Physiological condition monitoring based on biovibration and radio frequency data analysis

Abstract

The patient monitoring device includes an ECG sensor coupled to the patient, a sensor coupled to the patient and configured to generate a bio-oscillation signal, and a radio frequency monitoring device configured to generate information corresponding to electromagnetic energy reflected from the patient's thoracic cavity. The processor processes the ECG signal, the bio-oscillation signal, and the radio frequency information to generate a plurality of physiological parameters of the patient. The processor further performs at least one of a predictive analysis and a trend analysis of the plurality of physiological parameters to determine a current clinical condition of the patient. The trend analysis includes determining a substantial relationship between changes in the plurality of physiological parameters. The processor may further compare the patient's current clinical condition with predetermined clinically actionable criteria to determine one or more clinically actionable events and provide an output related to the one or more clinically actionable events.

Description

[Background technology]

[0001] Related applications This application is U.S. Provisional Application No. 62 / 644216, filed on 16 March 2018, entitled “Monitoring Physiological Status Based on Bio-Vibrational and Radio Frequency Data Analysis,” and claims priority under Section 119 of the U.S. Patent Act. The entirety of the subject matter described in the above application is hereby incorporated by reference as if it were fully described herein.

[0002] This disclosure relates to monitoring a patient's physiological state based on patient data obtained from multiple sensor sources, such as bio-vibration sensors and radio frequency sensors.

[0003] Patients with heart disease are prone to frequent recurrences of acute attacks resulting from the pathophysiology of congestive heart failure (CHF). For example, pulmonary congestion is a major cause of hospitalization and readmission among CHF patients. Similarly, patients with chronic kidney disease and undergoing hemodialysis are also susceptible to acute adverse events. For instance, some patients with end-stage renal disease may have moderate to severe pulmonary congestion before hemodialysis. These patients have a high morbidity of heart failure and a poor prognosis. Various electronic and mechanical devices exist to monitor and treat the pathophysiology of heart failure in patients. In some cases, depending on the underlying disease being monitored or treated, medical devices such as cardiac monitors or defibrillators may be surgically implanted in the patient or connected externally. In some cases, physicians may treat the pathophysiology of heart failure using medical devices alone or in combination with drug therapy.

[0004] Leaving heart failure untreated can lead to certain life-threatening arrhythmias. Both atrial and ventricular arrhythmias are common in patients with heart failure. One of the most life-threatening cardiac arrhythmias is ventricular fibrillation, which occurs when normal, regular electrical impulses are replaced by irregular, rapid impulses, causing the heart muscle to stop contracting normally. Patients often do not receive any noticeable, imminent warning of fibrillation, and therefore frequently die before necessary medical assistance can arrive. Other cardiac arrhythmias may include extremely slow heart rates, known as bradycardia, or extremely fast heart rates, known as tachycardia. Cardiac arrest can occur when a patient's heart is unable to supply sufficient blood flow to the brain and other vital organs due to various cardiac arrhythmias, including ventricular fibrillation, ventricular tachycardia, excitation-dissociation (PEA), and asymptomatic contractions (where the heart ceases all electrical activity). Monitoring patients with heart failure is generally useful to diagnose symptoms early and provide intervention as soon as possible. [Overview of the project]

[0005] In certain implementations, the patient monitoring system includes an ECG sensor connected to the patient and configured to detect one or more ECG signals from the patient; a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals from the patient; an ultrawideband radio frequency transceiver circuit connected to the patient and including one or more radio frequency antennas; and one or more processors. In some examples, the ultrawideband radio frequency transceiver is configured such that one or more radio frequency antennas direct radio frequency electromagnetic energy into the patient's thoracic cavity and receive it through the one or more radio frequency antennas, generating radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the patient's thoracic cavity. In some examples, one or more processors are configured to process one or more ECG signals, one or more cardiac vibration signals, and radio frequency information to generate a plurality of physiological parameters of the patient, including one or more combination physiological parameters. One or more processors may perform at least one of predictive and trend analyses of the plurality of physiological parameters, including the combination physiological parameters, to determine the patient's current clinical condition. In the implementations described herein, trend analysis includes determining the existence of substantial relationships between changes in several physiological parameters. One or more processors can determine one or more clinically usable events by comparing the patient's current clinical symptoms to predetermined clinically usable criteria, and cause an output device to provide an output regarding one or more clinically usable events. The implementations of the patient monitoring system described herein may include one or more of the following features:

[0006] In the specific implementation of the patient monitoring system described above, trend analysis includes correlation analysis.

[0007] In a specific implementation of the patient monitoring system described above, at least one of the following is performed on physiological parameters collected over a preceding period including at least 24 hours, at least 48 hours, at least 1 week, at least 2 weeks, at least 1 month, at least 6 weeks, at least 2 months, at least 4 months, at least 6 months, at least 1 year, and at least 2 years: predictive analysis and trend analysis.

[0008] In a specific implementation of the patient monitoring system described above, at least one of the following is performed on physiological parameters collected over a period prior to the available patient medical history: predictive analysis and trend analysis.

[0009] In a specific implementation of the patient monitoring system described above, one or more clinically usable events include at least one of the following: an automated event that is triggered without user input, and a manual event that is triggered based on a user response to an output and comprises one or more commands that perform one or more actions.

[0010] In specific implementations of the patient monitoring system described above, the output for one or more clinically usable events is based on exceeding one or more thresholds defined for multiple physiological parameters or for at least one outcome of predictive and trend analyses.

[0011] In a specific implementation of the patient monitoring system described above, predictive analysis involves inputting multiple physiological parameters into an artificial neural network and determining the patient's current clinical symptoms based on the output of the artificial neural network.

[0012] In a specific implementation of the patient monitoring system described above, predictive analysis involves inputting multiple physiological parameters into a deep learning process and determining the patient's current clinical symptoms based on the output of the deep learning process.

[0013] In specific implementations of the patient monitoring system described above, predictive analysis involves inputting multiple physiological parameters into a machine learning process and determining the patient's current clinical condition based on the output of the machine learning process. In some examples, the patient's current clinical condition includes a predictive score based on the output of the machine learning process, which indicates the likelihood of an adverse event occurring. In some examples, the adverse event includes one or more of the following: arrhythmic events, seizure events, syncope events, and hospitalization events.

[0014] In a specific implementation of the patient monitoring system described above, trend analysis involves determining whether at least one of several physiological parameters has exceeded a threshold, correlating at least one of the physiological parameters that exceeded the threshold with at least one additional physiological parameter selected from the several physiological parameters to generate a correlation score, and determining the patient's current clinical symptoms based on the correlation score. In some examples, the correlation score indicates a change in the patient's symptoms.

[0015] In a specific implementation of the patient monitoring system described above, the vibration sensor is further configured to sense one or more lung vibrations of the patient, where one or more lung vibrations include at least one of the following: bronchial vibration, wheezing, crackling, wheezing, blisters, pleural friction, squawk, glottal, pharyngeal, or other vibrations.

[0016] In a specific implementation of the patient monitoring system described above, one or more ECG signals include at least one of the following: heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, breath, heart rate irregularity, QRS height, QRS width, changes in size or shape of the morphology of one or more ECG signals, cosine RT, artificial pacing, QT interval, QT variation, T wave width, T wave alternant, T wave variation, and ST segment changes.

[0017] In a specific implementation of the patient monitoring system described above, one or more cardiac oscillatory signals include at least one of the following: S1 oscillatory, S2 oscillatory, S3 oscillatory, S4 oscillatory, and heart murmur oscillatory.

[0018] In a specific implementation of the patient monitoring system described above, radio frequency information includes measurements of the fluid content in the patient's pleural cavity.

[0019] In a specific implementation of the patient monitoring system described above, multiple physiological parameters include one or more of the following: left ventricular contraction time (LVST), electromechanical activation time (EMAT), %LVST, and left ventricular end-diastolic pressure (LVEDP).

[0020] In a specific implementation of the patient monitoring system described above, one or more processors are incorporated into a cardiac monitoring device adapted for patient wear.

[0021] In a specific implementation of the patient monitoring system described above, one or more processors are incorporated into a remote processing device.

[0022] In a specific implementation of the patient monitoring system described above, one or more processors are incorporated into a wearable defibrillator device adapted for patient wear.

[0023] In certain implementations, the second patient monitoring system includes at least one vibration sensor coupled to the patient and configured to detect one or more cardiac vibration signals, at least one ultrawideband radio frequency transceiver coupled to the patient, and one or more processors. In some examples, at least one ultrawideband radio frequency transceiver is configured to direct radio frequency electromagnetic waves towards the patient's lungs and to detect radio frequency information in response to the radio frequency electromagnetic waves that have passed through the patient's lungs. In some examples, one or more processors are configured to process the detected one or more cardiac vibration signals over a predetermined period of time to determine at least one cardiac vibration metric of the patient, process the patient's radio frequency information over a predetermined period of time to determine at least one pulmonary fluid metric of the patient, and determine outputs for one or more clinically usable events based on the determined at least one cardiac vibration metric and the determined at least one pulmonary fluid metric, and to cause an output device to make an output. Implementations of the second patient monitoring system described herein may include one or more of the following features:

[0024] In a specific implementation of the second patient monitoring system described above, one or more clinically usable events include at least one of an automated event that is triggered without user input and a manual event that is triggered based on a user response to an output and comprises one or more commands that perform one or more actions.

[0025] In a specific implementation of the second patient monitoring system described above, determining the output involves performing predictive analysis of the determined value or trend of at least one cardiac oscillatory metric, and the determined value or trend of at least one pulmonary fluid metric.

[0026] In a particular implementation of the second patient monitoring system described above, performing predictive analytics involves inputting a determination value or trend of at least one cardiac vibration metric and a determination value or trend of at least one pulmonary fluid metric into a machine learning process, determining a prediction score based on the output of the machine learning process, indicating that the prediction score represents the likelihood of an adverse event occurring, and determining an output based on the prediction score.

[0027] In a particular implementation of the second patient monitoring system described above, determining an output includes determining the existence of a substantial relationship between changes in at least one cardiac vibration metric and at least one pulmonary fluid metric by performing a trend analysis of the changes in at least one cardiac vibration metric and at least one pulmonary fluid metric. In some examples, detecting the existence of a substantial relationship between changes in at least one cardiac vibration metric and at least one pulmonary fluid metric by performing a trend analysis of the changes includes performing a correlation analysis.

[0028] In a particular implementation of the second patient monitoring system described above, determining an output includes performing a correlation analysis, which includes processing one or more cardiac vibration signals and radio frequency information to generate a plurality of physiological parameters of a patient, including one or more combined physiological parameters, correlating at least one of the plurality of physiological parameters exceeding a threshold with at least one additional physiological parameter selected from the plurality of physiological parameters to generate a correlation score, indicating that the correlation score represents a change in the patient's symptoms, and determining an output based on the correlation score.

[0029] In a particular implementation of the second patient monitoring system described above, one or more cardiac vibration signals include at least one of S1 vibration, S2 vibration, S3 vibration, S4 vibration, ventricular wall movement, and heart murmur vibration.

[0030] In a particular implementation of the second patient monitoring system described above, the radio frequency information includes a measurement of the liquid content within the patient's thoracic cavity.

[0031] In certain implementations, the third patient monitoring system includes an ECG sensor connected to the patient and configured to detect one or more ECG signals from the patient; a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals from the patient; an ultrawideband radio frequency transceiver circuit connected to the patient and including one or more radio frequency antennas; and one or more processors. In some examples, the ultrawideband radio frequency transceiver circuit is configured such that one or more radio frequency antennas direct radio frequency electromagnetic energy into the patient's thoracic cavity and receive it through the one or more radio frequency antennas, generating radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the patient's thoracic cavity. In some examples, one or more processors are configured to process one or more ECG signals, one or more cardiac vibration signals, and radio frequency information to generate multiple physiological parameters of the patient, including one or more combined physiological parameters. One or more processors may perform trend analysis of multiple physiological parameters, including combined physiological parameters, to generate trend results, update the patient's monitoring schedule based on the trend results, determine the patient's current clinical symptoms based on the trend results, and determine one or more clinically usable events by comparing the patient's current clinical symptoms to predetermined clinically usable criteria. One or more processors may cause an output device to provide output regarding one or more clinically usable events. Implementations of the third patient monitoring system described herein may include one or more of the following features:

[0032] In a specific implementation of the third patient monitoring system described above, one or more processors are further configured to process one or more ECG signals, one or more cardiac oscillation signals, and radio frequency information according to an updated monitoring schedule to generate updated multiple physiological parameters of the patient, to perform trend analysis of the updated multiple physiological parameters, including one or more combined physiological parameters, to produce updated trend results, and to determine updated clinical symptoms of the patient based on the updated trend results.

[0033] In a specific implementation of the third patient monitoring system described above, one or more clinically usable events include at least one of an automated event that is triggered without user input and a manual event that is triggered based on a user response to an output and comprises one or more commands that perform one or more actions.

[0034] In a specific implementation of the third patient monitoring system described above, one or more ECG signals include at least one of the following: heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, breath, heart rate irregularity, QRS height, QRS width, changes in size or shape of the morphology of one or more ECG signals, cosine RT, artificial pacing, QT interval, QT variability, T wave width, T wave alternant, T wave variability, and ST segment changes.

[0035] In a specific implementation of the third patient monitoring system described above, one or more cardiac oscillatory signals include at least one of the following: S1 oscillatory, S2 oscillatory, S3 oscillatory, S4 oscillatory, and heart murmur oscillatory.

[0036] In a specific implementation of the third patient monitoring system described above, radio frequency information includes measurements of the fluid content in the patient's pleural cavity.

[0037] In certain implementations, the fourth patient monitoring system includes an ECG sensor connected to the patient and configured to detect one or more ECG signals from the patient; a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals from the patient; an ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and positioned on at least one of the patient's aortas; and one or more processors. In some examples, the ultra-wideband radio frequency transceiver circuit is configured such that one or more radio frequency antennas direct radio frequency electromagnetic energy toward at least a portion of the patient and receive it through the one or more radio frequency antennas, generating radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from at least a portion of the patient. In some examples, one or more processors are configured to process one or more ECG signals, one or more cardiac vibration signals, and radio frequency information to generate a plurality of physiological parameters of the patient, including one or more combined physiological parameters. One or more processors can determine the patient's current clinical symptoms by performing at least one predictive analysis and trend analysis of multiple physiological parameters, including combined physiological parameters; determine one or more clinically usable events by comparing the patient's current clinical symptoms with predetermined clinically usable criteria; and cause an output device to output one or more clinically usable events. An implementation of the fourth patient monitoring system described herein may include one or more of the following features:

[0038] In a specific implementation of the fourth patient monitoring system described above, at least one aorta includes at least one of the radial artery, brachial artery, aorta, and one or more pulmonary arteries.

[0039] In a specific implementation of the fourth patient monitoring system described above, the radio frequency information includes at least one of the following: blood pressure information, cardiac wall motion information, blood flow information, heart rhythm information, and fluid content information. [Brief explanation of the drawing]

[0040] Various aspects of at least one example are discussed below with reference to the accompanying drawings, which are not intended to be drawn with scale. The drawings, including those for the description and further understanding of the various aspects and examples, are incorporated into and constitute part of this specification, but are not intended to limit the scope of this disclosure. The drawings, together with the rest of the specification, are used to illustrate the principles and workings of the described and claimed aspects and examples. In the drawings, each identical or substantially identical component shown in various drawings is indicated by similar numbers. For clarity, not all components may be labeled in all drawings.

[0041] [Figure 1] An example of a wearable medical device related to this disclosure is shown.

[0042] [Figure 2] A schematic diagram of a sample controller for a wearable medical device, as shown in Figure 1, is provided as an example of the disclosure.

[0043] [Figure 3] This document outlines the sample network related to the example disclosed herein.

[0044] [Figure 4A] An example of a sample radio frequency path unit attached to a patient, relating to this disclosure, is shown.

[0045] [Figure 4B] A schematic diagram of a radio frequency patch antenna unit relating to an example of this disclosure is shown.

[0046] [Figure 5A] A schematic plot of the propagation delay and amplitude of radio frequencies reflected from patient tissue, relating to an example of this disclosure, is shown. [Figure 5B] A schematic plot of the propagation delay and amplitude of radio frequencies reflected from patient tissue, relating to an example of this disclosure, is shown.

[0047] [Figure 6] The pulse waveform of an exemplary artery relating to an example of this disclosure is shown.

[0048] [Figure 7] A schematic diagram of a vibration sensor relating to an example of this disclosure is shown.

[0049] [Figure 8] A chart showing lung oscillations and associated time amplitude plots is provided.

[0050] [Figure 9] This document provides a sample overview of a process utilizing predictive analytics, as illustrated in this disclosure.

[0051] [Figure 10] This document provides a sample overview of a process utilizing trend analysis, as illustrated in this disclosure.

[0052] [Figure 11] A diagram of a patient monitoring system relating to an example of this disclosure is shown. [Figure 12] A diagram of a patient monitoring system relating to an example of this disclosure is shown.

[0053] [Figure 13] Two ECG lead signals from a sample relating to an example in this disclosure are shown.

[0054] [Figure 14] This document provides a sample process for advancing a machine learning process related to the examples in this disclosure.

[0055] [Figure 15] A sample architecture of an artificial neural network related to the examples in this disclosure is shown.

[0056] [Figure 16A] A sample graph of trend analysis results using the Y-axis based on normalization units, relating to the example of this disclosure, is shown. [Figure 16B] A sample graph of trend analysis results using the Y-axis based on normalization units, relating to the example of this disclosure, is shown. [Figure 16C] A sample graph of trend analysis results using the Y-axis based on normalization units, relating to the example of this disclosure, is shown. [Figure 16D] A sample graph of trend analysis results using the Y-axis based on normalization units, relating to the example of this disclosure, is shown.

[0057] [Figure 17] This document provides an example of a sample process flow for monitoring a patient's symptoms using the technology described herein. [Modes for carrying out the invention]

[0058] Wearable medical devices, such as cardiac event monitoring devices, are used in clinical settings or outpatient clinics to monitor and record various physiological signals from patients. These signals can be used to determine the patient's current symptoms, as well as to predict, plan for, and prepare for future adverse events, such as cardiac events, or other unfavorable changes in the patient's medical health status. For example, ECG monitoring combined with the patient's medical history can be used, for example, through a machine learning process to calculate the patient's risk score and predict, for example, the future occurrence of possible cardiac arrhythmia events. An example of such a machine learning process is described in U.S. Patent Application Publication 2016 / 0135706, entitled "Medical Premonitory Event Estimation," which is incorporated herein by reference.

[0059] In some implementations, the patient monitoring system may include sensors configured to collect physiological signals from the patient other than ECG signals. For example, a vibration sensor may be configured to collect bio-vibrational signals such as cardiac vibration signals, e.g., S1, S2, S3, and S4 signals, and lung vibration signals, e.g., vibration signals from the lungs in particular, or other airway-related anatomical regions such as the trachea and pharynx in particular. Furthermore, radio frequency sensors, such as ultra-wideband transceiver circuits, may be configured to collect information corresponding to radio frequency electromagnetic energy reflected from within the patient's thoracic cavity and / or heart. For example, a radio frequency sensor may be configured to monitor transthoracic (e.g., pulmonary) fluid volume and changes in that fluid volume. In the implementations described herein, the processing device may further process various signals and related information collected from various underlying physiological sensors to produce one or more combined physiological parameters, e.g., physiological parameters determined based on two or more various underlying physiological sensors and related information. Predictive analysis (e.g., using machine learning processes such as artificial neural networks) and trend analysis (e.g., correlation analysis) can be performed on collected signals and received information, as well as combined metrics, to determine the patient's current symptoms and one or more clinically usable events.

[0060] For example, this disclosure relates to patient monitoring devices and systems. The device or system may include: an ECG sensor connected to a patient and configured to detect one or more ECG signals from the patient; a sensor connected to a patient and configured to detect one or more bio-oscillating signals from the patient (including cardiac or pulmonary oscillatory signals); and a radio frequency-based monitoring device connected to a patient and comprising a radio frequency antenna and associated transceiver circuitry configured to direct radio frequency electromagnetic energy towards the patient's thoracic cavity and / or heart. The radio frequency transceiver circuitry produces a plurality of measurements corresponding to the radio frequency electromagnetic energy reflected from the patient's thoracic cavity and / or heart and received via the receiving radio frequency antenna. One or more processors process the one or more ECG signals, one or more cardiac or pulmonary oscillatory signals, and the radio frequency measurements to generate a plurality of physiological parameters of the patient, including one or more combined physiological parameters. Furthermore, the processors may further be configured to perform at least one of predictive and trend analyses of the plurality of physiological parameters, including the combined physiological parameters, to determine the patient's current clinical condition. In some implementations, a patient monitoring device connected to a patient may transmit physiological information measured from the patient to a remote server for analysis. On the remote server, one or more processors may be configured to perform at least one of predictive and trend analyses of several physiological parameters according to the principles described herein. For example, trend analysis may include determining the existence of substantial relationships between changes in several physiological parameters. The one or more processors may further determine one or more clinically usable events by comparing the patient's current clinical symptoms to predetermined clinically usable criteria, and cause an output device to provide output regarding one or more clinically usable events.

[0061] For example, a patient may be examined by a healthcare provider in an outpatient facility and asked to use one or more wearable patient monitoring devices described herein to monitor a set of the patient's physiological parameters. For example, monitoring may begin with only one of the physiological parameters, such as an ECG-based metric. Over time, or in response to specific symptoms described herein, additional sets of physiological parameters other than ECG parameters may be initiated, such as biovibration parameters or radio frequency-based parameters (or combinations thereof). Based on the collected set of physiological parameters, the device may perform processing to assess the patient's current clinical condition. At follow-up visits (e.g., weekly, bi-weekly, or monthly), the device may provide updated information on the patient's clinical condition. The device may further be configured to determine whether the patient is at high risk of developing heart failure symptoms that may ultimately require hospitalization. The patient and / or the patient's physician may be notified of possible decisions and appropriate intervention actions. For example, the patient's medications may be adjusted, and the physician may initiate careful monitoring of the outpatient and schedule follow-up visits. As a further example of the above, if a patient is identified as being at high risk of heart failure, they may be upgraded to long-term wearable monitoring and treatment devices such as a wearable cardioverter-defibrillator (WCD). These devices can monitor the patient's cardiac condition and, if appropriate, deliver one or more defibrillation treatments and / or pacing pulse treatments to the patient. While the patient is using it, the wearable defibrillator can continuously collect updated physiological information. This updated information is further provided to the physician, who can continue to monitor changes in the patient's health status by analyzing the updated physiological information and associated trend changes. For example, this analysis may lead to further treatment changes and provide information on when the risk of acute heart failure is reduced.

[0062] Many patients with heart disease also struggle to manage symptoms related to pleural effusion, leading to frequent recurrences of acute attacks. It is among these patients that congestive heart failure (CHF) may develop. Pulmonary congestion is a major cause of hospitalization and readmission among CHF patients. Therefore, measuring and monitoring the degree of pulmonary congestion is desirable. The radiofrequency sensors described herein can enable direct and accurate fluid measurement, for example, by monitoring changes in the patient's chest impedance. This information can be used by caregivers when formulating a treatment plan for the patient, potentially shortening hospital stays by enabling effective medication balancing. For example, this technology can detect edema early and avoid readmission.

[0063] Similarly, patients with chronic kidney disease (CKD) undergoing hemodialysis also require fluid management strategies. Approximately 60 percent of patients with end-stage renal disease (ESRD) may have moderate to severe pulmonary congestion prior to hemodialysis. Furthermore, patients diagnosed with CKD and undergoing continuous hemodialysis tend to have a high morbidity of heart failure (HF) and an overall poor prognosis. Thus, congestive heart failure is a recurring clinical symptom in dialysis patients. For these reasons, fluid assessment and management may be useful in addressing CKD and HF. This disclosure may utilize non-invasive wearable monitoring systems to integrate and / or analyze this information with bio-oscillation information, ECG information, and other combined metrics, and to assess chest impedance and / or fluid changes.

[0064] These methods offer several advantages over existing monitoring and predictive technologies. By combining physiological measurements from multiple sensor sources and by utilizing various types of analysis to verify changes in physiological signals, in addition to measurement, the disclosure provides a more robust and accurate analysis of a patient's current symptoms and the likelihood of changes in those symptoms. Based on this information, an individualized treatment plan can be created for the patient and regularly updated, while the patient's symptoms can be regularly monitored for improvement or deterioration.

[0065] The teachings of this disclosure may generally be applied to extracting physiological metrics for further processing from external medical monitoring devices and / or therapeutic devices (e.g., devices that are not fully implanted in the patient's body). External medical devices may include, for example, portable medical devices that may and are designed to move with the patient as the patient goes about their daily life. Illustrative portable medical devices may include wearable medical devices such as wearable defibrillators (WCDs), wearable cardiac monitoring devices, in-hospital devices such as in-hospital wearable defibrillators (HWDs), short-term wearable cardiac monitoring devices and / or therapeutic devices, mobile cardiac monitoring devices, and other similar wearable medical devices.

[0066] Wearable medical devices may allow for continuous use by patients. In some implementations, continuous use may be de facto, substantially, or nearly continuous. That is, a wearable medical device may be used continuously, except for sporadic periods when use is temporarily stopped (e.g., while the patient is bathing, changing into new and / or different clothes, charging / replacing the battery, washing clothes, etc.). However, such substantially or nearly continuous use as described herein may qualify as continuous use. For example, a wearable medical device may be configured for a patient to wear for 24 hours a day. In some implementations, the patient may remove the wearable medical device for short periods of time during the day (e.g., for 30 minutes while bathing).

[0067] Furthermore, wearable medical devices may be configured for use over extended periods or for long durations. Such devices may be configured for patient use over extended periods of several days, weeks, months, or even years. In some examples, a wearable medical device may be used by a patient for an extended period of at least one week. In some examples, a wearable medical device may be used by a patient for an extended period of at least 30 days. In some examples, a wearable medical device may be used by a patient for an extended period of at least one month. In some examples, a wearable medical device may be used by a patient for an extended period of at least two months. In some examples, a wearable medical device may be used by a patient for an extended period of at least three months. In some examples, a wearable medical device may be used by a patient for an extended period of at least six months. In some examples, a wearable medical device may be used by a patient for an extended period of at least one year. In some implementations, extended use may continue until a physician or other caregiver gives the patient explicit instructions to stop using the wearable medical device.

[0068] Regardless of the duration of wear, the use of a wearable medical device may include continuous or near-continuous wear by the patient as described above. For example, continuous use may include continuous wearing or attachment of the wearable medical device to the patient, for example, through one or more electrodes as described herein, for periods of both monitoring and periods during which the device may not be monitoring the patient but is still being worn or attached to the patient for other reasons. A wearable medical device may be configured to continuously monitor the patient for cardiac-related information (e.g., electrocardiogram (ECG) information including arrhythmia information, cardiac oscillations, lung oscillations, etc.) and / or non-cardiac information (e.g., blood oxygen, patient body temperature, blood glucose levels, tissue fluid volume, and / or lung oscillations). A wearable medical device may perform its monitoring at periodic or aperiodic time intervals, or periodically or aperiodicly. For example, monitoring during such intervals or periods may be triggered by user behavior or other events.

[0069] As described above, wearable medical devices can be configured to monitor other physiological parameters of a patient in addition to cardiac-related parameters. For example, a wearable medical device can be configured to monitor, for example, lung vibrations (e.g., using a microphone and / or accelerometer), respiratory vibrations, sleep-related parameters (e.g., snoring, sleep apnea), and tissue fluid (e.g., using a radio frequency transmitter and radio frequency sensor).

[0070] Other exemplary wearable medical devices include automated cardiac monitors and / or defibrillators for use in specific special situations and / or environments, such as within a combat zone or inside an emergency vehicle. Such devices may be configured to be used rapidly (or substantially rapidly) in emergency medical situations. In some examples, the wearable medical devices described herein may be pacable, for example, capable of providing pacing pulse therapy to a patient.

[0071] In an implementation, exemplary therapeutic medical devices may include, for example, in-hospital wearable defibrillators, or in-hospital continuous monitoring pacing devices. In such examples, electrodes may be attached to the patient's skin by adhesion. For example, the electrodes may include disposable adhesive electrodes. For example, the electrodes may include sensing and therapeutic components that are placed on separate adhesive patches for sensing and therapeutic electrodes. In some implementations, both the sensing and therapeutic components may be integrated and placed on the same electrode adhesive patch that is subsequently attached to the patient. In an exemplary implementation, the electrodes may include an adhesively attachable anterior therapeutic electrode, an adhesively attachable posterior therapeutic electrode, and multiple adhesively attachable sensing electrodes. For example, the adhesively attachable anterior therapeutic electrode is attached to the front of the patient's torso to administer pacing or defibrillation therapy. Similarly, the adhesively attachable posterior therapeutic electrode is attached to the posterior of the patient's torso. In an exemplary scenario, at least three adhesively attachable ECG sensing electrodes may be attached in a manner instructed by a trained professional to at least the upper part of the chest near the patient's right arm, the upper part of the chest near the patient's left arm, and the lower part of the patient's chest.

[0072] Patients monitored by in-hospital defibrillators and / or in-hospital pacing devices may be confined to their beds or rooms for considerable periods (e.g., more than 90 percent of patients stay in the hospital). As a result, the user interface may be configured to interact with non-patient users, such as nurses, for device-related functions, such as initial device baselines, setting and adjusting patient parameters, and changing the device battery.

[0073] In implementation, examples of therapeutic medical devices may include short-term continuous monitoring defibrillators and / or short-term continuous monitoring pacing devices, such as short-term outpatient wearable defibrillators. For example, such short-term outpatient wearable defibrillators may be prescribed by a physician for a patient exhibiting syncope. The wearable defibrillator may be configured to monitor a patient exhibiting syncope by analyzing the patient's cardiac activity for abnormal patterns that may indicate abnormal physiological function, for example. For example, such abnormal patterns may occur before, during, or after the onset of symptoms. In such exemplary implementations of the short-term wearable defibrillator, an electrode assembly may be attached to the patient's skin by adhesion, and the electrode assembly may have a configuration similar to that of the in-hospital defibrillator described above.

[0074] In some implementations, the medical device may be a patient monitoring device that does not have a therapeutic or therapeutic function. For example, such a patient monitoring device may include a cardiac monitoring device or cardiac monitor configured to monitor one or more cardiac physiological parameters of a patient in order to remotely monitor and / or diagnose the patient's symptoms. For example, the cardiac physiological parameters may include the patient's ECG information, cardiac vibration (using, for example, an accelerometer or microphone), and other relevant cardiac information. The cardiac monitoring device is a portable device that the patient may carry with them as they go about their daily life. The cardiac monitor may be configured to detect the patient's ECG via multiple cardiac sensing electrodes. For example, the cardiac monitor may be attached to the patient via at least three adhesive cardiac sensing electrodes placed around the patient's torso. Such cardiac monitors are used for monitoring cardiac events, e.g., patient populations reporting irregular cardiac symptoms and / or cardiac disease. Exemplary cardiac conditions may include atrial fibrillation, bradycardia, tachycardia, atrioventricular block, Laung-Gannon-Levine syndrome, atrial flutter, sinoatrial node dysfunction, cerebral ischemia, syncope, atrial arrest, and / or palpitations. For example, the patient may be prescribed a cardiac monitor for a longer period, such as 10 to 30 days or longer. In some mobile cardiac event monitoring applications, the portable cardiac monitor may be configured to monitor patients with cardiac malformations substantially continuously, and when such abnormalities are detected, the monitor may automatically transmit data about the abnormalities to a remote server. The remote server may be located in a 24 / 7 monitoring center where the data is interpreted by qualified cardiac-trained censors and / or caregivers, and feedback is provided to the patient and / or designated caregivers through periodic detailed reports or event-triggered reports. In certain cardiac event monitoring applications, the cardiac monitor may be configured so that the patient can report symptoms by manually pressing buttons on the cardiac monitor. For example, patients may report symptoms such as stagnation, shortness of breath, lightheadedness, rapid heartbeat, fatigue, fainting, chest discomfort, weakness, dizziness, and / or vertigo.A cardiac monitor may record predetermined physiological parameters of the patient (e.g., ECG information) for a set period of time (e.g., 1 to 30 minutes before the reported symptoms and 1 to 30 minutes after the reported symptoms). A cardiac monitor may be configured to monitor physiological parameters of the patient other than cardiac-related parameters. For example, a cardiac monitor may be configured to monitor, for example, cardiac oscillations (e.g., using an accelerometer or microphone), lung oscillations, respiratory oscillations, sleep-related parameters (e.g., snoring, sleep apnea), and tissue fluid.

[0075] Figure 1 shows an exemplary medical device 100 configured to be external, portable, wearable, and to implement one or more configurations described herein. For example, the medical device 100 may be a non-invasive medical device configured to be positioned substantially outside the patient. The medical device 100 may be a portable medical device that can and is designed to move with the patient as the patient goes about their daily life. For example, the medical device 100 described herein, such as the LifeVest® wearable defibrillator available from ZOL® Medical Inc., may be attached to the patient's body. The wearable defibrillator is typically worn for two to three months at a time, substantially or substantially continuously. During the period a patient wears the wearable defibrillator, it may be configured to continuously or substantially continuously monitor the patient's vital signs, and when the need for treatment is determined, the wearable defibrillator may be configured to deliver one or more therapeutic electrical pulses to the patient. For example, such therapeutic shocks may be pacing, defibrillation, or transcutaneous electrical nerve stimulation (TENS) pulses.

[0076] The medical device 100 may include, below, a garment 110, one or more sensing electrodes 112 (e.g., ECG electrodes), one or more therapeutic electrodes 114a and 114b (collectively referred to herein as therapeutic electrodes 114), a medical device controller 120, a connection pod 130, a patient interface pod 140, a belt 150, or one or more of any combination thereof. In some examples, at least some of the components of the medical device 100 may be configured to be attached to (or permanently integrated with) a garment 110 that can be worn around the patient's torso.

[0077] The medical device controller 120 can be operably connected to the sensing electrode 112, which can be attached to the garment 110, for example using hook-and-loop fasteners, or detachably attached to the garment. In some implementations, the sensing electrode 112 can be permanently integrated with the garment 110. The medical device controller 120 can also be operably connected to the treatment electrode 114. For example, the treatment electrode 114 can be further integrated with the garment 110, or in some implementations, the treatment electrode 114 can be permanently integrated with the garment 110.

[0078] Other configurations of the components are possible besides those shown in Figure 1. For example, the sensing electrode 112 may be configured to be attached to various locations around the patient's body 102. The sensing electrode 112 may be operably connected to the medical device controller 120 via a connection pod 130. In some implementations, the sensing electrode 112 may be attached to the patient 102 by adhesive. In some implementations, the sensing electrode 112 and at least one of the therapeutic electrode 114 may be included in a single integrated patch and attached to the patient's body by adhesive.

[0079] The sensing electrode 112 may be configured to detect one or more cardiac signals. Examples of such signals include ECG signals and / or other sensed cardiac physiological signals from a patient. In certain implementations, the sensing electrode 112 may include additional components such as an accelerometer, a vibration signal detection device, and other measuring devices that record additional parameters. For example, the sensing electrode 112 may further be configured to detect other types of patient physiological parameters and vibration signals, such as tissue fluid volume, cardiac vibration, lung vibration, respiratory-related vibration, and patient movement, which are anatomical features within the airway. An exemplary sensing electrode 112 includes, for example, a metal electrode with an oxide coating, such as a tantalum pentoxide electrode described in U.S. Patent No. 6,253,099, entitled "Cardiac Monitoring Electrode Apparatus and Method," the contents of which are incorporated herein by reference.

[0080] In some examples, the therapeutic electrode 114 may further include a sensor configured to detect ECG signals and other physiological signals from the patient. In some examples, the connection pod 130 may include a signal processor configured to amplify, filter, and digitize the cardiac signals before sending them to the medical device controller 120. When the medical device 100 determines that such treatment is guaranteed based on signals detected by the sensing electrode 112 and processed by the medical device controller 120, one or more of the therapeutic electrodes 114 may be configured to deliver one or more therapeutic defibrillation shocks to the patient's body 102. Exemplary therapeutic electrodes 114 may include conductive metal electrodes, such as stainless steel electrodes, which in certain implementations include one or more conductive gel dispensing devices configured to supply conductive gel to the metal electrodes before delivering therapeutic shocks.

[0081] In some implementations, the medical devices described herein may be configured to switch between a therapeutic medical device and a monitoring medical device configured to monitor a patient only (e.g., not provide or perform any therapeutic functions). For example, therapeutic components and associated circuits, such as therapeutic electrodes 114, may be disconnected (or connected) from the medical device as needed, or switched off (or on) from the medical device. For example, the medical device may have optional therapeutic elements (e.g., defibrillation electrodes and / or pacing electrodes, components, and associated circuits) configured to operate in therapeutic mode. As a means of converting the therapeutic medical device into a monitoring medical device for a specific purpose (e.g., operating only in monitoring mode) or for a patient, the optional therapeutic elements may be physically disconnected from the medical device. Alternatively, the optional therapeutic elements may be deactivated (e.g., by physical or software switching), effectively converting the therapeutic medical device into a monitoring medical device for a specific physiological purpose or for a specific patient. As an example of software switching, in order to deactivate the therapeutic elements of a medical device, an authorized person may access the medical device's protected user interface and select pre-configured options, or perform certain actions of other users through the user interface.

[0082] Figure 2 shows a component-level diagram of a sample medical device controller 120. As shown in Figure 2, the medical device controller 120 may include a therapeutic supply circuit 202, data storage 204, a network interface 206, a user interface 208, at least one battery 210, a sensor interface 212, an alarm manager 214, and at least one processor 218. A patient monitoring medical device may include a medical device controller 120 that includes similar components to those described above, but without the therapeutic supply circuit 202 (shown by a dotted line).

[0083] The therapeutic supply circuit 202 may be connected to one or more electrodes 220 (e.g., the therapeutic electrode 114 described above in relation to Figure 1) configured to deliver treatment to a patient. For example, the therapeutic supply circuit 202 may include, or be operably connected to, circuit components configured to generate and deliver therapeutic shocks. The circuit components may include, for example, a resistor, a capacitor, a relay and / or switch, an electrical bridge such as an h-bridge (e.g., including multiple insulated-gate bipolar transistors or IGBTs), a voltage and / or current measuring component, and other similar circuit components arranged and connected to cooperate with the therapeutic supply circuit and operate under the control of one or more processors (e.g., processor 218) to provide, for example, one or more pacing pulses or defibrillation therapeutic pulses.

[0084] Pacing pulses may be used to treat cardiac arrhythmias such as bradycardia (e.g., less than 30 heartbeats per minute) and tachycardia (e.g., more than 150 heartbeats per minute), for example, using fixed-rate pacing, demand pacing, or anti-tachycardia pacing. Defibrillation pulses may be used to treat ventricular tachycardia and / or ventricular fibrillation.

[0085] The capacitor may include a parallel-connected capacitor bank consisting of multiple capacitors (e.g., two, three, or four or more capacitors). These capacitors can be switched to a series connection during the discharge of the defibrillation pulse. For example, four capacitors with approximately 650 microfarads each may be used. The capacitors may have a surge rating in the range of 350 to 500 volts and can be charged from the battery pack in approximately 15 to 30 seconds.

[0086] For example, each defibrillation pulse may deliver energy in the range of 60 to 180 joules. In some implementations, the defibrillation pulse may be a biphasic truncated exponential waveform, thereby allowing the signal to switch between positive and negative portions (e.g., in the direction of charge). This type of waveform may be more effective in defibrillating patients at lower energy levels compared to other types of defibrillation pulses (e.g., single-phase pulses). For example, the amplitude and width of the two phases of the energy waveform may be automatically adjusted to deliver a precise amount of energy (e.g., 150 joules) regardless of the patient's body impedance. The therapeutic supply circuit 202 may be configured to perform switching and pulse supply operations, for example, under the control of a processor 218. The amount of energy delivered can be tracked as energy is delivered to the patient. For example, even if the pulse waveform is dynamically controlled based on factors such as the patient's body impedance to which the pulse is being delivered, the amount of energy may be kept at a predetermined constant value.

[0087] The data storage 204 may include, for example, one or more of the following: flash memory, solid-state memory, magnetic memory, optical memory, cache memory, a combination thereof, and other non-temporary computer-readable media. The data storage 204 may be configured to store executable instructions and data used for the operation of the medical device controller 120. In a particular implementation, the data storage may include executable instructions, which, when executed, cause the processor 218 to perform one or more functions.

[0088] In some examples, the network interface 206 may facilitate information communication between the medical device controller 120 and one or more other devices or entities via a communication network. For example, if the medical device controller 120 is contained within a portable medical device (such as medical device 100), the network interface 206 may be configured to communicate with a remote computing device, such as a remote server or other similar computing device. The network interface 206 may include a communication circuit that transmits data to an intermediary device, such as a base station, a "hotspot" device, a smartphone, a tablet, a portable computing device, and / or other devices near the wearable medical device, in accordance with the Bluetooth® wireless standard for exchanging such data over short distances. The intermediary device may then transmit the data to the remote server via a broadband cellular network communication link. This communication link may implement high-speed wireless broadband cellular technology (e.g., 2.5G, 2.75G, 3G, 4G, 5G cellular standards) and / or Long-Term Evolution (LTE) technology, or GSM / EDGE® and UMTS / HSPA® technologies. In some implementations, the intermediary device may communicate with the remote server via a Wi-Fi® communication link based on the IEEE 802.11 standard.

[0089] In a particular implementation, the user interface 208 may include one or more physical interface devices, such as input devices, output devices, and combined input / output devices, and a software stack configured to drive the operation of the devices. These user interface elements may display visual, auditory, and / or tactile content. Thus, the user interface 208 may receive inputs or make outputs, thereby enabling the user to interact with the medical device controller 120.

[0090] The medical device controller 120 may further include at least one battery 210 configured to power one or more components integrated into the medical device controller 120. The battery 210 may include a rechargeable multi-cell battery pack. In one exemplary implementation, the battery 210 may include three or more 2200mAh lithium-ion batteries to power other device components within the medical device controller 120. For example, the battery 210 may have its power output in the range of 20mA to 1000mA (e.g., 40mA) and may support run times of 24 hours, 48 ​​hours, 72 hours or more between charges. In a particular implementation, the battery capacity, run time, and type (e.g., lithium-ion, nickel-cadmium, or nickel metal hydride) may be modified to best suit the specific application of the medical device controller 120.

[0091] The sensor interface 212 may be connected to one or more sensors configured to monitor one or more physiological parameters of a patient. As shown in the figures, the sensors may be connected to the medical device controller 120 via a wired or wireless connection. The sensors may include one or more electrocardiogram (ECG) electrodes 222 (e.g., similar to the sensing electrodes 112 described above in relation to Figure 1), a biovibration sensor 224, a tissue fluid monitor 226 (e.g., based on an ultra-wideband radio frequency device), and a patient motion sensor 228.

[0092] The ECG electrode 222 can monitor the patient's ECG information. For example, the ECG electrode 222 may be a galvanic (e.g., conductive) electrode and / or a capacitive electrode configured to measure changes in the patient's electrophysiology in order to measure the patient's ECG information. The ECG electrode 222 may transmit information describing the ECG signal to the sensor interface 212 for subsequent analysis.

[0093] The bio-vibration sensor 224 may detect patient vibrations related to, for example, cardiac and pulmonary activity. For example, the bio-vibration sensor 224 may be configured to detect cardiac or chest vibration values ​​including one or all of S1, S2, S3, and S4. From these cardiac vibration values, a specific cardiac vibration metric or combination metric may be calculated, including any one or more of electromechanical activation time (EMAT), left ventricular contraction time (LVST), or left ventricular contraction time percentage (%LVST). The bio-vibration sensor 224 may include a vibration sensor configured to detect vibrations from the patient's cardiac system and supply an output signal corresponding to the detected cardiac vibrations. The bio-vibration sensor 224 may further include a multi-channel accelerometer, such as a 3-channel accelerometer, configured to sense motion within each of three orthogonal axes so that patient motion / body position can be detected and associated with the detected cardiac vibration information. The bio-vibration sensor 224 may transmit information describing the cardiac vibration information to the sensor interface 212 for subsequent analysis.

[0094] The tissue fluid monitor 226 may use radio frequency-based technology to assess the volume and fluid accumulation within a patient's body tissues. For example, the tissue fluid monitor 226 may be configured to measure the fluid content in the lungs, typical for the diagnosis and follow-up of pulmonary edema or pulmonary congestion in patients with heart failure. The tissue fluid monitor 226 may include one or more antennas configured to direct radio frequencies towards the patient's tissue and measure an output radio frequency signal in response to the radio frequencies that have passed through the tissue. In a particular implementation, the output radio frequency signal may include parameters indicating the volume of fluid in the patient's tissue. The tissue fluid monitor 226 may transmit information indicating the volume of tissue fluid to the sensor interface 212 for subsequent analysis. An example of a radio frequency sensor is further described in Figure 3 below.

[0095] The patient motion sensor 228 may include one or more accelerometers configured to measure motion data relating to patient movement. In certain implementations, the patient motion sensor 228 may be configured to measure the number of steps a patient takes over a specific period of time. For example, a patient may be instructed to perform a specific exercise, such as a walking test. The patient motion sensor 228 may be configured to measure step count and pace information during the specific exercise. However, it should be noted that the patient motion sensor 228 is shown as a separate component only as an example. In certain implementations, one or more accelerometers included in the patient motion sensor 228 may be integrated with other components, such as the biovibration sensor 224 or the tissue fluid monitor 226.

[0096] The sensor interface 212 may be connected to any one or combination of sensing electrodes / other sensors to receive other patient data indicating patient parameters. Once data from a sensor is received by the sensor interface 212, the data may be sent by the processor 218 to the appropriate component in the medical device controller 120. For example, if cardiac data is collected by the biovibration sensor 224 and transmitted to the sensor interface 212, the sensor interface 212 may transmit the data to the processor 218, which then relays the data to the cardiac event detector. The cardiac event data may further be stored in the data storage 204.

[0097] In a particular implementation, the alarm manager 214 may be configured to manage alarm profiles and notify one or more intended recipients of events designated as of interest to those recipients within the alarm profiles. These intended recipients may include users (patients, physicians, and monitoring personnel) as well as external entities such as computer systems (monitoring systems or emergency response systems). The alarm manager 214 may be implemented using hardware or a combination of hardware and software. For example, in some examples, the alarm manager 214 may be implemented as a software component stored in data storage 204 and executed by processor 218. In this example, instructions contained within the alarm manager 214 may cause processor 218 to configure alarm profiles and notify intended recipients using the alarm profiles. In other examples, the alarm manager 214 may be an application-specific integrated circuit (ASIC) coupled to processor 218 and configured to manage alarm profiles and notify intended recipients using alarms designated within the alarm profiles. Thus, the examples of the alarm manager 214 are not limited to specific hardware or software implementations.

[0098] In some implementations, the processor 218 includes one or more processors (or one or more processor cores), each configured to execute a set of instructions resulting in manipulated data and / or to control the operation of other components of the medical device controller 120. In some implementations, when performing a particular process (e.g., cardiac monitoring), the processor 218 may be configured to make specific logic-based decisions based on received input data, and the processor may further be configured to provide one or more outputs that can be used to control or otherwise notify subsequent processing to be performed by the processor 218 and / or other processors, or by circuits to which the processor 218 is communicably connected. Thus, the processor 218 responds in a specific way to a particular input stimulus and generates a corresponding output based on that input stimulus. In some exemplary cases, the processor 218 may go through a series of logical transitions, in which various internal register states and / or other internal or external bit cell states of the processor 218 may be set to high logic or low logic. The processor 218 referred to herein may be configured to perform functions in which software is stored in a data store connected to the processor 218, and such software is configured to cause the processor 218 to make a series of various logic decisions that result in the execution of such functions. The various components described herein as executable by the processor 218 may be implemented in various forms, such as special hardware, software, or a combination thereof. For example, the processor may be a digital signal processor (DSP), such as a 24-bit DSP processor. This processor may be a multicore processor having two or more processing cores, for example. This processor may be an advanced RISC machine (ARM) processor, such as a 32-bit ARM processor or a 64-bit ARM processor.This processor can run an embedded operating system, which may include services provided by the operating system that can be used for file system operations, display and audio generation, basic networking functions, firewall functions, data encryption, and communication.

[0099] Figure 3 shows a sample network 300 illustrating a sample connection configuration showing how a wearable medical device (e.g., the medical device 100 described above) may be operationally connected to a remote server. As described above in relation to Figure 2, the wearable medical device controller 120 includes a network interface 206 for transmitting data via a wireless link such as a Bluetooth® wireless link (e.g., via a “hotspot” or other base station or intermediary device), a broadband cellular link, or a Wi-Fi® communication link based on the IEEE 802.11 standard. As shown in Figure 3, the physician’s computer 302 and the wearable medical device 304 may be operationally connected to a monitoring server 308 via the network 306. In a particular implementation, while being worn, the wearable medical device 304 may collect information about the patient, including various patient metrics and patient parameters described herein. Depending on the connection to the network 306 and the programming of the wearable medical device 304, the wearable medical device may be configured to periodically transmit the collected information to the monitoring server 308 for further processing. For example, the monitoring server 308 may be configured to monitor the patient's physiological state based on patient data obtained from multiple sensor sources, including biovibration sensors and radio frequency sensors, and transmitted to the monitoring server by, for example, one or more wearable medical devices 304. In some examples, one or more physicians may use their computer 302 to review changes in the patient's health, receive instructions / recommendations to modify the patient's treatment plan, and perform other similar functions to access the patient's status information.

[0100] In some examples, as described above, the patient may wear a radio frequency device, such as a radio frequency transceiver, including an ultra-wideband transceiver circuit configured to direct radio frequency electromagnetic energy towards the patient via a radio frequency antenna and generate radio frequency information corresponding to the reflected electromagnetic energy. In certain implementations, the radio frequency device (transceiver and associated antenna) may be integrated into a patch worn by the patient, in addition to the wearable medical device described above. For example, as shown in Figure 4A, the patch 402 may be attached to the patient 400 by adhesive at a predetermined location on the patient's body.

[0101] In other implementations, the radio frequency device can be integrated into the clothing of a wearable defibrillator. In some implementations, the radio frequency device can be integrated into a wearable continuous event monitoring device. In some implementations, the radio frequency device can be integrated into one or more therapeutic electrodes and / or patches of a hospital wearable defibrillator. In the above implementations, the radio frequency device (e.g., integrated into patch 402) may be positioned on the lower left abdominal region of patient 400 as shown in Figure 4A and configured to direct the radio frequency electromagnetic energy into the patient's thoracic cavity, e.g., the patient's lungs and / or heart. In other examples, for example, the radio frequency device may be placed on at least one aorta, such as the radial artery, brachial artery, aorta, and one or more pulmonary arteries, to monitor the patient's arterial pulsation. Information on arterial pulsation may be used to monitor the patient's blood pressure measurement according to the implementations described below.

[0102] Radio frequency information corresponding to reflected electromagnetic energy from the patient's thoracic cavity may indicate pulmonary fluid volume (absolute value and volume change), chest impedance, blood pressure measurements, heart rate measurements, and / or specific cardiac conditions, based on monitoring of the patient's cardiac wall motion. Examples of radio frequency transceivers are described, for example, in U.S. Patent No. 8,989,837, entitled "Methods and Systems for Determining Fluid Content of Tissue," U.S. Patent No. 7,122,012, entitled "Detection of Fluids in Tissues," U.S. Patent Publication No. 2010 / 0256462, entitled "Method and System for Monitoring Thoracic Tissue Fluid," U.S. Patent No. 9,675,251, entitled "Electromagnetic Probes, Methods for Fabricating Thereof, and Systems Which Use Such Electromagnetic Probes," U.S. Patent No. 7,725,150, entitled "System and Method for Extracting Physiological Data Using Ultra-Wideband Radar and Improved Signal Processing Techniques," and U.S. Patent No. 9,002,427, entitled "Apparatus and Method for Continuous Noninvasive Measurement of Respiratory Function and Events," the contents of which are incorporated herein by reference. As described above, radio frequency information corresponding to the reflected electromagnetic energy from the patient's thoracic cavity can similarly indicate changes in the patient's chest impedance values.

[0103] Figure 4B shows a schematic diagram of an exemplary radio frequency device 430, such as the radio frequency device shown in Figure 4A. The radio frequency device 430 may be configured to function as a radio frequency transceiver using components contained within an integrated package 442, which may, for example, be in the form of a patch or be integrated into a wearable medical device as described above. In some implementations, the radio frequency device 430 may be implemented within a package 442 having a form factor of approximately 20 mm × 50 mm. In other examples, the form factor may be smaller, for example, in the range of approximately 10 mm × 25 mm to approximately 20 mm × 50 mm. In some examples, the package 442 may include an adhesive layer, for example, by which the radio frequency device 430 may be attached to the patient's skin.

[0104] The radio frequency device 430 includes at least two antennas, a transmitting antenna 432a and a receiving antenna 432b, which transmit radio frequency energy into the patient's pleural cavity and receive radio frequency energy from the patient's pleural cavity. In some implementations, antennas 432a and 432b may have flat and / or flexible contours that better conform to the shape and outline of the patient's body. A transceiver 436 is configured to generate a drive signal for transmitting and / or receiving radio frequency energy at antennas 432a and 432b. The transceiver 436 is further configured to receive and process reflected electromagnetic energy that antennas 432a and 432b receive from the patient's body. In certain implementations, an active background erasure circuit 434 erases background components from reflected signals, e.g., signals from depths and / or tissues of no interest. A processor 438 controls the operation of the components of the radio frequency device 430 described below. The processor 438 monitors one or more radio frequency signal path characteristics and can generate radio frequency information corresponding to the selected tissue depth (e.g., within a range of 1 cm to 20 cm) and / or the tissue of interest, such as the effective path length of the radio frequency path and one or more phase changes and / or amplitude changes of the reflected radio frequency relative to the transmitted radio frequency. The processor 438 can process this radio frequency information and convert it into interpretable physiological metrics such as thoracic fluid content (TFC), cardiac wall motion data, and / or arterial pulse information. In some implementations, the radio frequency device 430 may be configured to transmit its radio frequency information to a remote server via a communication interface 448. In such implementations, the remote server may be configured to process the received radio frequency information and perform the conversion to the physiological metrics described above. A power module 444, such as a thin battery, supplies power to the components of the patch unit.

[0105] In some implementations, the radio frequency device 430 may further include an ECG electrode 440 that electrically contacts the patient's skin, and an ECG acquisition circuit 450 that filters and digitizes the ECG signal for input to a processor 438. The ECG signal may be used to gate control the operation of transmitting a radio frequency to the patient's pleural cavity and receiving a radio frequency from the patient's pleural cavity. For example, a transceiver 436 may trigger radio frequency transmission based on the timing of the R wave of the ECG signal.

[0106] In a particular implementation, the radio frequency device 430 includes a user interface such as one or more indicator LEDs 446 that indicate the operating status of the patch (on / off, and optionally, parameters such as battery level, skin contact characteristics, or signal strength). Alternatively or additionally, the user interface may include a more informative display such as an LCD, as well as user controls such as on / off and adjustment buttons.

[0107] The communication interface 448 communicates with a remote console to transmit radio frequency data and ECG measurement data, and optionally to receive operational commands. For example, the communication interface 448 may include a wireless link such as Bluetooth® or a Wi-Fi link. For example, the remote console can be positioned near the patient's location and therefore can directly receive and process data from the communication interface 448. Alternatively, the communication interface 448 may communicate with a local gateway such as a personal computer, smartphone device, or dedicated “hotspot” device that communicates with a remote server on a network such as the Internet or a telephone network. In these implementations, the console may be a network server connected to one or more databases and configured to store radio frequency data and ECG data for subsequent reference, processing, and analysis. For example, physicians or other professionals may be provided with access and / or tools to perform data analysis. In some situations, the data may be available to another diagnostic computer system via a wired or wireless link. These system configurations are particularly useful for portable monitoring of multiple patients over extended periods in various geographical locations.

[0108] As described above, radio frequency devices such as device 430 can be used to monitor various patient metrics and parameters. For example, a radio frequency device may be configured to monitor tissue fluid metrics, blood pressure, chest wall motion, and other similar patient parameters.

[0109] To measure tissue fluid metrics, radio frequency devices may be configured to direct electromagnetic energy towards a tissue area (e.g., the pulmonary or thoracic cavity) and measure the amplitude and delay of the returned / reflected electromagnetic energy. For example, Figure 5A illustrates a schematic plot 500 showing amplitude, and Figure 5B illustrates a schematic plot 505 showing the propagation delay of radio frequencies reflected from a patient's heart. Note that the scales of plots 500 and 505 are arbitrary, as shown in Figures 5A and 5B. The delay and amplitude fluctuate periodically with each cycle of the heartbeat, although to a relatively low degree, as particularly indicated by the sharp peak of line 507 shown in Figure 5B and the overall downward shift of amplitude at line 502 shown in Figure 5A.

[0110] The recesses on both lines 502 and 507, from reference numeral 250 to reference numeral 260 on the horizontal scale, correspond to the inhalation period during the respiratory cycle. When the lungs are filled with air, these recesses in Figure 5B indicate that the effective radio frequency path length through the lungs narrows because the average dielectric constant along that path decreases while the physical distance between the antenna and the heart remains approximately constant. Exhalation empties the lungs, thus widening the effective radio frequency path length. Furthermore, the amplitude of the reflected wave in Figure 5A decreases during inhalation, presumably because the variation in dielectric constant increases, and therefore there are more reflections along the radio frequency path through the lungs when the lungs are filled with air.

[0111] In lungs with a large fluid content, the average dielectric constant is generally higher than in healthy lungs, and therefore the radio frequency path delay across the lung is greater. Because there is less reflection as the radio frequency crosses the lung, the overall amplitude may also be larger. On the other hand, during a respiratory cycle, the difference between an air-filled lung and an empty lung is expected to be smaller in both amplitude and delay than the difference shown in Figures 5A and 5B. Therefore, to monitor tissue fluid content, a processing device may, for example, compare the delay and possibly amplitude of the reflected wave to a baseline provided by healthy and unhealthy lungs, or to previous measurements made on the same patient. Additionally or alternatively, the processing device may assess the fluid volume in the lung by analyzing changes in the amplitude and / or delay of the reflected wave during one or more respiratory cycle processes. In certain implementations, to quantify the assessment of fluid retention, the actual physical distance traversed by the radio frequency passing through the lung may be measured, and the relationship (e.g., ratio) between the effective radio frequency path length and its physical distance may be calculated.

[0112] Additionally, radio frequency devices can be used to measure a patient's blood pressure. For example, information determined from the pulse waveform of a patient's artery can be used by a processing device to determine the patient's blood pressure. As shown in Figure 6, the pulse waveform 600 of a patient's artery can be obtained by directing a radio frequency to the patient's artery and measuring the reflected radio frequency. Based on the reflected wave, the processing device can measure changes in the radar cross-section (RCS) of the artery.

[0113] For example, during the cardiac cycle, a radio frequency device may generate and transmit radio frequencies toward an artery that may be located at a specific depth from the radio frequency device. In some examples, some or all of the transmitted radio frequencies may bounce back to the radio frequency device. In some cases, the radio frequency device may transmit radio frequencies continuously or intermittently. During the cardiac cycle, the diameter of the artery may vary over time, and the arterial RCS obtained by the radio frequency device may also change over time. In some implementations, from various RCS measurements, an arterial pulse waveform (e.g., pulse waveform 600) showing a pulse wave propagating through the artery may be determined. From the arterial pulse waveform, various clinical information can then be obtained, but not limited to, arteriosclerosis, pulse wave velocity, cardiac output, and (continuous or intermittent) measurements of blood pressure. In some embodiments, the reflected echo may be modulated by the artery during the cardiac cycle process, and information from the reflected echo may be used to determine / evaluate the arterial pulse waveform. For example, the measurement range may change during the cardiac cycle process, resulting in a change in the phase of the reflected wave. In such cases, this information can be used to determine / evaluate the pulse waveform of the artery.

[0114] In certain implementations, radio frequency devices may be calibrated to include fundamental measurements of the patient's blood pressure and pulse time progression (PTT) to more accurately determine the patient's blood pressure. PTT can be obtained by using multiple sensors attached at known locations on the patient, measuring the pulse arrival time (PAT) at each location. The processing device can calculate the PTT by calculating the difference in PATs at each location and knowing the distance between the sensors. This information can further be used to determine the patient's pulse wave velocity (PWV).

[0115] In certain implementations, the linear transformation relating systolic blood pressure (SBP) and diastolic blood pressure (DBP) to PTT may be expressed as follows: SBP = (a × PTT) + b, DBP = (c × PTT) + d The coefficients a, b, c, and d can be calibrated for each patient. In some embodiments, other types of conversions may be used to calculate blood pressure. For example, in a model assuming a constant thickness and radius of arteries, blood pressure P may be expressed as P = a × ln(PTT) + b, where again a and b are constants calibrated for each patient. In some embodiments, in either case, obtaining the PTT of pulses in the artery, and on the other hand the PWV, may be used to determine the blood pressure value in the artery. Additional examples relating to determining blood pressure using radio frequency devices are described, for example, in U.S. Patent Application Publication No. 2016 / 0345845, entitled "Systems, Apparatuses and Methods for Determining Blood Pressure," which is incorporated herein by reference.

[0116] From the information on the collected parameters and metrics described above (e.g., tissue fluid volume and blood pressure), additional metrics may be determined. For example, the processing device may determine information such as chest wall movement and respiratory rate by extracting respiratory information from fluid measurement information. For example, the processing device may be configured to associate chest wall expansion with the period when the patient inhales and chest wall contraction with the period when the patient exhales.

[0117] Cardiac vibration is a noise generated by the heartbeat and the resulting blood flow. Specifically, the vibration reflects the turbulence generated when the heart valves close. During cardiac monitoring, for example, one or more cardiac vibration sensors can be used to detect these unique and distinct vibrations, providing important auditory data about cardiac symptoms.

[0118] In healthy adults, each heartbeat involves at least two normal cardiac oscillations, often described as a thumping or beating sound. For example, the first (S1) and second (S2) cardiac oscillations are produced by the closing of the atrioventricular (AV) valves and semilunar (SL) valves, respectively. More specifically, the S1 oscillation represents the closing of the AV valves, which include the tricuspid valve located between the right atrium and right ventricle, and the mitral valve located between the left atrium and left ventricle. The S2 oscillation represents the closing of the SL valves, which include the pulmonary valve located between the right ventricle and pulmonary artery, pumping blood to the lungs for oxygen, and the aortic valve located between the left ventricle and aorta, pumping the oxygenated blood back to the body.

[0119] Cardiac systole refers to the portion of the cardiac cycle when the ventricles contract. Cardiac diastole is the portion of the cardiac cycle when the ventricles relax and blood is replenished after systole. Similarly, atrial diastole is the period when the atria relax. During ventricular diastole, the pressures in the left and right ventricles decrease from their peak levels during systole (e.g., 120 mmHg in a normal heart). When the pressure in the left ventricle falls below the pressure in the left atrium, the mitral valve opens, allowing stored blood from the atria to flow into the ventricles.

[0120] When the smaller upper atrial cavity contracts during late diastole, it pumps blood into the larger lower ventricular cavity. Once the lower ventricular cavity is filled and the valves to the atria close, the ventricles undergo isovolumetric contraction (contraction of the ventricles while all valves are closed), exhibiting the first stage of cardiac systole. The second stage of cardiac systole pumps blood from the left ventricle to the aorta and limbs of the body, and from the right ventricle to the lungs. Thus, the atria and ventricles contract in an alternating order. The left and right atria supply blood to the ventricles simultaneously. Then, the left and right ventricles contract simultaneously as well.

[0121] Table 1 below shows an overview of the cardiac cycle. Table 1 [Table 1]

[0122] In addition to S1 and S2 vibrations, S3 and S4 vibrations may be detected by high-sensitivity sensors such as vibration sensors. Generally, a physician performing a heart auscultation (for example, listening to internal cardiac vibrations with a stethoscope) will not be able to hear S3 vibrations in healthy adults.

[0123] The third cardiac oscillation, S3, is an oscillation that occurs immediately after the two normal cardiac oscillations (i.e., S1 and S2), which produce a "thump-thump" sound. S3 oscillations typically occur at the beginning of the mid-third of diastole, approximately 0.12 to 0.18 seconds after S2. This creates a classic rhythm that is compared to the tone of the word "Kentucky," where the last syllable indicates an S3 oscillation. S3 oscillations are lower in pitch than S1 or S2 oscillations because they do not originate from the heart valves. While S3 oscillations are generally harmless in young people, some trained athletes, and sometimes pregnant women, if S3 oscillations reappear later in life, they may indicate a cardiac disorder, such as left ventricular failure, as seen in diastolic congestive heart failure (CHF). S3 oscillations are thought to be caused by the reciprocal oscillation of blood between the ventricular wall and the blood rushing in from the atria. The reason why the third cardiac oscillation may not occur until the mid-third of diastole is likely because, during the early stages of diastole, the ventricles may not be sufficiently filled to generate enough pressure for the oscillation to occur. Generally, in indirect examination with a stethoscope, S3 is associated with heart failure because the detection of S3 with this indirect examination method means that the ventricles are stiffer than in a normal heart where the oscillation of blood hitting the ventricular wall is audible.

[0124] The intensity of the third cardiac vibration (S3 intensity) is based on the intensity and duration of the vibration. For example, a highly sensitive vibration sensor configured to detect S3 vibrations may provide an S3 vibration intensity value in the range of 0 to 10. In some implementations, reporting may indicate the presence of S3 if this intensity value is equal to or greater than 5.0.

[0125] The fourth cardiac oscillation, S4, is produced by the vibration of blood rushing into a hardened or hypertrophic ventricle. When heard on a stethoscope, S4 oscillation is a sign of pathological conditions such as systemic hypertension, severe aortic stenosis, and hypertrophic cardiomyopathy, commonly seen in left ventricular failure or left ventricular hypertrophy. It occurs immediately after atrial contraction at the end of diastole and just before S1 oscillation, sometimes creating a rhythm known as the "Tennessee" gallop.

[0126] As described above, wearable medical devices can be configured to monitor other physiological parameters of a patient in addition to cardiac-related parameters. In certain implementations, wearable medical devices can be configured to monitor using vibration sensors, such as microphones and / or accelerometers, located on the patient's chest area. In some implementations, vibration sensors can be configured to detect cardiac vibrations (S1, S2, S3, and S4 vibrations, heart murmurs), lung vibrations, respiratory / chest wall movements, sleep-related parameters (e.g., snoring, sleep apnea), and other similar vibration-based parameters.

[0127] Figure 7 shows a schematic diagram of a sample including a vibration sensor 700. In implementation, the vibration sensor 700 may include a hi-fi diaphragm 705, for example, a diaphragm based on a dynamic electret capacitor, ribbon base, or piezoelectric crystal. Multiple motion sensors 710 (e.g., at least two, four, six, or more) may be separately arranged around the periphery of the diaphragm 705. Vibration signals from the diaphragm 605 and the multiple motion sensors 710 may be digitized by a series of analog-to-digital converters (ADCs) 715 and processed via a digital signal processing unit 720. For example, the digital signal processing unit may include a series of digital filters.

[0128] For example, the motion sensor 710 may include a multi-axis accelerometer that generates a digitized signal that is input to the digital signal processing unit 720 along with the digitized signal of the diaphragm.

[0129] Signals from one or more of the multiple motion sensors 710 may be used to monitor low-frequency vibrations, such as respiratory movements and / or chest wall movements.

[0130] When monitoring vibration signals in the high-frequency range (e.g., specific lung vibrations, heart murmurs, etc.), the diaphragm signal may be analyzed as described below. To enable better separation of frequencies of interest, signals from peripheral motion sensors 710 may be summed to determine a common-mode signal. The common-mode signal can then represent low-frequency components that can be excluded from the diaphragm signal.

[0131] Tables such as Table 2 shown below may be stored in the memory of the sensor 700. A typical sampling rate in the range of 44.1 kHz to approximately 60 kHz can be implemented in the ADC to convert the acquired diaphragm vibration signal into a digital vibration signal. In some examples, the ADC 715 may implement a sample size in the range of 12 bits to 16 bits with a high bit length, enabling more dynamic distance resolution. Various digital filters may be performed on the digital input signal to eliminate interference signals, such as the 60 Hz component described above and common-mode rejection signals. The digitized vibration signal can then be analyzed to determine various vibrations based on the table. For example, frequency-selective filters and frequency-selective circuits may operate in the digital domain to isolate the frequency range of interest according to the table below. Exemplary digital filtering techniques may include, in particular, the Fast Fourier Transform (FFT), Discrete Cosine Transform (DCT), and Infinite Impulse Response (IIR) filters. The processor may be configured to receive instructions indicating the type of symptom to be monitored. Based on the symptoms indicated, the processor 725 may retrieve the relevant frequency range from memory and instruct the digital signal processing unit 720 to isolate the relevant signals for analysis and input them to the next stage. Table 2 [Table 2]

[0132] In certain implementations, vibration analysis of vibrations detected via a chest vibration sensor, such as the sensor 700 described above, may provide information about characteristic vibration patterns. Vibration analysis may include monitoring vibrations ranging from 1 / 10 Hz to approximately 1 Hz to monitor low-frequency thoracic movements, such as respiratory movements, chest wall movements, and, in some cases, cardiac wall movements. For example, if the sensor is substantially aligned with the patient's ventricular apex, a sensor implementing vibration analysis may detect and monitor ventricular wall movements. Similarly, other vibration patterns may be monitored.

[0133] In certain implementations, multiple frequency ranges of lung oscillations may be monitored simultaneously. For example, obstruction can produce chest oscillations such as paradoxical breathing. During inhalation, the diaphragm descends to its limit, pushing and expelling the contents of the abdominal cavity, creating negative pressure. This negative pressure pulls the chest wall inward, resulting in abdominal expansion and chest sagging during inhalation. This is the opposite movement to normal breathing. During exhalation with paradoxical breathing, the chest expands and the abdomen sags. Again, this movement is the opposite of normal breathing. The more flexible the chest wall becomes, as seen in infants, the easier the chest movements become to observe. With paradoxical breathing, the jaw is pulled further back with each breath as the tongue is retracted into the airway, often resulting in noisy breathing. Patients may exhibit, for example, wheezing, snoring, and / or grunting. Therefore, wheezing-related frequencies (>500 Hz) can be monitored by very low-frequency vibrations (0.2 Hz) of the chest wall and / or abdomen, which may indicate paradoxical respiratory movements.

[0134] For example, certain lung vibrations range from approximately 100Hz to 5000Hz (e.g., tracheal vibration), >500Hz (e.g., wheezing), >100Hz to 5000Hz (e.g., wheezing sounds), 〜They have characteristic patterns of various frequencies, including 150 Hz (e.g., blisters) and <350 Hz (e.g., pleural friction). Figure 8 shows various characteristic patterns of specific lung vibrations. As shown in Figure 8, the list of breath sounds 802 may have one or more associated amplitude-time plots 804. Each breath sound 802 may contain a unique set of acoustic characteristics. For example, as shown in Figure 8, normal lung vibrations may be characterized as low-pass filtered noise with a common frequency of 100 Hz–1000 Hz where the measured energy drops to 200 Hz. Various other lung vibrations, such as wheezing, wheezing, blisters, and pleural friction, have similar characteristics as shown in Figure 8. Similarly, each breath sound 802 may have associated amplitude-time plots 804, shown in Figure 8 as two non-extended-time plots 806 and an extended-time plot 808. For example, as shown in Figure 8, the prolonged time plot 808 of a particular breath sound 802 may correspond to a portion of the non-prolonged time plot 806, indicated by the dashed box. Additional pulmonary symptoms such as crackles, squawks, glottal and pharyngeal vibrations, and other similar pulmonary vibrations, as well as their corresponding frequencies, can be cited from A. Bohadana, G. Izbicki, and S. Kraman, authors of "Fundamentals of Lung Auscultation" in the New England Journal of Medicine (2014).

[0135] The frequencies associated with cardiac vibrations and heart murmurs generally fall within the range of approximately 20 Hz to 500 Hz. Low-frequency cardiac vibrations are those with dominant frequencies below approximately 100 Hz, such as S3, S4, and diastolic murmurs in mitral stenosis. Certain heart murmurs have high-frequency components, such as aortic regurgitation, with a dominant frequency of approximately 400 Hz. Patient metric analysis for tracking patients' health status

[0136] As described above, in the various scenarios relating to this disclosure, the patient monitoring system may include sensors configured to collect physiological signals from the patient other than ECG signals. For example, a vibration sensor may be configured to collect bio-vibrational signals such as cardiac and lung vibration signals. Furthermore, radio frequency sensors, such as ultra-wideband transceiver circuits, may be configured to collect information corresponding to radio frequency electromagnetic energy reflected from the patient's thoracic cavity and / or heart. In the implementations described herein, the processing device may further process the various signals and associated information collected from the various underlying physiological sensors to produce one or more combined physiological parameters, e.g., physiological parameters determined based on two or more various underlying physiological sensors and associated information. At least one of predictive analysis (e.g., using machine learning processes or artificial neural networks) and trend analysis (e.g., correlation analysis) may be performed on the collected signals and received information, as well as the combined metrics, to determine the patient's current symptoms and one or more clinically usable events.

[0137] More specifically, in a particular implementation, the patient monitoring system may include an ECG sensor connected to the patient and configured to detect one or more ECG signals from the patient; a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals from the patient; an ultrawideband radio frequency transceiver circuit connected to the patient and configured to direct radio frequency electromagnetic energy into the patient's thoracic cavity and receive it via the radio frequency antennas, and to generate radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the patient's thoracic cavity; and one or more processors. The one or more processors may be configured to process a) one or more ECG signals, b) one or more cardiac vibration signals, and c) radio frequency information to generate a plurality of physiological parameters of the patient, including one or more combined physiological parameters. One or more processors may further be configured to determine the patient's current clinical symptoms by performing at least one of a predictive analysis and a trend analysis of multiple physiological parameters, including combined physiological parameters, wherein the trend analysis determines the existence of substantial relationships between changes in the multiple physiological parameters, to determine one or more clinically usable events by comparing the patient's current clinical symptoms to predetermined clinically usable criteria, and to cause an output device to provide an output regarding one or more clinically usable events.

[0138] In another implementation, the patient monitoring system may include at least one vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals, at least one ultrawideband radio frequency transceiver connected to the patient, and one or more processors. The at least one ultrawideband radio frequency transceiver may be configured to direct radio frequency electromagnetic waves towards the patient's lungs and to detect radio frequency information in response to the radio frequency electromagnetic waves that have passed through the lungs. One or more processors may be configured to process the detected one or more cardiac vibration signals over a predetermined period of time to determine at least one cardiac vibration metric of the patient, process the patient's radio frequency information over a predetermined period of time to determine at least one pulmonary fluid metric of the patient, and determine outputs for one or more clinically usable events based on the determined at least one cardiac vibration metric and the determined at least one pulmonary fluid metric, and to cause an output device to produce an output.

[0139] In another implementation, the patient monitoring system may include an ECG sensor connected to the patient and configured to detect one or more ECG signals from the patient; a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals from the patient; an ultrawideband radio frequency transceiver circuit connected to the patient and including one or more radio frequency antennas; and one or more processors. The ultrawideband radio frequency transceiver may be configured such that one or more radio frequency antennas direct radio frequency electromagnetic energy into the patient's thoracic cavity and receive it through one or more radio frequency antennas, generating radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the patient's thoracic cavity. One or more processors may be configured to process one or more ECG signals, one or more cardiac vibration signals, and radio frequency information to generate multiple physiological parameters of a patient, including one or more combined physiological parameters; to perform trend analysis of the multiple physiological parameters, including the combined physiological parameters, to produce trend results; to update the patient's monitoring schedule based on the trend results; to determine the patient's current clinical symptoms based on the trend results; to determine one or more clinically usable events by comparing the patient's current clinical symptoms with predetermined clinically usable criteria; and to cause an output device to output information regarding one or more clinically usable events.

[0140] In another implementation, the patient monitoring system may include an ECG sensor connected to the patient and configured to detect one or more ECG signals from the patient; a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals from the patient; an ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and positioned on at least one of the patient's aortas; and one or more processors. The ultra-wideband radio frequency transceiver circuit may be configured such that one or more radio frequency antennas direct radio frequency electromagnetic energy toward at least a portion of the patient and receive it via one or more radio frequency antennas, generating radio frequency information corresponding to reflected radio frequency electromagnetic energy reflected from within at least a portion of the patient. One or more processors may be configured to process one or more ECG signals, one or more cardiac vibration signals, and radio frequency information to generate multiple physiological parameters of a patient, including one or more combined physiological parameters; to perform at least one of predictive analysis and correlation analysis of the multiple physiological parameters, including the combined physiological parameters, to determine the patient's current clinical symptoms; to determine one or more clinically usable events by comparing the patient's current clinical symptoms with predetermined clinically usable criteria; and to cause an output device to provide an output regarding one or more clinically usable events.

[0141] As described herein, one or more processes may be used to perform predictive and trend analysis of patients. For example, a predictive analysis process may be generated for various different cardiac diseases that utilizes data from a patient's medical device, including information on recorded ECG data, recorded vibration data, and radio frequency information collected for the patient. The predictive analysis may be used to determine the patient's current symptoms, any clinically usable events, and the likely outcomes for the patient. Figure 9 shows a sample overview of a predictive analysis process. A set of metrics 900, including metric 1, metric 2, and metric 3, may be provided to the predictive process 905. Depending on the design of the processing and the predicted output, various types of programming may be used for the predictive process 905. For example, the predictive process 905 may utilize machine learning and / or artificial neural networks, both of which are described in more detail below. By processing the input metrics 900, the predictive process 905 may produce one or more outputs 910. For example, output 910 may include the patient's current symptoms, any likely adverse events that may occur to the patient in the near future (e.g., cardiac events that may occur within the next 30 days), and any clinically usable events that the patient should take or that concern the patient. In some implementations, output 910 may provide feedback to the prediction process so that the process learns from the results and adjusts the prediction score based on changes in the patient's symptoms.

[0142] Figure 10 shows a sample overview of a trend analysis process. Process 1000 may include monitoring a first metric 1005. If a change is detected in the first metric 1005, or if the first metric exceeds a certain threshold, process 1000 may trigger monitoring of a second metric 1010. Similarly, if a change is detected in the second metric 1010, or if the second metric exceeds a certain threshold, process 1000 may trigger monitoring of a third metric 1015. If process 1000 detects a change in the third metric 1015, the process may output a signal 1020 to, for example, the patient or the patient's physician. For example, the output may include a recommended change in the treatment plan, such as changing the patient's medication. As shown in the figure, the output 1020 may be fed back to the trend analysis process to adjust its response to the change in the underlying metric.

[0143] Please note that the summaries shown in Figures 9 and 10 are for illustrative purposes only. For example, three metrics are shown in both summaries as an example of the number of metrics that may be used. In practice, a variety of other input metrics may be used in both predictive and trend analysis processes.

[0144] In one implementation of the general concept shown in Figures 9 and 10, metric 1 is an ECG metric, metric 2 is a biovibration metric (including cardiac vibration, pulmonary vibration, and low-frequency patient motion data), and metric 3 is a radio frequency-based physiological metric. Alternatively or additionally, one or more of metrics 1, 2, and 3 include a combination metric derived from one or more of the ECG metric, biovibration metric, and radio frequency-based physiological metric.

[0145] Figures 11 and 12 illustrate a patient monitoring system that indicates clinically usable events based on changes in the patient's physiological information. The system can make decisions, analyses, and / or classifications and provide notifications regarding clinically usable events according to predetermined clinically usable criteria.

[0146] As shown in Figure 11, the system 1100 receives various signals from the patient 1105. For example, the system 1100 may receive the patient's ECG signal 1110, bio-vibration signal 1115, and radio frequency signal 1120 from a wearable medical device connected to the patient 1105. As shown in the figure, the output 1155 of the predictive analysis classifier or trend analysis classifier 1150 may be fed back to the predictive analysis classifier or trend analysis classifier 1150 in a closed loop. For example, monitoring may begin with only one set of physiological parameters, such as the ECG signal 1110. Over time, or in response to specific symptoms as described herein, additional sets of physiological parameters other than the ECG parameters may be initiated, such as the bio-vibration signal 1115 or the radio frequency-based signal 1120 (or a combination of these parameters).

[0147] In certain implementations, the ECG signal 1110 may be processed to result in progression to ECG-based metrics 1125, including but not limited to heart rate, heart rate variability, ST elevation, ventricular premature contractions (PVCs), heart rhythm morphology, and other similar ECG metrics. Specific details of the extraction of ECG-based metrics 1125 are described in more detail below. Similarly, the bio-oscillation signal 1115 may be processed to result in progression to bio-oscillation metrics 1130, including cardiac oscillatory intensity values, lung oscillatory intensity values, LVST values, and other similar bio-oscillation values. Furthermore, the radiofrequency signal 1120 may be processed to result in progression to radiofrequency metrics 1135, including pleural effusion volume, cardiac wall motion metrics, and blood pressure. Metrics 1125, 1130, and 1135 may be integrated into a single set of physiological metrics 1145.

[0148] Furthermore, the above physiological metrics may be expanded to include combined physiological metrics. For example, a combined physiological metric may include metrics derived from two or more metrics 1125, 1130, and / or 1135. An example of a combined physiological metric is EMAT. EMAT represents a numerical representation of the time from the onset of the Q wave in the ECG signal, determined from the S1 cardiac oscillatory signal, to mitral valve closure. Generally, long-term EMAT values ​​are associated with reduced left ventricular contractility. Another example of a combined physiological metric is percentage EMAT (%EMAT). %EMAT is calculated as EMAT divided by the major RR interval in the ECG signal and indicates the efficiency of the heart's pumping function. A %EMAT >15% can adequately predict the risk of readmission due to heart failure at the time of patient discharge and after discharge. In the example, cardiac sound oscillatory parameters derived from cardiac or chest oscillatory signals include LVST. LVST can be calculated as the interval from S1 to S2 (S1-S2). Combined metrics based on LVST and RR interval information from a patient's ECG signal may include %LVST. For example, %LVST may be calculated as the ratio of the S1-S2 interval to the RR interval (e.g., S1-S2 / RR). Another example of a combined physiological metric is the EMAT / LVST ratio, which is useful in determining the degree of left ventricular dysfunction. Another example of a combined physiological metric is the systolic dysfunction index (SDI). The SDI is a multiplicative combination of ECG parameters and oscillatory parameters. The SDI is used to predict left ventricular systolic dysfunction with high specificity. The multiplicative score of the SDI is obtained from QRS duration, QR interval, %EMAT, and S3 oscillatory intensity. The SDI is reported as a value from 0 to 10. Other combined metrics may include %LVST, left ventricular end-diastolic pressure (LVEDP), and other relevant combined metrics obtained from two or more physiological metrics described herein.

[0149] Referring again to Figure 11, in some examples, physiological metrics 1145 may extend along with patient demographic information and patient medical history information 1140. For example, patient demographic information may include age, sex, race, etc. For example, patient medical history information may include previous illnesses, diagnoses, previous hospitalization periods, etc. A sample patient medical history record may include the information shown below, and sample inputs to the patient monitoring system are further shown in Table 3 below. Table 3 [Table 3]

[0150] In some implementations, an additional set of physiological metrics may be obtained based on patient activity test data1142 from one or more physical activity tests performed by a patient wearing a wearable medical device. For example, the device may monitor one or more activity tests performed by a patient, as shown below. In one example, the physical activity may be a physician-instructed physical assessment, such as an activity assessment of the WalkTest® administered by LifeVest®'s WCD. The purpose of the assessment is to monitor the patient's process during the assessment, monitoring parameters such as the number of steps taken by the patient, the distance covered during the assessment, and the speed of movement while the patient walks for approximately six minutes.

[0151] Before and after walking, patients may be asked to complete a health survey answering one or more questions about their overall health. For example, a patient may be asked to indicate their level of shortness of breath (e.g., an exemplary scale where 0 = normal sensation, 0.5 = able to maintain conversation while walking, 1 = may need to stop immediately). Another query may concern the patient's level of fatigue (e.g., how tired the patient feels). After the assessment, patients may be prompted to answer the same set of questions again, or additional questions. Responses to these questions may be normalized to a set of physiological parameters, for example, in the range of 0 to 1, 0 to 10, 0 to 100, or any other appropriate range, and stored as values ​​that can be entered into predictive and / or trend analyses. While numerical ranges are described herein, other scales, ranges, and / or methods may be used to quantify a patient's responses to a health survey. The patient's physician prescriber may have the patient repeat the assessment once a day or once a week. The device may remind the patient via the user interface when the next assessment is scheduled. While the health surveys described herein involve physical assessments, in some implementations, health surveys may be performed on the patient wearing the device separately from the physical assessment. For example, the device may prompt the patient to perform health surveys periodically (e.g., daily, weekly, or on another schedule). In some examples, the patient's physician may configure the device to perform health surveys as needed. In such cases, the patient's physician may instruct a technician to send one or more operational commands to a remote server to the wearable medical device to perform a health survey.

[0152] The distance walked over an evaluation duration (e.g., 6 minutes) may indicate the patient's current clinical state. For example, a patient who walks less than a predetermined duration (e.g., 350 meters) may be scored as having a relatively higher risk of death compared to a patient who walks 350 meters or more. In some cases, the input to predictive and / or trend analyses may be the raw distance the patient walks. In other cases, the distance may be normalized according to a predetermined scale. For example, a normalized scale may be generated that shows the distance the patient walks during the activity. For example, a scale from 0.0 to 1.0 showing the distance walked is shown in Table 4 below. Table 4 [Table 4]

[0153] In some cases, changes in measured distance may occur when a clinician inputs stride length into the device via a user interface and the device uses the stride length provided by the clinician. In some implementations, normalized stride length (e.g., based on similar patient population data) may be used when calculating the distance traveled.

[0154] Additionally or alternatively, the device may track the number of steps taken by the patient over an evaluation period (e.g., 6 minutes). Accelerometer data may be analyzed, for example, to count heel strikes (which may be detected, for example, when the sum of the three measurement axes of the accelerometer exceeds a preset threshold). For example, a scale from 0.0 to 1.0 indicating the number of steps taken is shown in Table 5 below. Table 5 [Table 5]

[0155] In some cases, the input to predictive and / or trend analysis may be the patient's raw step count. In other cases, the step count may be normalized according to a predetermined scale.

[0156] Other parameters that can be tracked include pace during evaluation, e.g., steps per minute and / or distance traveled per minute. As previously stated, in some examples, the input to predictive and / or trend analysis may be the patient's raw pace information. In other examples, the pace may be normalized according to a predetermined scale. For example, during the normalization process, these metrics may be converted and stored as values ​​in the range of 0 to 1, 0 to 10, 0 to 100, or any other appropriate range, and can be input to predictive and / or trend analysis. Numerical ranges are described herein, but other scales, ranges, and / or methods may be used to quantify patient metrics. Additional patient metrics are: • Heart rate during evaluation (average, maximum, expected, mode) • Respiratory rate during evaluation • Whether the patient completed the test (completed / not completed), or what percentage of the test was completed. • The patient performed a walking test; could this be an indicator that the patient has the problematic / worsened symptoms? It may include.

[0157] As described above, all physical activity assessment metrics can be normalized according to a predetermined scale and input into predictive and / or trend analysis.

[0158] In some implementations, in addition to or alternative to the above, the patient's overall performance on physical assessments such as the WalkTest® may be scored on a normalized scale. The overall performance score may be based, for example, on individual scores for each component of the physical assessment as described above, as well as information on the health assessment. For example, the overall performance may be graded on a scale ranging from 0 to 1, as shown in the table below. Table 6 [Table 6]

[0159] Referring again to Figure 11, the entire dataset of physiological metrics 1145 is sent to the predictive analysis classifier or trend analysis classifier 1150, which generates output 1155. Now referring to Figure 12, as shown in system 1200, the output 1155 of the predictive analysis classifier or trend analysis classifier 1150 may include a score indicating the patient's current overall clinical symptoms 1205. If the patient's grade is worsening, for example, if the clinical symptom score has a worsening trend and / or exceeds a threshold, the system may prompt specific actions. For example, the classifier may output a score from 0 to 1 indicating the patient's overall symptoms, with scores at the lower end of the scale (e.g., 0.0 to 0.25) indicating a patient in a stable state with no concerns, and scores at the upper end of the scale (e.g., 0.50 or higher) indicating a patient in an unstable state requiring close monitoring (e.g., indicating a potential for adverse events). For example, these adverse events may include one or more of the following: arrhythmic events (VT / VF), seizure events, syncope events, and hospitalization events. Based on the patient's current health status 1205, the system 1200 may generate recommended clinically usable events, such as adjustments to the patient's treatment plan 1210, and send the generated recommendations to caregivers such as a physician 1220.

[0160] In certain implementations, information regarding changes in the treatment plan may be fed back to the predictive analytics classifier or trend analytics classifier 1150, as shown in Figure 11. Such a feedback loop may provide improvements to the predictive analytics classifier or trend analytics classifier 1150, including information regarding changes in the treatment plan and the patient's response to those changes.

[0161] Additionally or alternatively, to observe trends in output scores, scores may be subject to one or more threshold conditions. For example, threshold conditions may trigger one or more clinically usable events. Table 7 below provides an exemplary set of patient health status score categories, threshold ranges, and patient current health status information. Table 7 [Table 7]

[0162] In some implementations, the above score categories may be part of a specific scoring scheme to be implemented in a specific device according to the embodiments described herein. In other specific implementations, this process may classify patients according to the grading of heart failure adopted by a physician or hospital association, society, or other regulatory authority. For example, such authorities may be the American College of Cardiology (ACC), the American Heart Association (AHA), and the New York Heart Association (NYHA). In this regard, the device may automatically classify patients into the appropriate grade and / or stage of heart failure based on a similar scoring scheme to the above. In some implementations, the user may configure in advance, via a user parameter set, which grading scheme the device will implement. For example, during setup, the user may be prompted to indicate a grading scheme according to one or more of the following options. The user can select these options via the user interface (e.g., locally on the device, or via remote configuration parameters on a server then sent to the device). • Unique scoring method (as described above) ·ACC / AHA method ·NYHA method You may show this.

[0163] The ACC / AHA method can be implemented as follows:

[0164] Stage A includes patients at risk of heart failure who have not yet developed structural cardiac changes (i.e., patients with diabetes who have not previously experienced infarction, and patients with coronary heart disease).

[0165] Stage B includes patients with structural heart disease (i.e., low ejection fraction, left ventricular hypertrophy, left ventricular dilation) who have not yet developed symptoms of heart failure.

[0166] Stage C refers to patients who have developed clinical heart failure.

[0167] Stage D refers to patients with refractory heart failure requiring advanced interventions (i.e., biventricular pacemakers, left ventricular assist devices, or transplant surgery).

[0168] The techniques described above can be used to map scores from the processes taught herein to the stages defined in the ACC / AHA scheme. For example, Table 8 below shows the correlation between the scoring techniques described above and the ACC / AHA scheme implementation. Table 8 [Table 8]

[0169] The NYHA model can be implemented as follows: The NYHA classifies each diagnosis into four grades. Grades I and II are considered mild. Grade III is considered moderate, and Grade IV is severe. In Grade I, there are no limitations on physical activity. Patients generally do not complain of fatigue or shortness of breath. Patients can still control their condition. Regular exercise, limiting alcohol consumption, and a healthy diet (moderate sodium intake) are all possible actions that can be taken early on. High blood pressure may need to be treated. Smoking cessation is essential.

[0170] In cases of Grade II heart failure, patients will experience some limitations in daily physical activities such as bending forward or walking. Patients may experience fatigue and shortness of breath. Non-invasive surgical interventions (depending on the patient), such as angiotensin-converting enzyme inhibitors or beta-blockers, may be considered.

[0171] Patients with Grade III heart failure experience clear limitations during physical activity. While they may remain pain-free at rest, most physical activities will likely result in excessive fatigue. Under medical supervision, the patient's diet and exercise may be monitored. Diuretics may be prescribed to control fluid retention.

[0172] Patients with Grade IV heart failure experience substantial discomfort during all physical activity. Significant signs of cardiac dysfunction may even be present at rest. Surgical options will be considered, along with the same considerations used for Grades I through III heart failure.

[0173] The techniques described above can be used to map scores from the processes taught herein to the stages defined by the NYHA scheme. For example, Table 9 below shows the correlation between the scoring techniques described above and NYHA scheme implementations. Table 9 [Table 9]

[0174] At any given time, one or more events may be triggered depending on the patient's grade and / or score. These events may be any of the automated events that are triggered without user input. For example, the system may automatically instruct an external medical device connected to the patient (e.g., a wearable defibrillator) to increase the sensitivity of detection processing during periods when the patient may be at high risk of sudden cardiac arrhythmia events. Alternatively, the system may output information about the patient's current symptoms and instruct caregivers and / or other persons to take action. Such actions may include changing the patient's treatment plan, such as changing medication dosages, or recommending that the patient be placed under high-level monitoring or admitted to a hospital.

[0175] For example, clinically applicable events may include, but are not limited to, external medical devices (e.g., wearable defibrillators), such as triggering controller changes to shorten the time from detection to treatment of sudden cardiac arrest. Furthermore, by detecting high-risk score categories, the system may prompt the patient, physician, responsible third party, medical team, and / or technical support to be notified of the change in risk. In this way, patients in high-risk score categories may be given attention to be monitored more frequently in the future and / or to have their treatment plan modified.

[0176] In some implementations, if a patient's clinical condition worsens, caregivers and / or technical support personnel may initiate real-time or near-real-time streaming of the patient's ECG data (and / or other physiological data) from an external medical device to a remote server for additional monitoring and analysis. For example, as shown in Figure 12, if the patient's current health status 1205 indicates a worsening of symptoms, the system may send the indication to the remote server to perform various notifications and / or analytical actions 1215.

[0177] In some cases, reporting and / or metric measurement, and the analysis period for such patients may be extended (e.g., from once every few hours or more to once every hour). In some cases, additional monitoring and / or reporting of the patient's symptoms and various physiological parameters may be initiated during periods of concern regarding the patient's symptoms (e.g., until the patient's symptoms stabilize or improve).

[0178] In some implementations, if a patient's symptoms are worsening but have not yet reached a predetermined critical threshold, meaning immediate action is not considered necessary (for example, if the classifier scores the patient's current health status as 0.5 or higher in the above example, but 0.65 or lower), physicians or technical support personnel may begin reporting the patient's physiological status more frequently (e.g., medically reporting the patient's symptoms) or begin streaming ECG data. Furthermore, if the patient falls into score category 3 (e.g., 0.5 or higher), physicians or technical support personnel may take additional actions, including, for example, instructing the patient to check external medical devices more frequently and / or ensuring that downtime for continuous monitoring is kept to a minimum.

[0179] If a patient in score category 4 has a high level of insufficient contraction, the actions that may be taken are not limited to notifying the patient and a responsible third party to seek a medical diagnosis, and notifying the responsible medical team of the patient's dangerous condition.

[0180] Treatment plan adjustments (1210) may be based on changing the medications administered to the patient to control and / or address the underlying pathology or symptoms of the patient's heart failure. As previously mentioned, heart failure is generally a long-term chronic disease that can worsen over time. Under the ACC / AHA system, there are four stages of heart failure (stages A, B, C, and D). As a patient's symptoms worsen, the patient's myocardium tends to pump less blood to the organs, and the patient progresses to the next stage of heart failure. In a standard treatment plan, the goal of HF treatment is to prevent the patient from progressing through the stages or to slow the progression. Treatment at each stage of heart failure may involve changes in medications, lifestyle behaviors, and cardiac devices. In various implementations, patient monitoring systems may base their recommendations on ACC / AHA or NYHA treatment guidelines. Basic treatment plans that may be applied to patients according to stage / grade are described below.

[0181] Depending on the implementation, a patient monitoring device and / or patient monitoring system may recommend one or more of the following actions. These actions may be recommended directly to the patient through the user interface of the device. In some cases, the proposed treatment plan and / or changes to the treatment plan may be recommended to the patient's primary caregiver and / or attending physician.

[0182] A typical ACC / AHA stage A is considered early heart failure. At this stage, patients are monitored for signs of hypertension, diabetes, coronary artery disease, metabolic syndrome, a history of alcoholism, a history of rheumatic fever, a family history of cardiomyopathy, and a history of taking medications that may damage the myocardium, such as certain anticancer drugs. An exemplary stage A treatment plan that a patient monitoring system may recommend includes: • Perform only ECG monitoring. The monitoring device does not need to initiate bio-vibration and / or radio frequency-based TFC monitoring of the patient. • Regular exercise, staying active, and daily walking ·no smoking • Treatment of hypertension (medication, low-sodium diet, active lifestyle) • Treatment for high cholesterol • Abstain from alcohol or do not use energy-boosting drugs. • Drug therapy: If the patient has coronary artery disease, diabetes, hypertension, or other vascular or heart disease, angiotensin-converting enzyme inhibitors (ACE-Is) or ARB-type antihypertensive drugs (ARBs) may be prescribed. If the patient has hypertension, beta-blockers

[0183] ACC / AHA Stage B is considered early heart failure. This means that the patient has been diagnosed with at least left ventricular systolic dysfunction, but has never presented with symptoms of heart failure. Most people with Stage B heart failure may have an echocardiogram showing an ejection fraction (EF) of less than 40%. This category may include people with heart failure and low EF (HF-rEF) for any cause. An exemplary Stage B treatment plan that a patient monitoring system may recommend includes: • Continue or modify the treatment listed in Stage A. For example, the monitoring device may initiate bio-vibration and / or radio frequency-based TFC monitoring of the patient. For example, you can increase the frequency of TFC measurements. If you were initially measuring TFC on a weekly basis, you can change to measuring it every two or three days. For example, a monitoring device may initiate a physical assessment and / or physical test on the patient. • (If the patient has not yet progressed with the treatment plan as part of Stage A of the patient's condition) Add an angiotensin-converting enzyme inhibitor (ACE-I) or an ARB-type antihypertensive drug (ARB). • Add a beta-blocker if the patient has a heart attack and the patient's ejection fraction (EF) is 40% or less (if the patient has not yet progressed with the treatment plan as part of Stage A). • If the patient has had a heart attack, or if the patient has diabetes and an ejection fraction (EF) of less than 35%, an aldosterone antagonist should be added (to reduce the risk of myocardial hypertrophy and insufficient myocardial pumping function). • To enable wearable defibrillator therapy. Consider possible surgical or interventional treatments for coronary artery occlusion, heart attack, valvular heart disease (in which case the patient may require valve repair or replacement surgery), or congenital heart disease.

[0184] Patients with ACC / AHA stage C are generally diagnosed with heart failure and have shown current or past signs and symptoms of the disease. Many symptoms of heart failure are present. The most common are: ·shortness of breath • Feeling tired (fatigue) • Unable to exercise • Legs become weak • Waking up due to the urge to urinate • Swelling (edema) of the feet, ankles, lower legs, and abdomen. That is the case.

[0185] An example of a Stage C treatment plan that a patient monitoring system may recommend includes the following: Continue or modify the treatments listed in Stage A and Stage B. For example, the monitoring device may initiate bio-vibration and / or radio frequency-based TFC monitoring of the patient (if it is not already doing so). For example, you can increase the frequency of TFC measurements. If you were previously measuring TFC every two to three days, you can change to measuring it daily. For example, a monitoring device may initiate frequent physical assessments and / or physical tests on the patient. • Add a beta-blocker (if the patient is not already taking that medication). • Add an aldosterone antagonist if vasodilators (e.g., ACE inhibitors, ARBs, or a combination of angiotensin receptor / neprilysin inhibitors) and beta-blockers do not alleviate the patient's symptoms (if the patient is not already taking that medication). • Add a hydralazine / nitrate combination if other treatments do not alleviate the patient's symptoms. For example, if a patient's heart rate is higher than 70 beats per minute and the patient is still experiencing symptoms, adding a medication that can lower the heart rate. • If pleural fluid content and / or S3 strength continue to worsen, add diuretics ("diuretics"). • Recommendation to limit sodium (salt) in the diet • Recommendation to track patients' weight daily • Limit fluid intake as much as possible if chest fluid content and / or S3 strength continue to worsen. • Cardiac resynchronization therapy whenever possible (e.g., biventricular pacemakers) • Implantable cardioverter-defibrillator (ICD) treatment whenever possible If treatment improves or prevents the patient's symptoms, the patient may still need to continue treatment to slow progression to stage D.

[0186] Patients with stage D and low ejection fraction (HF-rEF patients) generally have advanced symptoms that do not improve further with treatment. This is generally considered the final stage of heart failure. An exemplary stage D treatment plan that a patient monitoring system may recommend includes: • Continuation and / or modification of treatment as listed in Stage A, Stage B, and Stage C. • Heart transplant • Ventricular assist device • Heart surgery • Continuous intravenous inotropic agent infusion • Pain relief treatment or hospice care ·Treatment research Evaluation of more advanced treatment options, including

[0187] One or more physiological measurements extracted from the ECG signal may include one or more of the following: heart rate, heart rate variability, PVC load or PVC count, activity, noise quantification, atrial fibrillation, transient breath, heart rate irregularity, QRS height, QRS width, changes in morphology size or shape, cosine RT, artificial pacing, modified QT interval, QT variability, T wave width, T wave alternan, T wave variability, ST segment changes, early repolarization, delayed potential, fractional QRS / HF content, and fractional T wave / HF content.

[0188] The control unit can detect reference points in the ECG signal, such as points corresponding to the P wave, Q wave, R wave, S wave, and T wave, and extract individual measurements, such as QRS and PVC, from physiological parameter data. For example, the QT interval may provide a measure of the patient's heart failure, and the distance between the Q point and the T point may be determined and extracted from the physiological parameter signal.

[0189] Figure 13 shows two ECG lead signals, including a plot 1300 for left-right (SS) leads and a plot 1305 for front-back (FB) leads. In a particular implementation, the processing device may be configured to identify various pieces of information within each ECG signal for extraction, such as QRS measurements and PVC parameters. For example, the processing device may apply QRS and PVC detectors to the ECG signals to extract QRS measurement information 1302 and PVC measurement information 1304 from the SS lead plot 1300. The processing device may further extract PVC measurement information 1306 from the FB lead plot 1305, for example.

[0190] In certain implementations, a processing device may use the extracted QRS and PVC measurements determined by the QRS and PVC detectors, and / or reference points, to identify and extract various other measurements or parameters within the ECG signal, such as heart rate variability (HRV), RR interval, etc. For example, the outputs from the QRS and PVC detectors may be utilized by AFIB detectors, breath detectors, pace detectors, morphology detectors, T-wave detectors, and / or any other detectors within a control unit that extract measurements or parameters from the ECG signal. QRS detectors, PVC detectors, and other detectors are well known in the art, for example, as described in The Principles of Software QRS Detection (Kohler, Hennig et al.) in IEEE ENGINEERING IN MEDICINE AND BIOLOGY (January / February 2002), the entire content of which is cited by reference.

[0191] HRV measurement quantifies the temporal variation of the R-wave interval within a patient's electrocardiogram signal. The R-wave of a particular heartbeat corresponds to a point in the cardiac cycle during the early contractile phase, and from the signal processing point in the figure, a reliable reference time is provided for measuring the cardiac cycle interval. HRV is influenced by the autonomic nervous system, which consists of the sympathetic nervous system (SNS) and the parasympathetic nervous system (PNS). Observed HRV is considered an indicator of the dynamic interaction and balance between the SNS and PNS, providing a measure of nervous system capacity. Influenced by the autonomic nervous system, HRV serves as an indicator for diagnosing and evaluating a range of conditions, from congestive heart failure to sleep apnea. For example, reduced HRV has been found to be a precursor to increased mortality in elderly individuals with coronary heart disease. Reduced HRV is also seen after sudden cardiac arrest.

[0192] The variability measurement for HRV is the T-wave alternane, which is a variability measurement during myocardial recovery in the cardiac diastole (relaxation) phase, and measures the variability of the T-wave amplitude in the ECG.

[0193] In one example, extracting HRV data may involve filtering the ECG signal to remove noise and artifacts, placing the QRS group within the filtered ECG signal, finding the RR interval between the continuous R peaks, and processing the RR interval to obtain HRV. For example, a band-pass filter may be used to filter the ECG signal and place the QRS group. A band-pass filter with an operating frequency range wider than the frequency components of the QRS group is required. The frequency components of the QRS group are between 10 Hz and 25 Hz. Therefore, in one embodiment of this disclosure, the operating frequency range of the band-pass filter is approximately 5 Hz to approximately 28 Hz.

[0194] In one example, the R wave may be positioned as follows: The first maximum peak data value occurring in the filtered ECG signal is positioned. Upper and lower amplitude thresholds are determined from the positioned maximum peak value. The peak value and the minimum values ​​on both sides of the peak value are positioned. In this embodiment of the disclosure, both sides refer to the left and right sides of the peak value. It is verified whether the condition is met that the peak value exceeds the upper amplitude threshold and the minimum value falls below the lower amplitude threshold. If the condition is met, the position of the peak value is indicated as the R position. The position of the minimum value occurring closest to the left of the R position is indicated as the Q position, and the position of the minimum value occurring closest to the right of the R position is indicated as the S position. With respect to the time scale displaying the filtered ECG signal, the Q position occurs where the minimum value first occurs before the R position, and the S position occurs where the minimum value first occurs after the R position. Thus, the position of the QRS peak in the filtered ECG signal is determined.

[0195] In one embodiment of the present disclosure, a 1D array of ECG sample points x(n) is provided, and an upper amplitude threshold and a lower amplitude threshold (T upper and T lower The threshold is set after the maximum value (ref peak) is found within the first few seconds of the data. upper =ref_peak+0.4*ref_peak T lower =ref_peak-0.35*ref_peak It is defined as follows. Next, under the following conditions, x(i) is T upper and T lower It is located between, x(i+1)-x(i)<0, x(i)-x(i-1)>0, If the R-peak is at the point of maximum value, then the R-wave is thought to originate at point i.

[0196] The positions of other R waves in the filtered ECG signal may be determined by repeating the process of placing other peak values ​​and other minimums on either side of another peak value. If another peak value exceeds an upper amplitude threshold and both other minimums fall below a lower threshold, the peak value is indicated as the R position. The position of the minimum value occurring closest to the left of the R position is indicated as the Q position, and the position of the minimum value occurring closest to the right of the R position is indicated as the S position. In this way, the positions of other QRS peaks are determined.

[0197] In the example, heart rate variability data may include time-domain data, frequency-domain data, and geometric-domain data.

[0198] Time-domain data may include information on any one or more of the following parameters: mean RR intervals (mean RR), standard deviation of RR intervals (STD), mean instantaneous heart rate (mean HR), standard deviation of instantaneous heart rate (STD_HR), root mean square (RMSSD) of adjacent RR interval differences, number of consecutive RR intervals that differ by 50 ms or more (NN50), and percentage of consecutive RR intervals that differ by 50 ms or more (pNN50).

[0199] Frequency domain data may include information regarding any one or more of the following parameters: power in the very low frequency range (<= 0.04 Hz) (VLF), power in the low frequency range (0.04 Hz to 0.15 Hz) (LF), power in the high frequency range (0.15 Hz to 0.4 Hz) (HF), total power (TP) estimated from the variation of the NN interval within a segment and measured in ms2, ratio of LF power to HF power (LF / HF), LF power within the normalization unit (LF / (TP - VLF)×100 (LF norm ) and HF power within the normalization unit (HF / (TP - VLF)×100 (HF norm ).

[0200] All of the above physiological parameters and metrics regarding the patient's health state are collected as described above. Within the physiological parameter data, one data set need not contain the same number of parameters as another data set for comparison. Further, patient parameters may be stored as digital data converted from the form in which each of the four parameters was first obtained (such as an analog signal), i.e., by the initial form of the obtained measurement. Data on patient characteristics such as demographics and medical history may be transmitted to the system via a wireless network distributed through a hospital or a network of physicians. The prediction analysis process may be trained using all physiological parameters. Further, the process may be trained using the patient's demographics (e.g., age, gender) and medical history information. At the end of the training phase, the parameters found to be most important for achieving high accuracy will then be used as input to the real-time detection system.

[0201] Physiological parameters may be stored in an electronic database. In an example, this data includes a plurality of data sets, each set having at least one of a first parameter regarding heart vibration data and a second parameter regarding a radio frequency-based chest fluid content level. Each of the plurality of data sets further has a third "output" parameter regarding the patient's health state, such as a patient health state score. <,

[0202] The electronic database used to store the patient's physiological parameters may be a memory module such as a hard disk drive, optical disk, or solid-state device. During the training phase of the artificial neural network, the training of the patient's physiological parameters may be obtained from hospital records or from conducting field surveys of a patient pool, in which case the pool includes at least one group of patients designated to function as a control group. Thus, the patient's physiological parameters may include data from patients with various cardiac-related symptoms, patients who may be considered healthy, such as those showing no signs of cardiac disease, and further patients with various demographics.

[0203] A third output parameter is further trained within the process. This parameter may be referred to as an outcome, such as death, other adverse events, recovery from adverse events, or the patient's current health status. The electronic device may incorporate a processor or memory module that stores instructions for implementing the training process, and as a result, the device may analyze the physiological parameters of the patient being examined. The output of the electronic device may then be used to assist the surgeon or medical professional in making appropriate clinical decisions about how to treat the patient by predicting the patient's outcome.

[0204] For example, the process used may depend on the type of medical event to be predicted, and depending on the event, the patient may be classified or categorized into an appropriate heart failure score category (i.e., NYHA grade or ACC / AHA stage). For example, the processing device may be configured to calculate the event assessment of the cardiac arrest risk score using a first process or process, and to calculate the event assessment of the ventricular fibrillation risk score using a second different process or process. Thus, the imminent serious risk of the patient's condition deteriorating to cardiac arrest or other severe cardiopulmonary disease may be calculated in various ways. Event assessments of risk scores over various time periods may be calculated using various methods and processes. For example, the processing device may be configured to calculate the event assessment of the cardiac arrest risk score over a first time period using a first process or process, and to calculate the event assessment of the cardiac arrest risk score over a second set of different time periods using a second different process or process.

[0205] In some implementations, the machine learning classifiers described in more detail below may be trained on a large population, such as a population of thousands or tens of thousands of patient records, including electrophysiological information, demographic information, and medical history information. Machine learning tools may include, but are not limited to, classification tree decision models and regression tree decision models, such as random forests and gradient boosting (implemented using, for example, R, or any other statistical / mathematical programming language). Any other grade-based machine learning tool may be used, including artificial neural networks (described in more detail below) and support vector machines. Since machine learning tools may be computationally intensive, some or all of the processing performed by the machine learning tools may be on a server separate from the medical device.

[0206] An overview of how the Random Forest tool can be applied to a given dataset can illustrate how the Grading tool can function when interpreting a given parameter or metric. A Random Forest is a collection of decision trees. A decision tree is a flowchart-like structure where each node represents a test for a metric, and each branch represents the result of the test. The tree ends with a grading label, such as a decision made at the end after each of the metrics has been calculated. Each tree in the Random Forest tool takes one "vote" when classifying a given set of metrics. There are two components to the randomness involved in building a Random Forest. First, in the generation of each tree, a random subsample of the total dataset is selected to grow the tree. Second, at each node of the tree, a "splitter variable" is selected, dividing the original patients into two grades. For example, patients in one grade (e.g., response or occurrence of sudden cardiac arrest) may be separated from patients in the other grade (e.g., unresponsive). The tree grows with additional splitter variables until all terminal nodes (leaves) of the tree are fully at either one grade or the other. The tree is “tested” against previously set aside patient records. Each patient test record traverses the tree, descending one branch or the other depending on the metrics contained in the record for each splitter variable. Patient test records are assigned a predicted outcome (one vote) based on where the record ends up in the tree. The entire process may be repeated with a new random distribution of the original dataset to generate additional trees and eventually a “forest”. In any case, different subsets of patients may be used to build the tree and test its performance.

[0207] In developing the results described in the following example implementation, a predetermined number of model variations are trained. For example, each model variation is sequentially leveled (e.g., leveled from 1 to 100 for 100 runs). In each run of the model, the software randomly samples a predetermined proportion of the population (e.g., 80%) as the training set and sets aside the remaining portion (e.g., 20%) as the validation set.

[0208] As described above, machine learning tools can train classifiers on a first proportion of the underlying dataset, validate them on a second proportion of the dataset, or on another separate dataset. When evaluating the performance of each classifier, the performance of the basic decisions within the Random Forest decision tree can be evaluated based on specificity and sensitivity parameters. For example, the sensitivity parameter may be based on a measure of the classifier's ability to correctly predict whether a patient is at risk of needing treatment according to an appropriate score category. For example, the sensitivity parameter may be based on the proportion of patients who are adequately treated and at risk of needing treatment, as correctly predicted by the model. The specificity parameter may be based on the proportion of untreated patients and patients who are predicted by the relevant classifier not to be at risk of needing treatment. It may be advantageous to optimize the balance of individual performance variables, such as high levels of sensitivity and specificity. For example, by setting the specificity to a relatively high value, e.g., 95%, the basic threshold within the classifier model may be adjusted to minimize false positives. After specificity is defined, measuring sensitivity may be treated as a type of performance measure, for example, generally in the range of 15% to 35% of a given model. However, smaller or larger sensitivity values ​​are also possible.

[0209] For example, validation protocols can be used to validate the predictive performance of a training model, as described below. In an implementation, the validation phase may be used to determine appropriate threshold scores for classifying future patients (where the outcome is currently unknown and prediction of the outcome is desired), and to determine the predictive performance of each classifier model generated by a machine learning tool. A second group of individuals, such as a validation population (or cohort), may be used to validate various classifiers and associated threshold scores. For example, the validation population used could be a new validation population. The outcomes of patients in the validation cohort are eventually learned as these patients progress towards the end of device use. In one embodiment, the patients in the validation population may differ from the training and test groups of patients described above for training the classifiers. For example, the patient validation population and associated metrics (validation metrics) may be independent of the patient training population and associated metrics (training metrics). In some implementations, there may be overlap between validation metrics and training metrics.

[0210] In some implementations, the validation population may be updated by at least one of the following: 1) adjusting one or more metrics in the validation metric, and 2) expanding the validation metric by adding one or more additional patients to the patient population that constitutes the validation population. Thresholds for classifying future patients may be refined based on the updated validation metric. For example, metrics for patients currently being treated or monitored, or otherwise not progressing towards device decommissioning, may be used to adjust one or more metrics in the validation metric, or patient metrics may be added to the validation population as metrics from new patients. If new metrics for a patient are determined during patient monitoring or treatment, the validation metric may be adjusted. In some examples, when a monitored patient progresses towards device decommissioning, the patient's metrics may be added to the validation population and / or used to adjust metrics in the validation metric after the patient has progressed towards device decommissioning.

[0211] In some implementations, the training population may be updated by at least one of the following: 1) adjusting one or more metrics in the training metrics, and 2) expanding the training metrics based on adding one or more additional patients to the initial group of patients. The machine learning classifier model may be retrained based on the updated training metrics. For example, when additional patient metrics are determined from the current patients and / or metrics are determined from new patients, the machine learning classifier may be retrained, for example, for the increased number of metrics or new and different metrics, to provide an updated classifier model. The training population may be updated when new metrics for the current patients and / or metrics for new patients are determined, or after patients have progressed to the end of device use.

[0212] Figure 14 shows a sample flow 1400 for training and validating one or more classifier models of the machine learning process described above. A set or population of known patient records may be provided when the dataset is used to train and validate the classifier model. For example, a dataset of known patient records may include 1000 patients with a particular type of heart disease, such as VT, their treatment plans, and the outcomes of each of those patients. A percentage of the data from the known patient records may be used as the training dataset 1405. For example, 80%, i.e., 800 patient records, may be used as the training dataset 1405. As described above, the training data 1405 may include various available information from multiple patients, including patient ECG metrics 1125 (see, e.g., Figure 11), biovibration metrics 1130, radio frequency metrics (1135), combined physiological metrics 1145, demographic and medical history information 1140, and patient activity test data 1142. The training data 1405 may include historical information for each training dataset regarding how each training dataset is classified or scored into the appropriate score category (i.e., NYHA grade or ACC / AHA stage).

[0213] The training dataset 1405 can be supplied to the training module 1410. The training module 1410 may contain one or more non-trained data structures, such as a set of data trees (organized, for example, using the random forest tool described above). Using known input variables and known outcomes from the training dataset 1405, the training module 1410 can train its data structures by iterating through each data point in the training set to more accurately produce expected (and known) outcomes.

[0214] When the training module 1410 clears the training dataset 1405, it may output one or more trained classifier models 1415. One or more trained classifier models 1415 may represent a model set, which provides the most accurate grade and generates results for a known set of input variables that can be generated from the training data 1405. The validation module 1420 may further be configured to refine the trained classifier models 1415 with additional patient records. For example, a validation dataset 1425 may be input to the validation module 1420 to validate one or more trained classifier models 1415. To continue the above example, the validation dataset 1425 may contain 200 patient records. In general, there is no overlap between the training dataset and the validation dataset, as there is no benefit to running the same dataset twice.

[0215] As shown in Figure 14, the validation module 1420 may process the validation dataset 1425 to generate one or more validation classifier models 1430. Depending on the intended purpose of the validation classifier model 1430, this model may have the specific specificity or sensitivity described above.

[0216] As a validation classifier model used to classify new patients (for example, to generate new outputs for the patient metric set described herein), the generated results can be used to further validate this process using a closed-loop feedback system. For example, once a patient is classified and treated, the results of that treatment may be included in the patient record and may be validated, for example, by the patient's physician. The patient record, which is updated to include the known results, may then be provided to the validation module 1420 as feedback 1435. The validation module may process the feedback 1435 and compare the generated output with the patient's known results. Based on this comparison, the validation module 1420 may further refine the validation classifier model 1430, thereby providing a closed-loop system in which the model is periodically updated and upgraded.

[0217] In an alternative example, the system process may be implemented as a network of nodes interconnected to form an artificial neural network. For example, Figure 15 shows a topography of a sample artificial neural network 1500. The artificial neural network 1500 may include, for example, one or more nodes consisting of an input layer 1502, a series of hidden layers 1504, and one or more nodes consisting of an output layer 1506.

[0218] In an artificial neural network, a node contains multiple artificial neurons, each artificial neuron having at least one input with associated weights. The artificial neural network can be trained using its physiological parameters such that the associated weights of at least one input for each of the multiple artificial neurons are adjusted in response to first, second, and third parameters, respectively, of different datasets derived from a patient's physiological parameters. This results in an artificial neural network trained to generate a patient's health status score.

[0219] An artificial neural network may be a mathematical or computational model that simulates the structure and / or functional aspects of a biological neural network. In embodiments, a node of the artificial neural network includes at least one input, at least one artificial neuron, and at least one output. A neuron may reside in a single hidden layer of the artificial neural network and may have two or more inputs. In examples where the artificial neural network has multiple neurons, the multiple neurons may be distributed across one or more hidden layers. If multiple layers exist, each layer may be interconnected with the preceding and succeeding layers.

[0220] An artificial neural network may be an adaptive system that changes based on external or internal information flowing through it during a training or learning phase. Specifically, the weights (or strengths) of connections within the artificial neural network (such as between adjacent artificial neurons or between input neurons and artificial neurons) are adapted to change to match known outputs.

[0221] In the example, a first parameter (e.g., S3 oscillation intensity) and a second parameter (e.g., tissue fluid content), or a combination of the first and second parameters, may be classified as feature vectors of the patient's physiological parameters. The artificial neural network may be trained on these feature vectors. The artificial neural network may be implemented as memory-stored instructions that, when executed by a processor, cause the processor to perform the functions of the artificial neural network. In embodiments of this disclosure, the artificial neural network may be based on a support vector machine architecture, where the associated weights of at least one input of each of a plurality of artificial neurons are initialized from a library used by the support vector machine.

[0222] A support vector machine may have a set output that includes a decision function, which is given by the following: [Math 1] In the formula, sgn() is the sign function, (x, xi) is a pair of feature vectors, k(x, xi) is the kernel matrix constructed by x and xi, yi is 1 or -1, which is the label of the feature vector xi, and αi and b are the parameters of the artificial neural network.

[0223] For example, the artificial neural network may be based on an extreme learning machine architecture, where the associated weights of at least one input for each of the multiple artificial neurons are initialized through random selection by the extreme learning machine. The artificial neural network may be implemented as a single-layer feedforward network, thereby deriving predictions about patient viability from the following function. [Math 2] In the formula, xj is the input vector to one of several neurons for j=1, 2, ..., N input vectors, wi is the associated weight of the input of the neuron receiving the input vector xj, g(wi·xj+bi) is the output of the neuron receiving the input vector xj for i=1, 2, ..., N artificial neurons, βi is the output weight vector associating the i-th hidden neuron with each output neuron, and bi is the bias for the i-th hidden neuron.

[0224] Training of an artificial neural network may be based on backpropagation learning. For example, backpropagation learning may use the Levenberg-Marquardt process. Each of the multiple neurons in the artificial neural network may have an activation function, which is selected from a group of functions including hard limit (hardlim), sigmoid, sine, radial basis, and linear.

[0225] In this example, the results of the artificial neural network may have only two possible outcomes: either the patient's health is stable and good (no adverse events are expected), or the patient needs to be hospitalized (adverse events are expected).

[0226] In an alternative example, physiological parameter data may be divided into many parts. A first parameter set may be about the patient's ECG metrics, a second parameter set may be about the patient's cardiac oscillatory metrics, and a third parameter set may be about the patient's demographics and medical history. The first, second, and third parameter sets are then provided as sets of normalized data values ​​to be input into a scoring scheme. For example, the scoring scheme may assign each category to each parameter in the first, second, and third parameter sets. Each category may have multiple predetermined value ranges, each of which has a predetermined score. The scores for each parameter in the first, second, and third parameter sets are determined by assigning the normalized dataset to each predetermined value range, and by including a set of normalized data values ​​from the multiple value ranges of the categories associated with each parameter in the first, second, and third parameter sets. The total score may be obtained based on the sum of the scores of each parameter in the first, second, and third parameter sets as an indication of the patient's symptoms. The scoring method may be any suitable process or procedure and may be implemented in an electronic database in which scores can be assigned to each value range within each category associated with each parameter in the first, second, and third parameter sets. For example, the scoring method may be based on a mathematical model using logistic regression, such as univariate analysis.

[0227] In the example, the output of the patient's health status score may be a numerical value that can be determined according to statistical information or standard treatment information.

[0228] In addition to using learning processes such as artificial neural networks or machine learning processes as described above, trend analysis can also be used to monitor patients whose symptoms change and to produce outputs such as modifying the patient's treatment plan. In certain implementations, trend analysis may involve determining the existence of substantial relationships between changes in two or more physiological parameters. For example, as described above in relation to Figure 7, detecting a change in one particular metric may trigger monitoring of another metric. This additional monitoring may be performed to confirm the trend of the monitored metric and to provide additional information about the patient's overall symptoms.

[0229] One example of trend analysis is correlation analysis. Correlation analysis quantifies the linear relationship between two variables, and the correlation coefficient can be expressed as a value between negative 1.0 and 1.0, collectively known as Pearson's product-moment correlation coefficient and denoted as r. When the correlation coefficient approaches 1.0, it indicates a strong positive correlation between the two variables. When the correlation coefficient approaches negative 1.0, it indicates a weak negative correlation between the two variables. A correlation value close to zero does not indicate a linear relationship between the two variables.

[0230] In a particular example, there may be two sets of data samples, X and Y. For example, the X dataset may be data sampled from curve X, such as an S3 intensity curve of cardiac oscillation, and the Y dataset may be data samples from curve Y, such as a curve of chest fluid content measurement. In a particular implementation, correlation analysis may be performed using Pearson's product-moment correlation coefficient, Fisher transform, or other similar correlation functions. For example, Pearson's product-moment correlation coefficient can be used to calculate the correlation between n data pairs (X, Y), where X and Y are samples over a certain time. To continue the above example, X may be measured from an S3 intensity curve, and Y may be measured from a TFC measurement curve. The above Pearson product-moment correlation coefficient r can be obtained by swapping variance-covariance-based samples of the X, Y datasets. The resulting value of r is between -1.0 and 1.0. In this example, a value of 1.0 would indicate a perfect association between X and Y, i.e., as the S3 oscillation intensity increases, then the TFC measurement increases accordingly. A value of -1.0 would indicate a negative perfect association. For example, as the S3 vibration intensity increases, the TFC measurement then decreases. Conversely, as the S3 vibration intensity decreases, the TFC measurement then increases. A value of 0.0 indicates that there is no linear relationship between the variables.

[0231] As described herein, multiple metrics may be correlated to determine a patient's symptoms. For example, if a patient is likely to experience cardiac adverse events such as arrhythmias, a high correlation may exist between thoracic fluid content (TFC) and S3 oscillation intensity. When using the process described in Figure 10, TFC is considered metric 1 and may be represented on a normalized scale from 0 to 1000. Other normalized linear or nonlinear scales may be used. For example, the scale may be from 0 to 1, or 0 to 10, or 0 to 100. For example, the nonlinear scale may be a logarithmic scale. The processing device may monitor TFC to detect any changes or trends in the patient's TFC value.

[0232] For example, as shown in Figure 16A, the processing device may record a patient's TFC measurements over a period of several weeks. As shown in Figure 16A, the TFC measurements are indicated by line 1600. For example, a patient's initial TFC measurement may include a TFC measurement of 120 TFC units. In some examples, TFC units may be measured on a normalized scale from 0 to 200 TFC units. However, as shown in Figure 16A, the plot is adjusted to focus on the range of 100 to 160 TFC units. In week 1, the TFC measurement may rise to 130 TFC units. However, in week 2, the TFC measurement may fall to 125 TFC units. In week 3, the TFC measurement may rise to 150 TFC units, and in week 4, the TFC measurement may rise to 155 TFC units. Depending on the programming of the processing device, the processing device may trigger a second metric measurement based on the change in the TFC measurement. For example, the TFC measurement may exceed a predetermined threshold (e.g., 150 TFC units) or a threshold for a predetermined period (e.g., the second week of continuous TFC unit increases, or from the third to the fourth week of increases). These changes may trigger the processing device to monitor at least one additional metric. For example, as shown in Figure 16A, in the fourth week, the processing device also begins measuring the S3 vibration intensity, indicated by line 1602.

[0233] As described above, S3 vibration intensity can be measured on a normalized scale of 0 to 10 S3 intensity units, where 5.0 S3 intensity units represent the threshold at which the patient may experience cardiac disease and / or require additional treatment. Other normalized linear or nonlinear scales may be used. For example, the scale may be from 0 to 1 S3 intensity units, or from 0 to 10 S3 intensity units, or from 0 to 100 S3 intensity units. For example, a nonlinear scale may be a logarithmic scale. As shown in Figure 16A, the initial readings shown may be adjusted to focus on a range of 3 to 9 S3 intensity units. At week 4, the patient's S3 vibration intensity is measured as 4.5 S3 intensity units. However, at week 5, the patient's S3 vibration intensity rises to 5.0 S3 intensity units, and by week 6, the patient's S3 vibration intensity rises to 6.0 S3 intensity units. During the same period, the patients' TFC measurements also continued to rise, reaching 155 TFC units at week 5 and 165 TFC units at week 6.

[0234] In certain implementations, the processing device may perform trend analysis to determine the correlation coefficients for both TFC measurements and S3 vibration intensity. As shown in Figure 16A, an approximate linear relationship may exist between the two metrics, in which case the correlation coefficient may show a strong positive correlation between the two variables. Such a correlation may be interpreted by the processing device as indicating a specific cardiac adverse event characterized by a high correlation coefficient between TFC measurements and S3 vibration intensity. In certain implementations, a high correlation coefficient may further indicate a change in the patient's symptoms over a period of time, for example, six weeks as shown in Figure 16A.

[0235] In certain implementations, trend analysis may be used to determine how well a treatment plan is working for a patient. For example, as shown in Figure 16B, a patient may be monitored over a six-week treatment plan. Initially, the patient's TFC measurement may be monitored, shown as line 1610 in Figure 16B. As shown in Figure 16B, during the monitoring of TFC measurements over the first two weeks, the measurement decreases. Such a downward trend may trigger additional monitoring. For example, as shown in Figure 16B, the S3 vibration intensity, as well as %EMAT, measured in %EMAT units on a normalized scale of, for example, 0 to 100 EMAT units (adjusted to focus on a range of 10 to 70 %EMAT units, as shown in Figure 16B), may be triggered by the downward trend in the TFC measurement. As shown in Figure 16B, the S3 vibration intensity is shown as line 1612 and %EMAT is shown as line 1614. As further shown in Figure 16B, over the next four weeks, the TFC measurements, S3 vibration intensity, and %EMAT each remain relatively stable or gradually decrease. These results may indicate that the treatment plan is progressing well. In implementation, other metrics may be further validated. For example, if LVST decreases further during the same period, the device may indicate that the treatment plan is progressing well.

[0236] Figure 16C shows a 6-week trend analysis including the patient's overall grade score. As shown in Figure 16C, the patient's TFC measurement may show an upward trend over the first two weeks, indicated by line 1620, which generates an overall increase in the patient's overall grade score, indicated by line 1626. As described above, additional monitoring may be triggered after a steady trend in the second week. In this example, monitoring of both S3 vibration intensity and %EMAT may be initiated in the second week. As shown in Figure 16C, S3 vibration intensity is indicated by line 1622 and %EMAT is indicated by line 1624. As further shown in Figure 16C, the TFC measurement, S3 vibration intensity, and %EMAT each continued to rise between the second and sixth weeks.

[0237] As a result of these monitored metrics increasing, the patient's overall grade score continued to rise. As described above, the patient's overall grade score can be measured on a scale of grade units from 0.0 to 1.0, where 0.0 is the best condition and 1.0 is the worst condition. As shown in Figure 16C, the shown overall grade score readings can be adjusted to focus on a range of grade units, for example, from 0.1 to 0.7. As the patient's overall score continues to rise, the monitoring device can determine whether the score has exceeded a certain threshold (e.g., 0.50 grade units, or from one grade unit to another) and, accordingly, provide feedback to the patient's physician, for example. In the implementation, other metrics may be further validated. For example, if the LVST rises further during the same period, the device may determine that interventional treatment is needed to modify or manage the patient's treatment plan.

[0238] The metrics shown in Figures 16A to 16C are provided as examples. Additional metrics, such as LVST, can similarly be monitored and graphed over time. For example, as shown in Figure 16D, the processing device may record a patient's TFC measurement over a period of several weeks, indicated by line 1630. For example, the initial reading may include a TFC measurement of 120 TFC units. In week 1, the TFC measurement may rise to 130 TFC units. However, in week 2, the TFC measurement may fall to 125 TFC units. In week 3, the TFC measurement may rise to 150 TFC units, and in week 4, the TFC measurement may rise to 155 TFC units. Depending on the programming of the processing device, the processing device may trigger a second metric measurement based on a change in the TFC measurement. For example, the TFC measurement may exceed a predetermined threshold (e.g., 150 TFC units), or its increase may exceed a threshold for a predetermined period (e.g., week 2 when the TFC units have continuously increased, or week 3 to week 4 when they have increased). These changes may trigger the processing device to monitor at least one additional metric. For example, in week 4, as shown in Figure 16D, the processing device also begins measuring LVST, indicated by line 1632.

[0239] For example, at week 4, the patient's LVST may be measured at approximately 250 ms. However, at week 5, the patient's LVST rose to 290 ms, and by week 6, it had risen to 325 ms. During this same period, the patient's TFC measurement also continued to rise, for example, to 160 TFC units at week 5 and 165 TFC units at week 6. This rise in LVST can be used to confirm the interpretation that the pleural effusion in the patient is worsening, and in such cases, interventional treatment should be recommended. Conversely, if the TFC measurement decreases substantially from week 1 to the next week, for example, in the case of a downward trend from high TFC units to low TFC units, the patient's LVST can similarly be expected to decrease over the same period. A decrease in LVST can be used to confirm the interpretation that one or more interventional treatments to manage the pleural effusion appear to improve the patient's symptoms.

[0240] In certain implementations, the processing device may perform trend analysis to determine the correlation coefficients for both TFC measurements and LVST. As shown in Figure 16D, an approximate linear relationship exists between the two metrics, and in such cases, the correlation coefficient may show a positive correlation between the two variables. For example, a positive correlation coefficient may provide an indication that LVST increases as TFC measurements increase. Such a correlation showing an upward trend may be interpreted by the processing device as indicating a specific cardiac adverse event characterized by a positive correlation coefficient between TFC measurements and LVST. In certain implementations, the positive correlation coefficient may further indicate changes in the patient's symptoms over a period of time, for example, six weeks as shown in Figure 16D.

[0241] Figure 17 shows a sample process flow of a patient monitoring system described herein. For example, a series of sensors may be configured to detect the patient's raw signals 1705. In a particular implementation, an ECG sensor may be configured to detect one or more ECG signals from a patient, a vibration sensor may be configured to detect one or more bio-vibration signals from a patient, and an ultra-wideband radio frequency transceiver may be configured such that one or more antennas direct radio frequency electromagnetic energy toward the patient and receive it through one or more antennas, generating radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from a part of the patient such as the aorta or thoracic cavity.

[0242] In certain implementations, one or more processors may be configured to process raw signals to determine a set of patient physiological parameters.1710 For example, as described herein, the physiological parameters may include ECG metrics, biovibration metrics, radio frequency metrics, and / or combined physiological metrics. In some examples, the physiological parameters may be collected over a specific preceding period. For example, the period may include at least 24 hours, at least 48 hours, at least 1 week, at least 1 month, at least 6 weeks, at least 2 months, at least 4 months, at least 6 months, at least 1 year, and at least 2 years. In some examples, the preceding period corresponds to the period over which the patient's medical history is available to the patient.

[0243] One or more processors may be further configured to perform at least one of the following using physiological parameters: predictive analysis 1715 or trend analysis 1720. In a particular implementation, one or more processors may be configured to perform both predictive analysis 1715 and trend analysis 1720.

[0244] As described above, predictive analysis 1715 may include inputting physiological parameters into a trained process. For example, the trained process may include the artificial neural network or machine learning process described above. However, in certain implementations, the trained process may further include a deep learning process configured to analyze physiological parameters and output information about the patient's current health status.

[0245] Based on the output of predictive analytics and / or trend analytics, one or more processors may determine the patient's current health status.1725 Based on the patient's current health status, one or more processors may determine one or more clinically available events for the patient.1730 For example, clinically available events may include readmission, prescription of a wearable medical device such as a wearable defibrillator, an order to hospitalize the patient, a change in the treatment plan, and other similar events. In a particular implementation, clinically available events may include automated events that are triggered without user input, such as increasing the monitoring and / or analysis of one or more physiological signals. Similarly, clinically available events may include manual events that are triggered based on a user response to a generated output, and may include one or more orders that perform one or more actions, such as an order to hospitalize the patient.

[0246] One or more processors may generate outputs based on clinically usable events.1735 In a particular implementation, clinically usable events may include automated events that are triggered without user input, such as increasing the monitoring and / or analysis of one or more physiological signals. Similarly, clinically usable events may include manual events that are triggered based on a user response to a generated output, and may include one or more commands that perform one or more actions, such as a command to hospitalize a patient.

[0247] Various validations were conducted to analyze and verify the concepts and techniques described herein. For example, validations were conducted to evaluate the values ​​of cardiac disease-based biooscillation information described herein, as well as combinations of cardiac disease-based biooscillation information with one or more ECG metrics, in heart failure analysis. In the validations, a patient population including patients with a cardiac ejection fraction of <35% and hospitalized with decompensated heart failure was enrolled in a prospective observation protocol. All patients were fitted with a WCD equipped with an accelerometer. The WCD had the capability to record biooscillation and measure ECG signals. Each patient was to be fitted with the WCD in an outpatient setting. The patient population was monitored for heart failure events and emergency department visits for heart failure symptoms, and this information was collected for the patient population. Univariate and multivariate analyses were performed on the collected information to identify models that best predicted the occurrence of readmission or emergency department visits for early heart failure.

[0248] During validation, the patient population was divided into two groups based on the occurrence of heart failure events, resulting in a heart failure patient group and a non-heart failure patient group (based on hospitalization and emergency department visit information for heart failure in the patient population). The heart failure group had a lower BMI than the non-heart failure group (29+ / -6 compared to 26+ / -5), but all other demographic information was similar between the two groups. A multi-parameter model using heart rate, EMAT (from QRS expression to S1), and S3 intensity (e.g., based on S3 timing, intensity, duration, and frequency) statistically generated the best predictive models for decompensated heart failure events. Readmissions for any cause prior to WCD initiation were similar between the two groups (62% for heart failure vs. 63% for non-heart failure), and NYHA grades I and II were also similar (68% for heart failure vs. 69% for non-heart failure). However, after using WCD and model determination, the ability of NYHA grading to predict heart failure events was lower compared to using biooscillation information. For example, compared to the NYHA grading system's sensitivity of 30% and positive predictive value of 18%, the biooscillation predictor had a sensitivity of 68% and a positive predictive value of 28%. Therefore, based on this validation, it can be concluded that using biooscillation information alone, or in combination with ECG information and radiofrequency-determined pulmonary fluid volume (discussed below), may be more useful than the conventional NYHA grading system in the early detection of patients at risk of decompensated heart failure. Such heart failure can lead to patient readmission after an acute episode of decompensated heart failure.

[0249] The second validation was conducted to provide insights into tracking the disease status of heart failure patients using radiofrequency-determined pulmonary fluid volume. The patient population consisted of two groups. The first group consisted of acute heart failure patients with the following statistics: age 78 ± 8 years, 37% female, and BMI = 32 ± 7. The second group consisted of patients without acute heart failure (approximately 60% healthy and 40% with stable heart failure), with the following statistics: age 56 ± 16 years, 27% female, and BMI = 27 ± 5.

[0250] Each patient in the population underwent a chest CT scan while lying supine to determine initial fluid volume. Following this, RF readings were taken while lying supine from a wearable patch device positioned at the midline of the left axilla. An RF-based pulmonary fluid model was constructed for each patient using the reflected RF signals measured by the patch device, as well as anthropometric data. Pulmonary fluid was reported as a percentage of lung volume. Grading techniques were then used to compare the results and performance of the RF patch device with those of the chest CT scan.

[0251] The results of the above verification showed that all acute heart failure patients were measured to have higher pulmonary fluid volume than non-acute heart failure patients. Based on statistics, RF patch design and chest CT scans were performed to identify acute heart failure patients from non-acute heart failure patients. Sample data showing various statistical results determined from this verification can be seen in Table 10 below. Table 10 [Table 10]

[0252] As described above, the data obtained from the two validations demonstrate that radio frequency data can be used to assess whether a particular patient should be considered a heart failure patient or an acute heart failure patient. Additionally, the techniques described above can be used to incorporate a patient's bio-oscillation data together with their radio frequency data to indicate trends or changes in the patient's condition. For example, using the combined physiological parameter analysis described herein, patient information such as bio-oscillation information and radio frequency data can be combined with measured ECG information to form one or more combined metrics. Using the correlation analysis described herein (or, in other examples, another similar machine learning technique described above), patient information can be transformed or otherwise processed to quantify one or more trends or changes in the patient's condition. These trends can be further analyzed to determine what additional information can be determined from them. For example, further analysis of the trends can determine information such as whether the patient's overall health is improving / worsening, whether the patient's cardiac health is improving / worsening, and / or whether the patient may suffer another heart failure event in the near future (e.g., within the next 30 days) that may require an emergency room visit or readmission. For example, combined physiological parameters based on the patient's radiofrequency data and bio-vibration data can be used to determine whether a discharged patient is likely to experience a heart failure event in the near future, and / or whether the patient should be prescribed a portable medical device such as a WCD, as described in the following examples.

[0253] In the example, the patient may complain of chest pain when performing certain activities, such as sitting in a reclining position or lying on their back. The patient's physician may prescribe a wearable radiofrequency sensing device configured to measure the patient's thoracic fluid volume (TFC). The patient may wear the device for a course of several weeks. Over that period, the device may measure a steady increase in the patient's intrapleural fluid content. Upon return to the physician, the physician may download the data recorded by the radiofrequency sensing device into a trend analysis process. This process may detect trends indicating a steady increase in the patient's TFC. The physician may want to obtain additional physiological information for the patient and may further prescribe a mobile cardiac monitoring device that includes a vibration sensor configured to measure bio-vibrations. The patient wears both the radiofrequency sensing device and the mobile cardiac monitoring device for a period of time. Upon return to the physician, the recorded information from both monitoring devices may be entered into a trend analysis process. This process may identify trends indicating an increase in the patient's TFC by analyzing information regarding the patient's S3 vibration intensity. The process can determine the correlation between increased TFC and the patient's S3 oscillation intensity, potentially providing indications that the patient may have a cardiac condition such as congestive heart failure. The process can then provide physicians with these indications, along with recommended actions, such as changes to the patient's prescribed medications.

[0254] In an alternative example, a hospitalized patient may be fitted with at least one ECG sensor, at least one biovibration sensor, and at least one radiofrequency sensor. Before discharge, the data recorded by these sensors may be combined into one or more combinations of physiological parameters and input into a trained process such as an artificial neural network (or, in other examples, another similar machine learning technique as described above). The artificial neural network may transform the input information to provide information on the patient's clinical symptoms. This clinical symptom information may be further analyzed to determine the patient's current health status, whether or not to approve the patient's discharge, and the risk of the patient being readmitted within a specific period, for example, within 30 days. In some examples, even if the patient meets all the conditions necessary for discharge, the process may indicate that the patient is at high risk of readmission in the near future. In such examples, a physician or other similar caregiver may decide to keep the patient hospitalized for additional monitoring, modify the patient's treatment plan, or otherwise change the treatment being provided to the patient.

[0255] Even if the subject matter included herein is described in detail for illustrative purposes only, such details are for that purpose only, and this disclosure is not limited to the disclosed embodiments, but is intended to extend to modifications and equivalent arrangements within the spirit and scope of the appended claims. For example, this disclosure is intended to allow, wherever possible, one or more features of any embodiment to be combined with one or more features of any other embodiment.

[0256] Other examples are within the scope and spirit of the claims. Furthermore, the specific functions described above may be implemented using software, hardware, firmware, hardwiring, or any combination thereof. The features implementing the functions may further be physically located in various locations, and may include distributing some of the functions to implement them in various physical locations.

Claims

1. 1. A patient monitoring system comprising: an ECG sensor coupled to a patient and configured to detect one or more ECG signals of the patient; a vibration sensor coupled to the patient and configured to detect one or more cardiac vibration signals of the patient; an ultra-wideband radio frequency transceiver circuit coupled to the patient, the ultra-wideband radio frequency transceiver circuit having one or more radio frequency antennas; directing the one or more radio frequency antennas to direct radio frequency electromagnetic energy toward the patient's thoracic cavity; generating radio frequency information corresponding to reflected radio frequency electromagnetic energy received via the one or more radio frequency antennas and reflected from within the thoracic cavity; an ultra-wideband radio frequency transceiver circuit configured to one or more processors, a) processing the one or more ECG signals and b) the one or more cardiac vibration signals to generate a plurality of physiological parameters for the patient, the combined physiological parameter being based on one or more fiducial points in the one or more ECG signals and one or more occurrences of the one or more cardiac vibration signals; processing the radio frequency information to generate one or more radio frequency-based thoracic fluid parameters; performing a trend analysis of the plurality of physiological parameters comprising the combined physiological parameter to determine a trend of a current clinical condition of the patient, the trend analysis comprising: correlating the combined physiological parameter to at least one of the one or more radio frequency-based thoracic fluid parameters to generate a correlation coefficient when the combined physiological parameter exceeds a threshold; and determining the trend of the current clinical condition of the patient based on the correlation coefficient; determining one or more clinically actionable events based on the trend of the current clinical condition of the patient; and providing an output regarding said one or more clinically actionable events to an output device. one or more processors configured to: A patient monitoring system including:

2. The patient monitoring system of claim 1 , wherein the combined physiological parameter is electromechanical activation time (EMAT).

3. 10. The patient monitoring system of claim 1, wherein the one or more radio frequency based thoracic fluid parameters are thoracic fluid content (TFC).

4. 10. The patient monitoring system of claim 1, wherein the trend analysis is performed on physiological parameters collected over a previous period having one or more of at least 24 hours, at least 48 hours, at least one week, at least two weeks, at least one month, at least six weeks, at least two months, at least four months, at least six months, at least one year, and at least two years.

5. 10. The patient monitoring system of claim 1, wherein said trend analysis is performed on physiological parameters collected over a previous period corresponding to at least available medical history of said patient.

6. the one or more clinically actionable events: Automatic events that are triggered without user input; a manual event triggered based on a user response to the output and having one or more instructions to perform one or more actions; 10. The patient monitoring system of claim 1, comprising at least one of:

7. 7. A patient monitoring system according to any one of the preceding claims, wherein the correlation coefficient indicates a change in the patient's condition.

8. 10. The patient monitoring system of claim 1, wherein the vibration sensor is further configured to sense one or more pulmonary vibrations of the patient, the one or more pulmonary vibrations comprising at least one of bronchial vibrations, wheezing, crackles, wheezing, bullae, pleural rubs, squawks, glottal sounds, or pharyngeal sounds.

9. 2. The patient monitoring system of claim 1, wherein the one or more ECG signals include at least one of heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, pause, heart rate turbulence, QRS height, QRS width, changes in size or shape of the morphology of the one or more ECG signals, cosine R-T, artificial pacing, QT interval, QT variation, T wave width, T wave alternans, T wave variation, and ST segment changes.

10. The patient monitoring system of claim 1 , wherein the one or more cardiac vibration signals include at least one of an S1 vibration, an S2 vibration, an S3 vibration, an S4 vibration, and a heart murmur vibration.

11. The patient monitoring system of claim 1 , wherein the radio frequency information includes a measurement of fluid content within the thoracic cavity of the patient.

12. The patient monitoring system of claim 1 , wherein the one or more processors are incorporated within a cardiac monitoring device adapted to be worn by the patient.

13. The patient monitoring system of claim 1 , wherein the one or more processors are incorporated in a remote processing device.

14. 10. The patient monitoring system of claim 1, wherein the one or more processors are incorporated into a wearable defibrillation device adapted to be worn by the patient.

15. 1. A patient monitoring system comprising: an ECG sensor coupled to a patient and configured to detect one or more ECG signals of the patient; a vibration sensor coupled to the patient and configured to detect one or more cardiac vibration signals of the patient; an ultra-wideband radio frequency transceiver circuit coupled to the patient, the ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas; directing the one or more radio frequency antennas to direct radio frequency electromagnetic energy toward the patient's thoracic cavity; generating radio frequency information corresponding to reflected radio frequency electromagnetic energy received via the one or more radio frequency antennas and reflected from within the patient's thoracic cavity; an ultra-wideband radio frequency transceiver circuit configured to one or more processors, processing the one or more ECG signals and the one or more cardiac vibration signals to generate a plurality of physiological parameters for the patient, including a combined physiological parameter based on one or more fiducial points in the one or more ECG signals and one or more occurrences of the one or more cardiac vibration signals; processing the radio frequency information to generate one or more radio frequency-based thoracic fluid parameters; performing a trend analysis of the plurality of physiological parameters, including the combined physiological parameter, to generate a clinical trend, the trend analysis including: correlating the combined physiological parameter to at least one of the one or more radiofrequency-based thoracic fluid parameters to generate a correlation score when the combined physiological parameter exceeds a threshold; and determining a current clinical trend of the patient based on the correlation score; updating a monitoring schedule for the patient based on the trend in the clinical condition; determining one or more clinically actionable events based on the trend of the current clinical condition of the patient; causing an output device to provide an output regarding said one or more clinically actionable events. one or more processors configured to: A patient monitoring system including:

16. 16. The patient monitoring system of claim 15, wherein the combined physiological parameter is electromechanical activation time (EMAT).

17. 16. The patient monitoring system of claim 15, wherein the one or more radio frequency based thoracic fluid parameters are thoracic fluid content (TFC).

18. the one or more processors further process the one or more ECG signals, the one or more cardiac vibration signals, and the radio frequency information in accordance with the updated monitoring schedule to generate updated physiological parameters of the patient; 16. The patient monitoring system of claim 15, configured to perform a trend analysis of the updated plurality of physiological parameters including the one or more combined physiological parameters to generate an updated clinical symptom trend.

19. the one or more clinically actionable events: Automatic events that are triggered without user input; a manual event triggered based on a user response to the output, the manual event comprising one or more instructions to perform one or more actions; 20. A patient monitoring system according to any preceding claim 15 or 18, comprising at least one of:

20. 16. The patient monitoring system of claim 15, wherein the one or more ECG signals include at least one of heart rate, heart rate variability, PVC burden or PVC count, atrial fibrillation burden, pause, heart rate turbulence, QRS height, QRS width, changes in size or shape of the morphology of the one or more ECG signals, cosine R-T, artificial pacing, QT interval, QT variation, T wave width, T wave alternans, T wave variation, and ST segment changes.

21. 16. The patient monitoring system of claim 15, wherein the one or more cardiac vibration signals include at least one of an S1 vibration, an S2 vibration, an S3 vibration, an S4 vibration, and a heart murmur vibration.

22. 16. The patient monitoring system of claim 15, wherein the radio frequency information includes a measurement of fluid content within the thoracic cavity of the patient.

Images