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

Abstract

A wearable device, which includes an external patch or cover that adheres to the skin, is used to stimulate and identify changes in blood flow and coagulation. A non-invasive transcutaneous electrical muscle stimulator (EMS) is embedded in the patch or cover and provides sequential stimulation to the surrounding tissue of the blood vessel to promote blood flow. The stimulation system includes a series of electrodes positioned on the skin by a patch or cover, and an external programmable generator with wireless connectivity during stimulation. Biosensors in the patch or cover and other biosensors applied to the body periodically check whether there is an abnormal biomarker pattern. These patterns may be used as early indicators by artificial intelligence (AI) / machine learning (ML) systems, or by prediction methods to predict blood flow and clotting changes caused by venous thrombosis. When an abnormal biomarker pattern is detected, an alert may be sent and a treatment response initiated.

Description

Technical Field

[0001] The present disclosure relates generally to devices, systems, and methods for monitoring blood flow and coagulation, and more particularly, to devices and methods for monitoring thrombosis and related conditions by predicting the probability of thrombosis in the venous system based on non-invasive biosensor measurements. Background Art

[0002] A thrombotic event occurs when a blood clot (thrombus) blocks blood flow within the circulatory or vascular system. Depending on the blocked blood vessel, this blockage reduces the supply of oxygen and essential nutrients to body tissues, leading to cell damage and, if blood flow is not quickly restored, cell death. This blockage also prevents the flow of deoxygenated blood and metabolic waste products out of tissues. This obstruction increases pressure within the blood vessels, causing fluid to leak into the surrounding perivascular spaces, resulting in pain and swelling. Veins are the blood vessels that carry blood from tissues back to the heart. Therefore, a blood clot that forms in and travels through the venous system is called a venous thromboembolism (VTE). VTE that forms in the body's larger veins is called a deep vein thrombosis (DVT) and can occur in the arms, legs, pelvis, trunk, and even the brain (cerebral venous sinus thrombosis). Furthermore, a clot from a DVT can break off and travel to other parts of the body or cause an embolism elsewhere, blocking blood flow elsewhere. A blood clot that embolizes and remains in the lungs is called a pulmonary embolism (PE), which can be fatal.

[0003] Common features of deep vein thrombosis (DVT) include pain, skin discoloration (such as redness or bruising), swelling, or prominent superficial veins. Clues to pulmonary embolism (PE) may include shortness of breath or tachypnea, palpitations, dizziness, sweating, or sharp chest and rib pain that worsens with inspiration. Unfortunately, many signs and symptoms of VTE are nonspecific and can be mistaken for less severe causes, such as a lower extremity DVT misdiagnosed as a muscle strain or PE misdiagnosed as anxiety. This can lead to delayed diagnosis and worse clinical outcomes.

[0004] Overall, VTE affects 1 million people each year in the United States alone, resulting in up to 300,000 deaths. These figures are likely underestimated because annual VTE surveillance is not performed in the United States. Despite its high morbidity and mortality, VTE is considered a preventable condition in most cases. In fact, it is the leading cause of preventable death among hospitalized patients in the United States and worldwide. For patients who experience VTE, long-term complications and recurrence are of concern. One-third will develop another blood clot, often requiring lifelong anticoagulation. Another one-third will develop post-thrombotic syndrome, a major source of functional disability and decreased quality of life following an initial DVT diagnosis.

[0005] The pathogenesis of thrombosis has been well described by Virchow's triad, which describes three major factors: venous stasis, endothelial injury, and a hypercoagulable state, which, when present, create an environment conducive to thrombosis. Risk factors for venous thrombosis (VTE) are traditionally categorized based on whether they are identifiable (predisposing) or unidentifiable (unpredisposing). Risk factors for predisposing VTE may be genetic or acquired. Genetic factors include inherited deficiencies of antithrombin, protein C, and protein S. Acquired factors include medical conditions (such as infection and cancer), activity limitations, surgery (such as joint replacement, particularly for trauma or cancer), and medications (such as hormone replacement therapy). Hospitalization is significantly associated with the development of VTE; when VTE occurs during or shortly after a hospitalization, it is termed healthcare-associated VTE (HA-VTE). Regardless of classification, these risk factors may contribute to any or all of the elements of the Virchow triad. Recognition of these associations may improve management strategies and facilitate the development of novel tools ranging from VTE prevention to treatment.

[0006] Traditionally, individuals suspected of having VTE have been evaluated using pretest probability (PTP) scoring systems, such as the Wells Deep Venous Thrombosis (DVT) and Pulmonary Encephalitis (PE) score and the Geneva score. These scores combine specific criteria, including demographic characteristics, preexisting medical conditions, and active symptoms (e.g., calf pain and swelling in the setting of suspected DVT). These traditional scoring systems fail to account for social determinants of health (SDoH), defined by the World Health Organization (WHO) as “the environments in which people are born, grow, live, work, and age, and the systems in place to cope with disease.” SDoH is directly associated with the risk and outcomes of cardiovascular disease, including VTE. Without incorporating SDoH into risk assessment and outcome prediction, the application of predictive models using traditional datasets and indicators will not accurately reflect the true risk and outcome probabilities, and may even further exacerbate healthcare disparities and increase the burden of disease on marginalized and underserved populations. In reality, PTP results cannot safely rule out or confirm VTE.

[0007] When the traditional PTP system scores indicate a low probability of VTE, a serum D-dimer test is performed to help exclude the diagnosis of VTE. Alternatively, if the score indicates a high probability of VTE, the diagnosis can be confirmed with relevant imaging studies (such as ultrasound or CT angiography). Currently, there are no specific criteria for imaging studies to confirm or exclude the diagnosis of VTE, beyond clinical judgment. This inconsistency in management provides another opportunity for delayed diagnosis and treatment.

[0008] Treatment of VTE has traditionally involved a regimen of anticoagulants (ACs) or blood thinners. Many anticoagulants, such as warfarin, require frequent testing to ensure they remain within the therapeutic window, which often takes several weeks to achieve. Other blood thinners, such as direct oral anticoagulants (DOACs), generally do not require serum studies to ensure they remain within the therapeutic window; however, individual patient response does vary. Therefore, inappropriate dosing may go undetected, leading to worse outcomes: bleeding or, conversely, thrombotic events at subtherapeutic doses. In addition, physical therapy has become an important adjunct to treatment regimens when combined with medical therapy and is used to prevent long-term VTE-related complications.

[0009] Given the complex and varied nature of management from prevention to treatment and the complex and varying access to technology, there is a need for technologies that can safely and reliably assist with management in diverse settings across the continuum of care. Summary of the Invention

[0010] Various examples are now described to introduce a selection of concepts in a simplified form 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.

[0011] In an example 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. Non-invasive transcutaneous electrical muscle stimulators (EMS) are embedded in a patch or sleeve that is applied to the patient in anticipation of changes in blood flow and coagulation (e.g., post-operatively) to prevent thrombosis by externally stimulating the calf muscle or other local muscles. The stimulation system includes a series of electrodes positioned on the patient's skin via a patch or sleeve, and an external programmable stimulator that has wireless connectivity during stimulation, is battery-powered, and rechargeable for ease of mobility. Biosensors in the patch or sleeve, as well as other biosensors applied to the body, regularly check for abnormal biomarker patterns that could be used by artificial intelligence (AI) / machine learning (ML) systems to predict thrombosis. When such abnormal biomarker patterns are detected, healthcare professionals are notified that further management of the patient's potential VTE is required.

[0012] In an example configuration, at least one of a computer application, a remote computer, and a cloud server can process quantitative biosensor data collected by a biosensor and qualitative data collected to determine a patient's health status using a predictive algorithm. The predictive algorithm uses machine learning techniques to predict the probability of thrombosis forming in a patient's blood vessel, and calculates a risk score based on the predicted probability of thrombosis formed generated by the predictive algorithm. The computer application, remote computer, and / or cloud server can generate an alert representing the patient's status and / or initiate a therapeutic response to thrombosis based on a predetermined change in the risk score. The alert can be issued using different modes to initiate different actions depending on whether the alert recipient is a healthcare professional, the patient, or a caregiver. The different modes can include at least one of: a voice or audio message, an email, an SMS message using cellular data, a chat application, an electronic medical record (EMR) alert, a telemedicine system, and a message generated by artificial intelligence via a software application. Furthermore, the system can include a device gateway that receives data from the biosensor and a third-party data source and transmits it to at least one of the computer application, the remote computer, and the cloud server.

[0013] A method for monitoring blood flow and coagulation to predict thrombosis in a patient is also provided. The method includes: positioning a device at an area of ​​interest on the patient's body surface, the device configured to measure physiological biomarkers, generate local blood flow, and transmit the data to a remote computer server; generating local blood flow using the device; measuring biomarkers indicative of changes in blood flow and coagulation; and implementing a prediction algorithm on a computer or cloud server that uses machine learning techniques to predict the probability of thrombosis in the patient based at least on the measured values ​​of the biomarkers. Based on the predicted probability of thrombosis generated by the prediction algorithm, the method also includes calculating a risk score and performing at least one of generating an alert representing the patient's status and initiating a therapeutic response to thrombosis.

[0014] The method may also include transmitting data from the device in the outpatient setting or the communication device in the inpatient setting to a computer or cloud server, wherein the predictive algorithm is implemented on the computer or cloud server. In addition, measuring biomarkers indicative of changes in blood flow and coagulation may also include initiating the setting of the biomarker measurement device using an initial patient biomarker profile based on pre-assessed patient-specific information (which information highlights existing disease states or physiological conditions that affect or are affected by blood flow and coagulation and may alter the risk of thrombosis). For example, the pre-assessed patient-specific information may be based on a specific diagnosis, procedure, or therapy prescribed to the patient that alters blood flow and coagulation, and / or may include socioeconomic factors or social determinants of health that affect the incidence of thrombosis or lead to worse outcomes for patients diagnosed with thrombosis.

[0015] This Summary is intended to introduce various aspects of the claimed subject matter in a simplified form, with further description of the claimed subject matter provided in the main body of the Detailed Description. The specific combinations and order of elements listed in this Summary are not intended to limit the elements of the claimed subject matter. Rather, it should be understood that this section provides summary examples of some of the embodiments described in the following Detailed Description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above 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, in which:

[0017] Figure 1A is a posterior view of a patient's leg showing the location of the patient's popliteal vein.

[0018] Figure 1B is an exploded view of an example configuration of a system including a patch and a stimulation device adapted to acquire data from a biosensor placed on a patient's skin.

[0019] Figures 2A-2C 1 is a schematic diagram of an additional configuration of the system shown in FIG1, in order to apply to other anatomical locations, using a cover 220 placed on the patient's arm ( Figure 2A ) or on the patient's legs ( Figure 2B and 2C ).

[0020] Figure 3 is a schematic diagram of an example configuration of electronics for acquiring patient data from a biosensor and transmitting the patient data to a computer application.

[0021] Figure 4 is a schematic diagram illustrating an example of a patient journey use case to which the systems and methods described herein may be applied.

[0022] Figure 5 is a diagram illustrating an example configuration for transmitting acquired patient data to the cloud for applying a predictive model.

[0023] Figure 6 is a flow chart describing an example configuration of a method for predicting the likelihood of a patient developing a thrombus in a target blood vessel.

[0024] Figure 7 is a diagram that represents an example configuration of multiple data sources within the system. The data sources include devices that can transmit data through the device gateway and third-party sources that can transmit data to and from the cloud, such as public databases.

[0025] Figure 8 is a detailed flow chart depicting an example configuration of a method for predicting a patient's risk of developing a thrombosis, repeating the measurement at timed intervals if the risk score has not changed or is not of concern, or sending an alert to a responder (e.g., a healthcare professional) to initiate next steps in patient management when a critical threshold or pattern is detected.

[0026] Figure 9 is a hierarchical depiction of an example configuration of an alert process involving responders and actions that individuals or the system itself may take in patient management. DETAILED DESCRIPTION

[0027] Detailed descriptions of illustrative embodiments will now be described with reference to Figures 1-9. While this description provides detailed descriptions of possible implementations, it should be noted that these details are intended to be exemplary and in no way limit the scope of the inventive subject matter.

[0028] Figure 1A is a posterior view of a patient's leg showing the location of the patient's popliteal vein. Figure 1BFIG1 is an exploded view of an example configuration of a system 100, comprising a multi-layer adhesive patch 110 adapted to acquire data from biosensors 130 placed on a patient's body and a detachable electronics / stimulation device 120. As shown, the multi-layer adhesive patch 110 comprises at least an outer layer 140 having a flexible fabric covering and an inner layer 150 having electronic connections between the plurality of 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 connections to the detachable electronics / stimulation device 120, which houses electronics for acquiring patient data recorded by the plurality of biosensors 130 and electrodes 160 and transmitting the acquired data to a cloud and / or computer server for analyzing the patient data and implementing a machine learning algorithm configured to predict the probability of thrombus formation in the patient's blood vessels based on the acquired data. It should be understood that the electronics / stimulation device 120 can be integrated within the patch. In another configuration, the electronics / stimulation device 120 may be integrated and externally powered via radio frequency (RF), other wireless powering means, or wired (plug-in power).

[0029] Figure 1B The system is configured to align the biosensor 130 and the electrode 160 along a target blood vessel. For example, in an exemplary configuration, the multi-layer adhesive patch 110 may be placed along the popliteal vein of a patient's lower limb (e.g., Figure 1A It should be understood that the system can be implemented in a variety of configurations.

[0030] For example, Figures 2A-2C The configuration of the system 100 shown may include an arm configuration 200 ( Figure 2A ) and leg configuration 210( Figures 2B-2C ), these configurations incorporate a multi-layer sleeve 220 that is to be placed along a target vessel, such as the popliteal vein in the 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 a plurality of biosensors 130 for sensing physiological signals from the patient's skin and electrodes 160 for sensing bioimpedance and delivering electrical stimulation. The multi-layer sleeve 220 can be configured to accommodate different sizes. The multi-layer sleeve 220 can be closed around a limb using Velcro or other means. The electronic connections include a connection to the electronic / stimulation device 120, which houses electronics for acquiring patient data recorded by the plurality of biosensors 130 and electrodes 160 and transmitting the acquired data to a cloud and / or computer server for analyzing the patient data and implementing a machine learning algorithm configured to predict the probability of thrombus formation in the patient's vessel based on the acquired data.

[0031] Figure 2CThe example configuration of the system 100 shown further incorporates a mercury strain gauge 240 for plethysmography and includes one or more pressure cuffs 230 and 250 spaced along the vascular network to apply occlusive pressure to one or more target vessels with or without a multi-layered cuff 220. It should also be understood that targeted occlusion of a vessel can be achieved without the use of a cuff. For example, the target pressure can be provided by other means, such as a smart compression garment including shape memory alloys or electromechanical percussive massage. The components described herein will be connected to an apparatus 120 that houses electronics for acquiring patient data measured by the mercury strain gauge 240 and transmitting the acquired data to a cloud and / or computer server for analyzing the patient data and implementing a machine learning algorithm configured to predict the probability of thrombus formation in the patient's vessel based on the acquired data.

[0032] Figure 3 is a schematic diagram of an example configuration of electronics provided in a detachable electronics / stimulation device 120 and used to acquire patient data from multiple biosensors 130 and electrodes 160 and transmit the acquired patient data to an application on a local computing device or to a cloud and / or remote computer server. It should be understood that the electronics / stimulation device 120 can be integrated into the system 100 or 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 signal conditioning circuitry (one or more) 320, impedance measurement circuitry 330, data acquisition circuitry 340, and timing control circuitry 350. 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. Electrodes 160 can be used to acquire the voltage difference generated by current injected by current injection electrodes 360. The current is generated by signal generator circuitry 370. The delivered current can be configured to provide constant current stimulation. Constant current stimulation can be configured to reduce or eliminate patient perception by delivering frequencies between 20kHz and 100kHz. The constant current can be configured with an amplitude greater than 1mA to provide sufficient signal-to-noise ratio to detect impedance changes.

[0033] In an exemplary configuration, the stimulation electrode 310 can be used to stimulate muscle fibers or nerves in response to a signal generated by the signal generator circuit 370 to induce blood flow. This blood flow can be used to assist in acquiring data from the physiological sensor 130. In addition, this blood flow can be used to assist in preventing thrombosis. It should be understood that other methods of generating blood flow can be combined, including but not limited to pneumatic pressure, ultrasound, massage (or localized pressure), vibration, and passive and / or active exercise.

[0034] The microcontroller 300 includes a timing control circuit 350, which controls the timing of the signal generator 370, the data acquisition circuit 340, the signal conditioning circuit 320, and the impedance measurement circuit 330. Impedance measurements are timed based on the injection of current generated by the signal generator 370 into the current injection electrode 360. The data acquisition circuit 340 measures the voltage at the impedance measurement electrode 160 and transmits the acquired voltage to the 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 into the appropriate signal conditioning circuit 320. The signal conditioning circuit 320 may include, but is not limited to, filtering, strain gauge signal conditioning (isolation, bridge balancing, filtering, excitation voltage), thermopile signal conditioning (isolation, linearization, etc.), and other necessary signal conditioning to facilitate acquisition of physiological sensor data from the physiological sensor 130. Once acquired and conditioned by the appropriate signal conditioning circuit 320, the physiological sensor data is stored in the memory 380.

[0035] The communication circuit 390 facilitates the transmission of data from the memory 380 to a computer application 500 that is implemented on one or more smart devices (such as a cell phone or tablet) and is adapted to receive and process the acquired physiological and voltage data. The wireless communication circuit 390 may utilize Bluetooth Wireless LAN Cellular data or radio frequency (RF) circuitry facilitates communication with a local smartphone or other electronic device processing the computer application 500. The acquired patient data can then be transmitted from the computer application 500 to the cloud or another server ( Figure 5 ). Conversely, the communication circuit 390 may be adapted to transmit the acquired physiological data and voltage data directly from the detachable electronic / stimulation device 120 to a remote server device for processing.

[0036] like Figure 4As shown, different predefined settings, expressed in patient journey use cases 400, can be selected for the system. Predefined settings can be based on pre-assessed patient-specific information that highlights existing disease states or physiological conditions that affect or are affected by blood flow and coagulation and, therefore, may alter the risk of thrombosis. This would include, but is not limited to, specific diagnoses, procedures, or therapies that alter blood flow and coagulation. Examples include surgical use cases 410 such as hip replacement, cancer, infection, inflammatory diseases, sepsis, vascular insufficiency, dehydration, mobility impairment, pregnancy, and the like. Other predefined settings for the systems and methods described herein may involve monitoring medication use cases 420 (such as anticoagulants, antiplatelet drugs, or other blood-thinning medications) as well as non-pharmacological use cases 430 (such as exercise regimens or the use of prophylactic mechanical devices (such as pneumatic compressors) or surgical procedures (such as revascularization procedures (stents, bypass grafts)) or monitoring the patency of infusion or hemodialysis catheters. Additional predetermined settings of the systems and methods described herein may include socioeconomic factors or social determinants of health that affect the incidence of thrombosis and / or the outcomes of patients diagnosed with thrombosis, such as social support, education, health literacy, food shortages, access to medical services and available payment methods, living environment, etc. Social determinants of health can have quantitative measurement indicators, such as the Social Vulnerability Index (SVI) or the Area Deprivation Index (ADI). Qualitative data may include information from patients, such as how patients describe their relationship with their medical providers (communication, prejudice, etc.), or the consistency between the patient's expectations for the outcomes of a particular therapy (e.g., blood thinners) and the expectations of the medical provider. In each case, an initial patient biomarker profile is obtained and used as a baseline for comparative analysis. It should be understood that system 100 can be used in conjunction with preventive equipment. For example, system 100 can be placed under a pneumatic compressor and operate as the pneumatic compressor operates.

[0037] Figure 5 1 is a schematic diagram illustrating an example configuration for transmitting acquired patient data to a cloud 510 for application of a predictive model 520 to assess the probability of thrombosis. The cloud 510 includes circuitry for receiving patient data (530), analyzing the patient data (540), storing the analyzed patient data (550), and reporting the results of the data analysis to a healthcare professional (560). The system 100 of FIG. 1 can be used to assess a patient's risk of thrombosis in an outpatient setting (outpatient care, assisted living facilities, single-family homes, etc.) (570) or an inpatient setting (acute care hospitals, rehabilitation centers, nursing homes, etc.) (580).

[0038] In an outpatient setting 570, for example, a patient 585 can be at home and place the system 100 of FIG. 1 on the body near a target blood vessel. Data from the system 100 is transmitted to an application 500 that can run on any mobile platform (including Android, iOS, Windows, etc.) and configured on a single or multiple displays, including smart watches, mobile phones, tablets, computers, TV monitors, etc., which can be connected via Bluetooth. Wireless LAN Cellular data or other wireless means communicate with the system 100. Additionally, the computer application 500 can be configured to transmit the acquired data to the cloud 510.

[0039] In an inpatient setting 580, a patient 585 can be in a hospital and have the system 100 placed on the body near a target blood vessel. The system 100 can transmit the acquired patient data directly from the system 100 to the cloud 510, or another communication device can be present near the patient 585 for transmitting the data from the system 100 to the cloud 510.

[0040] Once the acquired patient data is transmitted to the cloud server of the cloud 510, the data is received at 530, analyzed at 540, and the predictive model 520 is implemented. Based on the predictions of the predictive model 520, a risk score is calculated and reported to the healthcare professional 590 via the healthcare professional interface 595 through the reporting software 560. The healthcare professional interface 595 can be displayed on a mobile phone, tablet, computer, patient status board, room monitor, etc., which are connected to the electronic medical record (EMR) or health information system (HIS) server. All data in the cloud 510, including the analysis data (540) and the model data (520), are stored in the data storage 550 and used to improve the predictive model 520 over time as more patient data is transmitted to the cloud 510.

[0041] Figure 6 6 is a flow chart describing an example configuration of a method 600 for predicting the likelihood of thrombosis in a patient. As shown, the method 600 begins by reading data from one or more data sets 610, including data from physiological sensors 130, electrodes 160, and other patient data (including demographic information, medical history, past or ongoing therapeutic interventions, serum biomarker values ​​(e.g., D-dimer, PT / PTT, INR, etc.), pain levels and other patient-reported symptoms, supplemental biometric data, and social determinants of health. The data set 610 may also include risk assessment and scoring combinations and their related variants (e.g., Caprini score, Wells criteria, PERC, etc.). At 620, the data read from the data set 610 is pre-processed, including any required signal conditioning and analysis.

[0042] Patient input information may also include subjective information such as indication of pain (yes / no, if yes, rated on a scale of 1-10), swelling (yes / no), discoloration (i.e., redness and / or bruising) (yes / no), localized warmth (yes / no), chest pain (yes / no), cough (yes / no), shortness of breath (yes / no), etc. Additional data that may be entered for analysis but collected prior to the monitoring period rather than during the monitoring period may include, for example, patient demographics (gender, race, age, etc.) and patient medical history (preexisting conditions, previous surgeries, medications, etc.).

[0043] The processed data set can be split into a training data set 630, a validation data set 640, and a test data set 650. The training data set 630 can 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 neighbor, decision tree, random forest, and / or support vector machine, which classify the input data as corresponding to a VTE condition or a non-VTE condition. The resulting validation data set 640 can be used to evaluate the prediction accuracy 642 of the classification 644 on the "trained" model 520. Based on the results of the prediction accuracy 642 obtained based on the validation data set 640, the trained model 520 is fine-tuned at 660. This iterative process can be repeated.

[0044] The best model 670 is selected based on the validation dataset 640, and the results are then confirmed at 672 based on the test dataset 650. The resulting classification 674 can be used to calculate a risk score 676 corresponding to the probability that the patient is likely to develop a thrombus in the target vessel.

[0045] Based on the calculated risk score 676, the system output report will vary depending on the recipient (e.g., patient 585 and healthcare professional 590) and whether the biomarker pattern corresponding to risk score 676 has changed. If risk score 676 has not changed, patient 585 and healthcare professional 590 will receive similar messages via patient interface 500 and healthcare professional interface 595, respectively, confirming the success of the biomarker check and subsequent data storage. On the other hand, if risk score 676 increases by a predetermined amount corresponding to an abnormal measurable biomarker pattern, an alert will prompt patient 585 via patient interface 500 to complete a device check to ensure that the leads and sensors are correctly positioned. If the device check raises concerns about device function or positioning, troubleshooting instructions will be provided to patient 585. If there are no device issues, additional information regarding current signs and symptoms may be requested from the patient via patient interface 500. Device alerts may also be sent to facilitate data analysis of transmitted and stored data and to report changes in risk status. Concurrently, the healthcare professional 590 may receive device alerts due to changes in risk status via the healthcare professional interface 595 , including providing the healthcare provider with access to stored patient data 550 .

[0046] Figure 7 7 is a schematic diagram showing multiple data sources within the system 700, the data sources including wearable devices or contactless sensors 710 (including wearable devices 100 ( Figure 1A ) and third-party sources that provide bidirectional data transmission to and from the cloud 510, such as public databases 790. The cloud 510, in turn, communicates with multiple data receiving devices, including patient status boards 730, in-room monitors 740, EMR / HIS servers 750, displays (such as smart TVs or computers 755 or tablets 760), smart watches 765 or cellular devices 770, etc., which can display and transmit raw data and processed data in various forms. The data sets 610 can be obtained from one or more sources at various points along one or more patient care journeys and under different patient conditions (e.g., before and after application of a treatment regimen). Information can be obtained from one or more data sets before the device is used and used as a patient-specific baseline. Patient-specific values ​​and / or values ​​from population-specific data sets can be used as a baseline to guide device monitoring and detection of abnormal biomarker patterns.

[0047] The dataset can include quantitative (temperature, heart rate, social vulnerability index) and qualitative (patient perceptions and expectations of care) data, as well as subjective (patient-reported symptoms) and objective (observed signs) information, through patient surveys. During the system's application, data beyond biomarker patterns associated with VTE development can be captured, stored, and analyzed to provide insights into relevant outcomes such as length of stay during hospitalization, readmission rates, mortality, the development of long-term complications, worsening of pre-existing medical conditions or the development of new medical conditions, and medication adherence. These outcomes may help develop new programs or strategies to improve patient safety, quality of patient care, cost of care, and healthcare resource utilization.

[0048] Figure 8 is a detailed flow chart depicting an example configuration of a method 800 for predicting a patient's risk of thrombosis and initiating an alert for further management, which may include but is not limited to a healthcare professional requesting additional diagnostic studies or initiating treatment to prevent thrombosis. Figure 8 In the example of FIG. 8 , the system 100 has been placed on a patient's limb and the sensor 130 is positioned near a target blood vessel. At 810, the current may be injected into the patient's limb via the stimulation electrode 310 and / or the current injection electrode 360 ​​(e.g., Figure 3 (as shown) electrical stimulation of muscles and / or nerves to generate local blood flow. However, it should be understood that other methods of generating blood flow may be used, such as pneumatic compression, ultrasound, massage (local pressure), vibration, and / or passive or active exercise. In another embodiment, an increase in risk may trigger a response that prompts the system to automatically initiate a treatment plan implemented by device 100 or to initiate it through communication with other treatment devices within the system.

[0049] At 820, changes in physiological biomarkers can be measured during local blood flow. For example, the physiological, non-invasive biosensor 130 shown in FIG1 can measure blood 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 (FDP) or other fibrinolytic biomarkers, von Willebrand factor (vWF), P-selectin protein, intercellular adhesion molecule (ICAM-1), thrombomodulin (THBD) protein, endothelial protein C receptor (EPCR), tissue factor pathway inhibitor (TFPI), forkhead box protein C2 (FOXC2), prospero homeobox protein 1 (PROX1), and the like. In another alternative configuration, such serum biomarkers previously collected can be provided as an additional data set 610. At 830, the biomarkers measured by the biosensor 130 are analyzed to identify any patterns. Biomarker measurement methods may include electrical impedance measurement, biocapacitance, thermal imaging, ultrasound imaging, auscultation, photoplethysmography, strain gauge plethysmography, etc.

[0050] An impedance change that may indicate thrombosis may be an impedance change of 1-10%, with 1-4% being the optimal range. On the other hand, an increase in local skin temperature may indicate the presence of a pathological process, such as thrombosis. For example, a temperature change of greater than 0.2°C may be measured for the contralateral limb or a limb outside the measurement area, with a range of changes between 0.4°C and 2.5°C (see, e.g., Shaydakov et al., "Effectiveness of infrared thermography in the diagnosis of deep vein thrombosis: an evidence-based review," J Vasc Diag Interven, 2017, Vol 5, pp. 7-14).

[0051] Once the biomarkers are measured at 820 and the acquired data is transmitted to the cloud 510, the data is analyzed at 830, along with any additional data sets 610 acquired from other sources, and the predictive model is implemented at 840. Based on the predictive model 520 ( Figure 5) output, a risk score is calculated at 850. If a critical threshold or abnormal pattern corresponding to an elevated risk is not detected at 860, the biomarker measurements can be repeated at timed intervals 880 after inducing local blood flow at 810. For example, the timed intervals can range from 5 minutes to 1 hour. On the other hand, if the calculated risk score indicates thrombosis, an alert is sent to a responder (e.g., a healthcare professional) at 870 to initiate subsequent steps in management.

[0052] Figure 9 An alert process 900 is described by which alerts 870 can be received in various modes 910, including as a voice or audio message, via email, via SMS utilizing cellular data, via a chat application, as an EMR alert, via a telemedicine system, and as an AI-generated message via a software platform or application. Responders 920 to the alert can be individuals (such as healthcare professionals, patients, and / or their caregivers) or devices within the system.

[0053] In response to the alert, the healthcare professional 590 can perform one or more actions 930, including requesting diagnostic studies (such as ultrasound imaging), initiating treatment, scheduling an in-person or virtual visit, consulting with other professionals on the care team (such as a vascular medicine specialist or social worker to address identified socioeconomic factors), or sending the patient directly to an emergency room for further testing or hospital admission. The action 940 prompted by the patient or caregiver 585 may include seeking emergency care, calling their healthcare professional, increasing or decreasing existing strategies (such as physical therapy exercises), or making no changes and continuing the current plan. In addition, the device 100 can respond through actions 950, including connecting other responders to third parties (such as insurance companies, community organizations to connect patients to community resources), or initiating an emergency response when the patient's risks are concerning and may lead to adverse outcomes. The device 100 can also automatically provide treatment by initiating a programmed electrical stimulation protocol, or communicate with other connected devices within the system that are programmed to deliver treatment (such as drug injection or infusion devices).

[0054] It will therefore be understood that the methods described herein achieve a method of predicting thrombosis in a patient by performing the following steps, which include:

[0055] positioning a device at an area of ​​interest on a patient's body surface, the device configured to measure physiological biomarkers, generate local blood flow, and transmit data to a remote computer server;

[0056] Use the device to generate local blood flow;

[0057] Measuring biomarkers that indicate changes in blood flow and coagulation, which can be influenced by predetermined settings that reflect patient journey use cases based on pre-assessed patient-specific data;

[0058] Integrate measured biomarker data with data from other connected devices (including third-party databases and servers) and survey-mediated patient reported data;

[0059] transferring data from biomarker measurements to a computer;

[0060] transfer data from a computer application in an outpatient setting or a communication device in an inpatient setting to a computer or cloud server;

[0061] implementing a prediction algorithm on a computer or cloud server that uses machine learning techniques to predict the probability of thrombosis in a patient based on at least the measured values ​​of the biomarker;

[0062] calculating a risk score based on the prediction of the probability of thrombosis generated by the prediction algorithm; and

[0063] At least one of generating an alarm representing a patient status and initiating a therapeutic response to the thrombosis is performed.

[0064] If the risk status has not changed or is not of concern, an alert may not be generated. If an alert is issued, the change in the patient's risk status will be communicated and responsive actions will be taken based on the responder and the severity of the status change.

[0065] The method may be repeated at timed intervals of, for example, between 5 minutes and 1 hour.

[0066] Methods of generating localized blood flow may include, but are not limited to, at least one of the following: electrical muscle stimulation; electrical nerve stimulation; pneumatic compression; ultrasound; massage (localized pressure); and vibration.

[0067] Methods of measuring biomarkers may include, but are not limited to, at least one of the following: electrical impedance measurement; biocapacitance measurement; thermal imaging; ultrasound imaging; auscultation; photoplethysmography; impedance plethysmography; and strain gauge plethysmography.

[0068] The method may also include, but is not limited to, implementing a response to thrombosis in the patient by at least one of: electrical neuromuscular stimulation; electrical nerve stimulation; pneumatic compression; ultrasound; massage; vibration; and light therapy.

[0069] The response may also include initiating treatment, such as by communicating with a drug delivery device to initiate medication therapy(ies), consulting a specialist, utilizing community resources, advising emergency services, and the like.

[0070] A corresponding thrombus monitoring system may include: a patch or sleeve having an outer layer made of a flexible, waterproof material and an inner layer having an electrical connection; 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 detachable electronic / stimulation device having a microcontroller connected to the electrical connection and including timing control circuitry, data acquisition circuitry for acquiring data from the plurality of physiological sensors and bioimpedance electrodes, signal conditioning circuitry configured to process data from the physiological sensors, impedance measurement circuitry configured to process data from the bioimpedance electrodes, and a signal generator circuitry configured to provide electrical stimulation to generate local blood flow and current injection for impedance measurement. Communication circuitry transmits data to and from the detachable electronic / stimulation device. A memory is also provided for storing acquired data and program instructions, and a battery is provided to power the device for mobility.

[0071] Physiological sensors may be set to predetermined settings based on patient-specific information, including but not limited to at least one of the following: existing disease states or diagnoses; physiological conditions that affect or are affected by blood flow and coagulation; recent surgical or procedural history; use of therapies that alter blood flow and coagulation; patient demographics; and social determinants of health. Physiological sensors may include photoplethysmography sensors, strain gauge plethysmography sensors, impedance plethysmography sensors, electrodes, ultrasound sensors, biocapacitive sensors, infrared thermopile sensors, electrodermal activity sensors, galvanic skin response sensors, and the like.

[0072] The microcontroller's signal conditioning circuitry 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 required to help acquire physiological data.

[0073] The communication circuitry to facilitate transmission of the acquired data to an application or other device may include wireless circuitry using Bluetooth Wireless LAN Cellular data or radio frequency circuits transmit data to facilitate communication. Computer applications can be configured on smart watches, phones, or tablets and configured to use Bluetooth Wireless LAN Cellular data or radio frequency circuitry communicates with the detachable electronic / stimulation device and a remote computer or cloud server. The acquired data can be transmitted to a device in an inpatient setting (e.g., a hospital or clinic) and / or configured to transmit the data to a computer application, a remote computer or cloud server, or other wireless or contactless sensing device within a network that includes the communication circuitry.

[0074] The remote computer or cloud server can be configured to analyze patient data, implement predictive models, calculate risk scores, and communicate the risk scores to healthcare professionals through an interface such as a Figure 7 The example mobile phone, tablet, computer, or other type of healthcare professional display interface) is reported to the healthcare professional.

[0075] in conclusion

[0076] Although various embodiments have been described above, it should be understood that they are presented only as examples and are not intended to be limiting. For example, any element associated with the above-described systems and methods may employ any desired functionality described herein. Therefore, the breadth and scope of the preferred embodiments should not be limited by any of the exemplary embodiments described above.

[0077] As discussed herein, logic, commands, or instructions implementing aspects of the methods described herein may be provided in a computing system 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-hosted machine instances. Another embodiment discussed herein includes incorporating the discussed techniques into other forms, including into other forms of programming logic, hardware configurations, or dedicated components or modules, including devices having corresponding means for performing such technical functions. The corresponding algorithms for implementing such technical functions may include part or all of the electronic operation sequences described herein, or other aspects depicted in the accompanying drawings and detailed description below. Such systems and computer-readable media containing instructions for implementing the methods described herein also constitute exemplary embodiments.

[0078] The processing functions described herein (see, for example, Figure 3-9 ) may be implemented in software in one embodiment. The software may include 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, whether local or networked). In addition, such functions correspond to modules, which may be software, hardware, firmware, or any combination thereof. Multiple functions may be performed in a single or multiple modules as needed, and the described embodiments are only examples. The software may be executed on a digital signal processor, ASIC, microprocessor, or other type of processor running on a computer system (such as a personal computer, server, or other computer system), thereby transforming such computer system into a specifically programmed machine.

[0079] Examples as described herein may include or operate on a processor, logic or several components, modules or mechanisms (referred to herein as "modules"). A module is a tangible entity (e.g., hardware) that is capable of performing a specified operation and may be configured or arranged in a particular manner. In an example, a circuit may be arranged as a module in a specified manner (e.g., internally or relative to an external entity such as other circuits). In an example, all or part of one or more computer systems (e.g., stand-alone, client, or server computer systems) or one or more hardware processors may be configured as a module via firmware or software (e.g., instructions, application portions, or applications) that operates to perform a specified operation. In an example, the software may reside on a machine-readable medium. When the software is executed by the underlying hardware of the module, it causes the hardware to perform the specified operation.

[0080] Thus, the term "module" should be understood to encompass a tangible hardware and / or software entity that is physically constructed, specifically configured (e.g., hardwired), or temporarily (e.g., transiently) configured (e.g., programmed) to operate in a specified manner or to perform some or all of any of the operations described herein. Considering that modules are examples of temporary configurations, each module need not be instantiated at all times. For example, where a module comprises a general-purpose hardware processor configured using software, the general-purpose hardware processor may be configured as a respective different module at different times. Thus, software may configure a hardware processor, for example, to constitute a particular module at one instance in time and to constitute a different module at another instance in time.

[0081] Those skilled in the art will appreciate that while the disclosure contained herein relates to techniques for measuring blood flow and coagulation in relation to the development of venous thrombosis, the techniques described herein may be applied to other vascular conditions. Accordingly, these and other such applications are intended to be within the scope of the following claims.

Claims

1. A method for monitoring blood flow and coagulation to predict thrombosis in a patient, comprising: positioning a device at an area of ​​interest on a patient's body surface, the device configured to measure physiological biomarkers, generate local blood flow, and transmit data to a remote computer server; generating localized blood flow using the device; measuring biomarkers that indicate changes in blood flow and clotting; transmitting data obtained from the measurement of the biomarkers to a computer; implementing a prediction algorithm on the computer, the prediction algorithm using machine learning techniques to predict a probability of a patient developing a thrombosis based at least on the measured values ​​of the biomarker; calculating a risk score based on the prediction of the probability of thrombosis generated by the prediction algorithm; as well as Based on the risk score, at least one of generating an alert representing a patient status and initiating a therapeutic response for thrombosis is performed.

2. The method according to claim 1, characterized in that It also includes repeating the steps of generating local blood flow, measuring biomarkers, transmitting data, implementing a predictive algorithm, calculating a risk score, and generating an alert or initiating treatment at timed intervals between 5 minutes and 1 hour.

3. The method according to claim 1, characterized in that Generating local blood flow includes at least one of the following: electrical muscle stimulation; electrical nerve stimulation; Pneumatic pressurization; Ultrasonic wave application; Massage (localized pressure); and vibration.

4. The method according to claim 1, wherein Biomarkers measured include at least one of the following: Electrical impedance measurement; Biocapacitance measurement; Thermal imaging; Ultrasound imaging; auscultation; Photoplethysmography; Impedance plethysmography; and Strain gauge plethysmography.

5. The method according to claim 1, characterized in that Initiation of treatment response based on biomarker measurement and the resulting risk score includes at least one of the following: electrical neuromuscular stimulation; electrical nerve stimulation; Pneumatic pressurization; ultrasound; massage; vibration; and Phototherapy.

6. The method according to claim 1, characterized in that Also included is transmitting data from a computer application in an outpatient setting or a communication device in an inpatient setting to the computer or cloud server, wherein the predictive algorithm is implemented on the computer or the cloud server.

7. The method according to claim 1, characterized in that Measuring biomarkers indicative of changes in blood flow and coagulation includes initiating setup of a biomarker measurement device using an initial patient biomarker profile based on pre-assessed patient-specific information highlighting existing disease states or physiological conditions that affect or are affected by blood flow and coagulation and can alter the risk of thrombosis.

8. The method according to claim 7, characterized in that The pre-assessed patient-specific information is based on the specific diagnosis, procedure, or therapy that alters blood flow and coagulation that is being prescribed for the patient.

9. The method according to claim 7, characterized in that The pre-assessed patient-specific information includes socioeconomic factors or social determinants of health that influence the incidence of thrombosis or lead to worse outcomes in patients diagnosed with thrombosis.

10. A system for monitoring blood flow and coagulation to predict thrombosis in a patient, comprising: a patch or sleeve adapted for placement on a patient, the patch or sleeve having an outer layer made of a flexible, waterproof material, an inner layer having electrical connections, a plurality of physiological sensors configured to measure biomarkers, and a plurality of electrodes configured to measure bioimpedance and deliver electrical stimulation; a detachable electronics / stimulation device having a microcontroller connected to the electrical connections and including a timing control circuit, a data acquisition circuit for acquiring data from the plurality of physiological sensors and the 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 generator circuit configured to provide electrical stimulation to generate local blood flow and to provide current injection for impedance measurement; as well as Communications circuitry for transmitting data to and from the detachable electronics / stimulation device.

11. The system according to claim 10, wherein: The sleeve also includes a strain gauge for plethysmography and at least one occlusive cuff configured to apply occlusive pressure to the target vessel.

12. The system according to claim 10, wherein: The signal generator 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.

13. The system according to claim 10, wherein: Also included is a memory for storing acquired data and program instructions; and a battery for powering at least one of the patch or sleeve, the detachable electronic / stimulation device, the signal generator, and the communication circuit.

14. The system according to claim 10, 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 biocapacitive sensor, an infrared thermopile sensor, a skin electrode activity sensor, and a skin electrode response sensor.

15. The system according to claim 10, wherein: The signal conditioning circuit of the microcontroller includes at least one of: a strain gauge signal conditioning circuit including isolation, bridge balancing, filtering, and excitation voltage measurement; and a thermopile signal conditioning circuit including isolation and linearization.

16. The system according to claim 10, wherein: Also includes: The computer application is configured on at least one of a smart watch, a mobile phone and a tablet computer and is configured to use Bluetooth, wireless local area network, Cellular or radio frequency circuitry in communication with said communications circuitry; and a remote computer or cloud server configured to communicate with the computer application.

17. The system according to claim 16, wherein: At least one of the computer application, the remote computer, and the cloud server processes the data transmitted by the communication circuit with a prediction algorithm that uses machine learning techniques to predict a probability of thrombosis in a patient and calculates a risk score based on the prediction of the probability of thrombosis generated by the prediction algorithm.

18. The system according to claim 17, wherein: At least one of the computer application, the remote computer, and the cloud server generates an alert representing a patient status, initiates a therapeutic response for thrombosis based on a predetermined change in the risk score, or both.

19. The system according to claim 18, wherein: The alert is sent using different modes to initiate different actions depending on whether the alert recipient is a healthcare professional, a patient, or a caregiver, the different modes including at least one of the following: voice or audio message, email, SMS text message using cellular data, chat application, EMR alert, telemedicine system, and message generated by artificial intelligence through a software application.

20. The system according to claim 16, wherein: Also includes: A device gateway is configured to receive data from the communication circuit and the third-party data source and transmit the data to at least one of the computer application, the remote computer, and the cloud server.

Images