JP2026502342A - Non-invasive devices, systems, and methods for monitoring blood flow and coagulation - Google Patents

Abstract

Wearable devices, including topical patches and sleeves applied to the skin, are used to stimulate and recognize changes in blood flow and clotting. A non-invasive transcutaneous electrical muscle stimulator (EMS) is embedded in the patch or sleeve and delivers continuous stimulation to perivascular tissue to promote blood flow. The stimulation system includes a series of electrodes positioned on the skin via the patch or sleeve and an external programmable generator with wireless connectivity during stimulation. Biosensors in the patch or sleeve and other biosensors applied to the body periodically check for abnormal biomarker patterns. These patterns may be used by artificial intelligence (AI)/machine learning (ML) systems as early indicators or by predictive methods to predict changes in blood flow and clotting, such as those caused by venous thrombosis. If an abnormal biomarker pattern is detected, an alert may be sent and a therapeutic response may be initiated.
[Selected Figure] Figure 1B

Description

The present disclosure relates generally to devices, systems, and methods for monitoring blood flow and coagulation, and more specifically to devices and methods for monitoring thrombi and related conditions by predicting the probability of thrombus development in the venous system from noninvasive biosensor measurements.

Thrombotic events occur when a blood clot (thrombus) blocks the flow of blood within the circulatory system, or vascular system. Depending on the blocked vessel, this blockage can reduce the supply of oxygen and essential nutrients carried in the blood to body tissues, leading to cell damage and potentially cell death if blood flow is not quickly restored. The blockage can also prevent the outflow of deoxygenated blood and metabolic waste products from the tissues. Preventing the evacuation of blood and waste products from tissues can increase intravascular pressure, causing fluid leakage in the surrounding perivascular spaces and resulting in pain and swelling. Veins are blood vessels that carry blood from tissues back to the heart. Therefore, blood clots that form in and travel through the venous system are called venous thromboembolism (VTE). VTE that occurs in the larger veins of the body is called deep vein thrombosis (DVT) and can affect the arms, legs, pelvis, torso, and even the brain (cerebral venous sinus thrombosis). Additionally, DVT can result in blood clots breaking off, which can travel or embolize to other parts of the body, thereby causing obstruction of blood flow elsewhere. Blood clots that embolize and lodge in the lungs are called pulmonary embolism (PE) and can be fatal.

Common features of DVT include pain, discoloration such as redness or bruising of the skin, and swelling or bulging of superficial veins. Clues to PE may include shortness of breath or rapid breathing, palpitations, dizziness, sweating, or sharp chest and rib pain that worsens with inspiration. Unfortunately, many of the signs and symptoms of VTE are nonspecific and can be misinterpreted as being caused by less urgent etiologies, such as muscle tension with lower extremity DVT or anxiety about PE. This can lead to poorer clinical outcomes due to delayed diagnosis.

In total, VTE affects 1 million people annually, contributing to as many as 300,000 deaths in the United States alone. These figures are likely underestimates due to the lack of annual surveillance for VTE in the United States. Despite its prevalence and mortality rate, VTE is considered a preventable disease in the majority of cases. In fact, VTE is the leading cause of preventable hospitalized deaths in the United States and worldwide. For those who experience VTE, long-term complications and recurrence are a concern. One in three people will develop another blood clot, often requiring lifelong anticoagulation therapy. Another third will develop post-thrombotic syndrome, a major cause of disability and reduced quality of life after an initial DVT diagnosis.

The pathogenesis of thrombosis has been clearly described by Virchow's triad, a principle that delineates three major factors that, when present, create a thrombosis-promoting environment: venous stasis, endothelial injury, and hypercoagulation. Risk factors for VTE are traditionally classified as identifiable (provoked) or unprovoked (unprovoked). Risk factors leading to provoked VTE can be genetic or acquired. Genetic factors include inherited deficiencies of antithrombin, protein C, and protein S. Acquired factors include infection and medical conditions such as cancer, immobility, surgery such as joint replacement, and responses to trauma or drug therapy, particularly cancer and hormone replacement therapy. Hospitalization has a clear association with the development of VTE, and when it occurs during or shortly after hospitalization, it is referred to as healthcare-associated or HA-VTE. However, when classified, these risk factors may induce any or all of the elements of Virchow's triad. Recognizing these associations can improve management and facilitate the development of novel tools for VTE prevention and treatment.

Traditionally, individuals suspected of having VTE are evaluated using pre-test probability (PTP) scoring systems, such as the Wells DVT and PE score and the Geneva score. These scoring batteries take into account specific criteria, including demographics, pre-existing conditions, and active symptoms, such as calf pain and swelling, which may indicate suspected DVT. These traditional scoring systems do not consider social determinants of health (SDoH), defined by the World Health Organization (WHO) as "the context in which people are born, grow, live, work, and age, and the systems in place to address disease." SDoH are directly associated with cardiovascular disease risk and outcomes, including VTE. Without including SDoH in risk assessment and outcome prediction, the application of predictive models utilizing traditional data sets and measurements will not accurately reflect true risk and outcome probabilities and will continue to exacerbate healthcare disparities and increase the disease burden experienced by marginalized and underserved populations. In practice, the results of the PTP cannot safely determine the input or output of the VTE.

If scoring from a conventional PTP system results in a low probability of VTE, serum D-dimer testing is performed to help rule out the VTE diagnosis. Alternatively, if VTE is likely based on scoring, the diagnosis can be confirmed with relevant imaging tests, such as ultrasound or CT angiography. Currently, no specific criteria exist for imaging tests to confirm or rule out a VTE diagnosis beyond clinical judgment. Such inconsistencies in management provide another opportunity for delayed care.

VTE treatment classically involves anticoagulant (AC) or blood thinner regimens. Many ACs, such as warfarin, require frequent testing to ensure they are within the therapeutic range, which often takes several weeks to achieve. Other blood thinners, such as direct oral anticoagulants (DOACs), typically do not require serum studies to ensure they are within the therapeutic range, but variability in patient response exists. As a result, inappropriate dosing may go undetected, thereby leading to worse outcomes due to bleeding or, conversely, thrombotic events if dosing is subtherapeutic. Furthermore, physical therapy, when implemented in conjunction with drug therapy, has become an important adjunct to treatment regimens and the prevention of long-term VTE-related complications.

The complexity and diversity of management and access to technologies from prevention to treatment necessitates technologies that can safely and reliably support management in a variety of settings along the spectrum of care.

SUMMARY OF THE INVENTION Various examples are now described to introduce in a simplified form a selection of concepts that are further described below in the Detailed Description. This Summary is not intended to be used to limit the scope of the claimed subject matter.

In a sample configuration, a patch is adhered to the back of the leg or other anatomical location, or a sleeve is applied to an area where venous thromboembolism (VTE) may occur. A noninvasive transcutaneous neuroelectrical muscle stimulator (EMS) is embedded in the patch or sleeve that is applied to the patient during conditions where changes in blood flow and clotting are expected, such as after surgery, to prevent blood clots through external stimulation of the calf muscles or other local muscles. The stimulation system includes a series of electrodes positioned on the patient's skin via the patch or sleeve and an external programmable stimulator that has wireless connectivity during stimulation and is battery-powered and rechargeable for ease of mobility. Biosensors in the patch or sleeve, as well as other biosensors applied to the body, are periodically checked for abnormal biomarker patterns that can be used by an artificial intelligence (AI)/machine learning (ML) system to predict blood clot formation. Detection of such abnormal biomarker patterns notifies a healthcare professional that further management of potential VTE in the patient is necessary.

In a sample configuration, at least one of the computer application, the remote computer, or the cloud server may process the quantitative biosensor data collected by the biosensor and the collected qualitative data determining the patient's health with a predictive algorithm that uses machine learning techniques to predict the patient's likelihood of developing a blood clot, and calculate a risk score based on the prediction of the likelihood of developing a blood clot generated by the predictive algorithm. The computer application, the remote computer, and/or the cloud server may generate an alert indicating the patient's condition and/or initiate a therapeutic response to the development of a blood clot based on a predetermined change in the risk score. The alert may be issued using different modalities to initiate different actions depending on whether the recipient of the alert is a healthcare professional, a patient, or a caregiver. The different modalities may include at least one of a voice or audio message, an email, an SMS text using cellular data, a chat application, an EMR alert, a telemedicine system, or an artificial intelligence-generated message via a software application. Additionally, the system may include a device gateway that receives and transmits data from the biosensor and third-party data sources to at least one of the computer application, the remote computer, or the cloud server.

A method for monitoring blood flow and coagulation to predict the development of a thrombus in a patient's body is also provided. The method includes positioning a device over a region of interest on the surface of the patient's body, the device being configured to measure physiological biomarkers, generate a localized blood flow, and transmit the data to a remote computer server; generating the localized blood flow using the device; measuring biomarkers indicative of changes in blood flow and coagulation; and implementing on a computer or cloud server a predictive algorithm that uses machine learning techniques to predict the patient's likelihood of developing a thrombus from at least the biomarker measurements. Based on the prediction of the likelihood of developing a thrombus generated by the predictive algorithm, the method further includes calculating a risk score and at least one of generating an alert indicative of the patient's condition or initiating a therapeutic response to the development of a thrombus.

The method may further include transferring data from the device in an outpatient setting or from the communication device in an inpatient setting to a computer or cloud server, where the predictive algorithm is implemented on the computer or cloud server. Measuring biomarkers indicative of altered blood flow and coagulation may further include initiating configuration of the biomarker measurement device using an initial patient biomarker profile based on pre-assessed patient-specific information highlighting pre-existing disease states or physiological conditions that may affect or be influenced by blood flow and coagulation, altering the risk of developing a blood clot. For example, the pre-assessed patient-specific information may be based on a particular diagnosis, procedure, or blood flow and coagulation alteration therapy prescribed for the patient, and/or may include socioeconomic or social determinants of health that affect the occurrence of a blood clot or contribute to poorer outcomes in patients diagnosed with a blood clot.

This Summary section is provided to introduce aspects of the inventive subject matter in a simplified form, with further description of the inventive subject matter following in the body of the Detailed Description. The particular combination and order of elements listed in this Summary section are not intended to provide limitations on the elements of the claimed subject matter. Rather, this section can be understood to provide summarized examples of some of the embodiments described in the Detailed Description below.

These and other beneficial features and advantages of the present invention will become apparent from the following detailed description taken in conjunction with the accompanying drawings.

FIG. 1 is a dorsal view of a patient's leg showing the positioning of the patient's popliteal vein.

FIG. 1 is an exploded view of a system consisting of a patch and stimulation device adapted to acquire data from a biosensor placed on a patient's skin in a sample configuration.

2A and 2B are diagrams of further configurations of the system shown in FIG. 1 adapted to other anatomical locations using a sleeve for placement on the patient's arm (FIG. 2A) or the patient's leg (FIGS. 2B and 2C).

FIG. 1 is a diagram of the electronics used to acquire patient data from the biosensor and transfer the patient data to a computer application in a sample configuration.

FIG. 1 illustrates an example patient journey use case to which the systems and methods described herein may be applied.

FIG. 10 illustrates the transfer of acquired patient data to the cloud for application of predictive models in a sample configuration.

1 is a flowchart illustrating a method for predicting the likelihood that a patient will develop a thrombus in a blood vessel of interest in a sample configuration.

FIG. 10 is a diagram representing multiple data sources in the system, including devices that can send data through a device gateway and third-party sources such as public databases that transfer data bidirectionally to the cloud in a sample configuration.

FIG. 10 is a detailed flowchart showing a method for predicting a patient's risk of developing a blood clot when a significant threshold or pattern is detected in a sample configuration, and repeating the measurement at timed intervals or sending an alert to a respondent, such as a healthcare professional, if the risk score remains unchanged or is not of concern, in order to initiate the next step in patient management.

FIG. 1 is a hierarchy diagram of the alert process for respondent actions and potential actions that can be taken in patient management by individuals or the system itself in a sample configuration.

A detailed description of an exemplary embodiment will now be provided with reference to Figures 1-9. While this description provides a detailed description of possible implementations, it should be noted that these details are intended as examples and in no way limit the scope of the inventive subject matter.

FIG. 1A is a dorsal view of a patient's leg showing the positioning of the patient's popliteal vein. FIG. 1B is an exploded view of a system 100 consisting of a multilayer adhesive patch 110 and a removable electronic/stimulation device 120 adapted to acquire data from biosensors 130 placed on the patient's body in a sample configuration. As shown, the multilayer adhesive patch 110 includes at least an outer layer 140 having a flexible fabric covering and an inner layer 150 having electronic connections between multiple biosensors 130 for sensing physiological signals from the patient's skin and electrodes 160 for sensing bioimpedance and delivering electrical stimulation. The electronic connections include a connection to a removable electronic/stimulation device 120 that houses electronics used to acquire patient data recorded by the multiple biosensors 130 and electrodes 160, transfer the acquired data to a cloud and/or computer server to analyze the patient data, and implement a machine learning algorithm configured to predict the probability of a thrombus developing in the patient's blood vessel based on the acquired data. It should be understood that the electronic/stimulation device 120 may be incorporated within the patch. Alternatively, the electronic/stimulation device 120 may be integrated and externally powered using radio frequency (RF), by other wireless power means, or by corded (plug-in power).

The system of FIG. 1B is configured to align the biosensor 130 and electrodes 160 along a blood vessel of interest. For example, the multilayer adhesive patch 110 may be placed along a popliteal vein in a patient's lower leg (as viewed from the rear in FIG. 1A) to predict the probability of a thrombus developing in a sample configuration. It should be understood that the system can be implemented in a variety of configurations.

For example, the configuration of system 100 shown in FIGS. 2A-2C may include an arm configuration 200 (FIG. 2A) and a leg configuration 210 (FIGS. 2B-2C) incorporating a multi-layer sleeve 220 positioned along a target blood vessel (e.g., the popliteal vein of a leg). The multi-layer sleeve 220 includes at least an outer layer having a flexible fabric covering and an inner layer having electronic connections between multiple biosensors 130 for detecting physiological signals from the patient's skin and electrodes 160 for detecting bioimpedance and delivering electrical stimulation. The multi-layer sleeve 220 may be configured to accommodate different sizes. The multi-layer sleeve 220 may be closed with Velcro or other means around the limb. The electronic connections include connection to an electronic/stimulation device 120 that houses electronics used to acquire patient data recorded by the multiple biosensors 130 and electrodes 160, transfer the acquired data to a cloud and/or computer server to analyze the patient data, and implement a machine learning algorithm configured to predict the probability of a thrombus developing in the patient's blood vessel based on the acquired data.

The exemplary configuration of system 100 shown in FIG. 2C further incorporates mercury strain gauges 240 for plethysmography and includes one or more pressure cuffs 230 and 250 spaced along the vascular network to apply occlusion pressure to the target vessel, with or without the multi-layer sleeve 220. It will be appreciated that targeted occlusion of a vessel can be achieved without the use of cuffs. For example, the target pressure can be provided by other means, such as a smart compression garment made from a shape memory alloy or electromechanical percussion massage. The components described herein are connected to a device 120 containing electronics used to acquire patient data measured by the mercury strain gauges 240, transfer the acquired data to a cloud and/or computer server to analyze the patient data, and implement machine learning algorithms configured to predict the probability of a thrombus developing in the patient's vessel based on the acquired data.

FIG. 3 is a diagram of electronics disposed in a removable electronic/stimulation device 120 and used to acquire patient data from multiple biosensors 130 and electrodes 160 and transfer the acquired patient data to an application on a local computing device or to a remote computer server in the cloud and/or sample configuration. It should be understood that the electronic/stimulation device 120 may be incorporated into the system 100 or may have other configurations. As shown, the multiple biosensors 130 and bioimpedance electrodes 160 are connected to the electronics of a microcontroller 300, which is powered by a battery 315 and includes a signal conditioning circuit 320, an impedance measurement circuit 330, a data acquisition circuit 340, and a timing control circuit 350. The biosensors 130 include, but are not limited to, photoplethysmography (PPG), infrared thermopiles, electrodermal activity (EDA) sensors, galvanic skin response (GSR) sensors, and/or strain gauge plethysmography. The electrodes 160 may be used to acquire a voltage difference generated by a current injected by a current injection electrode 360. The current is generated by signal generation circuitry 370. The delivered current may be configured to provide constant current stimulation. The constant current stimulation may be configured to reduce or eliminate patient perception by delivering a frequency between 20 kHz and 100 kHz. The constant current may be configured to have an amplitude greater than 1 mA to provide a sufficient signal-to-noise ratio to detect changes in impedance.

In a sample configuration, the stimulation electrodes 310 can be used to excite muscle fibers or nerves to induce blood flow in response to signals generated by the signal generating circuitry 370. This blood flow can be used to facilitate data acquisition from the physiological sensors 130. Additionally, the blood flow can be used to help prevent blood clotting. It is understood that other means of creating blood flow can be incorporated, which may include, but are not limited to, pneumatic compression, ultrasound, massage (or localized compression), vibration, and passive and/or voluntary movement.

The microcontroller 300 includes a timing control circuit 350 that controls the timing of the signal generator 370, data acquisition circuit 340, signal conditioning circuit 320, and impedance measurement circuit 330. The impedance measurement is timed based on the current generated by the signal generator 370 being injected into the current injection electrode 360. The data acquisition circuit 340 measures the voltage of the impedance measurement electrode 160 and transfers the acquired voltage to memory 380. Data acquisition from the physiological sensor 130 is also controlled by the timing control circuit 350. Physiological sensor data from the physiological sensor 130 is input to an appropriate signal conditioning circuit 320. The signal conditioning circuit 320 may include, but is not limited to, filtering, strain gauge signal conditioning (isolation, bridge balance, filtering, excitation voltage), thermopile signal conditioning (isolation, linearization, etc.), and other signal conditioning that may be required to facilitate acquisition of physiological sensor data from the physiological sensor 130. Once the physiological sensor data has been acquired and conditioned via applicable signal conditioning circuitry 320, the physiological sensor data is stored in memory 380.

The communications circuitry 390 facilitates the transfer of data from the memory 380 to a computer application 500 implemented on one or more smart devices, such as a phone or tablet, and adapted to receive and process the acquired physiological and voltage data. The wireless communications circuitry 390 can use BLUETOOTH®, WI-FI®, Zigbee®, cellular data, or radio frequency (RF) circuitry to facilitate communication to a local smartphone or other electronic device processing the computer application 500. The acquired patient data may then be transferred from the computer application 500 to the cloud or another server via a wired or wireless internet connection (FIG. 5). Conversely, the communications circuitry 390 may be adapted to transfer the acquired physiological and voltage data directly from the removable electronic/stimulation device 120 to a remote server device for processing.

As shown in FIG. 4, different predefined settings, represented by patient journey use cases 400, may be selected for the system. The predefined settings may be based on pre-assessed patient-specific information highlighting pre-existing disease states or physiological conditions that affect or are affected by blood flow and clotting, thus altering the risk of developing a thrombus. This includes, but is not limited to, specific diagnostic, procedural, or blood flow and clotting alteration therapies. Examples include surgery use cases 410, such as hip replacement, cancer, infection, inflammatory disease, sepsis, vascular insufficiency, dehydration, immobilization, and pregnancy. Other predefined settings for the described systems and methods include use cases 420 for pharmacological therapies, such as anticoagulants, antiplatelets, or other blood thinning medications, and use cases 430 for non-pharmacological therapies, such as exercise regimens, or the use of prophylactic mechanical devices, such as pneumatic compressors, or surgical therapies, such as revascularization procedures (stents, bypasses), or monitoring the patency of conduits for infusion or hemodialysis. Additional predetermined settings for the described systems and methods may include socioeconomic factors or social determinants of health that influence the occurrence and/or outcome of blood clots in patients diagnosed with blood clots, such as social support, education, health literacy, food insecurity, available access to and payment for medical care, and residential environment. Social determinants of health may have quantitative measures, such as the Social Vulnerability Index (SVI) or Area Deprivation Index (ADI). Qualitative data may include information from patients, such as how they describe their relationship with their healthcare provider (communication, bias, etc.) or the agreement between their expectations and those of their healthcare provider regarding the outcome of a particular treatment (e.g., blood thinners). In each case, an initial patient biomarker profile is obtained to serve as a baseline for comparative analysis. It should be understood that system 100 may also be used with preventative devices. For example, system 100 may be positioned below an air compressor and operate in conjunction with the operation of the air compressor.

FIG. 5 is a diagram depicting the transfer of acquired patient data to a cloud 510 for application of a predictive model 520 to assess the probability of developing a blood clot in a sample configuration. The cloud 510 includes circuitry for ingesting (530), analyzing (540), storing (550) the analyzed patient data, and reporting (560) the results of the data analysis to a healthcare professional. The system 100 of FIG. 1 can be used to assess a patient's risk of developing a blood clot in either an outpatient (e.g., outpatient clinic, assisted living facility, single-family home) setting (570) or an inpatient (e.g., acute care hospital, rehabilitation center, nursing home) setting (580).

In an outpatient setting 570, for example, a patient 585 may be at home and have the system 100 of FIG. 1 positioned on their body in proximity to a blood vessel of interest. Data from the system 100 is transferred to an application 500, which may run on any mobile platform, including Android, iOS, Windows, etc., and may be configured on one or more displays, including a smartwatch, cell phone, tablet, computer, television monitor, etc., capable of communicating with the system 100 via BLUETOOTH®, WI-FI®, Zigbee®, cellular data, or other wireless means. Additionally, the computer application 500 may be configured to transfer the acquired data to the cloud 510.

In an inpatient setting 580, a patient 585 is in a hospital and the system 100 can be placed on the body in proximity to the blood vessel of interest. The system 100 can transfer acquired patient data directly from the system 100 to the cloud 510, or there can be a separate communication device in proximity to the patient 585 that is used to transfer data from the system 100 to the cloud 510.

Once the acquired patient data is transferred to the cloud server of the cloud 510, the data is ingested at 530 and analyzed at 540 to implement the predictive model 520. Based on the prediction by the predictive model 520, a risk score is calculated and reported to the healthcare professional 590 by reporting software 560 via a healthcare professional interface 595. The healthcare professional interface 595 can be displayed on a mobile phone, tablet, computer, patient status board, room monitor, etc., connected to or otherwise connected to an electronic medical record (EMR) or health information system (HIS) server. All data in the cloud 510, including the analysis data (540) and model data (520), is stored in data storage 550 and used to improve the predictive model 520 over time as more patient data is transferred to the cloud 510.

FIG. 6 is a flowchart illustrating a method 600 for predicting a patient's likelihood of developing a thrombus in a sample configuration. As shown, method 600 begins with reading data from one or more datasets 610, including physiological sensors 130, electrodes 160, and other patient data (e.g., demographic information, medical history, past or ongoing interventions, serum biomarker values (e.g., D-dimer, PT/PTT, INR), pain scales and other patient-reported symptoms, supplemental biometric data, etc.), and social determinants of health. Dataset 610 may also include risk assessment and scoring batteries with associated variables (e.g., Caprini Score, Wells Criteria, PERC, etc.). Preprocessing of the data read from dataset 610 is performed in 620, including any necessary signal conditioning and analysis.

Patient input may also include subjective information such as signs of pain (Y/N, if so, on a scale of 1-10), swelling (Y/N), discoloration, i.e., redness and/or bruising (Y/N), heat (Y/N), chest pain (Y/N), cough (Y/N), and shortness of breath (Y/N). Additional data that may be entered for analysis, but that is not collected before and during the monitoring period, may include, for example, patient demographics (gender, race, age, etc.) and patient medical history (existing conditions, previous surgeries, medications, etc.).

The processed dataset may be divided into a training dataset 630, a validation dataset 640, and a test dataset 650. The training dataset 630 may be used to train a classifier 632, such as a classification machine learning algorithm of a machine learning device. The classification algorithm implemented by the classifier 632 may include logistic regression, k-nearest neighbors, decision trees, random forests, and/or support vector machines to classify input data as corresponding to a VTE condition or not. The resulting validation dataset 640 may be used to evaluate the predictive accuracy 642 of the classification 644 on the "trained" model 520. The trained model 520 is adjusted 660 according to the results of the predictive accuracy 642 based on the validation dataset 640. This iterative process may be repeated.

The best model 670 based on the validation dataset 640 is selected, and the results are then validated 672 on the test dataset 650. The resulting classification 674 can be used to calculate a risk score 676 corresponding to the likelihood that the patient will develop a thrombus in the vessel of interest.

Based on the calculated risk score 676, the system output report varies depending on the recipient (e.g., patient 585 vs. healthcare professional 590) and whether the risk score 676 corresponding to the biomarker pattern has changed. If the risk score 676 does not change, the patient 585 and healthcare professional 590 receive similar messages via the patient interface 500 and healthcare professional interface 595, respectively, confirming a successful biomarker check and subsequent data storage. On the other hand, if the risk score 676 rises by a predetermined amount in a manner corresponding to a measurable abnormality in the biomarker pattern, an alert prompts the patient 685 via the patient interface 500 to complete a device check to ensure the leads and sensors are correctly positioned. If the device check raises concerns about device function or positioning, troubleshooting instructions are provided to the patient 585. If there are no device issues, additional information regarding current signs and symptoms may be requested from the patient via the patient interface 500. A device alert may be sent for completion of data analysis of the transmitted and stored data, and a change in risk status may be reported. At the same time, the healthcare professional 590 can receive device alerts sent about changes in risk status via the healthcare professional interface 595, including providing the healthcare provider access to the stored patient data 550.

FIG. 7 is a diagram depicting multiple data sources within a system 700, including wearable or contactless sensors 710, including wearable devices 100 (FIG. 1A), which can transmit data 610 via a device gateway 720, and third-party sources, such as a public database 790, that provide bidirectional transfer of data to a cloud 510. The cloud 510 then communicates with multiple data-receiving devices, including a patient status board 730, a room monitor 740, an EMR/HIS server 750, a display, such as a smart television or computer 755 or tablet 760, a smart watch 765, or a cellular device 770, etc., which can display and communicate raw and processed data in various forms. Datasets 610 can be obtained from one or more sources at various points along one or more patient care journeys and across various patient conditions, such as before and after the administration of a treatment regimen. Information from one or more datasets can be obtained prior to device use and can serve as a patient-specific baseline. Patient-specific values and/or values from population-specific datasets can be used as baselines to guide device monitoring and the detection of abnormal biomarker patterns.

The dataset can include both quantitative (temperature, heart rate, social vulnerability index) and qualitative (patient care perceptions and expectations) data from patient surveys 780, as well as both subjective (patient-reported symptoms) and objective (observed signs) information. Data beyond biomarker patterns associated with VTE incidence can be acquired, stored, and analyzed during system implementation to provide insights into relevant outcome measures, such as hospitalized patient length of stay, hospitalization rates, mortality, development of long-term complications, worsening of existing medical conditions or development of new medical conditions, medication adherence, and the like. These outcome measures can contribute to the development of new protocols or strategies to improve patient safety, quality of patient care, cost of care, and utilization of healthcare resources.

FIG. 8 is a detailed flowchart illustrating a method 800 for predicting a patient's risk of developing a blood clot and initiating an alert for further management, including, but not limited to, a healthcare professional prescribing additional diagnostic studies or initiating treatment to prevent blood clot formation in the sample configuration. In the example of FIG. 8, the system 100 is placed on a patient's limb with the sensor 130 positioned in proximity to the target blood vessel. As shown in FIG. 3, localized blood flow can be generated at 810 by electrical stimulation of muscles and/or nerves via the stimulation electrode 310 and/or current injection electrode 360. However, it is understood that blood flow can be generated using other methods, such as pneumatic compression, ultrasound, massage (localized compression), vibration, and/or passive or voluntary movement. In another embodiment, the increased risk can initiate a response that prompts the system to automatically initiate a therapeutic regimen delivered by the device 100 or via communication with other therapeutic devices in the system.

Changes in physiological biomarkers can be measured during local blood flow at 820. For example, a physiological noninvasive biosensor 130, such as that shown in FIG. 1, can measure flow gradients, venous compliance, valve function, temperature gradients, oxygen gradients, and the like. In another configuration, the biosensor 130 can also measure molecular biomarkers, such as D-dimer test results, fibrin degradation products (FDPs) or other biomarkers of fibrinolysis, von Willebrand factor (vWF), P-selectin protein, intercellular adhesion molecule (ICAM-1), thrombomodulin (THBD) protein, endothelial protein receptor (EPCR), tissue factor pathway inhibitor (TFPI), forkhead box protein C2 (FOXC2), and prospero homeobox protein 1 (PROX1). In another alternative configuration, previously collected serum biomarkers such as these may be provided as additional data set 610. The biomarkers measured by the biosensor 130 are analyzed to identify any patterns at 830. Means for measuring biomarkers may include electrical impedance measurements, biocapacitance, thermal imaging, ultrasound imaging, auscultation, photoplethysmography, strain gauge plethysmography, etc.

Impedance changes that may indicate thrombus formation can be between 1-10% of the impedance, with 1-4% being the optimal range. Meanwhile, increases in local skin temperature may indicate a pathological process such as thrombus formation. For example, a temperature change of more than 0.2°C may be measured in the range of 0.4°C to 2.5°C relative to the contralateral limb or limb outside the measurement area (see, for example, Shaydakov et al., "Efficacy of Infrared Thermography in the Diagnosis of Deep Vein Thrombosis: An Evidence-Based Review," J Vasc Diag Interven, 2017, Vol. 5, pp. 7-14).

Once biomarkers are measured at 820 and the acquired data transferred to the cloud 510, the data is analyzed at 830 along with any additional datasets 610 acquired from other sources, and a predictive model is implemented at 840. A risk score is calculated at 850 based on the output of the predictive model 520 (FIG. 5). If no significant threshold or abnormal pattern corresponding to elevated risk is detected at 860, biomarker measurements may be repeated at timed intervals 880 upon the onset of local blood flow at 810. For example, the timed intervals may range from 5 minutes to 1 hour. On the other hand, if the calculated risk score indicates clot formation, an alert is sent at 870 to a respondent, such as a healthcare professional, to initiate the next step in management.

FIG. 9 illustrates an alert process 900 in which alerts 870 can be received through a variety of modalities 910, including as voice or audio messages, by email, by SMS using cellular data, by chat applications, as EMR alerts, via telemedicine systems, and as AI-generated messages via software platforms or applications. The responders 920 of the alerts can be individuals, such as healthcare professionals, patients and/or their caregivers, or devices within the system.

In response to the alert, the healthcare professional 590 can take one or more actions 930, including ordering a diagnostic study such as ultrasound imaging, initiating treatment, scheduling an in-person or virtual visit, consulting additional specialists on the care team, such as a vascular medicine specialist or social worker, to address identified socioeconomic factors, or sending the patient directly to the emergency room for further investigation or hospitalization. Patient or caregiver 585 prompted actions 940 can include seeking emergency treatment, calling a healthcare professional, emphasizing or de-emphasizing existing strategies, such as physical therapy exercises, or making no changes, and continuing the current regimen. Additionally, the device 100 can respond with actions 950, including connecting other respondents to third parties, such as insurance companies, community organizations, etc., to connect the patient to community-based resources, or can initiate an emergency response if the patient's risk is related to an adverse outcome. The device 100 can also automatically provide treatment by retrieving a programmed electrical stimulation regimen or communicate with other connected devices in the system programmed to administer treatment, such as drug injection or infusion devices.

Thus, the methods described herein include:
positioning a device over a region of interest on a surface of a patient's body, the device being configured to measure physiological biomarkers, generate local blood flow, and transmit data to a remote computer server;
generating localized blood flow using a device;
measuring biomarkers indicative of changes in blood flow and coagulation that may be affected by pre-defined settings that reflect a patient journey use case based on pre-assessed patient-specific data;
combining the measured biomarker data with data from other connected devices, including third-party databases and servers, and survey-mediated patient-reported data;
transferring data from the biomarker measurements to a computer;
transferring data from a computer application in an outpatient setting or a communication device in an inpatient setting to a computer or cloud server;
implementing on a computer or cloud server a predictive algorithm that uses machine learning techniques to predict the probability of thrombus formation in a patient from at least biomarker measurements;
calculating a risk score based on the prediction of the probability of thrombus formation generated by the predictive algorithm;
at least one of generating an alert indicative of the patient's condition or initiating a therapeutic response to the thrombotic event;
It is understood that a method for predicting a thrombus in a patient is performed by performing steps including:

If the risk status has not changed or is not of concern, no alert may be generated. If an alert is generated, the patient's risk status change is communicated and appropriate action taken depending on the responder and the severity of the status change.

The method may be repeated at time intervals ranging from, for example, 5 minutes to 1 hour.

Methods for generating localized blood flow may include, but are not limited to, at least one of electrical muscle stimulation, electrical nerve stimulation, pneumatic compression, ultrasound, massage (localized compression), or vibration.

Methods for measuring biomarkers may include, but are not limited to, at least one of electrical impedance measurement, biocapacitance measurement, thermal imaging, ultrasound imaging, auscultation, photoplethysmography, impedance plethysmography, or strain gauge plethysmography.

The method may further include implementing a response to the development of a thrombus in the patient via at least one of, but not limited to, electrical neuromuscular stimulation, electrical nerve stimulation, pneumatic compression, ultrasound, massage, vibration, or phototherapy.

The response may further include initiating treatment, for example, by initiating medication via communication with a drug delivery device, consulting a specialist, utilizing local resources, suggesting emergency services, etc.

A corresponding system for monitoring thrombi may include a patch or sleeve having an outer layer formed of a flexible, waterproof material, an inner layer with electrical connections, a plurality of physiological sensors configured to measure biomarkers, and a plurality of electrodes configured to measure bioimpedance and deliver electrical stimulation. The system also includes a removable electronic/stimulation device that connects to the electrical connections and has a microcontroller including a timing control circuit, a data acquisition circuit that acquires data from the plurality of physiological sensors and the bioimpedance electrodes, a signal conditioning circuit configured to process data from the physiological sensors, an impedance measurement circuit configured to process data from the bioimpedance electrodes, and a signal generation circuit configured to apply electrical stimulation to generate local blood flow and current injection for the impedance measurement. A communication circuit transfers data to and from the removable electronic/stimulation device. A memory is also provided for storing acquired data and program instructions, and a battery is provided for powering the device to enable ambulatory mobility.

The physiological sensors may be configured to predetermined settings based on patient-specific information, including, but not limited to, at least one of: existing disease states or diagnoses, physiological conditions affecting or affected by blood flow and coagulation, recent history of surgeries or procedures, use of blood flow and coagulation altering therapies, patient demographics, and social determinants of health. Physiological sensors may include photoplethysmography sensors, strain gauge plethysmography sensors, impedance plethysmography sensors, electrodes, ultrasound sensors, biocapacitance sensors, infrared thermopile sensors, electrodermal activity sensors, galvanic skin response sensors, etc.

The signal conditioning circuitry of the microcontroller may include strain gauge signal conditioning circuitry including isolation, bridge balancing, filtering, and excitation voltage measurement, thermopile signal conditioning circuitry including isolation and linearization, and other signal conditioning circuitry necessary to facilitate physiological data acquisition.

The communications circuitry facilitating transfer of the acquired data to an application or another device may include wireless circuitry facilitating communications using BLUETOOTH®, WI-FI®, Zigbee®, cellular data, or radio frequency circuitry to transfer the data. The computer application may be configured on a smartwatch, mobile phone, or tablet configured to communicate with the removable electronic/stimulation device and a remote computer or cloud server using BLUETOOTH®, WI-FI®, Zigbee®, cellular data, or radio frequency circuitry. The acquired data may be transferred to a device located in an inpatient setting, such as a hospital or clinic, and/or configured to communicate the data to a computer application, remote computer, or cloud server, or other wireless or contactless sensing device within a network that includes the communications circuitry.

The remote computer or cloud server may be configured to analyze patient data, implement predictive models, calculate risk scores, and report such scores to a healthcare professional via a healthcare professional interface, such as a healthcare professional-oriented mobile phone, tablet, computer, or other display interface of the type shown in FIG. 7.

Conclusion While various embodiments have been described above, it should be understood that they are presented by way of example only, and not by way of limitation. For example, any of the elements associated with the systems and methods described above may employ any of the desired functionality described above. Thus, the breadth and scope of a preferred embodiment should not be limited by any of the sample embodiments described above.

As described herein, logic, commands, or instructions implementing aspects of the methods described herein may be provided in computing systems including any number of form factors, such as desktop or notebook personal computers, mobile devices such as tablets, netbooks, and smartphones, client terminals, and server host machine instances. Other embodiments described herein include incorporating the techniques described herein into other forms, including programmed logic, hardware configurations, or other forms of specialized components or modules, including apparatuses having respective means for performing the functions of such techniques. Each algorithm used to implement the functions of such techniques may include some or all of the sequence of electronic operations described herein, or other aspects shown in the accompanying drawings and the detailed description below. Such systems and computer-readable media containing instructions for performing the methods described herein also constitute sample embodiments.

The processing functions described herein (e.g., with respect to Figures 3-9) may be implemented in software in one embodiment. The software may be comprised of computer-executable instructions stored on a computer-readable medium or computer-readable storage device, such as one or more non-transitory memories or other types of hardware-based storage devices, either local or networked. Furthermore, such functions correspond to modules, which may be software, hardware, firmware, or any combination thereof. Multiple functions may be performed in one or more modules as desired, and the described embodiments are merely examples. The software may be executed on a digital signal processor, ASIC, microprocessor, or other type of processor operating on a computer system, such as a personal computer, server, or other computer system, turning such a computer system into a specially programmed machine.

The examples described herein may include or operate on a processor, logic, or several components, modules, or mechanisms (herein "modules"). A module is a tangible entity (e.g., hardware) capable of performing specified operations and may be configured or arranged in a particular manner. In one example, a circuit may be arranged (e.g., internally or relative to an external entity, such as another circuit) in a specified manner as a module. In one example, one or more computer systems (e.g., standalone, client, or server computer systems) or one or more hardware processors may be configured, in whole or in part, by firmware or software (e.g., instructions, application portions, or applications) as modules that operate to perform specified operations. In one example, the software may reside on a machine-readable medium. The software, when executed by the underlying hardware of the module, causes the hardware to perform the specified operations.

The term "module" is therefore understood to encompass tangible hardware and/or software entities, which are physically constructed, specifically configured (e.g., hardwired), or temporarily (e.g., temporarily) configured (e.g., programmed) to operate in a specified manner or to perform some or all of the operations described herein. Considering examples in which modules are temporarily configured, each of the modules need not be instantiated at any one moment. For example, if the modules include a general-purpose hardware processor configured using software, the general-purpose hardware processor may be configured as each different module at different times. Thus, the software may, for example, configure the hardware processor to configure a particular module at one time and a different module at a different time.

As one of ordinary skill in the art will appreciate, while the disclosure contained herein relates to techniques for measuring blood flow and clotting associated with the development of venous thrombosis, the techniques described herein may be applied to other vascular conditions. Accordingly, these and other such applications are within the scope of the following claims.

Claims (21)

1. A system for monitoring blood flow and coagulation to predict the occurrence of a thrombus in a patient, comprising:
a patch or sleeve adapted to be placed on a patient, the patch or sleeve having an outer layer formed from a flexible, waterproof material, an inner layer having electrical connections, a plurality of physiological sensors configured to measure physiological biomarkers, and a plurality of electrodes configured to measure bioimpedance and deliver electrical stimulation;
a removable electronic/stimulation device having a microcontroller connected to the electrical connections, the microcontroller including a timing control circuit, a data acquisition circuit configured to acquire data from the plurality of physiological sensors and electrodes, a signal conditioning circuit configured to process data from the physiological sensors, and an impedance measurement circuit configured to process data from the electrodes;
a signal generating circuit configured to apply electrical stimulation to effect local blood flow and current injection for impedance measurement;
a communication circuit for transferring data to and from the removable electronic/stimulation device;
A system comprising: The system of claim 1, wherein the patch or sleeve further comprises a strain gauge for plethysmography and at least one occlusion cuff configured to apply occlusion pressure to a target vessel. The system of claim 1, wherein the signal generation circuit provides current injection for impedance measurement as a constant current signal having a frequency of 20 kHz to 100 kHz and an amplitude greater than 1 mA. The system of claim 1, further comprising a memory for storing acquired data and program instructions, and a battery for powering at least one of the patch or sleeve, the removable electronic/stimulation device, the signal generator, or the communication circuitry. The system of claim 1, wherein the physiological sensor includes at least one of a photoplethysmography sensor, a strain gauge plethysmography sensor, an impedance plethysmography sensor, an impedance electrode, an ultrasound sensor, a biocapacitance sensor, an infrared thermopile sensor, an electrodermal activity sensor, or a galvanic skin response sensor. The system of claim 1, wherein the signal conditioning circuitry of the microcontroller includes at least one of a strain gauge signal conditioning circuitry including isolation, bridge balancing, filtering, and excitation voltage measurement, or a thermopile signal conditioning circuitry including isolation and linearization. The system of claim 1 further comprising a computer application configured on at least one of a smartwatch, a mobile phone, or a tablet configured to communicate with the communication circuitry using BLUETOOTH (registered trademark), WI-FI (registered trademark), Zigbee (registered trademark), cellular, or radio frequency circuitry, and a remote computer or cloud server configured to communicate with the computer application. The system of claim 7, wherein at least one of the computer application, remote computer, or cloud server processes the data transmitted by the communication circuitry in a predictive algorithm that uses machine learning techniques to predict the patient's likelihood of developing a thrombus, and calculates a risk score based on the prediction of the likelihood of developing a thrombus produced by the predictive algorithm. The system of claim 8, wherein at least one of the computer application, the remote computer, or the cloud server generates an alert indicative of the patient's condition, initiates a therapeutic response to the thrombus event based on a predetermined change in the risk score, or both. The system of claim 9, wherein the alert is issued using different modalities to initiate different actions depending on whether the recipient of the alert is a healthcare professional, the patient, or a caregiver, the different modalities including at least one of a voice or audio message, email, SMS text utilizing cellular data, a chat application, an EMR alert, a telemedicine system, or an artificial intelligence generated message via the computer application. The system of claim 7, further comprising a device gateway that receives and transmits data from the communication circuitry and third-party data source to at least one of the computer application, the remote computer, or the cloud server. 1. A method for monitoring blood flow and coagulation to predict the occurrence of a thrombus in a patient, comprising:
positioning a device over a region of interest on a surface of the patient's body, the device being configured to measure physiological biomarkers, generate localized blood flow, and transfer data to a computer;
generating localized blood flow using the device;
measuring biomarkers indicative of changes in blood flow and coagulation;
transferring data from said biomarker measurements to said computer;
implementing on the computer a prediction algorithm that uses machine learning techniques to predict the probability of thrombus development in the patient from at least the biomarker measurements;
calculating a risk score based on the predicted probability of thrombus development generated by the prediction algorithm;
and at least one of generating an alert indicative of the patient's condition or initiating a therapeutic response to the thrombotic event based on the risk score;
A method comprising: The step of positioning the device over an area of interest on a surface of the patient's body comprises:
positioning a patch or sleeve adapted for placement on a surface of the patient's body, the patch or sleeve having an outer layer formed from a flexible, waterproof material, an inner layer having electrical connections, a plurality of physiological sensors configured to measure physiological biomarkers, and a plurality of electrodes configured to measure bioimpedance and deliver electrical stimulation;
connecting a removable electronic/stimulation device to the electrical connection, the removable electronic/stimulation device including a microcontroller with timing control circuitry, data acquisition circuitry for acquiring data from the plurality of physiological sensors and electrodes, signal conditioning circuitry configured to process data from the physiological sensors, impedance measurement circuitry configured to process data from the electrodes, signal generation circuitry configured to apply electrical stimulation to generate local blood flow and current injection for impedance measurement, and communication circuitry for transferring data to and from the removable electronic/stimulation device;
13. The method of claim 12, comprising: The method of claim 12 further comprises repeating the blood flow generation step, biomarker measurement step, data transfer step, predictive algorithm implementation step, risk score calculation step, and alert generation step or treatment initiation step at time intervals of 5 minutes to 1 hour. The step of generating local blood flow includes:
electrical muscle stimulation,
Electrical nerve stimulation,
Pneumatic compression,
Ultrasonic application,
Massage (localized pressure) or vibration,
The method of claim 12 , comprising at least one of: The step of measuring the biomarkers includes:
Electrical impedance measurement,
Biocapacitance measurements,
Thermal imaging,
ultrasound imaging,
auscultation,
Photoplethysmography,
Impedance plethysmography, or strain gauge plethysmography,
The method of claim 12 , comprising at least one of: Initiating a therapeutic response based on the biomarker measurements and the resulting risk score includes:
electrical neuromuscular stimulation,
Electrical nerve stimulation,
Pneumatic compression,
ultrasound,
massage,
vibration or light therapy,
The method of claim 12 , comprising at least one of: The method of claim 12, further comprising transferring data from the computer in an outpatient setting or from a communication device in an inpatient setting to a remote computer or cloud server, wherein the predictive algorithm is implemented on the remote computer or cloud server. The method of claim 12, wherein measuring biomarkers indicative of changes in blood flow and coagulation includes initiating configuration of the biomarker measurement device using an initial patient biomarker profile based on pre-assessed patient-specific information highlighting pre-existing disease states or physiological conditions that may affect or be affected by blood flow and coagulation, altering the risk of developing a thrombus. 20. The method of claim 19, wherein the pre-assessed patient-specific information is based on a particular diagnosis, procedure, or blood flow and coagulation altering therapy prescribed for the patient. 20. The method of claim 19, wherein the pre-assessed patient-specific information includes socioeconomic factors or social determinants of health that influence the occurrence of thrombus or contribute to poorer outcomes in patients diagnosed with thrombus.