Patient monitoring system

Abstract

The present invention relates to a patient monitoring system comprising: an ECG sensor coupled to a patient; a sensor coupled to a patient and configured to detect a biological vibration signal; and a radio frequency monitoring device configured to generate information in response to electromagnetic energy reflected from the thoracic cavity of the patient. A processor processes the ECG signal, the biological vibration signal, and the radio frequency information to generate a plurality of physiological parameters of the patient. The processor also 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 also compare the current clinical condition of the patient to predetermined clinically viable criteria to determine one or more clinically viable events and provide an output related to the one or more clinically viable events.

Description

[0001] This application is a divisional application of the invention patent application with application date of March 15, 2019, application number 201980032020.8, and titled “Monitoring physiological state based on biological vibration and radio frequency data analysis”. Technical Field

[0002] The present invention relates to monitoring a patient's physiological state based on patient data obtained from multiple sensor sources including bio-vibration sensors and radio frequency sensors. Background Art

[0003] Acute attacks caused by congestive heart failure (CHF) conditions in patients with cardiac pathology tend to recur frequently. For example, pulmonary congestion is the main reason for hospitalization and readmission of CHF patients. Similarly, chronic kidney disease patients undergoing hemodialysis also suffer from acute adverse events. For example, several patients with end-stage renal disease may have moderate to severe pulmonary congestion before hemodialysis. The prevalence of heart failure in these patients is very high, and the overall prognosis is poor. There are various electronic and mechanical devices for monitoring and treating the heart failure conditions of patients. In some examples, medical devices such as cardiac monitors or defibrillators can be implanted in patients or connected to patients from the outside through surgery, depending on the basic conditions being monitored or treated. In some cases, physicians can use medical devices to treat heart failure states alone or in combination with drug therapy.

[0004] If not treated, heart failure may lead to some life-threatening arrhythmias. Both atrial arrhythmias and ventricular arrhythmias are common in heart failure patients. One of the most lethal cardiac arrhythmias is ventricular fibrillation, which occurs when normal regular electrical pulses are replaced by irregular and rapid pulses, causing the myocardium to stop contracting normally. Since there is no perceptible warning of the impending fibrillation for the victim, death often occurs before necessary medical assistance can arrive. Other cardiac arrhythmias may include a too slow heart rate known as bradycardia or a too fast heart rate known as tachycardia. Cardiac arrest may occur in the case of various arrhythmias of the patient's heart (such as ventricular fibrillation, ventricular tachycardia, pulseless electrical activity (PEA) and cardiac arrest (heart stops all electrical activity) etc.) causing the heart to provide insufficient blood flow levels to the brain and other vital organs for maintaining life. Monitoring heart failure patients to assess heart failure symptoms at an early stage and provide interventional treatment as quickly as possible is generally useful. Summary of the invention

[0005] In a specific implementation, a patient monitoring system includes: 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; a radio frequency ultra-wideband transceiver circuit including one or more radio frequency antennas and coupled to the patient; and one or more processors. In some examples, the radio frequency ultra-wideband transceiver is configured to: cause the one or more radio frequency antennas to direct radio frequency electromagnetic energy into the chest cavity of the patient; and generate radio frequency information in response to reflected radio frequency electromagnetic energy reflected from the chest cavity of the patient and received by the one or more radio frequency antennas. In some examples, the one or more processors are configured to: process the one or more ECG signals, the one or more cardiac vibration signals, and the radio frequency information to generate a plurality of physiological parameters of the patient including one or more combined physiological parameters. The one or more processors may perform at least one of a predictive analysis and a trend analysis of the plurality of physiological parameters including the combined physiological parameters to determine the current clinical condition of the patient. In the implementation described herein, the trend analysis includes determining the existence of a substantial relationship between changes in the plurality of physiological parameters. The one or more processors may compare the patient's current clinical condition with predetermined clinically actionable criteria to determine one or more clinically actionable events, and cause an output device to provide an output related to the one or more clinically actionable events. Implementations of a patient monitoring system as described herein may include one or more of the following features.

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

[0007] In a specific implementation of the above patient monitoring system, at least one of the predictive analysis and the trend analysis is performed on physiological parameters collected within a previous time period, wherein the previous time period includes one or more of the following: 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.

[0008] In a specific implementation of the above patient monitoring system, at least one of the predictive analysis and the trend analysis is performed on physiological parameters collected within a previous time period corresponding to at least an available clinical history of the patient.

[0009] In a specific implementation of the above patient monitoring system, the one or more clinically actionable events include at least one of: an automatic event, which is triggered without user input; and a manual event, which is triggered based on a user response to the output and includes one or more instructions to perform one or more actions.

[0010] In a specific implementation of the above patient monitoring system, the output associated with the one or more clinically actionable events is based on a violation of one or more thresholds, wherein the one or more thresholds are defined relative to the multiple physiological parameters or the results of at least one of the predictive analysis and the trend analysis.

[0011] In a specific implementation of the above patient monitoring system, performing the predictive analysis includes: inputting the plurality of physiological parameters into an artificial neural network; and determining the patient's current clinical condition based on an output of the artificial neural network.

[0012] In a specific implementation of the above patient monitoring system, performing the predictive analysis includes: inputting the plurality of physiological parameters into a deep learning process; and determining the patient's current clinical condition based on an output of the deep learning process.

[0013] In a specific implementation of the above patient monitoring system, performing the predictive analysis includes: inputting the plurality of 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, wherein the predictive score represents the likelihood of an adverse event. In some examples, the adverse event includes one or more of an arrhythmia event, a stroke event, a syncope event, and a hospitalization event.

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

[0015] In a specific implementation of the above patient monitoring system, the vibration sensor is also configured to sense one or more lung vibrations of the patient, the one or more lung vibrations including at least one of bronchial vibrations, wheezes, crackles, wheezes, snoring sounds, pleural friction sounds, shrieks, glottal sounds, laryngeal sounds, and other vibrations.

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

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

[0018] In a specific implementation of the above patient monitoring system, the radio frequency information includes a measurement of fluid content within the patient's chest cavity.

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

[0020] In a specific implementation of the above patient monitoring system, the one or more processors are integrated into a cardiac monitoring device adapted to be worn by the patient.

[0021] In certain implementations of the above patient monitoring systems, the one or more processors are integrated into a remote processing device.

[0022] In a specific implementation of the above patient monitoring system, the one or more processors are integrated into a wearable defibrillator device adapted to be worn by the patient.

[0023] In a specific implementation, 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 radio frequency ultra-wideband transceiver coupled to the patient; and one or more processors. In some examples, the at least one radio frequency ultra-wideband transceiver is configured to: direct radio frequency electromagnetic waves through the patient's lungs; and detect radio frequency information in response to the radio frequency electromagnetic waves that have passed through the patient's lungs. In some examples, the one or more processors are configured to: process one or more cardiac vibration signals detected within a predetermined duration to determine at least one cardiac vibration metric of the patient; process the radio frequency information of the patient within a predetermined duration to determine at least one lung fluid metric of the patient; determine an output related to one or more clinically actionable events based on the determined at least one cardiac vibration metric and the determined at least one lung fluid metric; and cause an output device to provide the output. Implementations of the second patient monitoring system as described herein may include one or more of the following features.

[0024] In a specific implementation of the above second patient monitoring system, the one or more clinically actionable events include at least one of: an automatic event, which is triggered without user input; and a manual event, which is triggered based on a user response to the output and includes one or more instructions to perform one or more actions.

[0025] In a specific implementation of the above second patient monitoring system, determining the output includes performing a predictive analysis of the determined value or trend of the at least one heart vibration metric and the determined value or trend of the at least one lung fluid metric.

[0026] In a specific implementation of the above second patient monitoring system, performing the predictive analysis includes: inputting the determined value or trend of the at least one heart vibration metric and the determined value or trend of the at least one lung fluid metric into a machine learning process; determining a predictive score based on an output of the machine learning process, wherein the predictive score represents the likelihood of an adverse event; and determining the output based on the predictive score.

[0027] In a particular implementation of the second patient monitoring system above, determining the output includes performing a trend analysis of the changes in the at least one heart vibration metric and the changes in the at least one lung fluid metric to determine the presence of a substantial relationship between the changes in the at least one heart vibration metric and the changes in the at least one lung fluid metric. In some examples, performing a trend analysis of the changes to detect the presence of a substantial relationship between the changes in the at least one heart vibration metric and the changes in the at least one lung fluid metric includes performing a correlation analysis.

[0028] In a specific implementation of the above second patient monitoring system, determining the output includes performing a correlation analysis, which includes: processing the one or more cardiac vibration signals and the radio frequency information to generate multiple physiological parameters of the patient including one or more combined physiological parameters; associating at least one physiological parameter of the multiple physiological parameters that has exceeded a threshold with at least one additional physiological parameter selected from the multiple physiological parameters to generate a correlation score, wherein the correlation score represents a change in the patient's condition; and determining the output based on the correlation score.

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

[0030] In a specific implementation of the above second patient monitoring system, the radio frequency information includes a measurement of fluid content within the patient's chest cavity.

[0031] In a specific implementation, the third patient monitoring system includes: an ECG sensor coupled to the 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; a radio frequency ultra-wideband transceiver circuit including one or more radio frequency antennas and coupled to the patient; and one or more processors. In some examples, the radio frequency ultra-wideband transceiver circuit is configured to: cause the one or more radio frequency antennas to direct radio frequency electromagnetic energy into the chest cavity of the patient; and generate radio frequency information in response to reflected radio frequency electromagnetic energy reflected from the chest cavity of the patient and received by the one or more radio frequency antennas. In some examples, the one or more processors are configured to: process the one or more ECG signals, the one or more cardiac vibration signals, and the radio frequency information to generate a plurality of physiological parameters of the patient including one or more combined physiological parameters. The one or more processors may: perform trend analysis of the plurality of physiological parameters including the combined physiological parameters to generate trend results; update a monitoring schedule of the patient based on the trend results; determine a current clinical condition of the patient based on the trend results; and compare the current clinical condition of the patient with predetermined clinically actionable criteria to determine one or more clinically actionable events. The one or more processors may cause an output device to provide an output related to the one or more clinically actionable events.Implementations of the third patient monitoring system as described herein may include one or more of the following features.

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

[0033] In a specific implementation of the above third patient monitoring system, the one or more clinically actionable events include at least one of: an automatic event, which is triggered without user input; and a manual event, which is triggered based on a user response to the output and includes one or more instructions to perform one or more actions.

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

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

[0036] In a specific implementation of the third patient monitoring system above, the radio frequency information includes a measurement of fluid content within the patient's chest cavity.

[0037] In a specific implementation, a fourth patient monitoring system includes: an ECG sensor coupled to a patient and configured to detect one or more ECG signals of the patient; a vibration sensor coupled to a patient and configured to detect one or more cardiac vibration signals of the patient; a radio frequency ultra-wideband transceiver circuit including one or more radio frequency antennas and located on at least one major artery of the patient; and one or more processors. In some examples, the radio frequency ultra-wideband transceiver circuit is configured to: cause the one or more radio frequency antennas to direct radio frequency electromagnetic energy into at least a portion of the patient; and generate radio frequency information in response to reflected radio frequency electromagnetic energy reflected from at least a portion of the patient and received by the one or more radio frequency antennas. In some examples, the one or more processors are configured to: process the one or more ECG signals, the one or more cardiac vibration signals, and the radio frequency information to generate a plurality of physiological parameters of the patient including one or more combined physiological parameters. The one or more processors may: perform at least one of a predictive analysis and a trend analysis of the plurality of physiological parameters including the combined physiological parameters to determine a current clinical condition of the patient; compare the current clinical condition of the patient with a predetermined clinically actionable standard to determine one or more clinically actionable events; and cause an output device to provide an output related to one or more clinically actionable events. Implementations of the fourth patient monitoring system as described herein may include one or more of the following features.

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

[0039] In a specific implementation of the fourth patient monitoring system above, the radio frequency information includes at least one of blood pressure information, heart wall motion information, blood flow information, heart rhythm information and fluid content information. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Various aspects of at least one example are discussed below with reference to the accompanying drawings, which are not intended to be drawn to scale. These figures are included to provide illustration and further understanding of various aspects and examples, and are incorporated into and constitute a part of this specification, but are not intended to limit the scope of the invention. The accompanying drawings, together with the rest of the specification, are used to illustrate the principles and operations of the described and claimed aspects and examples. In the figures, each identical or nearly identical component shown in each figure is represented by a similar reference numeral. For clarity, each component may not be labeled in each figure.

[0041] Figure 1 A wearable medical device according to an example of the present invention is depicted.

[0042] Figure 2 Depicted is an example of an example according to the present invention such as Figure 1 Schematic diagram of a sample controller for use with a wearable medical device is shown.

[0043] Figure 3 A sample network overview according to an example of the present invention is depicted.

[0044] Figure 4A A sample radio frequency patch unit is depicted attached to a patient according to an example of the present invention.

[0045] Figure 4B A schematic diagram of a radio frequency patch antenna unit according to an example of the present invention is depicted.

[0046] Figure 5A and 5B Depicted is a schematic plot of propagation delay and amplitude of radio frequency waves reflected from patient tissue according to an example of the present invention.

[0047] Figure 6 An exemplary arterial pulse waveform according to an example of the present invention is depicted.

[0048] Figure 7 A schematic diagram of a vibration sensor according to an example of the present invention is depicted.

[0049] Figure 8 Graph depicting lung vibrations and associated time-amplitude plots.

[0050] Fig. 9 A sample overview of a process using predictive analytics according to an example of the present invention is depicted.

[0051] Fig.10 A sample overview of a process for using trend analysis according to an example of the present invention is depicted.

[0052] Fig.11 and 12 Depicted is a diagram of a patient monitoring system according to an example of the present invention.

[0053] Fig.13 A sample two-lead ECG signal according to an example of the present invention is depicted.

[0054] Fig.14 A sample process for developing a machine learning process according to examples of the present invention is depicted.

[0055] Fig.15 A sample architecture of an artificial neural network according to an example of the present invention is depicted.

[0056] Figures 16A to 16D A sample graph showing trend analysis results according to an example of the present invention, wherein the y-axis is based on normalized units.

[0057] Fig.17 A sample process flow for monitoring a patient's condition using techniques as described herein, according to examples of the present invention is depicted. DETAILED DESCRIPTION

[0058] Wearable medical devices such as cardiac event monitoring devices are used in clinical or outpatient settings to monitor and record various physiological signals of patients. These signals can be used to determine the patient's current condition, as well as predict, plan, and prepare for future adverse events (such as possible cardiac events or other adverse changes in the patient's medical health). For example, ECG monitoring in conjunction with a patient's medical history can be used, for example, by a machine learning process to calculate a patient's risk score and predict, for example, the occurrence of possible arrhythmic events in the future. An example of such a machine learning process is described in U.S. Patent Application Publication No. 2016 / 0135706, entitled "Medical Premonitory Event Estimation," the contents of which are incorporated herein by reference.

[0059] In some implementations, the patient monitoring system may include sensors configured to collect patient physiological signals other than ECG signals. For example, a vibration sensor may be configured to collect biological vibration signals, such as heart vibration signals (e.g., S1, S2, S3, and S4 signals) and lung vibration signals (e.g., vibration signals from the lungs or other airway-related anatomical regions (such as the trachea and pharynx, etc.)). In addition, a radio frequency sensor, such as an ultra-wideband transceiver circuit, may be configured to collect information in response to radio frequency electromagnetic energy reflected from the patient's chest and / or heart. For example, the radio frequency sensor may be configured to monitor transthoracic (e.g., lung) fluid levels and changes associated therewith. In the implementation described herein, the processing device may also process various collected signals and related information from different basic physiological sensors to generate one or more combined physiological parameters, such as physiological parameters and related information determined based on two or more different basic physiological sensors. The collected signals and received information and the combined metrics may be subjected to at least one of predictive analysis (e.g., using a machine learning process such as an artificial neural network) and trend analysis (e.g., correlation analysis) to determine the patient's current condition and one or more clinically actionable events.

[0060] For example, the present invention relates to a patient monitoring device and system. The device or system may include: an ECG sensor coupled to a patient and configured to detect one or more ECG signals of the patient; a sensor coupled to a patient and configured to detect one or more cardiac vibration signals (including cardiac vibration or lung vibration signals) of the patient; and a radio frequency-based monitoring device, which includes a radio frequency antenna and associated transceiver circuits, which are coupled to the patient and configured to direct radio frequency electromagnetic energy into the patient's chest and / or toward the heart. The radio frequency transceiver circuit generates multiple measurements in response to radio frequency electromagnetic energy reflected from the patient's chest and / or heart and received via a receiving radio frequency antenna. One or more processors process one or more ECG signals, one or more cardiac vibration signals or lung vibration signals, and radio frequency measurements to generate multiple physiological parameters of the patient including more than one combined physiological parameter. In addition, the processor may be further configured to perform at least one of a predictive analysis and a trend analysis of multiple physiological parameters including the combined physiological parameters to determine the patient's current clinical condition. In some implementations, a patient monitoring device coupled to a patient may send physiological information measured from the patient to a remote server for analysis. At the remote server, one or more processors may be configured to perform at least one of a predictive analysis and a trend analysis of a plurality of physiological parameters according to the principles described herein. For example, the trend analysis may include determining the existence of a substantial relationship between changes in a plurality of physiological parameters. The one or more processors may also compare the patient's current clinical condition with predetermined clinically actionable criteria to determine one or more clinically actionable events, and cause an output device to provide an output related to the one or more clinically actionable events.

[0061] As an example, a patient may be examined by a health care provider at an outpatient facility and be asked to use one or more wearable patient monitoring devices described herein to monitor a set of patient physiological parameters. For example, monitoring may be initiated for only one set of physiological parameters (such as ECG-based metrics, etc.). Over time or in response to a specific state described herein, additional sets of physiological parameters other than ECG parameters, such as bio-vibration parameters or radio frequency-based parameters (or their combination parameters), etc., may be initiated. Based on the collected set of physiological parameters, the device may perform a process for assessing the patient's current clinical condition. In a follow-up visit (e.g., weekly, biweekly, or monthly), the device may provide updated information related to the patient's clinical condition. The device may also be configured to determine whether a patient is at high risk of developing symptoms of heart failure that may require eventual hospitalization. The patient and / or their physician may be notified of the determination, and appropriate interventional actions may be taken. For example, the patient's medication may be adjusted, and the physician may initiate closer outpatient monitoring and schedule additional clinic visits. Further to the above example, once identified as a high risk for heart failure, the patient can be upgraded to a wearable monitoring and treatment device, such as a wearable cardioverter defibrillator (WCD), etc., over an extended period of time. Such a device can monitor the patient's cardiac state and, if approved, provide one or more therapeutic defibrillation and / or pacing pulses to the patient. The wearable cardioverter defibrillator can continue to collect updated physiological information during the patient's use. The updated information is also provided to the physician, who can continue to monitor changes in the patient's health by analyzing trend changes associated with the updated physiological information. For example, such analysis can guide further treatment changes and provide information about when the risk of acute heart failure has been reduced.

[0062] Many patients with cardiac pathology also suffer from conditions associated with pleural fluid management and therefore have frequent recurring acute episodes. Among such patients may be those with congestive heart failure (CHF). Pulmonary congestion is a leading cause of hospitalization and readmission for CHF patients. Therefore, it may be desirable to measure and monitor the extent of pulmonary congestion. The radiofrequency sensors described herein can allow for direct and accurate measurement of fluid, including by monitoring changes in the patient's thoracic impedance. Caregivers can use this type of information to coordinate a patient's treatment regimen and potentially shorten hospital stays by achieving an effective balance of medications. For example, the technology can provide early edema detection to prevent hospital readmissions.

[0063] Similarly, patients with chronic kidney disease (CKD) undergoing hemodialysis also need a fluid management strategy. In patients with end-stage renal disease (ESRD), approximately 60% may have moderate to severe pulmonary congestion before hemodialysis. In addition, the prevalence of heart failure (HF) in patients diagnosed with CKD and undergoing maintenance hemodialysis is very high, and the overall prognosis is poor. Therefore, congestive heart failure is a common clinical manifestation in dialysis patients. For these reasons, fluid assessment and management can be useful for managing CKD and HF. In the present invention, a non-invasive, wearable monitoring system can be used to assess thoracic impedance and / or fluid changes, and combines and / or analyzes the information in conjunction with bio-vibration information, ECG information, and other combined metrics.

[0064] This approach offers several advantages over existing monitoring and prediction techniques. By combining physiological measurements from multiple sensor sources and using various types of analysis to verify and measure changes in physiological signals, the present invention provides a more robust and accurate analysis of the patient's current state and the likelihood that the patient's condition will change. Based on this information, a personalized treatment plan can be created and regularly updated for the patient, while the patient's state is regularly monitored for positive or negative changes.

[0065] The teachings of the present invention may be generally applied to extracting physiological measurements from external medical monitoring and / or treatment devices (e.g., devices that are not fully implanted in a patient) for further processing. The external medical device may, for example, include a mobile medical device that is capable of and designed to move with the patient as the patient goes about his or her daily routine. Exemplary mobile medical devices may be wearable medical devices such as wearable cardioverter-defibrillators (WCDs), wearable cardiac monitoring devices, in-hospital devices such as in-hospital wearable defibrillators (HWDs), short-term wearable cardiac monitoring and / or treatment devices, mobile cardiac monitoring devices, and other similar wearable medical devices, etc.

[0066] The wearable medical device may be capable of continuous use by the patient. In some implementations, continuous use may be substantially continuous or nearly continuous in nature. That is, the wearable medical device may be continuously used except for sporadic time periods during which use is temporarily stopped (e.g., when the patient takes a shower, when the patient refits new and / or different clothing, when the battery is charged and / or replaced, when clothing is washed, etc.). However, such substantially continuous or nearly continuous use as described herein may still be considered continuous use. For example, the wearable medical device may be configured to be worn by the patient for up to 24 hours a day. In some implementations, the patient may remove the wearable medical device within a short portion of the day (e.g., within half an hour of taking a shower).

[0067] In addition, the wearable medical device can be configured as a long-term or extended use medical device. Such a device can be configured to be used by a patient for an extended period of days, weeks, months, or even years. In some examples, the wearable medical device can be used by a patient for an extended period of at least one week. In some examples, the wearable medical device can be used by a patient for an extended period of at least 30 days. In some examples, the wearable medical device can be used by a patient for an extended period of at least one month. In some examples, the wearable medical device can be used by a patient for an extended period of at least two months. In some examples, the wearable medical device can be used by a patient for an extended period of at least three months.

[0068] In some examples, the wearable medical device may be used by the patient for an extended period of at least six months.

[0069] In some examples, the wearable medical device may be used by the patient for an extended period of at least one year.

[0070] In some implementations, extended use can be uninterrupted until a physician or other caregiver provides specific instructions to the patient to cease use of the wearable medical device.

[0071] Regardless of how long the extended period of wear is, the use of the wearable medical device may include continuous or nearly continuous wearing 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, by one or more electrodes as described herein, during a monitoring period and a period when the device may not be monitoring the patient but is still otherwise worn by the patient or otherwise attached to the patient. The wearable medical device is configured to continuously monitor the patient to obtain cardiac-related information (e.g., electrocardiogram (ECG) information, including arrhythmia information, cardiac vibrations, lung vibrations, etc.) and / or non-cardiac information (e.g., blood oxygen, the patient's body temperature, glucose levels, tissue fluid levels, and / or lung vibrations). The wearable medical device may perform its monitoring at periodic or non-periodic time intervals or times. For example, monitoring during an interval or time may be triggered by a user action or other event.

[0072] As described above, the wearable medical device can be configured to monitor other physiological parameters of the patient in addition to heart-related parameters. For example, the 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), tissue fluid (e.g., using a radio frequency transmitter and sensor), etc.

[0073] Other wearable medical devices include automatic heart monitors and / or defibrillators for use in specific specialized conditions and / or environments (such as combat zones or within emergency vehicles). Such devices can be configured so that they can be used immediately (or substantially immediately) in life-saving emergencies. In some examples, the wearable medical devices described herein can be pacing-enabled, e.g., capable of providing therapeutic pacing pulses to a patient.

[0074] In an implementation, an exemplary therapeutic medical device may include an in-hospital continuous monitoring defibrillator and / or pacing device, such as an in-hospital wearable defibrillator. In such an example, the electrode may be attached to the patient's skin. For example, the electrode may include a disposable attachment electrode. For example, the electrode may include a sensing component and a therapeutic component disposed on a separate sensing electrode attachment patch and a therapeutic electrode attachment patch. In some implementations, both the sensing component and the therapeutic component may be integrated and disposed on the same electrode attachment patch that is then attached to the patient. In an exemplary implementation, the electrode may include a frontally attachable therapeutic electrode, a back-attachable therapeutic electrode, and a plurality of attachably attachable sensing electrodes. For example, a frontally attachable therapeutic electrode is attached to the front of the patient's torso to deliver pacing or defibrillation therapy. Similarly, a back-attachable therapeutic electrode is attached to the back of the patient's torso. In an exemplary scenario, at least three ECG attachably attachable sensing electrodes may be attached to at least the upper chest of the patient near the right arm, the upper chest of the patient near the left arm, and toward the bottom of the patient's chest in a manner prescribed by a trained professional.

[0075] Patients being monitored by in-hospital defibrillators and / or pacemakers may be confined to a bed or room for a significant amount of time (e.g., 90% or more of the patient's stay in the hospital). As a result, the user interface may be configured to interact with a user other than the patient (e.g., a nurse) to perform device-related functions such as initial device baseline, setting and adjusting patient parameters, and replacing device batteries.

[0076] In an implementation, examples of therapeutic medical devices may include a short-term continuous monitoring defibrillator and / or pacing device, such as a short-term outpatient wearable defibrillator. For example, a physician may prescribe such a short-term outpatient wearable defibrillator for a patient presenting with syncope. The wearable defibrillator may be configured to monitor a patient presenting with syncope by, for example, analyzing the patient's cardiac activity to detect abnormal patterns that may indicate abnormal physiological function. For example, such an abnormal pattern may occur before, during, or after the onset of symptoms. In this exemplary implementation of a short-term wearable defibrillator, the electrode assembly may be adherently attached to the patient's skin and have a configuration similar to that of the in-hospital defibrillator described above.

[0077] In some implementations, the medical device may be a patient monitoring device without treatment or treatment functions. For example, such a patient monitoring device may include a cardiac monitoring device or a cardiac monitor configured to monitor one or more cardiac physiological parameters of a patient (e.g., for remote monitoring and / or diagnosis of a patient's state). For example, such cardiac physiological parameters may include the patient's ECG information, cardiac vibrations (e.g., using an accelerometer or microphone), and other relevant cardiac information. The cardiac monitoring device is a portable device that a patient can carry while carrying out his or her daily affairs. The cardiac monitor may be configured to detect the patient's ECG through a plurality of cardiac sensing electrodes. For example, the cardiac monitor may be attached to the patient via at least three attached cardiac sensing electrodes disposed around the patient's torso. Such a cardiac monitor is used for cardiac event monitoring, for example, for a patient population reporting irregular cardiac symptoms and / or states. Exemplary cardiac states may include atrial fibrillation, bradycardia, tachycardia, atrioventricular block, Lown-Ganong-Levine syndrome, atrial flutter, sinus node dysfunction, cerebral ischemia, syncope, atrial pauses, and / or palpitations. For example, a cardiac monitor can be prescribed for such a patient over an extended period of time (e.g., 10 to 30 days or longer). In some mobile cardiac event monitoring applications, a portable cardiac monitor can be configured to monitor the patient's cardiac abnormalities substantially continuously, and when such an abnormality is detected, the monitor can automatically send data related to the abnormality to a remote server. The remote server can be located in a 24-hour manned monitoring center, where qualified, cardiac trained inspectors and / or caregivers interpret the data and provide feedback to the patient and / or designated caregiver via detailed periodic or event-triggered reports. In a specific cardiac event monitoring application, the cardiac monitor is configured to allow the patient to manually press a button on the cardiac monitor to report symptoms. For example, a patient can report symptoms such as missed beats, shortness of breath, dizziness, increased heart rate, fatigue, fainting, chest discomfort, weakness, dizziness and / or vertigo, etc. The cardiac monitor can record predetermined physiological parameters (e.g., ECG information) of the patient within a predetermined amount of time (e.g., 1 to 30 minutes before reporting symptoms and 1 to 30 minutes after reporting symptoms). The cardiac monitor may be configured to monitor other physiological parameters of the patient in addition to cardiac-related parameters. For example, the cardiac monitor may be configured to monitor, for example, cardiac vibrations (e.g., using an accelerometer or microphone), lung vibrations, respiratory vibrations, sleep-related parameters (e.g., snoring, sleep apnea), tissue fluid, etc.

[0078] Figure 1An exemplary medical device 100 is shown that is external, mobile, and wearable by a patient 102 and is configured to implement one or more of the configurations described herein. For example, the medical device 100 can be a non-invasive medical device configured to be substantially external to the patient's body. Such a medical device 100 can be, for example, a mobile medical device that is capable of and designed to move with the patient as the patient goes about his or her daily routine. For example, a medical device 100 as described herein can be attached to the patient's body, such as from Medical Corporation Wearable cardioverter defibrillator. Such a wearable defibrillator is typically worn almost continuously or substantially continuously for 2 to 3 months at a time. During the period of time that the patient wears it, the wearable defibrillator can be configured to continuously or substantially continuously monitor the patient's vital signs, and can be configured to deliver one or more therapeutic electrical pulses to the patient when it is determined that treatment is required. For example, such therapeutic shocks can be pacing, defibrillation, or transcutaneous electrical nerve stimulation (TENS) pulses.

[0079] Medical device 100 may include one or more of the following: garment 110, one or more sensing electrodes 112 (e.g., ECG electrodes), one or more therapy electrodes 114a and 114b (collectively referred to herein as therapy electrodes 114), medical device controller 120, connection box 130, patient interface box 140, belt 150, or any combination thereof. In some examples, at least some components of medical device 100 may be configured to be attached to garment 110 that can be worn around a patient's torso (or in some examples, permanently integrated into garment 110).

[0080] The medical device controller 120 can be operably coupled to the sensing electrodes 112, which can be attached to the garment 110 (e.g., assembled into the garment 110 or removably attached to the garment), for example, using hook and loop fasteners. In some implementations, the sensing electrodes 112 can be permanently integrated into the garment 110. The medical device controller 120 can be operably coupled to the therapy electrodes 114. For example, the therapy electrodes 114 can also be assembled into the garment 110, or in some implementations, the therapy electrodes 114 can be permanently integrated into the garment 110.

[0081] Apart from Figure 1Component configurations other than those shown are possible. For example, the sensing electrodes 112 may be configured to be attached at various locations around the body of the patient 102. The sensing electrodes 112 may be operably coupled to the medical device controller 120 via the connection box 130. In some implementations, the sensing electrodes 112 may be adhesively attached to the patient 102. In some implementations, at least one of the sensing electrodes 112 and the therapy electrodes 114 may be included on a single integrated patch and adhesively applied to the patient's body.

[0082] The sensing electrodes 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 the patient. In a specific implementation, the sensing electrodes 112 may include additional components, such as accelerometers, vibration signal detection devices, and other measurement devices for recording additional parameters. For example, the sensing electrodes 112 may also be configured to detect other types of patient physiological parameters and vibration signals, such as tissue fluid levels, heart vibrations, lung vibrations, breathing-related vibrations of anatomical features in the airway path, patient movement, etc. An exemplary sensing electrode 112 includes a metal electrode with an oxide coating (such as a tantalum pentoxide electrode, etc.), as described, for example, in U.S. Patent 6,253,099 entitled "Cardiac Monitoring Electrode Apparatus and Method", the entire contents of which are incorporated herein by reference.

[0083] In some examples, the treatment electrode 114 may also be configured to include a sensor configured to detect ECG signals and other physiological signals of the patient. In some examples, the connection box 130 may include a signal processor configured to amplify, filter, and digitize the cardiac signals before sending them to the medical device controller 120. One or more treatment electrodes 114 may be configured to deliver one or more therapeutic defibrillation shocks to the body of the patient 102 if the medical device 100 determines that such treatment is approved based on the signal detected by the sensing electrode 112 and processed by the medical device controller 120. Exemplary treatment electrodes 114 may include conductive metal electrodes such as stainless steel electrodes, wherein in a specific implementation, the conductive metal electrodes include one or more conductive gel deployment devices configured to deliver conductive gel to the metal electrodes before delivering the therapeutic shock.

[0084] In some implementations, a medical device as described herein may be configured to switch between a therapeutic medical device and a monitoring medical device, wherein the monitoring medical device is configured to monitor only a patient (e.g., not provide or perform any therapeutic functions). For example, therapeutic components such as therapeutic electrodes 114 and associated circuits may be optionally decoupled from (or coupled to) the medical device or disconnected from (or connected to) the medical device. For example, a medical device may have an optional therapeutic element (e.g., defibrillation and / or pacing electrodes, components, and associated circuits) configured to operate in a therapeutic mode. The optional therapeutic element may be physically decoupled from the medical device as a component used to convert the therapeutic medical device into a monitoring medical device for a specific purpose (e.g., for operation in a monitoring-only mode) or patient. Optionally, the optional therapeutic element may be deactivated (e.g., by a physical or software switch), thereby essentially causing the therapeutic medical device to behave as a monitoring medical device for a specific physiological purpose or a specific patient. As an example of a software switch, an authorized person may access a protected user interface of the medical device and select a preconfigured option or perform some other user action via the user interface to deactivate the therapeutic element of the medical device.

[0085] Figure 2 A sample component level diagram of a medical device controller 120 is shown. Figure 2 As shown, the medical device controller 120 may include a therapy delivery circuit 202, a data store 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 the components described above, but does not include the therapy delivery circuit 202 (shown in phantom).

[0086] The therapy delivery circuit 202 may be coupled to one or more electrodes 220 (e.g., as described above in conjunction with Figure 1 The therapy electrodes 114 described herein. For example, therapy delivery circuit 202 may include or be operably connected to circuit components configured to generate and deliver a therapy shock. The circuit components may include, for example, resistors, capacitors, relays and / or switches, bridges such as an H-bridge (e.g., including a plurality of insulated gate bipolar transistors or IGBTs), voltage and / or current measurement components, and other similar circuit components arranged and connected such that the circuit components work in conjunction with the therapy delivery circuit and under the control of one or more processors (e.g., processor 218) to, for example, provide one or more pacing or defibrillation therapy pulses.

[0087] Pacing pulses may be used to treat cardiac arrhythmias such as bradycardia (e.g., less than 30 beats per minute) and tachycardia (e.g., more than 150 beats per minute) using, for example, fixed-rate pacing, demand pacing, and anti-tachycardia pacing. Defibrillation pulses may be used to treat ventricular tachycardia and / or ventricular fibrillation.

[0088] The capacitor may include a parallel connected capacitor bank consisting of a plurality of capacitors (e.g., two, three, four or more capacitors). These capacitors may be switched to be connected in series during the defibrillation pulse discharge. For example, four capacitors of about 650uF may be used. The capacitor may have a surge rating of 350 to 500 volts and may be charged by the battery pack for about 15 to 30 seconds.

[0089] For example, each defibrillation pulse may deliver 60 to 180 joules of energy. In some implementations, the defibrillation pulse may be a biphasic truncated exponential waveform, whereby the signal may switch between a positive portion and a negative portion (e.g., a charging direction). This type of waveform may be effective for defibrillating a patient at a lower energy level when compared to other types of defibrillation pulses (such as monophasic pulses, etc.). 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 therapy delivery circuit 202 may be configured to perform switching and pulse delivery operations, for example, under the control of the processor 218. As energy is delivered to the patient, the amount of energy being delivered may be tracked. For example, the amount of energy may be maintained at a predetermined constant value even when the pulse waveform is dynamically controlled based on factors such as the body impedance of the patient to which the pulse is being delivered.

[0090] The data storage 204 may include one or more of non-transitory computer-readable media such as flash memory, solid-state memory, magnetic memory, optical memory, cache memory, combinations thereof, etc. The data storage 204 may be configured to store executable instructions and data for operating the medical device controller 120. In a particular implementation, the data storage may include executable instructions that, when executed, are configured to cause the processor 218 to perform one or more functions.

[0091] In some examples, the network interface 206 can facilitate information communication between the medical device controller 120 and one or more other devices or entities via a communication network. For example, where the medical device controller 120 is included in an ambulatory medical device (such as the medical device 100), the network interface 206 can be configured to communicate with a remote computing device such as a remote server or other similar computing device. The network interface 206 can include a computer program product for communicating with the medical device controller 120 based on the medical device controller 120. The intermediate device may in turn communicate the data to the remote server via a broadband cellular network communication link. The communication link may implement 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 technology for high-speed wireless communication. In some implementations, the intermediate device may be based on the IEEE 802.11 standard, via Wi-Fi TM Communication link to communicate with remote server.

[0092] In a specific 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 device. These user interface elements may present visual, audio, and / or tactile content. Thus, the user interface 208 may receive input or provide output, thereby enabling a user to interact with the medical device controller 120.

[0093] The medical device controller 120 may also include at least one battery 210 configured to provide power to one or more components integrated in the medical device controller 120. The battery 210 may include a rechargeable multi-cell battery pack. In an exemplary implementation, the battery 210 may include three or more 2200mAh lithium-ion batteries for providing power to other device components within the medical device controller 120. For example, the battery 210 may provide a power output ranging from 20mA to 1000mA (e.g., 40mA) output, and may support 24 hours, 48 ​​hours, 72 hours, or more of run time between each charge. In a specific implementation, the battery capacity, run time, and type (e.g., lithium-ion, nickel-cadmium, or nickel-metal hydride) may be varied to best suit the specific application of the medical device controller 120.

[0094] The sensor interface 212 may be coupled to one or more sensors configured to monitor one or more physiological parameters of the patient. As shown, the sensor may be coupled to the medical device controller 120 via a wired or wireless connection. The sensor may include one or more electrocardiogram (ECG) electrodes 222 (e.g., in combination with the above) Figure 1 The sensing electrodes 112 are similar to those described above), a bio-vibration sensor 224, an interstitial fluid monitor 226 (eg, based on an ultra-wideband radio frequency device), and a patient movement sensor 228.

[0095] The ECG electrodes 222 can monitor the patient's ECG information. For example, the ECG electrodes 222 can be galvanic (e.g., conductive) and / or capacitive electrodes configured to measure changes in the patient's electrophysiological phenomena to measure the patient's ECG information. The ECG electrodes 222 can send information describing the ECG signal to the sensor interface 212 for subsequent analysis.

[0096] The bio-vibration sensor 224 can detect patient vibrations associated with, for example, heart and lung activity. For example, the bio-vibration sensor 224 can be configured to detect heart or heart vibration values, including any one or all of S1, S2, S3, and S4. Based on these heart vibration values, specific heart vibration metrics or combined metrics can be calculated, including electro-mechanical activation time (EMAT), left ventricular contraction time (LVST), or percentage of left ventricular contraction time (% LVST). The bio-vibration sensor 224 can include a vibration sensor configured to detect vibrations from the heart system of the subject and provide an output signal in response to the detected heart vibrations. The bio-vibration sensor 224 can also include a multi-channel accelerometer, such as a three-channel accelerometer configured to sense movement of each of three orthogonal axes so that patient movement / body position can be detected and correlated with the detected heart vibration information. The bio-vibration sensor 224 can send information describing the heart vibration information to the sensor interface 212 for subsequent analysis.

[0097] The tissue fluid monitor 226 can use radio frequency-based technology to assess the level and accumulation of fluid in the patient's body tissue. For example, the tissue fluid monitor 226 can be configured to measure the fluid content in the lungs, which is often used to diagnose and follow up on pulmonary edema or pulmonary congestion in patients with heart failure. The tissue fluid monitor 226 may include one or more antennas, wherein the one or more antennas are configured to direct radio frequency waves through the patient's tissue and measure output radio frequency signals in response to the waves that have passed through the tissue. In a specific implementation, the output radio frequency signal includes parameters indicating the fluid level in the patient's tissue. The tissue fluid monitor 226 can send information describing the tissue fluid level to the sensor interface 212 for subsequent analysis. The following is a description of the structure of the tissue fluid monitor 226. Figure 4A and 4B Examples of radio frequency sensors are further described in .

[0098] The patient movement sensor 228 may include one or more accelerometers configured to measure motion data associated with patient movement. In a specific implementation, the patient movement sensor 228 may be configured to measure the number of steps taken by the patient in a specific amount of time. For example, the patient may be instructed to perform a specific exercise such as a walking test. The patient movement sensor 228 may be configured to measure the pace and pace information during the specific exercise. However, it should be noted that the patient movement sensor 228 is shown as a separate component only by way of example. In a specific implementation, one or more accelerometers included in the patient movement sensor 228 may be integrated into other components such as a biological vibration sensor 224 or an interstitial fluid monitor 226.

[0099] The sensor interface 212 may be coupled to any one or combination of sensing electrodes / other sensors to receive other patient data indicative of patient parameters. Once the sensor interface 212 has received data from the sensors, the data may be directed by the processor 218 to appropriate components within the medical device controller 120. For example, if cardiac data is collected by the bio-vibration sensor 224 and sent to the sensor interface 212, the sensor interface 212 may send the data to the processor 218, which in turn relays the data to the cardiac event detector. The cardiac event data may also be stored on the data storage 204.

[0100] In a specific implementation, the alarm manager 214 may be configured to manage alarm profiles and notify one or more intended recipients of events specified in the alarm profile as being of interest to the intended recipients. These intended recipients may include external entities such as users (patients, physicians, and monitoring personnel) and computer systems (monitoring systems or emergency 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 the data storage unit 204 and executed by the processor 218. In this example, the instructions included in the alarm manager 214 may cause the processor 218 to configure the alarm profile and use the alarm profile to notify the intended recipient. In other examples, the alarm manager 214 may be an application specific integrated circuit (ASIC), which is coupled to the processor 218 and is configured to manage the alarm profile and use the alarm specified in the alarm profile to notify the intended recipient. Therefore, the example of the alarm manager 214 is not limited to a specific hardware or software implementation.

[0101] In some implementations, the processor 218 includes one or more processors (or one or more processor cores), wherein the one or more processors are each configured to perform a series of instructions for obtaining operational data and / or controlling the operation of other components of the medical device controller 120. In some implementations, when performing a specific process (e.g., cardiac monitoring), the processor 218 may be configured to perform a specific logic-based judgment based on the received input data, and is also configured to provide one or more outputs that can be used to control or otherwise inform the processor 218 and / or other processors or circuits to which the processor 218 is communicatively coupled to perform subsequent processing to be performed. Thus, the processor 218 reacts to a specific input stimulus in a specific manner and generates a corresponding output based on the input stimulus. In some exemplary cases, the processor 218 may continue to perform a series of logic transitions, wherein various internal register states and / or other bit cell states inside or outside the processor 218 may be set to logic high or logic low. As mentioned herein, the processor 218 can be configured to execute functions stored in a data storage unit coupled to the processor 218 by software, which is configured to cause the processor 218 to proceed with a series of various logical decisions that result in the functions being executed. The various components described herein as executable by the processor 218 can be implemented in various forms of dedicated hardware, software, or a combination thereof. For example, the processor can be a digital signal processor (DSP), such as a 24-bit DSP processor, etc. The processor can be, for example, a multi-core processor with two or more processing cores. The processor can be an advanced RISC machine (ARM) processor, such as a 32-bit ARM processor or a 64-bit ARM processor, etc. The processor can execute an embedded operating system and include services provided by the operating system that can be used for file system operations, display and audio generation, basic networking, firewalls, data encryption, and communications.

[0102] Figure 3 A sample network 300 is shown depicting a sample topology showing how a wearable medical device (eg, the medical device 100 described above) may be operably connected to a remote server. Figure 2 The wearable medical device controller 120 includes a controller for controlling the wearable medical device 120 by, for example, Wireless link (e.g., via a "hotspot" or other base station or intermediate device), broadband cellular link, or Wi-Fi based on the IEEE 802.11 standard TM The network interface 206 transmits data via a wireless link such as a communication link. Figure 3As shown, the doctor's computer 302 and the wearable medical device 304 can be operably connected to the monitoring server 308 via the network 306. In a specific implementation, when being worn, the wearable medical device 304 can be collecting information related to the patient, such as various patient metrics and parameters as described herein. Depending on the connection to the network 306 and the programming of the wearable medical device 304, the wearable medical device can be configured to periodically send the collected information to the monitoring server 308 for further processing. For example, the monitoring server 308 can be configured to monitor the patient's physiological state based on patient data obtained from multiple sensor sources (including bio-vibration sensors and radio frequency sensors) and sent to the monitoring server through, for example, one or more wearable medical devices 304. In some examples, one or more physicians can use the doctor's computer 302 to access patient status information to check changes in the patient's condition, receive instructions / recommendations for changing the patient's treatment plan, and perform other similar functions.

[0103] In some examples, as described above, the patient may wear a radio frequency device, such as a radio frequency transceiver, such as an ultra-wideband transceiver circuit configured to direct radio frequency electromagnetic energy into the patient's body via a radio frequency antenna and generate radio frequency information in response to the reflected electromagnetic energy. In a specific implementation, in addition to the wearable medical device described above, the radio frequency device (transceiver and associated antenna) may also be integrated into a patch worn by the patient. For example, Figure 4A As shown, patch 402 may be attached to a prescribed location on the body of patient 400 .

[0104] In other implementations, the RF device may be integrated into a garment of a wearable cardioverter defibrillator. In some implementations, the RF device may be integrated into a wearable continuous event monitoring device. In some implementations, the RF device may be integrated into one or more therapy electrodes and / or patches of a hospital wearable defibrillator. In the above implementations, the RF device (e.g., integrated into patch 402) may be as follows: Figure 4A The RF device is shown as being located on the left lower abdominal region of the patient 400 and is configured to direct RF electromagnetic energy into the chest cavity (e.g., toward the patient's lungs and / or heart). In other examples, the RF device can be placed on at least one major artery (such as the radial artery, the brachial artery, the aorta, and one or more pulmonary arteries, etc.) to, for example, monitor the patient's arterial pulse. Information related to the arterial pulse can be used to monitor the patient's blood pressure measurement according to implementations described later.

[0105] Radio frequency information responsive to electromagnetic energy reflected from the patient's chest cavity may indicate lung fluid levels (absolute values ​​and changes in levels), thoracic impedance, blood pressure measurements, heart rate measurements, and / or specific cardiac states based on monitoring the patient's heart wall motion. For example, 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 Application 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. 7,725,150 entitled “Apparatus and Method for Continuous Noninvasive Measurement of Respiratory Function and An example of a radio frequency transceiver is described in U.S. Patent 9,002,427 to "Events", the contents of which are incorporated herein by reference. As described above, radio frequency information responsive to electromagnetic energy reflected from the patient's chest can indicate changes in the patient's thoracic impedance value.

[0106] Figure 4B Shows such as Figure 4ASchematic diagram of an exemplary RF device 430 such as the RF device shown. RF device 430 can be configured to be used as a RF transceiver using components contained in an integrated package 442, for example, in the form of a patch, or integrated into a wearable medical device as described above. In some implementations, RF device 430 can be implemented in a package 442 having a form factor of approximately 20×50 mm. In other examples, the form factor may be smaller, such as in the range of approximately 10×25 mm to approximately 20×50 mm. In some examples, package 442 may include an adhesion layer, for example, by which RF device 430 can be attached to the patient's skin.

[0107] The radio frequency device 430 includes at least two antennas: a transmitting antenna 432a and a receiving antenna 432b for transmitting radio frequency energy to and receiving radio frequency energy from the patient's chest. In some implementations, the antennas 432a-b may have a flat and / or flexible profile to better conform to the shape and shape of the patient's body. The transceiver 436 is configured to generate a drive signal for transmitting and / or receiving radio frequency energy through the antennas 432a-b. The transceiver 436 is also configured to receive and process the reflected electromagnetic energy received by the antennas 432a-b from the patient's body. In a specific implementation, the active background elimination circuit 434 eliminates background components from the reflected signal, such as signals from depths and / or tissues of no interest. The processor 438 controls the operation of the components of the radio frequency device 430 described later. The processor 438 can monitor one or more RF signal path characteristics and generate RF information corresponding to a selected tissue depth (e.g., in the range of 1 to 20 cm) and / or a tissue of interest, such as the effective path length of the RF wave path and one or more phase and / or amplitude changes of the reflected RF wave relative to the transmitted RF wave. The processor 438 can process the RF information and transform the information into interpretable physiological metrics, such as pleural fluid content information (TFC), cardiac wall motion data, and / or arterial pulse information. In some implementations, the RF device 430 can be configured to send the RF information to a remote server via the communication interface 448. In these implementations, the remote server can be configured to process the received RF information and perform the transformation into the above-mentioned physiological metrics. A power module 444, such as a low-profile battery, provides power to the components of the patch unit.

[0108] In some implementations, the RF device 430 may also include ECG electrodes 440 that are in electrical contact with the patient's skin, and ECG acquisition circuitry 450 for filtering and digitizing ECG signals for input into the processor 438. The ECG signal may be used to gate the transmission and reception of RF waves relative to the patient's chest. For example, the transceiver 436 may trigger RF transmission based on the timing of the R wave of the ECG signal.

[0109] In a particular implementation, the radio frequency device 430 includes a user interface, such as one or more indicator LEDs 446 that signal the operational state of the patch (on / off, and possibly parameters such as battery level, skin contact quality, or signal strength, etc.). Alternatively or in addition, the user interface may include a more informative display (such as an LCD, etc.) and user controls (such as on / off and adjustment buttons, etc.).

[0110] The communication interface 448 communicates with the remote control console to send RF and ECG measurement data and receive operation commands in some instances. For example, the communication interface 448 may generally include a wireless link such as Bluetooth. TM Or WiFi link, etc. For example, the remote console can be located near the patient's location, so data from the communication interface 448 can be directly received and processed. Optionally, the communication interface 448 can communicate with a local gateway such as a personal computer, a smart phone device, or a dedicated "hotspot" device, which communicates with the remote server through a network such as the Internet or a telephone network. In these implementations, the console can be a networked server connected to one or more databases and configured to store radio frequency and ECG data for subsequent viewing, processing and analysis. For example, access and / or tools can be provided to a physician or other expert to analyze the data. In some cases, the data can be used for another diagnostic computer system via a wired or wireless communication link. These system configurations are particularly useful for extended flow monitoring of multiple patients at different geographical locations.

[0111] As described above, radio frequency devices such as device 430 can be used to monitor various measurements and parameters of a patient. For example, a radio frequency device can be configured to monitor interstitial fluid measurements, blood pressure, chest wall motion, and other similar patient parameters.

[0112] To measure interstitial fluid measurements, the RF device can be configured to direct electromagnetic energy into an area of ​​tissue (e.g., the lungs or chest cavity) and measure the amplitude and delay of the returning / reflected electromagnetic energy. Figure 5A illustrates a schematic plot 500 showing amplitude, and Figure 5B A schematic plot 505 showing the propagation delay of radio frequency waves reflected from the patient's heart is illustrated. Figure 5A and 5B As shown, the scale of plots 500 and 505 is arbitrary. The delay and (to a lesser extent) the amplitude vary periodically with the cardiac cycle, as shown in FIG. Figure 5B The peaks of line 507 are shown as well as Figure 5A The amplitude of line 502 is shown to be generally shifted downward as shown.

[0113] The concave portion of lines 502 and 507 between markings 250 and 260 on the horizontal scale corresponds to an inspiratory period during a respiratory cycle. Figure 5B This depression in indicates that the effective RF path length through the lungs decreases as the lungs fill with air, because the physical distance between the antenna and the heart remains constant while the average dielectric constant along the path decreases. Exhalation empties the lungs of air, thus increasing the effective RF path length. Figure 5A The amplitude of the reflected waves in also decreases during inspiration, probably because as the lungs fill with air, the change in the dielectric constant increases, and thus the reflections along the RF path through the lungs increase.

[0114] For lungs with high fluid content, the average dielectric constant will generally be higher than for healthy lungs, so the path delay of the RF wave through the lung will be greater. The overall amplitude may also be greater due to reduced reflections as the wave passes through the lung. On the other hand, the difference between a lung filled with air and an empty lung during the respiratory cycle is expected to be greater in both amplitude and delay. Figure 5A and 5B The differences shown are small. Thus, to monitor tissue fluid content, the processing device may, for example, compare the delay and possibly the amplitude of the reflected wave to a benchmark provided by healthy and unhealthy lungs, or to a measurement previously made on the same patient. Additionally or alternatively, the processing device may assess the amount of fluid in the lungs by analyzing changes in the delay and / or amplitude of the reflected wave during one or more respiratory cycles. In a specific implementation, to quantify the assessment of fluid accumulation, the actual physical distance traversed by the radio frequency waves through the lungs may be measured, and a relationship (such as a ratio, etc.) between the effective radio frequency path length and the physical distance may be calculated.

[0115] In addition, the radio frequency device can be used to measure the patient's blood pressure. For example, information determined based on the patient's arterial pulse waveform can be used by the processing device to determine the patient's blood pressure. Figure 6 As shown, the patient's arterial pulse waveform 600 can be obtained by directing radio frequency waves into the patient's artery and measuring the reflected radio frequency waves. Based on the reflected waves, the processing device can measure the change of the radar cross section (RCS) of the artery.

[0116] For example, during the cardiac cycle, the RF device may generate and transmit RF waves toward an artery that may be located at a certain depth from the RF device. In some examples, some or all of the transmitted RF waves may be reflected back to the RF device. In some instances, the RF device may transmit RF waves continuously or non-continuously. During the cardiac cycle, the diameter of the artery may change over time, and the RCS of the artery obtained by the RF device may also change over time. Based on the measurement of different RCS, in some implementations, an arterial pulse waveform (e.g., pulse waveform 600) representing a pulse wave propagating through the artery may be determined. In turn, based on the arterial pulse waveform, various clinical information may be obtained, such as but not limited to arterial hardness, pulse wave velocity, cardiac output, blood pressure measurement (continuous 1 or non-continuous). In some embodiments, the reflected echo may be modulated by the artery during the cardiac cycle, and information from the reflected echo may be used to determine / estimate the arterial pulse waveform. For example, the measurement range may change during the cardiac cycle, resulting in a change in the phase of the reflected wave. In such an instance, such information may be used to determine / estimate the arterial pulse waveform.

[0117] In a particular implementation, in order to more accurately determine the patient's blood pressure, the radio frequency device can be calibrated to include basic measurements of the patient's blood pressure and pulse transit time (PTT). PTT can be obtained by using multiple sensors attached to the patient at known locations and measuring the pulse arrival time (PAT) at each location. By calculating the difference in the PAT at each location and knowing the distance between the sensors, the processing device can calculate PTT. This information can also be used to determine the patient's pulse wave velocity (PWV).

[0118] In a specific implementation, the linear transformation relating systolic blood pressure (SBP) and diastolic blood pressure (DBP) to PTT may be expressed as follows:

[0119] SBP=(a×PTT)+b,

[0120] DBP=(c×PTT)+d

[0121] Wherein, the coefficients a, b, c and d can be calibrated for each patient. In some embodiments, other types of transformations can be used to calculate blood pressure. For example, for a model assuming constant arterial thickness and radius, the blood pressure P can be expressed as P=a×ln(PTT)+b, where a and b are again constants to be calibrated for each patient. In any case, in some embodiments, obtaining the PTT or conversely the PWV of the pulse in the artery can be used to determine the blood pressure level in the artery. Additional examples related to determining blood pressure using a radiofrequency device are described, for example, in U.S. Patent Application Publication 2016 / 0345845 entitled “Systems, Apparatuses and Methods for Determining Blood Pressure,” the contents of which are incorporated herein by reference.

[0122] Based on information related to the collected parameters and metrics described above (e.g., tissue fluid levels and blood pressure), additional metrics can be determined. For example, by extracting respiratory information from fluid measurement information, the processing device can determine information such as chest wall motion and respiratory rate. For example, the processing device can be configured to associate chest wall expansion with time periods when the patient is inhaling and chest wall contraction with time periods when the patient is exhaling.

[0123] Heart vibrations are the noise produced by the beating heart and the resulting blood flow through the heart. Specifically, the vibrations reflect the turbulence created when the heart valves close. For example, in cardiac monitoring, one or more heart vibration sensors can be used to detect these unique and distinct vibrations, which provide important auditory data about the state of the heart.

[0124] In healthy adults, there are at least two normal heart vibrations that may occur with each heartbeat, which are generally described as lub and dub (or dup). For example, the first heart vibration (S1) and the second heart vibration (S2) are generated due to the closure of the atrioventricular valve (AV valve) and the semilunar valve (SL valve), respectively. More specifically, the S1 vibration represents the closure of the AV valves including the tricuspid valve located between the right atrium and the right ventricle, and the mitral valve located between the left atrium and the left ventricle. The S2 vibration represents the closure of the SL valves including the pulmonary valve that ejects blood to the lungs to obtain oxygen and is located between the right ventricle and the pulmonary artery, and the aortic valve that ejects oxygenated blood to the body and is located between the left ventricle and the aorta.

[0125] Systole refers to the part of the cardiac cycle when the ventricles contract. Diastole is the part of the cardiac cycle when the ventricles relax and refill with blood after systole. Similarly, atrial diastole is the period of time when the atria are relaxing. During ventricular diastole, the pressure in the left and right ventricles begins to drop from the peak value reached during systole (e.g., 120 mmHg in a normal heart). When the pressure in the left ventricle drops below the pressure in the left atrium, the mitral valve opens, causing the accumulated blood from the atria to flow into the ventricles.

[0126] When the smaller upper atrial chambers contract at the end of diastole, they send blood down to the larger lower ventricular chambers. When the lower chambers are filled and the valves of the atria close, the ventricles undergo isovolumetric contraction (ventricular contraction with all valves closed), marking the first stage of contraction. The second stage of contraction sends blood from the left ventricle to the aorta and limbs, and from the right ventricle to the lungs. Thus, the atria and ventricles contract in an alternating sequence. The left and right atria feed blood into the ventricles simultaneously. Then, the left and right ventricles also contract simultaneously.

[0127] Table 1 below shows a summary of the cardiac cycle:

[0128]

[0129]

[0130] Table 1

[0131] In addition to S1 and S2 vibrations, S3 and S4 vibrations may also be picked up by sensitive sensors such as vibration sensors, etc. Typically, an examining physician performing cardiac auscultation (eg, using a stethoscope to listen to internal heart vibrations) will not hear S3 vibrations in healthy adults.

[0132] The third heart vibration, S3, is a vibration that occurs shortly after the normal two "lub-dub" heart vibrations (i.e., S1 and S2). The S3 vibration usually occurs at the beginning of the middle third of diastole, about 0.12 to 0.18 seconds after S2. This classically produces a rhythm compared to the rhythm of the word "Kentucky" whose last syllable represents the S3 vibration. The fundamental pitch of the S3 vibration is lower than that of the S1 or S2 vibration because it is not a vibration of the origin of the valve. The S3 vibration is usually benign in young people, some trained athletes, and sometimes in pregnant women, but if this vibration reappears in old age, it may indicate a heart problem, such as left ventricular failure in dilated congestive heart failure (CHF), etc. The S3 vibration is believed to be caused by the back and forth oscillation of blood between the ventricular walls caused by the blood pouring in from the atria. The reason why the third heart vibration does not occur until the middle third of diastole may be that in early diastole, the filling of the ventricles is insufficient to produce enough tension to cause reverberation. Typically, in stethoscope-mediated examinations, S3 is associated with heart failure, since the fact that an S3 can be obtained via this method means that the ventricles are stiffer than those of a normal heart, where the vibrations of the blood hitting the walls can be heard.

[0133] The intensity of the third heart vibration (S3 intensity) is based on the intensity and persistence of the vibration. For example, a sensitive vibration sensor configured to detect S3 vibrations can provide an S3 vibration intensity value in the range of 1 to 10. In some implementations, if the intensity value is equal to or exceeds 5.0, the reporting process can declare that S3 is present.

[0134] The fourth heart vibration, S4, is produced by the vibration of blood forced into a stiff or hypertrophied ventricle. If heard during a stethoscope examination, the S4 vibration is a sign of a pathological condition, usually left ventricular failure or hypertrophy as in systemic hypertension, severe valvular aortic stenosis, and hypertrophic cardiomyopathy. This vibration occurs just after atrial contraction at the end of diastole and just before the S1 vibration, producing a rhythm sometimes called the "Tennessee" gallop.

[0135] As described above, the wearable medical device can be configured to monitor other physiological parameters of the patient in addition to heart-related parameters. In a specific implementation, the wearable medical device can be configured to monitor, for example, using a vibration sensor such as a microphone and / or an accelerometer located on the chest area of ​​the patient. In some implementations, the vibration sensor can be configured to detect heart vibrations (S1, S2, S3, and S4 vibrations, murmurs), lung vibrations, respiratory / chest wall motion, sleep-related parameters (e.g., snoring, sleep apnea), and other similar vibration-based parameters.

[0136] Figure 7A sample schematic diagram including a vibration sensor 700 is shown. In an implementation, the vibration sensor 700 may include a high-fidelity diaphragm 705, such as a dynamic electret condenser, a ribbon-based or piezoelectric crystal-based diaphragm, etc. A plurality of motion sensors 710 (e.g., at least two, four, six, or more) may be positioned around the periphery of the diaphragm 705, respectively. The vibration signals from the diaphragm 605 and the plurality of motion sensors 710 may be digitized by a series of analog-to-digital converters (ADCs) 715 and processed by a digital signal processing unit 720. For example, the digital signal processing unit may include a series of digital filters.

[0137] For example, the motion sensor 710 may include a multi-axis accelerometer that produces a digitized signal that is input to the digital signal processing unit 720 along with the digitized diaphragm signal.

[0138] Signals from one or more of the plurality of motion sensors 710 may be used to monitor low frequency vibrations, such as breathing and / or chest wall motion.

[0139] When monitoring higher frequency range vibration signals (e.g., certain lung vibrations, heart murmurs, etc.), the diaphragm signal may be analyzed as outlined below. To allow for better isolation of the high frequencies of interest, the signals from the peripheral motion sensors 710 may be summed to determine a common mode signal. The common mode signal may represent a low frequency component, which in turn may be removed from the diaphragm signal.

[0140] Tables such as Table 2 below may be stored in the memory of the sensor 700. Typical sampling rates ranging from 44.1 kHz to about 60 kHz may 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 ranging from 12 bits to 16 bits, with a higher bit length to allow for a more dynamic range of resolution. Various digital filters may be run on the input digital signal to, for example, remove interfering signals (such as the 60 Hz component and common mode rejection signal as described above). The digitized vibration signal may then be analyzed to determine various vibrations based on the table. For example, frequency selective filters and circuits may operate in the digital domain to isolate the frequency range of interest according to the following table. Exemplary digital filtering techniques may include fast Fourier transform (FFT), discrete cosine transform (DCT), infinite impulse response (IIR) filter, etc. The processor may be configured to receive an indication of the type of state to be monitored. Based on the indicated state, the processor 725 may retrieve the relevant frequency range from the memory and instruct the digital signal processing unit 720 to isolate the relevant signal for analysis and input to the next level.

[0141] Monitoring status Digital filter range Breathing / chest wall movement 0.1-10Hz stridor >500Hz Wheezing >100~5000Hz Snoring 100~200Hz Pleural friction rub <350Hz S1~S4 heart vibration 20~500Hz Diastolic murmur 50~150Hz Aortic regurgitation 200~600Hz

[0142] Table 2

[0143] In a particular implementation, vibration analysis of vibrations detected via a chest vibration sensor (such as sensor 700 described above) can provide information related to characteristic vibration patterns. The vibration analysis can include monitoring vibrations in the range of 1 / 10 to about 1 Hz to monitor low-frequency chest motion (such as breathing, chest wall motion, and in some cases heart wall motion). For example, with the sensor substantially aligned with the apex of the patient's ventricle, a sensor implementing the vibration analysis can detect and monitor ventricular wall motion. Similarly, other vibration patterns can be monitored.

[0144] In a specific implementation, more than one frequency range of lung vibration can be monitored at one time. For example, an obstruction may produce a rocking chest movement, such as paradoxical breathing. During inspiration, the diaphragm drops to the maximum extent, pushing the abdominal contents downward and outward and generating negative pressure. This negative pressure pulls the chest wall inward, resulting in an increase in the abdomen and a decrease in the chest during inspiration (the opposite movement of normal breathing). During inspiration with paradoxical breathing, the chest rises and the abdomen drops. Again, this movement is the opposite movement of normal breathing. The more compliant the chest wall is (as in a toddler), the easier it is to see the chest movement. In the case of paradoxical breathing, when the tongue is pulled down on the airway, the lower jaw is also pulled back, and breathing usually becomes noisy. Patients may experience, for example, wheezing, snoring and / or snoring. Therefore, very low frequency vibrations (.2Hz) of the chest wall and / or abdomen, which can indicate abnormal breathing movements, can be used to monitor wheezing-related frequencies (>500Hz).

[0145] For example, certain lung vibrations have characteristic patterns at various frequencies including approximately 100-5000 Hz (e.g., tracheal vibrations), >500 Hz (e.g., stridor), >100-5000 Hz (e.g., wheezing), ~150 Hz (e.g., snoring), and <350 Hz (e.g., pleural friction rub). Figure 8 shows various characteristic patterns of certain lung vibrations. Figure 8 As shown, the list of breath sounds 802 may have one or more associated amplitude-time plots 804. Each breath sound 802 may include a unique set of acoustic features. Figure 8 As shown in , normal lung vibrations can be characterized as low-pass filtered noise with a typical frequency of 100-1000 Hz, with a measured energy drop at 200 Hz. Various other lung vibrations such as stridor, wheeze, and pleural friction rub have similar characteristics, such as Figure 8 Similarly, each breath sound 802 may have an associated amplitude-time plot 804 (in Figure 8 806 and an expanded time plot 808). For example, Figure 8 As shown, the expanded time plot 808 for a particular breath sound 802 may correspond to the portion of the unexpanded time plot 806 indicated by the dashed box. Additional lung states such as crackles, shrieks, glottal sounds, laryngeal sounds, and other similar lung vibrations and their corresponding frequencies may be obtained from "Fundamentals of Lung Auscultation" by A. Bohadana, G. Izbicki, and S. Kraman, New England Journal of Medicine (2014).

[0146] Frequencies involved in cardiac vibrations and murmurs are generally in the range of 20 to 500 Hz. Low frequency cardiac vibrations are those with a dominant frequency less than about 100 Hz (such as S3, S4, and the diastolic murmur of mitral stenosis). Some murmurs have high frequency components such as aortic regurgitation, where the dominant frequency is about 400 Hz.

[0147] Analyze patient metrics used to track patient status

[0148] As described above, in various scenarios related to the present invention, the patient monitoring system may include sensors configured to collect patient physiological signals other than ECG signals. For example, a vibration sensor may be configured to collect biological vibration signals such as heart vibration signals and lung vibration signals. In addition, radio frequency sensors such as ultra-wideband transceiver circuits may be configured to collect information in response to radio frequency electromagnetic energy reflected from the patient's chest and / or heart. In the implementation described herein, the processing device may also be configured to process various collected signals and related information from different basic physiological sensors to generate one or more combined physiological parameters (e.g., physiological parameters and related information determined based on two or more different basic physiological sensors). The collected signals and received information and the combined metrics may be subjected to at least one of predictive analysis (e.g., using a machine learning process or an artificial neural network) and trend analysis (e.g., correlation analysis) to determine the patient's current state and one or more clinically feasible events.

[0149] More specifically, in a particular implementation, a patient monitoring system may include: an ECG sensor coupled to a patient and configured to detect one or more ECG signals of the patient; a vibration sensor coupled to a patient and configured to detect one or more cardiac vibration signals of the patient; a radio frequency ultra-wideband receiver circuit including one or more radio frequency antennas and coupled to a patient and configured to: cause the one or more radio frequency antennas to direct radio frequency electromagnetic energy into a chest cavity of the patient; and generate radio frequency information in response to reflected radio frequency electromagnetic energy reflected from within the chest cavity of the patient and received by the one or more radio frequency antennas; 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 more than one combined physiological parameter. The one or more processors are further configured to: perform at least one of a predictive analysis and a trend analysis of the plurality of physiological parameters including the combined physiological parameters to determine a current clinical condition of the patient, wherein the trend analysis includes determining the existence of a substantial relationship between changes in the plurality of physiological parameters; compare the current clinical condition of the patient with a predetermined clinically actionable standard to determine one or more clinically actionable events; and cause an output device to provide an output related to the one or more clinically actionable events.

[0150] In another implementation, a patient monitoring system may include: at least one vibration sensor coupled to a patient and configured to detect one or more cardiac vibration signals; at least one radio frequency ultra-wideband transceiver coupled to the patient; and one or more processors. The at least one radio frequency ultra-wideband transceiver may be configured to: direct radio frequency electromagnetic waves through the patient's lungs; and detect radio frequency information in response to the radio frequency electromagnetic waves having passed through the lungs. The one or more processors may be configured to: process the one or more cardiac vibration signals detected within a predetermined duration to determine at least one cardiac vibration metric of the patient; process the radio frequency information of the patient within a predetermined duration to determine at least one lung fluid metric of the patient; determine an output associated with one or more clinically actionable events based on the determined at least one cardiac vibration metric and the determined at least one lung fluid metric; and cause an output device to provide an output.

[0151] In another implementation, a patient monitoring system may include: an ECG sensor coupled to a patient and configured to detect one or more ECG signals of the patient; a vibration sensor coupled to a patient and configured to detect one or more cardiac vibration signals of the patient; a radio frequency ultra-wideband transceiver circuit including one or more radio frequency antennas and coupled to the patient; and one or more processors. The radio frequency ultra-wideband transceiver may be configured to: cause the one or more radio frequency antennas to direct radio frequency electromagnetic energy into the chest cavity of the patient; and generate radio frequency information in response to reflected radio frequency electromagnetic energy reflected from the chest cavity of the patient and received by the one or more radio frequency antennas. The one or more processors may be configured to: process the one or more ECG signals, the one or more cardiac vibration signals, and the radio frequency information to generate a plurality of physiological parameters of the patient including more than one combined physiological parameter; perform trend analysis on the plurality of physiological parameters including the combined physiological parameter to generate trend results; update a monitoring schedule for the patient based on the trend results; determine a current clinical condition of the patient based on the trend results; compare the current clinical condition of the patient with predetermined clinically actionable criteria to determine one or more clinically actionable events; and cause an output device to provide an output related to the one or more clinically actionable events.

[0152] In another implementation, a patient monitoring system may include: an ECG sensor coupled to a patient and configured to detect one or more ECG signals of the patient; a vibration sensor coupled to a patient and configured to detect one or more cardiac vibration signals of the patient; a radio frequency ultra-wideband transceiver circuit including one or more radio frequency antennas and located on at least one major artery of the patient; and one or more processors. The radio frequency ultra-wideband transceiver circuit may be configured to: cause the one or more radio frequency antennas to direct radio frequency electromagnetic energy into at least a portion of the patient; and generate radio frequency information in response to reflected radio frequency electromagnetic energy reflected from at least a portion of the patient and received by the one or more radio frequency antennas. The one or more processors may be configured to: process the one or more ECG signals, the one or more cardiac vibration signals, and the radio frequency information to generate a plurality of physiological parameters of the patient including more than one combined physiological parameter; perform at least one of a predictive analysis and a correlation analysis of the plurality of physiological parameters including the combined physiological parameter to determine a current clinical condition of the patient; compare the current clinical condition of the patient with a predetermined clinically actionable criterion to determine one or more clinically actionable events; and cause an output device to provide an output related to the one or more clinically actionable events.

[0153] As described herein, one or more processes can be used to provide predictive and trend analysis for a patient. For example, a predictive analysis process can be created for various different heart diseases that uses data from the patient's medical device, including recorded ECG data, recorded vibration data, and information related to radio frequency information collected for the patient. Predictive analysis can be used to determine the patient's current state and any clinically actionable events and possible outcomes for the patient. Fig. 9 A sample overview of the predictive analysis process is shown. A set of metrics 900 (including metric 1, metric 2, and metric 3) can be provided to the prediction process 905. Depending on the design of the process and the expected output, various types of programming can be used for the prediction process 905. For example, the prediction process 905 can use machine learning and / or artificial neural networks (both of which are described in more detail below). By processing the input metrics 900, the prediction process 905 can generate one or more outputs 910. For example, the output 910 can include the current state of the patient, any possible adverse events that may occur in the patient in the near future (e.g., cardiac events that may occur in the next 30 days), and any clinically feasible events that should be taken by the patient or related to the patient. In some implementations, the output 910 can be fed back into the prediction process so that the process learns from the results and adjusts its prediction score based on changes in the patient's condition.

[0154] Fig.10 A sample overview of a trend analysis process is shown. Process 1000 may include monitoring a first metric 1005. If a change is detected in the first metric 1005 or the first metric exceeds a certain threshold, process 1000 may trigger monitoring a second metric 1010. Similarly, if a change is detected in the second metric 1010 or the second metric exceeds a certain threshold, process 1000 may trigger monitoring a third metric 1015. If process 1000 detects a change in the third metric 1015, the process may output 1020 an indication to, for example, the patient or the patient's physician. For example, the output may include a suggested change to a treatment regimen, such as a change to a patient's medication, etc. As shown, output 1020 may be fed back into the trend analysis process to cause the process to adjust its response to changes in the underlying metric.

[0155] It should be noted that Fig. 9 and 10 The overviews shown are shown by way of example only. For example, three metrics are shown in the two overviews as an example of the number of metrics that can be used. In actual applications, various other numbers of input metrics can be used for both the predictive analysis process and the trend analysis process.

[0156] exist Fig. 9 and 10In one implementation of the general scheme shown, metric 1 is an ECG metric, metric 2 is a bio-vibration metric (including heart vibration, lung vibration, and low-frequency patient movement data), and metric 3 is an RF-based physiological metric. Alternatively or additionally, one or more of metrics 1, 2, and 3 include a combined metric derived from one or more of an ECG metric, a bio-vibration metric, and an RF-based physiological metric.

[0157] Fig.11 and 12 A patient monitoring system for indicating clinically actionable events based on changing physiological information of a patient is shown. The system can determine, analyze and / or classify and notify clinically actionable events according to predetermined clinically actionable criteria.

[0158] like Fig.11 As shown, the system 1100 receives various signals from the patient 1105. For example, the system 1100 can receive the patient's ECG signal 1110, bio-vibration signal 1115, and radio frequency signal 1120 from, for example, a wearable medical device coupled to the patient 1105. As shown, the output 1155 of the prediction or trend analysis classifier 1150 can be fed back to the prediction or trend analysis classifier 1150 in a closed loop manner. For example, monitoring can be initiated for only one set of physiological parameters (such as ECG signal 1110, etc.). Over time or in response to a specific state as described herein, additional physiological parameter sets other than ECG parameters, such as bio-vibration signal 1115 or radio frequency-based signal 1120 (or a combination thereof), etc., can be initiated.

[0159] In a particular implementation, the ECG signal 1110 may be processed and result in the development of ECG-based metrics 1125, such as, but not limited to, heart rate, heart rate variability, ST segment elevation, premature ventricular contraction (PVC), heart rhythm morphology, and other similar ECG metrics. Specific details related to the extraction of ECG-based metrics 1125 are described in further detail below. Similarly, the bio-vibration signal 1115 may be processed and result in the development of bio-vibration metrics 1130, such as heart vibration intensity values, lung and other lung vibration intensity values, LVST values, and other similar bio-vibration values. In addition, the radio frequency signal 1120 may be processed and result in the development of radio frequency metrics 1135, such as pleural fluid level values, heart wall motion metrics, and blood pressure. Metrics 1125, 1130, and 1135 may be combined into a set of physiological metrics 1145.

[0160] In addition, the above physiological metrics can be extended to include combined physiological metrics. For example, the combined physiological metrics can include metrics derived from two or more of the metrics 1125, 1130 and / or 1135. An example of a combined physiological metric is EMAT. EMAT represents the quantification of the time from the start of the Q wave of the ECG signal to the closure of the mitral valve, determined by the S1 heart vibration. Typically, an extended EMAT value is 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 main RR interval in the ECG signal, and represents the efficiency of the pumping function of the heart. %EMAT of >15% can highly predict the risk of hospitalization again due to heart failure when the patient is discharged and after the patient is discharged. In an example, the cardiac acoustic vibration parameters derived from the heart or heart vibration signal include LVST. LVST can be calculated as the interval (S1-S2) from S1 to S2. A combined metric based on the LVST and RR interval information from the patient's ECG signal can include %LVST. For example, %LVST can be calculated as the ratio of the interval from S1 to S2 relative to the RR interval, such as (S1-S2 / RR). Another example of a combined physiological metric is the ratio of EMAT / LVST, which helps determine the degree of left ventricular dysfunction. Another example of a combined physiological metric is the systolic dysfunction index (SDI). SDI is a multiplicative combination of ECG and vibration parameters. SDI has been shown to predict left ventricular systolic dysfunction with high specificity. The multiplicative score SDI is derived from QRS duration, QR interval, %EMAT and S3 vibration intensity. SDI is reported as a value between 0 and 10. Other combined metrics can include %LVST, left ventricular end-diastolic pressure (LVEDP), and other related combined metrics derived from two or more of the physiological metrics described herein.

[0161] Reference again Fig.11 In some examples, physiological metrics 1145 can be expanded with patient demographic and patient medical history information 1140. For example, patient demographic information can include age, gender, race, etc. For example, patient medical history information includes past medical conditions, diagnoses, past hospitalizations, etc. A sample patient history record can include information as shown below, and a sample input to a patient monitoring system is also shown in Table 3 below.

[0162]

[0163] Table 3

[0164] In some implementations, additional physiological metric sets may be derived based on patient activity test data 1142 from one or more physical activity tests performed by the patient while wearing the wearable medical device. For example, as shown below, the device may monitor one or more activity tests performed by the patient. In one example, the activity may be a physical assessment ordered by a physician, such as by WalkTest by WCD TM Activity Assessment. The purpose of the assessment is to monitor the patient's progress during the assessment of monitoring parameters such as the number of steps, distance traveled during the assessment, and the patient's rate of movement during approximately 6 minutes of walking.

[0165] Before and after walking, the patient may be asked to take a health survey, answering one or more questions related to the patient's overall health. For example, the patient may be asked to indicate the level of shortness of breath (e.g., an exemplary scale may be 0 = feeling normal, 0.5 = being able to maintain a conversation while walking, 1 = need to stop immediately). Another inquiry may be related to the patient's fatigue level (e.g., how tired the patient feels). After the assessment, the patient may be prompted to answer the same set of questions or additional questions again. The answers to these questions may be standardized into a series of physiological parameters (e.g., stored as values ​​of 0 to 1, 0 to 10, 0 to 100 or any other suitable range) and input into prediction and / or trend analysis. Although numerical ranges are described here, other scales, ranges and / or methods of quantifying the patient's answers to the health survey may be used. The patient's physician prescriber may allow the patient to repeat the assessment every day or every week. When the patient is scheduled for an assessment next time, the device may provide a reminder to the patient via a user interface. Although the health survey described here is conducted in the context of a physical assessment, in some implementations, a health survey may be given to the patient wearing the device separately from the physical assessment. For example, the device can prompt the patient to take a health survey on a regular basis (e.g., daily, weekly, or some other schedule). In some examples, the patient's physician can configure the device to administer the health survey as needed. In these cases, the patient's physician can instruct a technician to cause the remote server to send one or more operational commands to the wearable medical device to administer the health survey.

[0166] The distance walked within the assessment duration (e.g., 6 minutes) can indicate the patient's current clinical condition. For example, if the patient walks less than a preset duration (such as 350 meters), the patient can be scored as having a relatively high risk of death relative to patients who cover more than 350 meters. In some examples, the input to the prediction and / or trend analysis may be the raw distance covered by the patient. In other examples, the distance can be standardized according to a predetermined scale. For example, a standardized scale representing the distance covered by the patient during the activity can be generated. For example, a scale of 0.0 to 1.0 representing the distance covered is shown below in Table 4:

[0167] Example Assessment Scoring · Exemplary patient presentation during assessment ·0 The patient walked more than 1000 meters during the six-minute walk test. ·0.25 Patients walked between 600 and 999 meters during the six-minute walk test. ·0.5 Patients walked between 350 and 599 meters during the six-minute walk test. ·0.75 Patients walked between 100 and 349 meters during the six-minute walk test. ·1 The patient walked less than 100 meters during the six-minute walk test.

[0168] Table 4

[0169] In some examples, when using a clinician-provided stride length, the clinician inputs the stride length into the device via a user interface to measure potential differences in distance. In some implementations, a standardized stride length (e.g., based on similar patient population data) can be implemented when calculating the distance covered.

[0170] Additionally or alternatively, the device may track the number of steps taken by the patient over the duration of the assessment (e.g., 6 minutes). The accelerometer data may be analyzed to count, for example, heel strikes (which may be detected, for example, if the sum of the three measurement axes of the accelerometer exceeds a preset threshold). For example, a scale of 0.0 to 1.0 representing steps taken is shown below in Table 5:

[0171] Example Assessment Scoring · Exemplary patient presentation during assessment ·0 The patient walked more than 500 steps during the six-minute walk test. ·0.25 Patients walked 300 to 499 steps during the six-minute walk test. ·0.5 Patients walked between 175 and 299 steps during the six-minute walk test. ·0.75 Patients walked between 50 and 174 steps during the six-minute walk test. ·1 The patient takes fewer than 50 steps during the six-minute walk test.

[0172] Table 5

[0173] In some examples, the input to the prediction and / or trend analysis can be the raw number of steps taken by the patient. In other examples, the number of steps can be normalized according to a predetermined scale.

[0174] Another parameter that can be tracked includes the pace during the assessment, e.g., steps per minute and / or distance covered per minute. As previously described, in some examples, the input to the prediction and / or trend analysis can be the patient's raw pace information. In other examples, the pace can be standardized according to a predetermined scale. For example, during the standardization process, the metric can be transformed and stored as a value ranging from 0 to 1, 0 to 10, 0 to 100, or any other suitable range, and input into the prediction and / or trend analysis. Although numerical ranges are described herein, other scales, ranges, and / or methods of quantifying a patient's metrics can be used. Additional patient metrics can include:

[0175] Heart rate during the evaluation period (average, peak, mean, mode)

[0176] Respiration rate during assessment

[0177] Whether the patient completed the test (yes / no) or the percentage of patients who completed the test

[0178] Whether the patient has performed a walking test – could be an indicator that the patient is having difficulty / getting worse

[0179] As described above, all physical activity assessment metrics may be normalized according to a predetermined scale and input into predictive and / or trend analysis.

[0180] In some implementations, in addition to or as an alternative to the above, the patient is TM The overall performance in the physical assessment of the above-mentioned physical assessment can be scored on a standardized metric. The overall performance score can be based on the individual scores of the components of the physical assessment, such as those described above, and the information related to the health assessment. For example, as shown in the following table, the overall performance can be rated on a scale ranging from 0 to 1.

[0181]

[0182] Table 6

[0183] Reference again Fig.11 , the complete data set of physiological metrics 1145 is delivered to a prediction or trend analysis classifier 1150, and an output 1155 is generated. Now referring to Fig.12 As shown in the system 1200, the output 1155 of the prediction or trend analysis classifier 1150 may include a score indicating the patient's current overall clinical condition 1205. In the event that the patient's classification deteriorates (e.g., the clinical condition score has a trend of deterioration and / or crosses a threshold), the system may prompt a specific action. In one example, the classifier may output a score between 0 and 1 indicating the overall patient condition, wherein a score at the lower end of the scale (e.g., between 0.0 and 0.25) may indicate a stable patient that is not causing concern, while a score at the upper end of the scale (e.g., above 0.50) may indicate a poor patient condition that requires close monitoring (e.g., indicating the possibility of an adverse event). For example, such an adverse event may include one or more of an arrhythmic event (VT / VF), a stroke event, a syncope event, and a hospitalization event. Based on the current patient condition 1205, the system 1200 may generate a recommended clinically feasible event, such as adjusting the patient's treatment plan 1210 and delivering the generated recommendation to a caregiver such as a physician 1220.

[0184] In certain implementations, information related to changes in the treatment plan can be fed back to the Fig.11A prediction or trend analysis classifier 1150 is shown. This feedback loop can improve the predictions of the trend analysis classifier 1150 (including information related to changes in the treatment plan and the patient's response to the changes).

[0185] In addition to or as an alternative to observing trends in the output scores, the scores may be subject to one or more threshold conditions. For example, the threshold conditions may trigger one or more clinically actionable events. Table 7 below provides an exemplary set of patient status score categories, threshold ranges, and current patient status information.

[0186]

[0187]

[0188] Table 7

[0189] In some implementations, the above scoring categories can be a part of a proprietary scoring scheme implemented in a proprietary device according to the embodiments described herein. In certain other implementations, the process can classify patients according to the heart failure classification adopted by a physician or hospital group, association or other regulatory agency. For example, this authority 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 can automatically classify patients into appropriate heart failure categories and / or stages based on the above-mentioned similar scoring schemes. In some implementations, the user can pre-configure which classification scheme the device will implement via user settings parameters. For example, the user can be prompted to indicate the classification scheme according to one or more following options when setting. The user can indicate its options via a user interface (for example, locally in the device or via a remote configuration parameter on a server, which is then sent to the device).

[0190] Proprietary scoring scheme (as described above)

[0191] ACC / AHA program

[0192] NYHA regimen

[0193] The ACC / AHA approach can be implemented as follows:

[0194] Stage A: Patients at risk for heart failure who have not yet developed structural cardiac changes (ie, patients with diabetes, patients with coronary artery disease but without prior infarction)

[0195] Stage B: Patients with structural heart disease (ie, reduced ejection fraction, left ventricular hypertrophy or dilatation) who have not yet developed symptoms of heart failure

[0196] Stage C: Patients with clinical heart failure

[0197] Stage D: Patients with refractory heart failure who require advanced intervention (ie, biventricular pacemaker, left ventricular assist device, transplantation)

[0198] The techniques described above can be used to map the scores from the process taught herein to the stages as defined by the ACC / AHA protocol. For example, Table 8 below shows the correlation between the scoring techniques described above and the ACC / AHA protocol implementation:

[0199]

[0200] Table 8

[0201] The NYHA regimen can be implemented as follows. The NYHA divides each diagnosis into four categories. Class I and Class II are considered mild. Class III is considered moderate, and Class IV is severe. In Class I, there are no restrictions on physical activity. Patients generally do not complain of excessive fatigue or experience shortness of breath. Patients are still able to manage the disease. Regular exercise, limiting alcohol, and eating a healthy diet (with moderate sodium intake) are all easy actions to take. High blood pressure needs to be managed. Quitting smoking is crucial.

[0202] In the case of Class II heart failure, the patient will feel slight limitations in daily physical activities such as bending or walking. They will tire on exertion and may experience shortness of breath. Non-invasive surgical procedures such as ACE inhibitors or Beta blockers (depending on the patient) may be considered.

[0203] Class III heart failure patients experience some limitations during physical activity. They may remain comfortable at rest, but most strenuous activities will result in excessive fatigue. Under the care of a physician, their diet and exercise may be monitored. Diuretics may be prescribed to combat water retention.

[0204] Patients with Class IV heart failure can barely perform any physical activity without discomfort. There may be obvious signs of heart problems even at rest. Surgical options will be explored, as will treatments for Classes I-III.

[0205] The techniques described above can be used to map the scores from the process taught herein to the stages as defined by the NYHA scheme. For example, Table 9 below shows the correlation between the scoring techniques described above and the NYHA scheme implementation:

[0206]

[0207] Table 9

[0208] Depending on the classification and / or score of the patient at any given time, one or more events can be triggered. Such events can be automatic events that are triggered without user input. For example, the system can automatically instruct an external medical device (e.g., a wearable defibrillator) coupled to the patient to increase the sensitivity of its detection process during a time period when the patient may be at an increased risk of a sudden cardiac arrhythmia event. Alternatively, the system can output information related to the patient's current condition and provide guidance to caregivers and / or other people to take action. Such actions can include suggesting changes to the patient's treatment plan, such as changing the dosage of a drug or placing the patient under a higher degree of observation or hospitalizing the patient.

[0209] For example, clinically actionable events can be directed to external medical devices (e.g., wearable defibrillators), such as, but not limited to, changes in trigger controllers, such that the time from detection of sudden cardiac arrest to treatment is shortened. In addition, detection of categories with increased risk scores can prompt the system to notify the patient, physician, responsible third party, medical team, and / or technical support of the change in risk. In this way, patients in categories with increased risk scores can be marked for more frequent future observations and / or changes in treatment plans.

[0210] In some implementations, if the patient's clinical condition is deteriorating, the caregiver and / or technical support personnel may cause the patient's external medical device to initiate real-time or substantially real-time streaming of the patient's ECG data (and / or other physiological data) to a remote server for additional monitoring and analysis. Fig.12 As shown, if the current patient condition 1205 indicates a worsening condition, the system can send an indication to a remote server for various notification and / or analysis actions 1215.

[0211] In some examples, the periodicity of reporting and / or metric components and analysis for such patients may be increased (e.g., from once every several or more hours to once every hour). In some examples, additional monitoring and / or reporting of the patient's condition and various physiological parameters may be initiated for the duration of the time period of interest to the patient's condition (e.g., until the patient's condition stabilizes or improves).

[0212] In some implementations, if the patient's condition has worsened but has not yet reached a predetermined critical threshold, it may be deemed that no immediate action is required (e.g., in the above example, if the classifier scores the patient's current condition at or above 0.5 but below 0.65, the physician or technical support personnel may initiate more frequent reporting of the patient's physiological condition (e.g., medical reporting of the patient's condition) or initiate streaming of ECG data). In addition, if the patient is placed in score category 3 (e.g., at or above 0.5), the physician or technical support personnel may take additional actions, including, for example, instructing more frequent checks of external medical devices and / or ensuring that downtime for continued monitoring is kept to a minimum.

[0213] In the event of a high cardiac arrest for a patient in scoring category 4, actions that may be taken are, but are not limited to, notifying the patient and responsible third parties to seek medical attention and notifying the responsible medical team of the patient's risk status.

[0214] Adjustments to the treatment plan 1210 can be based on changes to the medication given to the patient to control and / or treat the patient's underlying heart failure condition or symptoms. As previously mentioned, heart failure is generally a chronic, long-term condition that may worsen over time. Under the ACC / AHA program, there are 4 stages of heart failure (stages A, B, C, D). As the patient's condition worsens, the patient's heart muscle tends to pump less blood to its organs, and the patient enters the next stage of heart failure. In the standard care program, the goal of HF treatment is to prevent the patient from developing through different stages or to slow down development. The treatment of each stage of heart failure may involve changes in medication, lifestyle behavior, and cardiac devices. In various implementations, the patient monitoring system can make recommendations based on ACC / AHA or NYHA treatment guidelines. The following outlines a basic care plan that can be applied to patients based on the patient's stage / classification.

[0215] Depending on the implementation, the patient monitoring device and / or system may suggest one or more of the following actions. These actions may be suggested directly to the patient via the user interface of the device. In some cases, the proposed treatment plan and / or changes to the treatment plan may be suggested to the patient's primary caregiver and / or physician.

[0216] Typical ACC / AHA Stage A is considered pre-heart failure. At this stage, the patient is monitored for hypertension, diabetes, coronary artery disease, metabolic syndrome, history of alcohol abuse, history of rheumatic fever, family history of cardiomyopathy, history of taking medications that may damage the heart muscle (such as certain cancer drugs). Exemplary Stage A treatment plans that a patient monitoring system may recommend include the following:

[0217] ECG monitoring only

[0218] ○ The monitoring device may not initiate biovibration and / or RF-based TFC monitoring of the patient

[0219] Exercise regularly, be active, and walk every day

[0220] Quit smoking

[0221] Treatment for high blood pressure (medication, low-sodium diet, active lifestyle)

[0222] Treatment for high cholesterol

[0223] · No alcohol or recreational drug use

[0224] ·drug:

[0225] ○ Angiotensin-converting enzyme inhibitors (ACE-I) or angiotensin II receptor blockers (ARBs) if the patient has coronary artery disease, diabetes, high blood pressure, or other vascular or heart disease

[0226] ○ If the patient has hypertension, use beta blockers

[0227] ACC / AHA Stage B is considered pre-heart failure. This means that the patient has been diagnosed with at least left ventricular systolic dysfunction, but may never have had symptoms of heart failure. Most people with stage B heart failure may have an echocardiogram (echo). This echocardiogram shows an ejection fraction (EF) of 40% or less. This category can include people with heart failure and reduced EF (HF-rEF) for any reason. An exemplary stage A treatment plan that a patient monitoring system may recommend includes the following:

[0228] Continue or modify the actions listed in Stage A

[0229] o For example, the monitoring device may initiate bio-vibration and / or radio frequency-based TFC monitoring of the patient.

[0230] o For example, the frequency of TFC measurements can be increased. If TFC is initially measured once a week, this can be changed to once every 2 to 3 days.

[0231] o For example, the monitoring device may initiate a physical assessment and / or physical test of the patient.

[0232] Add an angiotensin-converting enzyme inhibitor (ACE-I) or angiotensin II receptor blocker (ARB) if it is not already part of the patient's Phase A management plan

[0233] Add a Beta Blocker if the patient has had a heart attack and the patient’s EF is 40% or less (if the patient is not already part of a Phase A treatment plan)

[0234] If the patient has had a heart attack or has diabetes and an EF of 35% or less, add an aldosterone antagonist (to reduce the risk that the heart muscle will become enlarged and pump poorly)

[0235] Possible wearable cardioverter-defibrillator therapy

[0236] Consider possible valve surgery or intervention as a treatment for coronary artery blockage, heart attack, valvular disease (patients may need valve repair or replacement valve surgery), or congenital heart disease.

[0237] People with ACC / AHA stage C have generally been diagnosed with heart failure and are currently or have previously shown signs and symptoms of the condition. There are many possible symptoms of heart failure. The most common are:

[0238] Shortness of breath

[0239] · Feeling tired (fatigue)

[0240] Less able to exercise

[0241] · Weak legs

[0242] Getting up to urinate

[0243] Swelling (edema) in the feet, ankles, calves, and abdomen

[0244] An exemplary Stage C treatment plan that a patient monitoring system might recommend includes the following:

[0245] Continue or modify the actions listed in Stages A and B

[0246] o For example, the monitoring device may initiate (if not already monitoring) bio-vibration and / or radio frequency-based TFC monitoring of the patient.

[0247] o For example, the frequency of TFC measurements can be increased. If TFC was previously measured every 2 to 3 days, this can be changed to once a day.

[0248] o For example, the monitoring device may initiate frequent physical assessments and / or physical tests on the patient.

[0249] Add a beta blocker (if the patient is not already taking such a medication)

[0250] If vasodilators (eg, ACE-I, ARB, or angiotensin receptor / neprilysin inhibitor combination) and beta-blockers do not relieve the patient's symptoms, add an aldosterone antagonist (if the patient is not already taking such a medication)

[0251] If other treatments do not relieve the patient's symptoms, add a hydralazine / nitrate combination.

[0252] If, for example, the patient's heart rate is greater than 70 beats per minute and the patient is still symptomatic, add medication that can slow the heart rate

[0253] If pleural fluid content and / or S3 intensity continues to worsen, add a diuretic (“water pill”)

[0254] ·Restriction of dietary sodium (salt) is recommended.

[0255] It is recommended to track the patient's weight on a daily basis.

[0256] If pleural effusion volume and / or S3 intensity continue to worsen, possible fluid restriction

[0257] Possible cardiac resynchronization therapy (eg, biventricular pacemaker)

[0258] Possible implantable cardioverter defibrillator (ICD) therapy

[0259] If treatment makes the patient's symptoms better or stops, the patient may still need to continue treatment to slow progression to stage D.

[0260] Patients with stage D and reduced EF (HF-rEF patients) have advanced symptoms that generally do not get better 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 the following:

[0261] Continue with and / or modify the actions listed in Stages A, B, and C

[0262] ·Evaluate more advanced treatment options, including:

[0263] Heart transplantation

[0264] Ventricular assist device

[0265] Cardiac surgery

[0266] Continuous infusion of intravenous inotropic drugs

[0267] Palliative or end-of-life care

[0268] Research treatment

[0269] The 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 count, activity, noise quantization, atrial fibrillation, brief pauses, heart rate oscillations, QRS height, QRS width, changes in morphological size or shape, cosine RT, artificial pacing, corrected QT interval, QT variability, T wave width, T wave alternans, T wave variability, ST segment changes, early repolarization, late potentials, fragmented QRS / HF content, and fragmented T wave / HF content.

[0270] The control unit may detect reference points in the ECG signal (e.g., points corresponding to the P wave, Q wave, R wave, S wave, and T wave) to extract individual measurements (e.g., QRS, PVC, etc.) from the physiological parameter data. For example, the QT interval may provide a measure of heart failure in the subject, and the distance between the Q point and the T point may be determined and extracted from the physiological parameter signal.

[0271] Fig.13 A two-lead ECG signal is shown, including a plot 1300 of a side-to-side (SS) lead and a plot 1305 of a front-to-back (FB) lead. In a particular implementation, the processing device may be configured to identify various information (such as QRS measurements and PVC parameters, etc.) in each ECG signal for extraction. For example, the processing device may apply a QRS detector and a PVC detector to the ECG signal to extract QRS measurement information 1302 and PVC measurement information 1304 from the SS lead plot 1300. The processing device may also extract, for example, PVC measurement information 1306 from the FB lead plot 1305.

[0272] In a particular implementation, the processing device may use the extracted QRS and PVC measurements and / or the reference points determined by the QRS detector and the PVC detector to identify and extract various other measurements or parameters in the ECG signal, such as heart rate variability (HRV), RR intervals, etc. For example, the outputs from the QRS detector and the PVC detector may be used by an AFIB detector, an interval detector, a pace detector, a morphology detector, a T wave detector, and / or any other detector in a control unit for extracting measurements or parameters from the ECG signal. QRS, PVC, and other detectors are well known in the art, for example, as described in The Principles of Software QRS Detection (Kohler, Hennig et al.), IEEE ENGINEERING IN MEDICINE AND BIOLOGY (January / February 2002), the entire contents of which are incorporated by reference.

[0273] HRV measurement quantifies the variability of the RR intervals in the patient's electrocardiogram signal over time. The R wave of a particular heartbeat corresponds to a point in the cardiac cycle during early systole and provides a reliable time reference for making cardiac cycle-to-cycle measurements from a signal processing perspective. HRV is influenced by the autonomic nervous system, which consists of the sympathetic nervous system (SNS) and the parasympathetic nervous system (PNS). The observed HRV is considered to be an indicator of the dynamic interaction and balance between the SNS and PNS, providing a measure of the capacity of the nervous system. HRV is used as an indicator for diagnosing and evaluating various conditions affected by the autonomic system, ranging from congestive heart failure to sleep apnea. For example, reduced HRV has been found to be a predictor of increased mortality from coronary heart disease in the elderly. Reduced HRV can also be seen after sudden cardiac arrest.

[0274] A variability measure related to HRV is T-wave alternans, which is a measure of the variation in myocardial recovery during the diastole (relaxation) phase and measures the fluctuation in the amplitude of the T wave of the ECG.

[0275] In one example, extracting HRV data may include filtering the ECG signal to remove noise and artifacts; locating the QRS complex within the filtered ECG signal; finding the RR interval between consecutive R peaks; and processing the RR interval to obtain HRV. For example, the ECG signal is filtered using a bandpass filter and the QRS complex is located. A bandpass filter having an operating frequency range wider than the frequency components of the QRS complex must be used. The frequency components of the QRS complex are between 10 and 25 Hz. Therefore, in one embodiment of the present invention, the operating frequency range of the bandpass filter is between about 5 Hz and about 28 Hz.

[0276] In one example, the R wave can be located as follows. The maximum peak data value that first appears in the filtered ECG signal is located. The upper amplitude threshold and the lower amplitude threshold are determined based on the located maximum peak. The peak and the minimum value on both sides of the peak are located. In this embodiment of the present invention, the two sides refer to the left and right sides of the peak. Check whether the condition that the peak value is higher than the upper amplitude threshold and the minimum value is lower than the lower amplitude threshold is met. If this condition is met, the position of the peak is represented as the R position. The position of the minimum value that most recently appeared on the left side of the R position is represented as the Q position, and the position of the minimum value that most recently appeared on the right side of the R position is represented as the S position. With reference to the time scale on which the filtered ECG signal is plotted, the Q position appears at the position where the minimum value first appears before the R position, and the S position appears at the position where the minimum value first appears after the R position. The position of the QRS peak within the filtered ECG signal is therefore determined.

[0277] In one embodiment of the present invention, given a 1D array of ECG sample points x(n), after finding the maximum value (ref_peak) within the first few seconds of the data, an upper amplitude threshold and a lower amplitude threshold (T upper and T lower ). The threshold is defined as:

[0278] T upper =ref_peak+0.4*ref_peak

[0279] T lower =ref_peak-0.35*ref_peak

[0280] Then, an R wave is considered to occur at point i if the following conditions are met:

[0281] x(i) is located in T upper and T lower between;

[0282] x(i+1)-x(i)<0; and

[0283] x(i)-x(i-1)>0;

[0284] Among them, the R peak is the point with the maximum value.

[0285] The position of the other R wave in the filtered ECG signal can be located by iterating the following process: locate another peak and locate other minimum values ​​on both sides of the other peak. In the case where the other peak is higher than the upper amplitude threshold and the other minimum values ​​are lower than the lower threshold, the position of the peak is represented as the R position. The position of the minimum value that most recently appeared on the left side of the R position is represented as the Q position, and the position of the minimum value that most recently appeared on the right side of the R position is represented as the S position. In this way, the position of another QRS peak is determined.

[0286] For example, heart rate variability data may include time domain data, frequency domain data, and geometry domain data.

[0287] The time domain data may include information relating to any one or more of the following parameters: the mean of the RR intervals (mean RR), the standard deviation of the RR intervals (STD), the mean of the instantaneous heart rate (mean HR), the standard deviation of the instantaneous heart rate (STD_HR), the root mean square of the difference between adjacent RR intervals (RMSSD), the number of consecutive RR intervals that differ by more than 50 ms (NN50), and the percentage of consecutive RR intervals that differ by more than 50 ms (pNN50).

[0288] The frequency domain data may include information related to 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 to 0.15 Hz) (LF), power in the high frequency range (0.15 to 0.4 Hz) (HF), total power (TP) estimated from the variation of NN intervals within a segment and measured in ms2, ratio of LF power to HF power (LF / HF), LF power expressed in normalized units (LF / (TP-VLF)×100 (LF norm )), and HF power in standardized units (HF / (TP-VLF)×100(HF norm )).

[0289] All of the above physiological parameters and metrics associated with the patient's condition are collected as described. Within the physiological parameter data, one data set may not contain the same number of parameters as another data set. In addition, the patient parameters can be stored as digital data converted from the form (such as an analog signal) in which each of the four parameters was originally obtained, thereby obtaining the original form of the measurement. Data of patient characteristics (such as demographics and medical history, etc.) can be sent to the system via a wireless network distributed through a hospital or physician network. All physiological parameters can be used to train the predictive analysis process. In addition, patient demographics (e.g., age, gender) and medical history information can be used to train the process. At the end of the training phase, the parameters found to be most relevant to achieving high accuracy will be used as input to the real-time detection system.

[0290] The physiological parameters may be stored in an electronic database. In an example, the data includes a plurality of data sets, each data set having at least one of a first parameter associated with cardiac vibration data and a second parameter associated with a radiofrequency-based pleural fluid content level. Each of the plurality of data sets also has a third "output" parameter associated with a patient condition, such as a patient condition score.

[0291] The electronic database for storing patient physiological parameters may be a memory module such as a hard drive, an optical disk, or a solid-state device. During the training phase of the artificial neural network, the training patient physiological parameters may be obtained from hospital records or from a field study of a patient pool, wherein the pool includes at least one patient group designated as a control group. Thus, the patient physiological parameters may include data for patients with various heart-related diseases, patients who may be considered healthy (such as patients with no signs of heart disease, etc.), and further various demographic patients.

[0292] A third output parameter is also trained within the process. This parameter is occasionally referred to as an outcome (e.g., death, other adverse event, recovery from an adverse event, or the patient's current condition). The electronic device may include a processor or memory module that stores instructions for implementing the trained process so that the device can analyze the physiological parameters of the patient being examined. The output of the electronic device can then be used to assist an operator or medical professional in predicting the patient's outcome, thereby making appropriate clinical decisions about how to treat the patient.

[0293] For example, the process used may depend on the type of medical event to be predicted and classify or categorize the patient into an appropriate heart failure score category (or NYHA class or ACC / AHA stage) based on the event. For example, the processing device may be configured to use a first process or process for calculating event estimates for a risk score for cardiac arrest, and a different second process or process for calculating event estimates for a risk score for ventricular fibrillation. Thus, the risk of an impending acute deterioration of the subject's medical condition to cardiac arrest or other serious cardiopulmonary disease may be calculated by various methods. Different methods and processes may be used to calculate event estimates for risk scores for different time periods. For example, the processing device may be configured to use a first process or process for calculating event estimates for a risk score for cardiac arrest within a first time period, and a different second process or process for calculating event estimates for a risk score for cardiac arrest within a different second time period.

[0294] In some implementations, a machine learning classifier as described in further detail above can be trained on a large population (e.g., a population ranging from thousands of patient records to tens of thousands of patient records, where the patient records include electrophysiological information, demographic information, and medical history information). Machine learning tools can include, but are not limited to, classification and regression tree decision models, such as random forests and gradient boosting, etc. (e.g., implemented using R or any other statistical / mathematical programming language). Any other classification-based machine learning tools can be used, including artificial neural networks (as described in more detail below) and support vector machines. Because machine learning tools can be computationally intensive, some or all of the processing of the machine learning tools can be performed on a server separate from the medical device.

[0295] An overview of how the Random Forest tool can be applied to a given data set can show how the classification tool can work when interpreting a given parameter or metric. A random forest is a collection of decision trees. A decision tree is a flow chart-like structure in which each node represents a test on a metric and each branch represents the result of the test. The tree ends with a classification label (e.g., the decision ultimately made after calculating each metric). Each tree in the Random Forest tool gets a "vote" when classifying a given set of metrics. Two random components are involved in building a random forest. First, when creating each tree, a random subsample of the total data set is selected to grow the tree. Second, at each node of the tree, a "separator variable" is selected and the underlying patients are divided into two categories. For example, a class of patients (e.g., responding or experiencing sudden cardiac arrest) can be separated from another class of patients (e.g., unresponsive). The tree grows using additional separator variables until all terminal nodes (leaves) of the tree are completely one class or another. The tree is "tested" for patient records that have previously been set aside. Each patient test record traverses the tree, descending one branch or the other depending on the metrics of the various separator variables included in the record. The patient test record is assigned a predicted outcome (vote) based on the record's position in the tree. The entire process can be repeated with new random splits of the base data set to produce additional trees and ultimately a "forest." In each case, a different subset of patients can be used to build the tree and test the tree's performance.

[0296] In producing the results described in the following exemplary implementation, a predetermined number of model variations are trained. For example, each model variation is labeled sequentially (e.g., labeled 1 to 100 for 100 runs). In each run of the model, the software randomly samples a predetermined portion of the population (e.g., 80% portion) as a training set and sets aside the remaining portion (e.g., 20%) as a validation set.

[0297] As described above, the machine learning tool can train a classifier on the first part of the basic data set and verify the classifier on the second part of the data set or another separate data set. When evaluating the performance of each classifier, the performance of the basic decision in the decision tree in the random forest can be evaluated based on the specificity parameter and the sensitivity parameter. For example, the sensitivity parameter can be based on the measure of the ability of the classifier to correctly predict whether the patient is at risk of treatment according to the appropriate scoring category. For example, the sensitivity parameter can be based on the proportion of appropriately treated patients in patients who are correctly predicted by the model to be at risk of being treated. The specificity parameter can be based on the proportion of patients who are not treated and are predicted by the relevant classifier to be not at risk of treatment. It can be advantageous to optimally balance various performance variables such as sensitivity and specificity at a high level. For example, by setting the specificity to a relatively high value (e.g., 95%), the basic threshold in the classifier model can be adjusted to minimize false positives. After defining the specificity, the measure of sensitivity can be regarded as a type of performance measure (e.g., for a given model, generally in the range of 15 to 35%), however, smaller or larger values ​​of sensitivity are also possible.

[0298] For example, the prediction performance of the trained model can be verified by the verification scheme described below. In implementation, the verification period can be used to clarify the appropriate threshold score for classifying future patients (when the result is currently unknown and the prediction of the desired result), and can be used to determine the prediction performance of each classifier model generated by the machine learning tool. In order to verify various classifiers and related threshold scores, a second group of individuals can be used, for example, a verification population (or queue). For example, the verification population used can be a new verification population. When these patients progress to the end of the use of the device, the results of the patients in the verification queue are finally learned. In an embodiment, the patient in the verification population can be different from the above-mentioned one group of training and test patients for training the classifier. For example, the verification population of the patient and its related metrics (verification metrics) can be independent of the training population of the patient and its related metrics (training metrics). In some implementations, there may be overlap between the verification metric and the training metric.

[0299] In some implementations, the validation population can be updated by at least one of the following operations: 1) adjusting one or more metrics in the validation metrics; and 2) expanding the validation metrics based on adding an additional one or more subjects to the subject population that constitutes the validation population. The thresholds used to classify future patients can be improved based on the updated validation metrics. For example, metrics of a patient who is currently being treated or monitored or otherwise has not yet progressed through the end of device use can be used to adjust one or more metrics in the validation metrics, or the patient's metrics can be added to the validation population as metrics from a new subject. The validation metrics can be adjusted when new metrics for the patient are determined during the monitoring or treatment of the patient. In some examples, when a monitored patient progresses through the end of device use, the patient's metrics can be added to the validation population and / or used to adjust metrics in the validation metrics after the patient has progressed through the end of device use.

[0300] In some implementations, the training population can be updated by at least one of the following operations: 1) adjusting one or more metrics in the training metrics; and 2) expanding the training metrics based on adding an additional one or more subjects to the first plurality of subjects. The machine learning classifier model can be retrained based on the updated training metrics. For example, when additional patient metrics are determined based on the current patient and / or metrics from new patients are determined, the machine learning classifier can be retrained, for example, on the increased number of metrics or on new and different metrics to provide an updated classifier model. The training population can be updated when new metrics for the current patient and / or metrics for new patients are determined or after the patient has progressed through the end of device use.

[0301] Fig.14 A sample stream 1400 is shown for training and validating one or more classifier models used in a machine learning process as described above. A collection or population of known patient records can be provided as a data set for training and validating a classifier model. For example, a known patient record data set can include 1,000 patients with a particular type of heart disease (such as VT), their treatment regimens, and related outcomes for each patient. A percentage of the known patient data records can be used as a training data set 1405. For example, 80% or 800 of the patient records can be used as a training data set 1405. As described above, the training data 1405 can include various available information for multiple patients, including the patients' ECG measurements 1125 (e.g., see Fig.11 ), bio-vibration metrics 1130, radio frequency metrics (1135), combined physiological metrics 1145, demographic and medical history information 1140, and patient activity and test data 1142. Training data 1405 may include historical information for each training data set regarding how each training data set was classified or scored into the appropriate scoring category (or NYHA class or ACC / AHA stage).

[0302] The training date set 1405 can be fed into a training module 1410. The training module 1410 can include one or more untrained data structures, such as a series of data trees (e.g., organized using the random forest tool described above). Using known input variables and known outcomes from the training data set 1405, the training module 1410 can iteratively process each data point in the training set, thereby training the data structure to more accurately produce the expected (and known) outcomes.

[0303] Once the training module 1410 has exhausted the training data set 1405, the training module may output one or more trained classifier models 1415. The one or more trained classifier models 1415 may represent a set of models that provide more accurate classification and generation of results for a known set of input variables that may be generated from the training data 1405. The validation module 1420 may be configured to further improve the trained classifier models 1415 using additional patient records. For example, a validation data set 1425 may be input into the validation module 1420 to validate the one or more trained classifier models 1415. To continue with the above example, the validation data set 1425 may include 200 patient records. Typically, there is no overlap between the training data set and the validation data set, as there is no advantage in running the same data set twice.

[0304] like Fig.14 As shown, the validation module 1420 can process the validation data set 1425 to generate one or more validated classifier models 1430. Depending on the intended use of the validated classifier models 1430, these models can have a particular specificity or sensitivity as described above.

[0305] As a validated classifier model for classifying new patients (e.g., to generate new outputs for patient metrics sets as described herein), the generated results can be used to better validate the process using a closed-loop feedback system. For example, as the patient is classified and treated, the results of the treatment can be included in the patient record and verified by, for example, the patient's physician. The patient record, now updated to include the known results, can then be provided to the validation module 1420 as feedback 1435. The validation module can process the feedback 1435, comparing the generated output with the patient's known results. Based on the comparison, the validation module 1420 can also improve the validated classifier model 1430, thereby providing a closed-loop system that regularly updates and upgrades the model.

[0306] In another example, the process may be implemented as a network of nodes that are interconnected to form an artificial neural network. Fig.15Shown is the topology of a sample artificial neural network 1500. The artificial neural network 1500 may, for example, include one or more nodes organized into an input layer 1502, a series of hidden layers 1504, and one or more nodes organized into an output layer 1506.

[0307] In the artificial neural network, the node includes a plurality of artificial neurons, each artificial neuron including at least one input having an associated weight. The artificial neural network can be trained using physiological parameters so that the associated weight of at least one input of each artificial neuron in the plurality of artificial neurons is adjusted in response to corresponding first, second, and third parameters in different data sets from the patient's physiological parameters. This results in the artificial neural network being trained to generate a patient condition score.

[0308] An artificial neural network may be a mathematical or computational model that simulates the structural and / or functional aspects of a biological neural network. In an embodiment, a node of an artificial neural network includes at least one input, at least one neuron, and at least one output. A neuron may be present in a single hidden layer of an artificial neural network and may take 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. Where there is more than one layer, each layer may be interconnected with previous and subsequent layers.

[0309] Artificial neural networks can be adaptive systems that change based on external or internal information flowing through the artificial neural network during the training or learning phase. Specifically, the weights (or strengths) of connections within the artificial neural network (such as between adjacent artificial neurons or between inputs and artificial neurons) adapt to change to match known outputs.

[0310] In an example, a first parameter (e.g., S3 vibration intensity) and a second parameter (e.g., tissue fluid content) or a combination of the first parameter and the second parameter may be classified as a feature vector of a patient's physiological parameter. The artificial neural network may be trained using the feature vector. The artificial neural network may be implemented as instructions stored in a memory, which, when executed by a processor, causes the processor to perform the functions of an artificial neural network. In an embodiment of the present invention, the artificial neural network may be based on a support vector machine architecture, wherein the associated weights of at least one input of each of the plurality of artificial neurons are initialized according to a library used by the support vector machine.

[0311] A support vector machine may have an aggregate output comprising a decision function given by:

[0312]

[0313] Where sgn() is a sign function, (x,xi) is a set of eigenvectors, k(x,xi) is a kernel matrix consisting of x and xi, yi is 1 or -1 as the label of the eigenvector xi, and αi and b are artificial neural network parameters.

[0314] For example, the artificial neural network can be based on an extreme learning machine architecture, wherein the associated weights of at least one input of each of the plurality of artificial neurons are initialized by random selection of the extreme learning machine. The artificial neural network can be implemented as a single-layer feed-forward network, thereby deriving a prediction of the survivability of the patient according to the following function:

[0315]

[0316] Wherein, xj is the input vector of one of the multiple neurons for j=1,2,...,N input vectors; wi is the associated weight of the input of the neuron receiving the xj input vector; g(wi·xj+bi) is the output of the neuron for i=1,2,...,N artificial neurons receiving the xj input vector; βi is the output weight vector associating the i-th hidden neuron with the corresponding output neuron; and bi is the bias of the i-th hidden neuron.

[0317] The training of the artificial neural network can be based on back propagation learning. For example, back propagation learning can use the Levenberg-Marquardt process. Each of the multiple neurons of the artificial neural network can have an activation function selected from the group of functions of hardlim, sigmoid, sine, radial basis and linear function.

[0318] In the example, the outcome of the artificial neural network may be only two possible values: the patient is in stable condition (no adverse events are expected) or the patient is admitted to the hospital (adverse events are expected).

[0319] In another example, the physiological parameter data may be partitioned into multiple parts. The first parameter set may be associated with the patient's ECG measurement; the second parameter set may be associated with the patient's heart vibration measurement, and the third parameter set may be related to the patient's demographics and medical history. The first parameter set, the second parameter set, and the third parameter set are provided as a set of standardized data values ​​that are then input into the scoring scheme. For example, the scoring scheme can assign corresponding categories to each parameter in the first parameter set, the second parameter set, and the third parameter set. Each category can have multiple predefined value ranges, each of which has a predefined score. The scores of each parameter in the first parameter set, the second parameter set, and the third parameter set are determined by assigning the standardized data set to the corresponding predefined value ranges of the multiple value ranges of the categories associated with the corresponding parameters of the first parameter set, the second parameter set, and the third parameter set. The total score can be derived based on the sum of the scores of each parameter in the first parameter set, the second parameter set, and the third parameter set as an indication of the patient's condition. The scoring scheme can be any suitable process or process that can be implemented in an electronic database that can assign scores to each range of values ​​within each category associated with each parameter of the first parameter set, the second parameter set, and the third parameter set. For example, the scoring scheme can be based on a mathematical model using logistic regression, such as a univariate analysis.

[0320] In an example, the output patient condition score may be a numerical value, which may be determined based on statistical information or standard medical information.

[0321] In addition to using a learning process such as an artificial neural network or machine learning process described above, trend analysis can also be used to monitor changes in a patient's condition and provide an output (such as a change in a patient treatment regimen). In a specific implementation, trend analysis can include determining the existence of a substantial relationship between changes in two or more physiological parameters. For example, as described above with respect to Figure 7 As described above, detecting a change in a particular metric can trigger monitoring of another metric. Such additional monitoring can be performed to confirm trends in the monitored metric and provide additional information related to the patient's overall status.

[0322] An example of trend analysis is correlation analysis. Correlation analysis is the quantification of the linear relationship between two variables and can be represented by a value between negative 1.0 and 1.0 (commonly referred to as the Pearson product-moment correlation coefficient and expressed as r). When the correlation coefficient is close to 1.0, it indicates that there is a strong positive correlation between the two variables. When the correlation coefficient is close to negative 1.0, it indicates that there is a weak negative correlation between the two variables. A correlation value close to zero indicates that there is no linear association between the two variables.

[0323] In a specific example, there may be two data sample sets X and Y. For example, the X data set may be data sampled from a curve X (such as a heart vibration S3 intensity curve), and the Y data set may be data samples from a curve Y (such as a pleural fluid content measurement curve). In a specific implementation, a Pearson correlation function, a Fisher transform, or other similar correlation functions may be used for correlation analysis. For example, using the Pearson correlation function, a correlation relationship between n pairs of data {X, Y} may be calculated, where X and Y are samples of a fixed duration. 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 Pearson product moment r as described above may be obtained by replacing samples based on variance and covariance of the {X, Y} data set. The resulting value of r is a value between -1.0 and 1.0. In this example, a value of 1.0 would represent a perfect X, Y relationship, i.e., as the S3 vibration intensity increases, the TFC measurement then increases accordingly. A value of -1.0 would represent a perfect negative relationship. For example, as the S3 vibration intensity increases, the TFC measurement then decreases. Conversely, as the S3 vibration intensity decreases, the TFC measure then increases. A value of 0.0 means that there is no linear relationship between the variables.

[0324] As described herein, multiple metrics may be correlated to determine the patient's condition. For example, if the patient is likely to experience an adverse cardiac event such as an arrhythmia, there may be a high correlation between the thoracic fluid content (TFC) and the S3 vibration intensity. Fig.10 In the process described, TFC can be considered as a metric 1 and expressed on a standardized scale from 0 to 1000. Other standardized linear or non-linear scales can be used. For example, the scale can be 0 to 1, or 0 to 10, or 0 to 100. For example, the non-linear scale can be a logarithmic scale. The processing device can monitor TFC to detect any changes or trends in the patient's TFC value.

[0325] For example, Fig.16A As shown, the processing device can record TFC measurements of the patient over a period of several weeks. Fig.16A As shown, the TFC measurement is represented by line 1600. The initial measurement of the patient's TFC may, for example, include a TFC measurement of 120 TFC units. In some examples, the TFC units may be measured on a standardized scale of 0 to 200 TFC units. However, as Fig.16AAs shown, the plot is adjusted to focus on the range of 100 to 160 TFC units. In week 1, the TFC measurement may increase to 130 TFC units. However, in week 2, the TFC measurement may drop to 125 TFC units. In week 3, the TFC measurement may increase to 150 TFC units, and in week 4, the TFC measurement may increase to 155 TFC units. In accordance with the programming of the processing device, the processing device may trigger a second metric measurement based on changes in the TFC measurement. For example, the TFC measurement may have exceeded a predetermined threshold (e.g., 150 TFC units) or a predetermined threshold time period (e.g., TFC units increased for two consecutive weeks, or increased in three out of four weeks). These changes may trigger the processing device to monitor at least one additional metric. For example, as Fig.16A As shown, in week 4, the processing device also begins to measure the S3 vibration intensity represented by line 1602.

[0326] As described above, S3 vibration intensity can be measured on a standardized scale of 0 to 10 S3 intensity units, where 5.0 S3 intensity units represents a threshold at which the patient may be experiencing a heart attack and / or require additional treatment. Other standardized linear or non-linear scales can be used. For example, the scale can be 0 to 1 S3 intensity units, or 0 to 10 S3 intensity units, or 0 to 100 S3 intensity units. For example, the non-linear scale can be a logarithmic scale. Fig.16A As shown, the initial reading shown can be adjusted to focus on the range of 3-9 S3 intensity units. At week 4, the patient's S3 vibration intensity was measured as 4.5 S3 intensity units. However, at week 5, the patient's S3 vibration intensity had increased to 5.0 S3 intensity units, and by week 6, the patient's S3 vibration intensity had increased to 6.0 S3 intensity units. At the same time, the patient's TFC measurement also continued to increase, increasing to 155 TFC units at week 5 and to 165 TFC units at week 6.

[0327] In certain implementations, the processing device may perform a trend analysis to determine the correlation coefficient between the TFC measurement and the S3 vibration intensity. Fig.16A As shown, there may be a substantially linear relationship between the two metrics, and therefore, there may be a correlation coefficient that indicates a strong positive correlation between the two variables. This association may be interpreted by the processing device as indicating a particular adverse cardiac event, characterized by a high correlation coefficient between the TFC measurement and the S3 vibration intensity. In a particular implementation, a high correlation coefficient may also indicate that the patient has had a period of time (e.g., Fig.16A Figure 2 shows the changes in the six weeks shown.

[0328] In certain implementations, trend analysis can be used to determine how a treatment plan is working for a patient. Fig. 16BAs shown, the patient can be monitored during the six-week treatment plan. Initially, the patient's TFC measurement (at Fig. 16B 1610). Fig. 16B As shown, during the first two weeks of monitoring of TFC measurements, a decrease was measured. This downward trend may trigger additional monitoring. For example, Fig. 16B As shown, the S3 vibration intensity measured in %EMAT units on a standardized scale of, for example, 0 to 100 EMAT units, and the %EMAT (e.g. Fig. 16B Adjustment as shown to focus on 10-70% EMAT units) can be triggered by a downward trend in the TFC measurement. Fig. 16B As shown, the S3 vibration intensity is represented by line 1612, and the %EMAT is represented by line 1614. Over the next four weeks, as Fig. 16B As further shown, the TFC measurement, S3 vibration intensity, and %EMAT each remain relatively stable or gradually decrease. This result can indicate that the treatment plan is progressing well. In implementations, other metrics can also be studied. For example, if LVST also decreases during the same time period, the device can confirm that the treatment plan is progressing well.

[0329] Fig. 16C A six-week trend analysis including the patient's overall categorical score is shown. Fig. 16C As shown, over the first two weeks, the TFC measurement for the patient represented by line 1620 may be trending upward, resulting in a general increase in the patient's overall classification score represented by line 1626. As above, after two weeks of a constant trend, additional monitoring may be triggered. In this example, in the second week, both S3 vibration intensity and %EMAT monitoring may begin. Fig. 16C As shown, the S3 vibration intensity is represented by line 1622, and the %EMAT is represented by line 1624. Fig. 16C As further shown, TFC measures, S3 vibration intensity, and %EMAT each continued to increase between weeks 2 and 6.

[0330] As these monitoring metrics increase, the patient's overall classification score continues to increase. As described above, the patient's overall classification score can be measured on a scale of 0.0 to 1.0 classification units, where 0.0 classification units is the best case scenario and 1.0 classification units is the worst case scenario. Fig. 16CAs shown, the overall classification score reading shown can be adjusted to focus on a range of, for example, 0.1 to 0.7 classification units. As the patient's overall score continues to increase, the monitoring device can determine whether the score exceeds a certain threshold (e.g., 0.50 classification units, or from one classification unit to another classification unit), and can provide feedback to, for example, the patient's physician accordingly. In implementations, other metrics can also be studied. For example, if LVST also increases during the same time period, the device can confirm that intervention is needed to change or manage the patient's treatment plan.

[0331] like Fig.16A The metrics shown in Figures 1 to 3 are provided by way of example. Other metrics such as LVST may be monitored and plotted over time. For example, Fig.16D As shown, the processing device may record TFC measurements for the patient over a number of weeks as represented by line 1630. For example, an initial reading may include a TFC measurement of 120 TFC units. In week 1, the TFC measurement may increase to 130 TFC units. However, in week 2, the TFC measurement may decrease to 125 TFC units. In week 3, the TFC measurement may increase to 150 TFC units, and in week 4, the TFC measurement may increase to 155 TFC units. In accordance with the programming of the processing device, the processing device may trigger a second metric measurement based on changes in the TFC measurement. For example, the TFC measurement may have exceeded a predetermined threshold (e.g., 150 TFC units), or the increase may exceed a predetermined threshold time period (e.g., TFC units increase for two consecutive weeks, or increase in three out of four weeks). These changes may trigger the processing device to monitor at least one additional metric. For example, if Fig.16D As shown, at week 4, the processing device also begins measuring LVST represented by line 1632.

[0332] For example, at week 4, the patient's LVST can be measured at about 250ms. However, at week 5, the patient's LVST has increased to 290ms, and before week 6, the patient's LVST has increased to 325ms. At the same time, the patient's TFC measurement also continues to increase, for example, increasing to 160 TFC units at week 5, and increasing to 165 TFC units at week 6. This increase in LVST can be used to confirm the explanation that the pleural effusion accumulation in the patient is worsening, so intervention is recommended. On the contrary, if the TFC measurement decreases significantly from one week to the next (for example, presenting a downward trend from a higher TFC unit toward a lower TFC unit), the patient's LVST is also expected to decrease in the same time period. The reduction in LVST can be used to confirm that one or more interventional treatments for pleural effusion management seem to improve the patient's condition.

[0333] In certain implementations, the processing device may perform a trend analysis to determine the correlation coefficient between the TFC measurement and the LVST. Fig.16D As shown, there is a generally linear relationship between the two metrics, and therefore, there may be a correlation coefficient that indicates a positive correlation between the two variables. For example, a positive correlation coefficient may provide an indication that LVST increases with increasing TFC measurements. This association indicating an increasing trend may be interpreted by the processing device as indicating a particular adverse cardiac event characterized by a positive correlation coefficient between TFC measurements and LVST. In a particular implementation, a positive correlation coefficient may also indicate that a patient has had an adverse cardiac event over a period of time (e.g., Fig.16D Figure 2. Changes in the six weeks shown.

[0334] Fig.17 A sample process flow of a patient monitoring system as described herein is shown. For example, the sensor set may be configured to detect 1705 raw signals from a patient. In a specific implementation, the ECG sensor may be configured to detect one or more ECG signals of the patient, the vibration sensor may be configured to detect one or more bio-vibration signals of the patient, and the RF ultra-wideband transceiver may be configured to cause one or more antennas to direct RF electromagnetic energy into the patient and generate RF information in response to reflected RF electromagnetic energy received by the one or more antennas and reflected from a portion of the patient (such as a major artery or chest cavity, etc.).

[0335] In a particular implementation, one or more processors may be configured to process the raw signals to determine 1710 a set of physiological parameters of the patient. 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 within a specific prior time period. For example, the time period may include at least 24 hours, at least 48 hours, at least one week, 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. In some examples, the prior time period corresponds to a time period for which a clinical history is available for the patient.

[0336] The one or more processors may also be configured to use the physiological parameters to perform at least one of predictive analysis 1715 or trend analysis 1720. In certain implementations, the one or more processors may be configured to perform both predictive analysis 1715 and trend analysis 1720.

[0337] As described above, predictive analysis 1715 may include inputting physiological parameters into a training process. For example, the trained process may include an artificial neural network or a machine learning process as described above. However, in certain implementations, the trained process may also include a deep learning process configured to analyze the physiological parameters and output the patient's current condition information.

[0338] Based on the output of the predictive analysis and / or trend analysis, one or more processors can determine 172 the current patient condition. Based on the current patient condition, one or more processors can determine 1730 one or more clinically actionable events for the patient. For example, clinically actionable events may include re-hospitalization, prescribing a wearable medical device (such as a wearable defibrillator, etc.), instructing the patient to go to the hospital, changing the treatment plan, and other similar events. In a specific implementation, clinically actionable events may include automatic events triggered without user input, such as increasing monitoring and / or analysis of one or more physiological signals. Similarly, clinically actionable events may include manual events triggered based on user responses, and the generated output may include one or more instructions to perform one or more actions (such as instructions for the patient to go to the hospital, etc.).

[0339] The one or more processors may generate 1735 outputs based on clinically actionable events. In a particular implementation, clinically actionable events may include automatic events triggered without user input, such as increasing monitoring and / or analysis of one or more physiological signals. Similarly, clinically actionable events may include manual events triggered based on user responses, and the generated outputs may include one or more instructions to perform one or more actions (such as instructions to have the patient go to a hospital, etc.).

[0340] Various studies have been conducted to analyze and validate the concepts and techniques described herein. For example, studies have been conducted to evaluate the value of cardiac-based bio-vibration information as described herein and the combination of cardiac-based bio-vibration information with one or more ECG metrics in heart failure analysis. In the study, a subject population including subjects with ejection fraction <35% and hospitalized for decompensated heart failure was enrolled in a prospective observational program. All subjects were equipped with a WCD equipped with an accelerometer. The WCD is capable of recording bio-vibrations and measuring ECG signals. Each subject is to wear a WCD in an outpatient setting. The subject population is monitored for heart failure events and emergency room visits to obtain heart failure symptoms, and this information is collected for the subject population. The collected information is subjected to univariate and multivariate analysis to identify the model that best predicts the incidence of early heart failure readmission or emergency room visits.

[0341] During the study, the subject population was divided into two groups based on the incidence of heart failure events, thereby obtaining a heart failure subject group and a non-heart failure subject group (based on the heart failure hospitalization and emergency room visit information of the subject population). The BMI of the heart failure group (26+ / -5vs 29+ / -6) was lower than that of the non-heart failure group, but all other demographic information between the two groups was similar. The multi-parameter model using heart rate, EMAT (from QRS to S1) and S3 intensity (e.g., based on S3 timing, intensity, persistence and frequency) statistically produced the best prediction model for decompensated heart failure events. Before the start of WCD wearing, the all-cause readmission rate between the two groups (62% vs. for heart failure and 63% for non-heart failure) was similar to the NYHA I+II class classification (68% vs. for heart failure and 69% for non-heart failure). However, after WCD use and model determination, the ability of NYHA class to predict heart failure events was lower than the ability to predict heart failure events by using bio-vibration information. For example, the bio-vibration information predictor had a sensitivity of 68% and a positive predictive value of 28%, compared to the NYHA classification system's sensitivity of 30% and a positive predictive value of 18%. Therefore, based on the study, it can be concluded that the use of bio-vibration information alone or in combination with ECG information and radiofrequency-determined lung fluid levels (as discussed below) can be used for early diagnosis of decompensated heart failure in high-risk patients compared to the traditional NYHA classification system. This heart failure may lead to the subject's readmission to the hospital after an acute decompensated heart failure episode.

[0342] A second study has been conducted to provide insight into the use of radiofrequency determined lung fluid levels to track the disease state of subjects with heart failure. The subject population included two groups. The first group included subjects with acute heart failure, who had the following demographics: age was 78 years + / - 8 years; 37% were female; and BMI = 32 + / - 7. The second group included subjects without acute heart failure (approximately 60% healthy and 40% stable heart failure patients), the second group had the following demographics: age was 56 years + / - 16 years; 27% were female; and BMI = 27 + / - 5.

[0343] Each subject in the group underwent a supine chest CT scan to determine the initial fluid level. This was followed by a supine RF reading from the wearable patch device position on the left mid-axillary line. An RF-based lung fluid model was established for each patient using the reflected RF signal measured by the patch device and anthropometric data. Lung fluid was reported as a percentage of lung volume. Classification analysis techniques were then used to compare the RF patch device and chest CT scan results and performance.

[0344] The results of the above study indicated that all acute heart failure subjects were measured to have lung fluid levels higher than those of non-acute heart failure subjects. Statistically, the RF patch design and chest CT scans performed were used to identify acute heart failure subjects from non-acute heart failure subjects. Sample data showing various determined statistical results of this study can be seen in Table 10 below.

[0345]

[0346] Table 10

[0347] The data obtained from the two studies described above indicate 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. In addition, using the techniques described above, the patient's bio-vibration data can be merged with the patient's radio frequency data to show trends or changes in the patient's medical condition. For example, using the combined physiological parameter analysis as described herein, patient information such as bio-vibration information and radio frequency data can be combined with the measured ECG information into one or more combined metrics. Using correlation analysis as described herein (or other similar machine learning techniques as described above in other examples), patient information can be transformed or otherwise processed to quantify one or more trends or changes in the patient's medical condition. Trends can be further analyzed to determine which additional information can be determined from these trends. For example, trends can be further analyzed to determine information such as: the patient's overall health is improving / deteriorating, the patient's cardiac health is improving / deteriorating, and / or the patient may suffer from another heart failure event that may require an emergency room visit or readmission in the near future (e.g., the next 30 days). Combined physiological parameters based on, for example, patient radiofrequency and biovibration data may also be used to determine whether a patient being discharged from the hospital is likely to experience a heart failure event in the near future and / or should be prescribed an ambulatory medical device (such as a WCD as described in the examples below).

[0348] In an example, a person may complain of chest pain when performing certain activities, such as sitting in a reclined position or lying on their back. Their physician may prescribe a radio frequency sensing device for the patient to wear, which is configured to measure the patient's TFC. The patient may wear the device for several weeks. During this period of time, the device can measure a steady increase in the fluid content in the patient's chest cavity. Upon returning to the physician, the physician can download the data recorded by the radio frequency sensing device into a trend analysis process. The process can detect a trend indicating that the patient's TFC is steadily increasing. The physician may wish to obtain additional physiological information for the patient and may further prescribe a mobile cardiac monitoring device including a vibration sensor configured to measure biological vibrations. The patient wears both the radio frequency sensing device and the mobile cardiac monitoring device for a period of time. Upon returning to the physician, the recorded information from the two monitoring devices can be input into the trend analysis process. The process can confirm the trend indicating that the patient's TFC is increasing by analyzing information related to the patient's S3 vibration intensity. The process can determine the correlation between the increase in TFC and the patient's S3 vibration intensity, thereby providing an indication that the patient may suffer from a heart disease such as congestive heart failure. The process can provide such indications to the physician as well as recommended actions to be taken (such as modifying the patient's prescribed medications, etc.).

[0349] In another example, during the hospital stay, the patient can wear at least one ECG sensor, at least one biovibration sensor, and at least one radio frequency sensor. Before discharge, the data recorded by these sensors can be combined into one or more combined physiological parameters and input into a trained process such as an artificial neural network (or other similar machine learning techniques as described above in other examples). The artificial neural network can transform the input information to provide the patient's clinical condition information. The clinical condition information can be further analyzed to determine the patient's current condition, whether the patient is allowed to be discharged, and what is the risk of the patient's re-hospitalization within a specific time (e.g., within 30 days). In some examples, even if the patient completes all necessary discharge requirements, the process may indicate that the patient is at high risk of re-hospitalization in the near future. In this case, the physician or other similar caregiver may decide to keep the patient in the hospital for additional monitoring, change the patient's treatment plan, or otherwise change the care provided to the patient.

[0350] Although the subject matter contained herein has been described in detail for illustrative purposes, it should be understood that such details are used for that purpose only and that the invention is not limited to the disclosed embodiments, but rather is intended to cover modifications and equivalent arrangements within the spirit and scope of the appended claims. For example, it should be understood that the present invention contemplates that, to the extent possible, one or more features of any embodiment may be combined with one or more features of any other embodiment.

[0351] Other examples are within the scope and spirit of the specification and claims. In addition, some of the functions described above can be implemented using software, hardware, firmware, hard wiring, or any combination of these. Features that implement functions can also be physically located in various locations, including being distributed so that parts of the functions are implemented at different physical locations.

[0352] This application claims the benefit of U.S. Provisional Application No. 62 / 644,216, filed on March 16, 2018, entitled “Monitoring Physiological Status Based on Bio-Vibrational and Radio Frequency Data Analysis,” under 35 U.S.C. § 119(e). All subject matter set forth in the above-referenced applications is hereby incorporated by reference in its entirety into this application, as if fully set forth herein.

Claims

1. A patient monitoring system, comprising: an electrocardiogram sensor coupled to a patient and configured to detect one or more electrocardiogram signals of the patient; a vibration sensor coupled to the patient and configured to detect one or more cardiac vibration signals of the patient; A radio frequency ultra-wideband transceiver circuit comprising one or more radio frequency antennas, and the radio frequency ultra-wideband transceiver circuit is coupled to the patient and is configured to: causing the one or more radio frequency antennas to direct radio frequency electromagnetic energy into the chest cavity of the patient, and generating radio frequency information in response to reflected radio frequency electromagnetic energy reflected from within the chest cavity and received by the one or more radio frequency antennas; as well as One or more processors configured to: processing the one or more electrocardiogram signals and the one or more cardiac oscillation signals to generate electro-mechanical activation time parameters, i.e., EMAT parameters, of the patient, processing the radio frequency information to generate a pleural fluid content parameter of the patient, namely a TFC parameter, performing a trend analysis of the EMAT parameter and the TFC parameter to determine the current clinical condition of the patient, wherein the trend analysis comprises determining the existence of a substantial relationship between changes in the EMAT parameter and changes in the TFC parameter, comparing the current clinical condition of the patient to predetermined clinically actionable criteria to determine one or more clinically actionable events; as well as An output device is caused to provide an output related to the one or more clinically actionable events.

2. The patient monitoring system according to claim 1, wherein: The trend analysis includes correlation analysis.

3. The patient monitoring system according to claim 2, wherein: The correlation analysis includes: Determining whether the EMAT parameter has exceeded a threshold; correlating the EMAT parameters that have exceeded the threshold with the TFC parameters to generate a correlation score; and The current clinical condition of the patient is determined based on the relevance score.

4. The patient monitoring system according to claim 3, wherein: The relevance score indicates a change in the patient's condition.

5. The patient monitoring system according to any one of claims 1 to 4, wherein: The one or more processors are further configured to perform a predictive analysis on at least one of the EMAT parameter and the TFC parameter to determine a predictive score, the predictive score indicating a likelihood of an adverse event occurring.

6. The patient monitoring system according to claim 5, wherein: At least one of the predictive analysis and the trend analysis is performed on at least one of the EMAT parameter and the TFC parameter collected within a previous time period, wherein the previous time period includes one or more of the following: 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.

7. The patient monitoring system according to claim 5, wherein: At least one of the predictive analysis and the trend analysis is performed on at least one of the EMAT parameter and the TFC parameter collected within a previous time period corresponding to at least an available clinical history of the patient.

8. The patient monitoring system according to claim 5, wherein: The outputs associated with the one or more clinically actionable events are based on: a violation of one or more thresholds, the one or more thresholds being defined relative to one or more of the EMAT parameters and the TFC parameters; or A result of at least one of the predictive analysis and the trend analysis.

9. The patient monitoring system according to claim 5, wherein: Performing the predictive analysis includes: inputting the EMAT parameters and the TFC parameters into an artificial neural network; and The current clinical condition of the patient is determined based on an output of the artificial neural network.

10. The patient monitoring system according to claim 5, wherein: Performing the predictive analysis includes: Inputting the EMAT parameters and the TFC parameters into a deep learning process; and The current clinical condition of the patient is determined based on an output of the deep learning process.

11. The patient monitoring system according to claim 5, wherein: Performing the predictive analysis includes: inputting the EMAT parameters and the TFC parameters into a machine learning process; and The current clinical condition of the patient is determined based on an output of the machine learning process.

12. The patient monitoring system of claim 5, wherein: The adverse events include one or more of arrhythmia events, stroke events, syncope events, and hospitalization events.

13. A patient monitoring system according to any one of claims 1 to 4, wherein: The one or more clinically actionable events include at least one of the following: Automatic events, which are triggered without user input; and A manual event that is triggered based on a user response to the output related to the one or more clinically actionable events and includes one or more instructions to perform one or more actions.

14. The patient monitoring system according to any one of claims 1 to 4, wherein: The vibration sensor is also configured to sense one or more lung vibrations of the patient, the one or more lung vibrations including at least one of bronchial vibrations, wheezes, crackles, wheezes, snoring sounds, pleural friction sounds, shrieks, glottal sounds, laryngeal sounds, and other vibrations.

15. The patient monitoring system according to any one of claims 1 to 4, wherein: The one or more ECG signals include at least one of heart rate, heart rate variability, premature ventricular contraction load or count, atrial fibrillation load, pauses, heart rate oscillations, QRS height, QRS width, changes in the morphological size or shape of the one or more ECG signals, cosine RT, artificial pacing, QT interval, QT variability, T wave width, T wave alternations, T wave variability, and ST segment changes.

16. A patient monitoring system according to any one of claims 1 to 4, wherein: The one or more heart vibration signals include at least one of S1 vibration, S2 vibration, S3 vibration, S4 vibration and heart murmur vibration.

17. A patient monitoring system according to any one of claims 1 to 4, wherein: The radio frequency information includes a measurement of fluid content within the patient's chest cavity.

18. A patient monitoring system according to any one of claims 1 to 4, wherein: The EMAT parameter is EMAT or %EMAT.

19. A patient monitoring system according to any one of claims 1 to 4, wherein: The one or more processors are integrated into a cardiac monitoring device suitable for being worn by the patient.

20. The patient monitoring system according to any one of claims 1 to 4, wherein: The one or more processors are integrated into a remote processing device.

21. A patient monitoring system according to any one of claims 1 to 4, wherein: The one or more processors are integrated into a wearable defibrillator device adapted to be worn by the patient.

22. A patient monitoring system comprising: an electrocardiogram sensor coupled to a patient and configured to detect one or more electrocardiogram signals of the patient; a vibration sensor coupled to the patient and configured to detect one or more cardiac vibration signals of the patient; A radio frequency ultra-wideband transceiver circuit, comprising one or more radio frequency antennas, the radio frequency ultra-wideband transceiver circuit being coupled to the patient and configured to: causing the one or more radio frequency antennas to direct radio frequency electromagnetic energy into the chest cavity of the patient, and generating radio frequency information in response to reflected radio frequency electromagnetic energy reflected from within the chest cavity and received by the one or more radio frequency antennas; as well as One or more processors configured to: processing the one or more electrocardiogram signals, the one or more cardiac vibration signals, and the radio frequency information to generate a plurality of physiological parameters of the patient including one or more combined physiological parameters, performing at least one of a predictive analysis and a trend analysis of the plurality of physiological parameters including the one or more combined physiological parameters to determine a current clinical condition of the patient, wherein the trend analysis comprises determining the existence of a substantial relationship between changes in the plurality of physiological parameters, comparing the current clinical condition of the patient to predetermined clinically actionable criteria to determine one or more clinically actionable events, and causing an output device to provide an output related to the one or more clinically actionable events; Wherein, performing the predictive analysis includes: inputting the plurality of physiological parameters into at least one of an artificial neural network, a deep learning process, and a machine learning process, and The current clinical condition of the patient is determined based on an output of at least one of the artificial neural network, the deep learning process, and the machine learning process.

23. The patient monitoring system of claim 22, wherein: The one or more combined physiological parameters include one or more of the following: electro-mechanical activation time parameter EMAT, %EMAT, percentage of left ventricular contraction time %LVST, EMAT / LVST ratio, left ventricular end-diastolic pressure LVEDP, and systolic dysfunction index SDI.

24. The patient monitoring system of claim 22, wherein: The trend analysis includes correlation analysis.

25. The patient monitoring system of claim 24, wherein: The correlation analysis includes: determining whether one of the combined physiological parameters has exceeded a threshold; correlating a combined physiological parameter of the combined physiological parameters that has exceeded the threshold with another combined physiological parameter of the combined physiological parameters to generate a correlation score; and The current clinical condition of the patient is determined based on the relevance score.

26. The patient monitoring system of claim 25, wherein: The relevance score indicates a change in the patient's condition.

27. A patient monitoring system according to any one of claims 22 to 26, wherein: The predictive analysis includes performing a predictive analysis on at least one of the plurality of physiological parameters to determine a predictive score, the predictive score representing a likelihood of an adverse event occurring.

28. A patient monitoring system according to any one of claims 22 to 26, wherein: The predictive analysis and the trend analysis are performed on at least one of the multiple physiological parameters collected within a previous time period, wherein the previous time period includes one or more of the following: 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.

29. A patient monitoring system according to any one of claims 22 to 26, wherein: At least one of the predictive analysis and the trend analysis is performed on at least one of the plurality of physiological parameters collected within a prior time period corresponding to at least an available clinical history of the patient.

30. A patient monitoring system according to any one of claims 22 to 26, wherein: The outputs associated with the one or more clinically actionable events are based on: a violation of one or more thresholds, the one or more thresholds being defined relative to one or more of the plurality of physiological parameters; or A result of at least one of the predictive analysis and the trend analysis.

31. The patient monitoring system of claim 27, wherein: The adverse events include one or more of arrhythmia events, stroke events, syncope events, and hospitalization events.

32. A patient monitoring system according to any one of claims 22 to 26, wherein: The one or more clinically actionable events include at least one of the following: Automatic events, which are triggered without user input; and A manual event that is triggered based on a user response to the output related to the one or more clinically actionable events and includes one or more instructions to perform one or more actions.

33. A patient monitoring system according to any one of claims 22 to 26, wherein: The vibration sensor is also configured to sense one or more lung vibrations of the patient, the one or more lung vibrations including at least one of bronchial vibrations, wheezes, crackles, wheezes, snoring sounds, pleural friction sounds, shrieks, glottal sounds, laryngeal sounds, and other vibrations.

34. A patient monitoring system according to any one of claims 22-26, wherein: The one or more ECG signals include at least one of heart rate, heart rate variability, premature ventricular contraction load or count, atrial fibrillation load, pauses, heart rate oscillations, QRS height, QRS width, changes in the morphological size or shape of the one or more ECG signals, cosine RT, artificial pacing, QT interval, QT variability, T wave width, T wave alternations, T wave variability, and ST segment changes.

35. A patient monitoring system according to any one of claims 22-26, wherein: The one or more heart vibration signals include at least one of S1 vibration, S2 vibration, S3 vibration, S4 vibration and heart murmur vibration.

36. A patient monitoring system according to any one of claims 22-26, wherein: The radio frequency information includes a measurement of fluid content within the patient's chest cavity.

37. A patient monitoring system according to any one of claims 22-26, wherein: The one or more processors are integrated into a cardiac monitoring device suitable for being worn by the patient.

38. A patient monitoring system according to any one of claims 22-26, wherein: The one or more processors are integrated into a remote processing device.

39. A patient monitoring system according to any one of claims 22-26, wherein: The one or more processors are integrated into a wearable defibrillator device adapted to be worn by the patient.

Images