed in the wearable device 102 and a transceiver deployed in the external computing device and configured to receive data from the transmitter. The wearable garment can be a sock, a glove, a sleeve, and / or any other clothing item. For example, the wearable device 102 is a sock that can be put on the foot of the patient 201. The wearable garment of the wearable device 102 can generally be made of any type of material, and the present disclosure does not limit such materials. For example, the wearable garment can be made of a textile including natural fibers, such as, for example, wool, linen, cotton, hemp, and / or the like. In some embodiments, the wearable garment may also or instead be formed from one or more synthetic fibers, such as, for example, polyester, aramid, acrylic, nylon, spandex, olefin, carbon fiber, and / or the like. The wearable garment may generally have a variety of sizes to appropriately fit patients 201 of different sizes. For example, wearable garments may be available in small, medium, large, and / or extra-large sizes having different lengths and / or widths depending on the size of the patient 201.

[0027] Providing the patient 201 with an appropriately fitted wearable garment allows the wearable device 102 to have consistent placement of multiple sensors 202, 204, 206, 208, 210 between wearable garments of the same size and between wears of the same wearable garment. The sensors 202, 204, 206, 208, 210 are positioned relative to the wearable garment at locations corresponding to specific areas on the patient's body or are positioned thereon, such that when the patient 201 wears the wearable garment, the sensors 202, 204, 206, 208, 210 are positioned adjacent to the patient 201. Thus, the wearable garment of the wearable device 102 can have repeatable sensor placement, wherein appropriate pressure is induced by the wearable garment to maintain contact and proximity of the sensors 202, 204, 206, 208, 210 to a body part (such as a foot).

[0028] In addition, the sensors 202, 204, 206, 208, 210 can be positioned to correspond to intervals of the body part, so that one or more of the multiple sensors 202, 204, 206, 208, 210 are dedicated to interval measurements. For example, in an embodiment, the foot can be divided into intervals, so that the forefoot has sensors 202, 204, the midfoot has sensors 206, the rear foot has sensors 208, and / or the calf has sensors 210. The use of multiple sensors 202, 204, 206, 208, 210 can help minimize errors and improve signal-to-noise ratios. The sensors 202, 204, 206, 208, 210 that are communicatively coupled to the sensor module 110 can be a cluster of sensors that measure pulse oximetry, heart rate, temperature, bioimpedance, and / or other vital signs, as well as statistical confidence percentages of blood perfusion levels, which combined can improve the accuracy and reliability of the device.

[0029] The plurality of sensors 202, 204, 206, 208, 210 operate by providing measurements that can be used to establish a blood perfusion baseline based on the ankle-brachial index (ABI) of the patient 201, and then detecting changes in blood perfusion in the foot of the patient 201 before, during, and / or after an intervention. The system control module 105 can process changes in the data from the sensors 202, 204, 206, 208, 210 to determine the status of various body compartments at which the sensors 202, 204, 206, 208, 210 are placed. For example, when the oxygen saturation (SpO2) level is determined by each of the plurality of sensors 202, 204, 206, 208, 210 to measure the percentage of hemoglobin binding sites in the bloodstream at the measurement site that are occupied by oxygen (i.e., the percentage of oxygen-saturated hemoglobin relative to total hemoglobin), an image or other visual material (e.g., a light array) can present an indication of whether the blood perfusion of the patient 201 is good, poor, or critical. In addition, when the sensors 202, 204, 206, 208, 210 are placed against multiple areas of the foot, for example, the device can detect interval differences in blood perfusion within the foot. For example, the interval covered by sensor 202 may have critical blood perfusion, the interval covered by sensors 204, 206 may have poor blood perfusion, and the interval covered by sensors 208, 210 may have good blood perfusion. By incorporating multiple sensors 202, 204, 206, 208, 210 and analyzing the data generated, the wearable device 102 provides both instant feedback and trend data via the system control module 105 to assess blood perfusion both instantly and over time.

[0030] Reference now Figure 3, a method 400 is shown as a control scheme that can be implemented by the system 100 and used to provide blood perfusion assessment using the wearable device 102. The method 400 can be implemented by Figure 1 The perfusion module 112 of the system control module 105 is executed. At block 402, the perfusion module 112 of the system control module 105 receives a first set of blood perfusion metrics associated with an individual from a plurality of sensors 202, 204, 206, 208, 210. As discussed above, the system control module 105 includes a sensor module 110 communicatively coupled to the plurality of sensors 202, 204, 206, 208, 210. The plurality of sensors 202, 204, 206, 208, 210 may each be a separate sensor or a cluster of sensors, including but not limited to a blood pressure monitor, a pulse oximeter, an optical heart sensor, a thermometer, a bioimpedance sensor, and / or the like. The blood perfusion metric may be any measurement related to blood perfusion in the body and may be determined based on at least information received from the plurality of sensors 202, 204, 206, 208, 210. Thus, the blood perfusion metric includes blood oxygen, heart rate, bioimpedance, temperature, ankle brachial pressure, or a combination thereof. The first set of blood perfusion metrics received may be from one or more regions of the body covered by the wearable device 102. For example, referring to Figure 2 , each interval can be a part of the foot. Sensors 202, 204, 206, 208, 210 can collect information related to an individual (e.g., Figure 2 The system may further comprise a first set of blood perfusion metrics associated with the patient 201 ) and transmit the data to the perfusion module 112 of the system control module 105 , for example via the communication path 104 .

[0031] Return to reference Figure 3At block 404, the wearable device 102 generates a first reading based on the first set of blood perfusion metrics. The data received by the perfusion module 112 can be used to determine a pre-intervention reading that is used to establish a baseline level of blood perfusion. The perfusion module 112 can correlate the sensor measurements with the determined ABI (or other blood perfusion metrics) to define the blood perfusion level and screen for PAD. The ABI can be determined by measuring and selecting the high pressure of two arteries at the ankle and dividing the higher pressure by the brachial atrial systolic pressure at the arm. The measurements used to determine the ABI can be received from the wearable device 102 and / or an external measurement device. The readings may include the status of various intervals of the body where the sensors 103, 202, 204, 206, 208, 210 are placed. For example, when determining the SpO2 level, the readings may indicate whether the patient's blood perfusion is good, poor, or critical for each interval. As another example, the perfusion module may generate a graph of blood oxygen (ranging from 0 to 100) versus ABI (ranging from 0 to 1.5). The status of blood perfusion may be stratified such that for any blood oxygen reading, an ABI from 0 to 0.5 is critical, an ABI from 0.5 to 1 is poor, and an ABI from 1 to 1.5 is good. It should be understood that embodiments are not limited to three classifications of blood perfusion and may include more or fewer classifications.

[0032] In addition, when the sensors 103, 202, 204, 206, 208, 210 are placed against multiple areas, the wearable device 102 can determine the interval difference in blood perfusion between two or more intervals of the patient. Figure 2 , the wearable device 102 can determine an interval difference in blood perfusion between a forefoot having sensor 202, a midfoot having sensor 206, and / or a rearfoot having sensor 208, wherein the interval difference indicates a steady decrease in blood perfusion from the rearfoot to the forefoot.

[0033] Still reference Figure 3 At block 406, the perfusion module 112 receives a second set of blood perfusion metrics associated with an individual wearing the wearable device 102 (which may be a wearable garment) from the plurality of sensors 202, 204, 206, 208, 210. The perfusion module 112 may receive the second set of blood perfusion metrics in a manner similar to block 402. Unlike block 402, block 406 may occur during and / or after an intervention (such as surgery or other medical intervention) to improve blood perfusion of the patient 201.

[0034] At block 408, the perfusion module 112 generates a second reading based on the second set of blood perfusion metrics. That is, the data received by the perfusion module 112 of the wearable device 102 can be used to determine the effect of the intervention on changes in blood perfusion during the intervention and / or to establish a post-intervention reading of the current blood perfusion level. Generating the second reading can be performed in a manner similar to block 404.

[0035] At block 410, the perfusion module 112 determines an intervention state based on the first reading and the second reading. The perfusion module 112 of the wearable device 102 can identify a difference between the first reading and the second reading to define an intervention state for improving blood perfusion and indicating a level of improvement in blood perfusion. The difference can be a local difference to identify changes in a specific interval over time (e.g., the difference between the first reading and the second reading can be calculated for the same sensor or sensor group 202, 204, 206, 208, 210). For example, the difference between the first reading and the second reading of the forefoot can be determined. The difference can also be or be an interval difference to identify how the degree of difference between the two intervals changes over time (e.g., the difference change between two or more sensors can be calculated). For example, the difference between the midfoot and the forefoot on the first reading can be compared with the difference between the midfoot and the forefoot on the second reading. The difference between the midfoot and the forefoot on the first reading can indicate that the midfoot has poor blood perfusion and the forefoot has critical blood perfusion. Figure 2 A second, post-intervention reading may be presented showing that the forefoot region covered by sensor 204 has improved to similar poor blood perfusion as the midfoot. The difference between the first reading and the second reading in this example would be the area covered by sensor 204 in the forefoot, indicating that the intervention provided only a minor improvement in blood perfusion.

[0036] In some embodiments, the intervention state may be determined using a machine learning model that is communicatively coupled to the perfusion module 112 and / or other components of the system control module 105. The machine learning model may be a classifier that participates in an unsupervised machine learning algorithm such as k-means clustering, hierarchical clustering, and / or the like. The machine learning model may analyze multiple readings taken together with other reference data to classify the multiple readings as belonging to various blood perfusion levels. For example, if the difference in features (e.g., blood oxygen, temperature, bioimpedance, etc.) between the first reading and the second reading is similar to the difference in features of the readings taken from the patient 201 who has undergone a successful intervention, then the second reading may be classified as successful. The data collected by the device may also be used to classify the state of the patient 201. The device may receive data from various other patients (e.g., ABI, SpO2, bioimpedance, and temperature) and their classifications (e.g., good, poor, or critical blood perfusion) to train a machine learning model to classify the patient. After training, data related to changes in blood perfusion in the foot before, during, and / or after the intervention may be used as input to the trained machine learning model to generate an output representing the classification of the patient. In some embodiments, the reference data may include previous blood perfusion measurements and / or previous intervention states from multiple individuals. The multiple individuals may be from a representative cross-section of a general population or a subset thereof having similar attributes to the patient 201. For example, if the patient 201 has a particular medical condition, the reference data may be from individuals having the same medical condition.

[0037] Still reference Figure 3 At block 412, the perfusion module 112 generates an intervention recommendation indicating whether an additional intervention is recommended based on the first reading, the second reading, the intervention status, or a combination thereof. The perfusion module 112 may generate the intervention recommendation using a machine learning model as described herein. The machine learning model may be a decision tree, a Bayesian classifier, a support vector machine, a convolutional neural network, and / or the like. Intervention as discussed herein may refer to a medical procedure including, but not limited to, angioplasty, bypass surgery, atherectomy, thrombolytic procedures, and / or other procedures for treating symptoms and / or conditions caused by poor blood perfusion.

[0038] Data collected by one or more components of the wearable device 102 and / or the system control module 105 as described herein can be used as training inputs for machine learning models to generate predictions about the patient's state and subsequent intervention needs. The data may include changes in blood perfusion of the patient 201 before, during, and / or after the intervention. In addition to the patient's data, the system control module 105 may also receive historical data sets from multiple individuals, the historical data sets including previous blood perfusion metrics, previous interventions and intervention types, previous intervention states before, during, and after the intervention, or a combination thereof. The historical data sets may be used to train the machine learning model to obtain more accurate predictions. Data from other patients may be from a representative sample of the general population. In some cases, a representative sample of the population may be a representative sample with similar attributes to the patient 201. For example, if the patient 201 has diabetes, data related to blood perfusion in the feet of other diabetic patients may be used to train the machine learning model.

[0039] The intervention suggestion may indicate whether additional intervention is needed, how much additional intervention is needed, and / or when additional intervention may be needed. If the second reading is an intra-intervention reading, the intervention suggestion may be a continued intervention suggestion, which includes an indication of whether to provide continued intervention, a predicted intervention state (e.g., a predicted intervention perfusion state), or a combination thereof. In an embodiment, the predicted intervention perfusion state may indicate a predicted perfusion state result of the medical intervention at or after the completion of the intervention. In an embodiment, the predicted intervention perfusion state may indicate a predicted perfusion state result of the medical intervention in a time period after the intervention. The indication that continued intervention should be provided may be an indication that the current intervention is insufficient for a threshold level of blood perfusion, which threshold level may be predetermined or user-defined. For example, while the intervention is being performed, the doctor performing the intervention may receive an indication in real time from the wearable device 102 and / or the system control module 105 that more intervention work should be performed before the intervention is terminated because some areas are at a critical level. The predicted intervention state may be an indication of the possible results of the current intervention as demonstrated by the training data for training the machine learning model. For example, while an intervention is being performed, the physician performing the intervention may receive a prediction in real time from the wearable device 102 and / or the system control module 105 that the current intervention may have improved blood perfusion in only a portion of the foot rather than the entire foot.

[0040] If the second reading is a post-intervention reading, then the intervention suggestion is a subsequent intervention suggestion, which includes a suggested treatment course, a predicted intervention state, or a combination thereof. The subsequent intervention suggestion may be a suggested treatment course after the intervention. The suggested treatment course may be based on past cases with similar first readings, second readings, and / or intervention states and treatment courses that solve past cases as provided to the machine learning model in the training data. The machine learning model may be trained to make treatment course suggestions based on past case inputs, suggested treatment courses, and results. Past cases within positive results may then be used to suggest similar treatment courses. Non-limiting examples of treatment course suggestions may include (one or more) additional interventions, specific therapies (such as massage and / or medication), and similar treatments for improving circulation and blood perfusion. As an embodiment and non-limiting example of treatment course suggestions, after performing the intervention, the doctor may receive an indication from the wearable device 102 and / or the system control module 105 that the additional intervention should be performed. The subsequent intervention suggestion may also or instead include a predicted intervention state. The predicted intervention state may be an indication of the possible outcome of the most recently performed intervention as demonstrated by the training data that trained the machine learning model. For example, after performing an intervention, the physician may receive an indication from the wearable device 102 and / or the system control module 105 that blood perfusion will likely be in a good state within a week after the intervention.

[0041] In some embodiments, the steps of method 400 may be performed by a system 100 including a wearable device 102, wherein the wearable device 102 may have one or more sensors 103 ( Figure 1 ) of multiple sensors 202, 204, 206, 208, 210 to collect blood perfusion metrics, which are then transmitted to the system control module 105 and / or the external computing device 120 for processing according to the steps of method 400.

[0042] Reference now Figure 4 , a method 500 for strengthening a machine learning model is shown. The method 500 may be performed by the perfusion module 112 of the system control module 105 to enhance the performance of the machine learning model of the perfusion module 112. The method 500 may be a continuation of the method 400 to further train the machine learning model. At block 502, the perfusion module 112 receives a third set of blood perfusion metrics associated with an individual wearing the wearable device 102 from a plurality of sensors. The perfusion module 112 may perform the following steps similar to Figure 3 Receive a third set of blood perfusion metrics in the manner of blocks 402 and 406. Unlike blocks 402 and 406, block 502 can occur after a period of recovery from an intervention (such as surgery) to determine the accuracy of previous predictions of the machine learning model and improve the training of the machine learning model for future predictions.

[0043] At block 504, the wearable device generates a third reading as a subsequent intervention reading after generating the intervention recommendation and based on the third set of blood perfusion metrics. The third reading can be a subsequent reading after the intervention to determine the accuracy of the predicted intervention state previously made by the machine learning model by comparing the third reading to the predicted intervention state previously made by the machine learning model. If the comparison is within a certain threshold, then a certain level of accuracy is determined and quantified. Generating the third reading can be similar to Figure 3 The method is performed in blocks 404 and 408.

[0044] Still reference Figure 4 , at box 506, the system control module 105 (such as via the perfusion module 112) further trains the machine learning model based on the comparison of the intervention recommendation to the third reading to improve the subsequent follow-up intervention recommendation. The intervention recommendation and / or the third reading can be incorporated into the training data used to train the machine learning model. The machine learning model can be retrained on the updated training data set. For example, the machine learning model may determine that the comparison of the intervention recommendation to the third reading may be greater than an allowed predetermined threshold. In these embodiments, the machine learning model can be trained based on the third reading so that the subsequent follow-up intervention recommendation is within the allowed predetermined threshold. In these embodiments, the machine learning model can be trained by adjusting or otherwise changing the parameters and associated weights in the machine learning model to improve the model accuracy so that the subsequent follow-up intervention recommendation is within the allowed predetermined threshold. In an embodiment, the updated machine learning model can be verified by comparing with additional readings taken after the subsequent follow-up intervention recommendation that are within an acceptable threshold.

[0045] In some embodiments, the steps of method 500 may be performed by a system 100 including a wearable device 102, wherein the wearable device 102 may have one or more sensors 103 ( Figure 1 ) of multiple sensors 202, 204, 206, 208, 210 to collect blood perfusion metrics, which are then transmitted to the system control module 105 and / or the external computing device 120 for processing according to the steps of method 500.

[0046] Reference now Figure 5, shows a scenario in which a patient 603 wears a wearable device 102 for providing blood perfusion assessment. The system 100 for assessing blood perfusion may include a wearable device 102 (which may include one or more components of a system control module 105), an external computing device 610 (which may additionally or alternatively include one or more components of the system control module 105), and an electronic display 602. For example, the patient 603 may wear the wearable device 102 before, during, and / or after an intervention for PAD. The wearable device 102 may be connected to a wearable device 102 via one or more sensors 103 ( Figure 1 ) collects data such as pulse oximetry, heart rate, temperature, bioimpedance, and / or other vital signs (collectively, “blood perfusion metrics”). The raw data collected by the wearable device 102 can be processed by the system control module 105 into a reading indicating the level of blood perfusion. For example, ABI, pulse oximetry, and bioimpedance can each be used for screening for PAD. The perfusion module 112 of the system control module 105 can process the first set of perfusion metrics to generate a first reading 606. In an embodiment, the first reading 606 can be transmitted from the system control module 105 to an external computing device 610, which can store, relay, interpret, and / or otherwise utilize the perfusion metrics and / or readings 606, 608 from the system control module 105. For example, the external computing device 610 can relay the readings 606, 608 to the electronic display 602. In some embodiments, the wearable device 102 only collects perfusion metrics via one or more sensors 103 and transmits the data to an external computing device 610 including a system control module 105 to perform the remaining processing, such as generating readings 606, 608. This can reduce the cost of the wearable device 102 by placing the computational load on the external computing device 610. In other embodiments, the wearable device 102 can include one or more components of the system control module 105, such as a processor 106 and / or memory 108 coupled thereto to provide computing capabilities.

[0047] During the intervention, the physician operating on the patient 603 can view the patient information 604, the first reading 606, and the second reading 608 on the electronic display 602. The first reading 606 can display the blood perfusion level to establish a baseline, which here shows a critical level of blood perfusion throughout the foot. During the intervention, the system control module 105 can also collect a second set of blood perfusion metrics and determine a second reading 608 of blood perfusion. Figure 5The second reading 608 of the first reading 606 can indicate that the hindfoot has improved significantly, the midfoot has improved moderately, and the forefoot has improved slightly since the intervention began. However, the second reading 608 can also indicate that the area around the big toe of the foot has not improved. The wearable device 102 can identify these differences between the first reading 606 and the second reading 608 to define the intervention state. The difference may be local, such as the big toe area of ​​the second reading 608, and may also be regional, such as greater improvement to the hindfoot.

[0048] The system control module 105 can generate an intervention recommendation using a machine learning model that is communicatively coupled to the perfusion module 112. The machine learning model can be trained on a data set having first and second readings of a device for multiple interventions performed on previous patients, and one or more blood perfusion metrics describing the patient's outcome for each intervention. There can be a threshold level of blood perfusion such that the system control module 105 is configured to prefer a blood perfusion level above a critical level. Thus, due to the lack of improvement throughout the foot, the system control module 105 can recommend that the physician continue the intervention. The recommendation can provide the physician with a more objective, data-driven approach to determine the likelihood of success of an intervention to treat PAD. In some embodiments, the generation of the intervention recommendation can be performed by the system 100. For example, an external computing device 610 can generate the intervention recommendation.

[0049] The embodiments may be further described in conjunction with the following numbered clauses:

[0050] 1. A system for assessing blood perfusion, comprising: a wearable garment; a plurality of sensors secured to the wearable garment; a processor communicatively coupled to the plurality of sensors; a memory component communicatively coupled to the processor; a machine learning model stored in the memory component; and machine-readable instructions stored in the memory component, the machine-readable instructions causing the processor to perform operations, the operations comprising: receiving a first set of blood perfusion metrics associated with an individual wearing the wearable garment from the plurality of sensors; generating a first reading based on the first set of blood perfusion metrics; receiving a second set of blood perfusion metrics associated with the individual wearing the wearable garment from the plurality of sensors; generating a second reading based on the second set of blood perfusion metrics; determining an intervention perfusion state for a medical intervention to improve blood perfusion of the individual based on the first reading and the second reading and indicating a level of improvement in blood perfusion; and generating, using the machine learning model, an intervention recommendation indicating whether an additional intervention is recommended based on the first reading, the second reading, the intervention perfusion state, or a combination thereof.

[0051] 2. The system of clause 1, wherein the first set of blood perfusion metrics and the second set of blood perfusion metrics include blood oxygenation, heart rate, bioimpedance, temperature, ankle-brachial pressure, or a combination thereof.

[0052] 3. A system as described in any preceding clause, wherein the plurality of sensors are positioned on the wearable garment such that when the individual wears the wearable garment, the plurality of sensors are positioned adjacent to the individual.

[0053] 4. A system as described in any of the preceding clauses, wherein: the first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; the second reading is an intervention reading used to establish a current reading of blood perfusion during the medical intervention; and the intervention recommendation is a continue intervention recommendation, which includes an indication of whether to continue the intervention, a predicted intervention perfusion state indicating a predicted perfusion state result of the medical intervention at or after the completion of the intervention, or a combination thereof.

[0054] 5. A system as described in any of the preceding clauses, wherein: the first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; the second reading is a post-intervention reading used to establish a current reading of blood perfusion; and the intervention recommendation is a subsequent intervention recommendation, the recommendation comprising a recommended course of treatment, a predicted intervention perfusion state indicating a predicted perfusion state outcome of the medical intervention within a time period following the medical intervention, or a combination thereof.

[0055] 6. A system as described in any of the preceding clauses, wherein the machine-readable instructions cause the processor to perform operations, the operations also including: receiving a third set of blood perfusion metrics associated with the individual wearing the wearable garment from the multiple sensors; generating a third reading as a subsequent intervention reading after generating an intervention recommendation and based on the third set of blood perfusion metrics; and training a machine learning model based on a comparison of the intervention recommendation and the third reading to improve a subsequent subsequent intervention recommendation.

[0056] 7. A system as described in any of the preceding clauses, wherein the machine-readable instructions cause the processor to perform operations, the operations further comprising: before generating an intervention recommendation, receiving a historical data set including previous blood perfusion measurements, previous interventions, previous intervention states, or a combination thereof from multiple individuals.

[0057] 8. A system as described in clause 7, wherein the machine-readable instructions cause the processor to perform operations, the operations also including: training a machine learning model based on a historical data set before generating an intervention recommendation.

[0058] 9. A system for assessing blood perfusion, comprising: a processor; a memory component communicatively coupled to the processor; a machine learning model stored in the memory component; and machine readable instructions stored in the memory component, the machine readable instructions causing the processor to perform operations, the operations comprising: receiving a first set of blood perfusion metrics associated with an individual from a wearable device having a plurality of sensors for assessing blood perfusion when the individual wears the wearable device; generating a first reading based on the first set of blood perfusion metrics; receiving a second set of blood perfusion metrics associated with the individual from the wearable device when the individual wears the wearable device; generating a second reading based on the second set of blood perfusion metrics; determining an intervention perfusion state for improving blood perfusion of the individual based on the first reading and the second reading and indicating a level of improvement in blood perfusion; and using the machine learning model, generating an intervention recommendation indicating whether additional intervention is recommended based on the first reading, the second reading, the intervention perfusion state, or a combination thereof.

[0059] 10. The system of clause 9, wherein the first set of blood perfusion metrics and the second set of blood perfusion metrics include blood oxygenation, heart rate, bioimpedance, temperature, ankle-brachial pressure, or a combination thereof.

[0060] 11. The system of any of clauses 9-10, wherein the plurality of sensors from the wearable device are positioned on the wearable device such that when the individual wears the wearable device, the plurality of sensors are positioned adjacent to the individual.

[0061] 12. A system as described in any of clauses 9-11, wherein: the first reading is a pre-intervention reading for establishing a baseline reading of blood perfusion; the second reading is an intervention reading for establishing a current reading of blood perfusion; and the intervention recommendation is a continue intervention recommendation, which includes an indication of whether to provide a continue intervention, a predicted intervention perfusion state indicating a predicted perfusion state result of the medical intervention at or after the intervention is completed, or a combination thereof.

[0062] 13. A system as described in any of clauses 9-12, wherein: the first reading is a pre-intervention reading for establishing a baseline reading of blood perfusion; the second reading is a post-intervention reading for establishing a current reading of blood perfusion; and the intervention recommendation is a subsequent intervention recommendation, which includes a recommended treatment course, a predicted perfusion intervention state indicating a predicted perfusion state outcome of the medical intervention within a time period after the medical intervention, or a combination thereof.

[0063] 14. A system as described in any of clauses 9-13, wherein the machine-readable instructions cause the processor to perform operations, the operations also including: receiving a third set of blood perfusion metrics associated with the individual from the wearable device while the individual is wearing the wearable device; generating a third reading as a subsequent intervention reading after generating an intervention recommendation and based on the third set of blood perfusion metrics; and training a machine learning model based on a comparison of the intervention recommendation and the third reading to improve a subsequent subsequent intervention recommendation.

[0064] 15. A system as described in clause 14, wherein the machine-readable instructions cause the processor to perform operations, the operations also including: before generating an intervention recommendation: receiving a historical data set from multiple individuals including previous blood perfusion measurements, previous interventions, previous intervention states, or a combination thereof; and training a machine learning model based on the historical data set to generate an intervention state prediction based on the blood perfusion measurements, interventions, intervention states, or a combination thereof.

[0065] 16. A method for assessing blood perfusion, comprising: receiving, using a processor, a first set of blood perfusion metrics associated with an individual wearing the wearable device having multiple sensors for assessing blood perfusion; generating, using the processor, a first reading based on the first set of blood perfusion metrics; receiving, using the processor, a second set of blood perfusion metrics associated with the individual wearing the wearable device from the wearable device; generating, using the processor, a second reading based on the first set of blood perfusion metrics; determining, based on the first reading and the second reading, an intervention perfusion state for improving blood perfusion in the individual; and generating, using a machine learning model, an intervention recommendation indicating whether additional intervention is recommended based on the first reading, the second reading, the intervention perfusion state, or a combination thereof.

[0066] 17. A method as described in clause 16, wherein: the first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; the second reading is an intervention reading used to establish a current reading of blood perfusion; and the intervention recommendation is a continue intervention recommendation, which includes an indication of whether to continue the intervention, a predicted intervention perfusion state indicating a predicted perfusion state result of the medical intervention at the time of completion of the intervention or after the completion of the intervention, or a combination thereof.

[0067] 18. A method as described in any of clauses 16-17, wherein: the first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; the second reading is a post-intervention reading used to establish a current reading of blood perfusion; and the intervention recommendation is a subsequent intervention recommendation, which includes a recommended treatment course, a predicted intervention perfusion state indicating a predicted perfusion state of a medical intervention within a time period after the medical intervention, or a combination thereof.

[0068] 19. The method as described in any of clauses 16-18 further includes: receiving a third set of blood perfusion metrics associated with an individual wearing the wearable device from the wearable device; generating a third reading as a subsequent intervention reading after generating an intervention recommendation and based on the third set of blood perfusion metrics; and training a machine learning model based on a comparison of the intervention recommendation and the third reading to improve subsequent subsequent intervention recommendations.

[0069] 20. The method as described in clause 19 also includes: before generating an intervention recommendation: receiving a historical data set from multiple individuals including previous blood perfusion measurements, previous interventions, previous intervention states, or a combination thereof; and training a machine learning model based on the historical data set to generate an intervention state prediction based on the blood perfusion measurements, interventions, intervention states, or a combination thereof.

[0070] It should now be understood that the embodiments disclosed herein are generally directed to wearable devices, systems, and methods for providing blood perfusion assessment. The wearable device, which may be a wearable garment, includes multiple sensors and a computing system for analyzing data collected by the multiple sensors. The computing system may have machine-readable instructions executable by a processor for quantifying the perfusion of a body part wearing the wearable garment based on the collected data. This in turn can make the determination of the success of a PAD intervention more objective. The machine-readable instructions may also include a machine learning model that is trained on sensor data from multiple patients with PAD interventions of varying degrees of success. The machine learning model may also provide follow-up monitoring to determine perfusion success after the intervention, and enhance the machine learning model in future determinations and predictions.

[0071] It is noted that the limitations herein on components of the present disclosure being "configured" or "programmed" in a particular manner to implement a particular property or to operate in a particular manner are structural limitations, not limitations of intended use. More specifically, references herein to the manner in which a component is "configured" or "programmed" represent the existing physical condition of the component, and thus should be regarded as an explicit limitation of the structural characteristics of the component.

[0072] Unless otherwise specified, the execution or implementation order of the operations in the examples of the present disclosure shown and described herein is not required. That is, unless otherwise specified, the operations can be performed in any order, and the examples of the present disclosure may include additional or fewer operations relative to the operations disclosed herein. For example, it is contemplated that it is within the scope of the various aspects of the present disclosure to perform or implement a particular operation before, simultaneously with, or after another operation.

[0073] Having described the subject matter of the present disclosure in detail and with reference to specific embodiments thereof, it is noted that the various details disclosed herein should not be understood to imply that these details are related to elements that are essential components of the various embodiments described herein, even if specific elements are illustrated in each of the figures accompanying this description. In addition, it will be apparent that modifications and variations may be made without departing from the scope of the present disclosure, which includes, but is not limited to, the embodiments defined in the appended claims. More specifically, although some aspects of the present disclosure are identified herein as preferred or particularly advantageous, it is contemplated that the present disclosure is not necessarily limited to these aspects.

Claims

1. A system for assessing blood perfusion, comprising: Wearable clothing; multiple sensors affixed to a wearable garment; a processor communicatively coupled to the plurality of sensors; a memory component communicatively coupled to the processor; a machine learning model stored in a memory component; as well as Machine-readable instructions stored in the memory component, the machine-readable instructions causing the processor to perform operations comprising: receiving, from the plurality of sensors, a first set of blood perfusion metrics associated with an individual wearing the wearable garment; generating a first reading based on the first set of blood perfusion metrics; receiving, from the plurality of sensors, a second set of blood perfusion metrics associated with an individual wearing the wearable garment; generating a second reading based on a second set of blood perfusion metrics; determining an intervention perfusion state for a medical intervention to improve blood perfusion in the individual based on the first reading and the second reading and indicative of a level of improvement in blood perfusion; and Using the machine learning model, an intervention recommendation is generated indicating whether an additional intervention is recommended based on the first reading, the second reading, the intervention perfusion state, or a combination thereof.

2. The system of claim 1, wherein the first set of blood perfusion metrics and the second set of blood perfusion metrics include blood oxygenation, heart rate, bioimpedance, temperature, ankle-brachial pressure, or a combination thereof.

3. The system of claim 1, wherein the plurality of sensors are positioned on the wearable garment such that when the individual wears the wearable garment, the plurality of sensors are positioned adjacent to the individual.

4. The system of claim 1, wherein: The first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; The second reading is an intervention reading used to establish a current reading of blood perfusion during the medical intervention; and The intervention recommendation is a continue intervention recommendation including an indication of whether a continue intervention should be provided, a predicted intervention perfusion state indicating a predicted perfusion state outcome of the medical intervention at or after completion of the intervention, or a combination thereof.

5. The system of claim 1, wherein: The first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; The second reading is a post-intervention reading used to establish a current reading of blood perfusion; and The intervention recommendation is a subsequent intervention recommendation that includes a recommended course of treatment, a predicted intervention perfusion state indicating a predicted perfusion state outcome of the medical intervention within a time period following the medical intervention, or a combination thereof.

6. The system of claim 1, wherein the machine-readable instructions cause the processor to perform operations further comprising: receiving a third set of blood perfusion metrics associated with the individual wearing the wearable garment from the plurality of sensors; generating a third reading as a subsequent intervention reading after generating the intervention recommendation and based on the third set of blood perfusion metrics; as well as A machine learning model is trained based on the comparison of the intervention recommendations and the third reading to improve subsequent follow-up intervention recommendations.

7. The system of claim 1, wherein the machine-readable instructions cause the processor to perform operations further comprising: Prior to generating an intervention recommendation, a historical data set including previous blood perfusion metrics, previous interventions, previous intervention states, or a combination thereof is received from a plurality of individuals.

8. The system of claim 7, wherein the machine-readable instructions cause the processor to perform operations further comprising: Train machine learning models on historical datasets before generating intervention recommendations.

9. A system for assessing blood perfusion, comprising: processor; a memory component communicatively coupled to the processor; a machine learning model stored in a memory component; as well as Machine-readable instructions stored in the memory component, the machine-readable instructions causing the processor to perform operations comprising: receiving a first set of blood perfusion metrics associated with an individual from a wearable device having a plurality of sensors for assessing blood perfusion while the individual is wearing the wearable device; generating a first reading based on the first set of blood perfusion metrics; receiving a second set of blood perfusion metrics associated with the individual from the wearable device while the individual is wearing the wearable device; generating a second reading based on a second set of blood perfusion metrics; determining an intervention perfusion state for improving blood perfusion in the individual based on the first reading and the second reading and indicative of a level of improvement in blood perfusion; and Using the machine learning model, an intervention recommendation is generated indicating whether an additional intervention is recommended based on the first reading, the second reading, the intervention perfusion state, or a combination thereof.

10. The system of claim 9, wherein the first set of blood perfusion metrics and the second set of blood perfusion metrics include blood oxygenation, heart rate, bioimpedance, temperature, ankle-brachial pressure, or a combination thereof.

11. The system of claim 9, wherein the plurality of sensors from the wearable device are positioned on the wearable device such that when the individual wears the wearable device, the plurality of sensors are positioned adjacent to the individual.

12. The system of claim 9, wherein: The first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; The second reading is an intervention reading used to establish the current reading of blood perfusion; and The intervention recommendation is a continue intervention recommendation including an indication of whether a continue intervention should be provided, a predicted intervention perfusion state indicating a predicted perfusion state outcome of the medical intervention at or after completion of the intervention, or a combination thereof.

13. The system of claim 9, wherein: The first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; The second reading is a post-intervention reading used to establish a current reading of blood perfusion; and The intervention recommendation is a subsequent intervention recommendation that includes a recommended course of treatment, a predicted intervention perfusion state indicating a predicted perfusion state outcome of the medical intervention within a time period following the medical intervention, or a combination thereof.

14. The system of claim 9, wherein the machine-readable instructions cause the processor to perform operations further comprising: receiving, from the wearable device, a third set of blood perfusion metrics associated with the individual while the individual is wearing the wearable device; generating a third reading as a subsequent intervention reading after generating the intervention recommendation and based on the third set of blood perfusion metrics; as well as A machine learning model is trained based on the comparison of the intervention recommendations and the third reading to improve subsequent follow-up intervention recommendations.

15. The system of claim 14, wherein the machine-readable instructions cause the processor to perform operations further comprising: Before generating intervention recommendations: receiving a historical data set including previous blood perfusion measurements, previous interventions, previous intervention states, or a combination thereof from a plurality of individuals; as well as A machine learning model is trained based on the historical data set to generate an intervention state prediction based on a blood perfusion metric, an intervention, an intervention state, or a combination thereof.

16. A method for assessing blood perfusion, comprising: receiving, using a processor, from a wearable device having a plurality of sensors for assessing blood perfusion, a first set of blood perfusion metrics associated with an individual wearing the wearable device; generating, using a processor, a first reading based on the first set of blood perfusion metrics; receiving, using a processor, from the wearable device, a second set of blood perfusion metrics associated with an individual wearing the wearable device; generating, using a processor, a second reading based on the first set of blood perfusion metrics; determining an intervention perfusion state for improving blood perfusion in the individual based on the first reading and the second reading and indicative of a level of improvement in blood perfusion; as well as Using the machine learning model, an intervention recommendation is generated indicating whether an additional intervention is recommended based on the first reading, the second reading, the intervention perfusion state, or a combination thereof.

17. The method of claim 16, wherein: The first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; The second reading is an intervention reading used to establish the current reading of blood perfusion; and The intervention recommendation is a continue intervention recommendation including an indication of whether a continue intervention should be provided, a predicted intervention perfusion state indicating a predicted perfusion state outcome of the medical intervention at or after completion of the intervention, or a combination thereof.

18. The method of claim 16, wherein: The first reading is a pre-intervention reading used to establish a baseline reading of blood perfusion; The second reading is a post-intervention reading used to establish a current reading of blood perfusion; and The intervention recommendation is a subsequent intervention recommendation that includes a recommended course of treatment, a predicted intervention perfusion state indicating a predicted perfusion state outcome of the medical intervention within a time period following the medical intervention, or a combination thereof.

19. The method of claim 16, further comprising: receiving, from the wearable device, a third set of blood perfusion metrics associated with an individual wearing the wearable device; generating a third reading as a subsequent intervention reading after generating the intervention recommendation and based on the third set of blood perfusion metrics; as well as A machine learning model is trained based on the comparison of the intervention recommendations and the third reading to improve subsequent follow-up intervention recommendations.

20. The method of claim 19, further comprising: Before generating intervention recommendations: receiving a historical data set including previous blood perfusion measurements, previous interventions, previous intervention states, or a combination thereof from a plurality of individuals; as well as A machine learning model is trained based on the historical data set to generate an intervention state prediction based on a blood perfusion metric, an intervention, an intervention state, or a combination thereof.

Images