Monitoring of Physiological States Based on Analysis of Biovibration and Radio Frequency Data

Abstract

To provide a method of monitoring physiological status of a patient on the basis of patient data obtained from a plurality of sensor sources such as a bio-vibrational sensor and a radio frequency sensor and diagnosing cardiac failure symptoms early.SOLUTION: A patient monitoring device includes: an ECG sensor coupled to a patient; a sensor coupled to the patient and configured as bio-vibrational signals; and a radio frequency monitoring device configured to produce information responsive to electromagnetic energy reflected from the patient's thoracic cavity. A processor processes the ECG signals, the bio-vibrational signals, 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.SELECTED DRAWING: Figure 11

Description

Background Art

[0001] Related Applications This application is a U.S. Provisional Application No. 62 / 644,216, entitled "Monitoring Physiological Status Based on Bio-Vibrational and Radio Frequency Data Analysis," filed on Mar. 16, 2018, and claims priority under 35 U.S.C. § 119 to this provisional application. The entire content of the above application is hereby incorporated by reference into this application as if fully set forth herein.

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

[0003] Patients suffering from heart disease tend to frequently experience recurrences of acute episodes due to the condition of congestive heart failure (CHF). For example, pulmonary congestion is a major cause of hospitalization and readmission among patients with CHF. Similarly, patients with chronic kidney disease undergoing hemodialysis are further troubled by acute adverse events. For example, some patients with end-stage kidney disease may have moderate to severe pulmonary congestion prior to hemodialysis. These patients have a high incidence of heart failure and a poor prognosis. There are various electronic and mechanical devices for monitoring and treating the condition of heart failure in patients. In some examples, a medical device such as a heart monitor or defibrillator may be surgically implanted or externally connected to a patient depending on the underlying disease to be monitored or treated. In some cases, a physician may treat the condition of heart failure using only a medical device or in combination with drug therapy.

[0004] Leaving the treatment of heart failure untreated can lead to life-threatening arrhythmias. Both atrial and ventricular arrhythmias are common in patients with heart failure. One of the most life-threatening arrhythmias is ventricular fibrillation, which occurs when normal and regular electrical impulses are replaced by irregular and rapid impulses, causing the myocardium to stop normal contractions. Since patients do not receive any palpable warning of impending fibrillation, they often die before the necessary medical support arrives. Other arrhythmias can include extremely slow heart rates known as bradycardia or extremely fast heart rates known as tachycardia. Cardiac arrest can occur when a patient suffers from various cardiac arrhythmias such as ventricular fibrillation, ventricular tachycardia, pulseless electrical activity (PEA), and asystole (where the heart stops all electrical activity), causing the patient's heart to not supply sufficient blood flow to the life-sustaining brain and other vital organs. It is generally useful to monitor patients with heart failure in order to diagnose the symptoms of heart failure early and perform intervention treatment as soon as possible.

Summary of the Invention

[0005] In certain implementations, 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, an ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and coupled to the patient, and one or more processors. In some examples, the ultra-wideband radio frequency transceiver is configured to direct one or more radio frequency antennas to direct radio frequency electromagnetic energy towards the patient's chest cavity and generate radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the patient's chest cavity and received via the one or more radio frequency antennas. In some examples, the one or more processors are configured to process one or more ECG signals, 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 predictive analysis and trend analysis of the plurality of physiological parameters including the combined physiological parameters to determine the patient's current clinical condition. In the implementations described herein, 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 to a predefined clinically usable criterion to determine one or more clinically usable events and cause an output device to output an output regarding the one or more clinically usable events. Implementations of the patient monitoring system described herein may include one or more of the following features.

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

[0007] In certain implementations of the patient monitoring system described above, at least one of predictive analysis and trend analysis is performed on physiological parameters collected over a previous period including one or more of at least 24 hours, at least 48 hours, at least one week, at least two weeks, at least one month, at least six weeks, at least two months, at least four months, at least six months, at least one year, and at least two years.

[0008] In certain implementations of the patient monitoring system described above, at least one of predictive analysis and trend analysis is performed on physiological parameters collected over a previous period corresponding to at least the available patient medical history.

[0009] In certain implementations of the patient monitoring system described above, one or more clinically actionable events include at least one of an automated event triggered without user input and a manual event triggered based on a user response to an output and comprising one or more instructions to perform one or more actions.

[0010] In certain implementations of the patient monitoring system described above, an output regarding one or more clinically actionable events is based on exceeding one or more thresholds defined for a plurality of physiological parameters or at least one result of predictive analysis and trend analysis.

[0011] In certain implementations of the patient monitoring system described above, performing predictive analysis includes inputting a plurality of physiological parameters into an artificial neural network and determining the patient's current clinical symptoms based on the output of the artificial neural network.

[0012] In certain implementations of the patient monitoring system described above, performing predictive analysis includes inputting a plurality of physiological parameters into a deep learning process and determining the patient's current clinical symptoms based on the output of the deep learning process.

[0013] In certain implementations of the patient monitoring system described above, performing predictive analytics includes inputting a 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 prediction score based on the output of the machine learning process, and the prediction score indicates the likelihood of a harmful event occurring. In some examples, the harmful events include one or more of arrhythmia events, seizure events, syncope events, and hospitalization events.

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

[0015] In certain implementations of the patient monitoring system described above, the vibration sensor is further configured to sense one or more lung vibrations of the patient, and the one or more lung vibrations include at least one of bronchial vibrations, wheezing, crackles, wheezes, bubbling sounds, pleural friction rubs, squawks, glottal sounds, pharyngeal sounds, or other vibrations.

[0016] In certain implementations of the patient monitoring system described above, the one or more ECG signals include at least one of heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, respiration, cardiac arrhythmia, QRS height, QRS width, change in size or shape of the morphology of the one or more ECG signals, cosine R-T, artificial pacing, QT interval, QT variability, T wave width, T wave alternans, T wave variability, and ST segment change.

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

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

[0019] In a particular implementation of the patient monitoring system described above, the plurality of physiological parameters includes one or more of left ventricular systolic time (LVST), electromechanical activation time (EMAT), %LVST, and left ventricular end diastolic pressure (LVEDP).

[0020] In a particular implementation of the patient monitoring system described above, one or more processors are incorporated within a heart monitoring device adapted to be worn by a patient.

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

[0022] In a particular implementation of the patient monitoring system described above, one or more processors are incorporated within a wearable defibrillation device adapted to be worn by a patient.

[0023] In certain implementations, the second patient monitoring system includes at least one vibration sensor coupled to a patient and configured to detect one or more cardiac vibration signals, at least one ultra-wideband radio frequency transceiver coupled to the patient, and one or more processors. In some examples, the at least one ultra-wideband radio frequency transceiver is configured to direct radio frequency electromagnetic waves towards the patient's lungs and detect radio frequency information responsive to the radio frequency electromagnetic waves passing through the patient's lungs. In some examples, the one or more processors are configured to process the detected one or more cardiac vibration signals over a predetermined period to determine at least one cardiac vibration metric of the patient, process the patient's radio frequency information over a predetermined period to determine at least one lung fluid metric of the patient, determine an output regarding 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 the output to be provided to an output device. Implementations of the second patient monitoring system described herein may include one or more of the following features.

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

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

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

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

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

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

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

[0031] In certain implementations, a third 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, an ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and coupled to the patient, and one or more processors. In some examples, the ultra-wideband radio frequency transceiver circuit is configured to direct one or more radio frequency antennas to direct radio frequency electromagnetic energy toward the patient's chest cavity and, via the one or more radio frequency antennas, receive and generate radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the patient's chest cavity. In some examples, the one or more processors are configured to process one or more ECG signals, 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 can perform a trend analysis of the plurality of physiological parameters, including the combined physiological parameters, to generate a trend result, update the patient's monitoring schedule based on the trend result, determine the patient's current clinical condition based on the trend result, and compare the patient's current clinical condition with a predetermined clinically usable criterion to determine one or more clinically usable events. The one or more processors can cause an output device to output an output regarding one or more clinically usable events. Implementations of the third patient monitoring system described herein may include one or more of the following features.

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

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

[0034] In a particular implementation of the third patient monitoring system described above, one or more ECG signals include at least one of heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, respiration, cardiac arrhythmia, QRS height, QRS width, change in size or shape of the morphology of one or more ECG signals, cosine R-T, artificial pacing, QT interval, QT variability, T wave width, T wave alternans, T wave variability, and ST segment change.

[0035] In a particular implementation of the third patient monitoring system described above, 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 particular implementation of the third patient monitoring system described above, the radio frequency information includes a measurement of the liquid content in the patient's thoracic cavity.

[0037] In certain implementations, 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 the patient and configured to detect one or more cardiac vibration signals of the patient, an ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and disposed over at least one major artery of the patient, and one or more processors. In some examples, the ultra-wideband radio frequency transceiver circuit is configured to direct one or more radio frequency antennas to direct radio frequency electromagnetic energy to at least a portion of the patient and receive, via the one or more radio frequency antennas, radio frequency information corresponding to reflected radio frequency electromagnetic energy reflected from within at least a portion of the patient. In some examples, the one or more processors are configured to process one or more ECG signals, 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 can perform at least one of predictive analysis and 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 to a predetermined clinically usable criterion to determine one or more clinically usable events, and cause an output device to output an output regarding the one or more clinically usable events. Implementations of the fourth patient monitoring system described herein may include one or more of the following features.

[0038] In certain implementations of the fourth patient monitoring system described above, 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 certain implementations of the fourth patient monitoring system described above, the radio frequency information includes at least one of blood pressure information, cardiac 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 considered below with reference to the accompanying drawings, which are not intended to be drawn to scale. The figures include descriptions of various aspects and examples and further understanding, are incorporated into and constitute a part of this specification, but are not intended to limit the scope of the present disclosure. The drawings, together with the rest of the specification, are provided to explain the principles and operations of the described and claimed aspects and examples. In the figures, each identical or substantially identical component shown in various figures is denoted by a similar number. For clarity, not all components may be labeled in all figures.

[0041]

Figure 1

[0042]

Figure 2

[0043]

Figure 3

[0044]

Figure 4A

[0045]

Figure 4B

[0046]

Figure 5A

Figure 5B

[0047]

Figure 6

[0048]

Figure 7

[0049]

Figure 8

[0050]

Figure 9

[0051]

Figure 10

[0052]

Figure 11

Figure 12

[0053]

Figure 13

[0054]

Figure 14

[0055]

Figure 15

[0056]

Figure 16A

Figure 16B

Figure 16C

Figure 16D

[0057]

Figure 17

DETAILED DESCRIPTION OF THE INVENTION

[0058] A wearable medical device such as a cardiac event monitoring device is used in a clinical setting or an outpatient clinic to monitor and record various physiological signals of a patient. These signals can be used to determine the patient's current symptoms and to predict, plan for, and prepare for future adverse events such as possible cardiac events or other unfavorable changes to the patient's medical health status. For example, ECG monitoring combined with the patient's medical history can be utilized, for example, via a machine learning process, to calculate the patient's risk score and predict, for example, the future occurrence of possible arrhythmia events. 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 content of which is incorporated herein by reference.

[0059] In some implementations, a patient monitoring system can include sensors configured to collect a patient's physiological signals other than ECG signals. For example, a vibration sensor can be configured to collect biovibration signals such as cardiac vibration signals, such as S1, S2, S3, and S4 signals, and lung vibration signals, such as vibration signals from other airway-related anatomical regions, such as the lungs, or particularly the trachea and pharynx. Further, a radio frequency sensor, such as an ultra-wideband transceiver circuit, can be configured to collect information corresponding to radio frequency electromagnetic energy reflected from within the patient's chest cavity and / or heart. For example, the radio frequency sensor can be configured to monitor the transthoracic (e.g., lung) fluid volume and changes related to the same. In the implementations described herein, the processing device can further process the various signals and related information collected from the various underlying physiological sensors to generate one or more combined physiological parameters, such as physiological parameters determined based on two or more of the various underlying physiological sensors and related information. At least one of predictive analytics (e.g., using a machine learning process such as an artificial neural network) and trend analysis (e.g., correlation analysis) can be performed on the collected signals and received information, as well as the combined metrics, to determine the patient's current condition and one or more clinically actionable events.

[0060] For example, the present disclosure relates to patient monitoring devices and systems. 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 the patient and configured to detect one or more bio-vibration signals of the patient (including cardiac vibration signals or pulmonary vibration signals), and a radio-frequency based monitoring device including a radio-frequency antenna coupled to the patient and configured to direct radio-frequency electromagnetic energy towards the patient's chest cavity and / or heart, and associated transceiver circuitry. The radio-frequency transceiver circuitry generates a plurality of measurements corresponding to radio-frequency electromagnetic energy reflected from and received via the receiving radio-frequency antenna from the patient's chest cavity and / or heart. One or more processors process the one or more ECG signals, the one or more cardiac vibration signals or pulmonary vibration signals, and the radio-frequency measurements to generate a plurality of physiological parameters of the patient including one or more combined physiological parameters. Further, the processor may be further configured to perform at least one of predictive analysis and trend analysis of the plurality of physiological parameters including the combined physiological parameters to determine the patient's current clinical condition. In some implementations, the patient monitoring device coupled to the patient may transmit physiological information measured from the patient to an analysis remote server. At the remote server, one or more processors may be configured to perform at least one of predictive analysis and trend analysis of the plurality of physiological parameters according to the principles described herein. For example, trend analysis may include determining the existence of a substantial relationship of changes in the plurality of physiological parameters. One or more processors may further compare the patient's current clinical condition with a predetermined clinically usable criterion to determine one or more clinically usable events, and cause an output device to output an output regarding the one or more clinically usable events.

[0061] As an example, a patient may be examined by a healthcare provider at an outpatient facility and required to use one or more wearable patient monitoring devices described herein for monitoring a set of the patient's physiological parameters. For example, the monitoring may start with only one of the set of physiological parameters, such as an ECG-based metric. Over time, or in response to specific symptoms described herein, additional sets of physiological parameters other than ECG parameters, such as biometric vibration parameters or radio frequency-based parameters (or combined parameters thereof), may be started. Based on the set of physiological parameters collected, the device may perform processing to evaluate the patient's current clinical condition. At the time of the patient's follow-up visit (e.g., once a week, once every two weeks, or once a month), the device may provide updated information regarding the patient's clinical condition. The device may further be configured to determine whether the patient is at high risk of developing heart failure symptoms that may ultimately require hospitalization. It may notify the patient and / or the patient's physician of decisions that may be taken and appropriate intervention actions. For example, the patient's medications may be adjusted, and the physician may initiate close monitoring of the outpatient and schedule a follow-up visit. As a detail of the above example, if a patient is identified as being at high risk of heart failure, they may be escalated to a wearable monitoring device and treatment device, such as a wearable cardioverter defibrillator (WCD), for an extended period. Such devices can monitor the patient's heart disease and, if warranted, perform one or more defibrillation treatments and / or pacing pulse treatments on the patient. While the patient is using it, the wearable cardioverter defibrillator can continue to collect updated physiological information. This updated information is further provided to the physician, who can continue to monitor changes in the patient's health state by analyzing trends associated with the updated physiological information. For example, this analysis may lead to further treatment changes and provide information regarding cases where the risk of acute heart failure is reduced.

[0062] Many patients suffering from heart disease further struggle with the management of symptoms related to pleural effusion, leading to frequent recurrence of acute episodes. Such patients can become those with congestive heart failure (CHF). Pulmonary congestion is a major cause of hospitalization and readmission among CHF patients. Therefore, it is desirable to measure and monitor the degree of pulmonary congestion. The radio frequency sensors described herein can enable direct and accurate fluid measurement, for example, by monitoring changes in a patient's chest impedance. Such information can be utilized by caregivers when formulating a patient's treatment plan and has the potential to shorten the hospital stay by enabling an effective drug balance. For example, this technology can detect early edema and avoid readmission.

[0063] Similarly, patients with chronic kidney disease (CKD) undergoing hemodialysis further require fluid management strategies. Approximately 60 percent of patients with end-stage renal disease (ESRD) may have moderate to severe pulmonary congestion prior to hemodialysis. Additionally, patients diagnosed with CKD and undergoing continuous hemodialysis tend to have a high incidence of heart failure (HF) and poor overall prognosis. Therefore, congestive heart failure is a recurring clinical symptom in dialysis patients. For these reasons, fluid assessment and management can be useful in addressing CKD and HF. In the present disclosure, a non-invasive wearable monitoring system can be used to integrate and / or analyze this information together with biovibration information, ECG information, and other combined metrics, and to evaluate chest impedance and / or fluid changes.

[0064] Such methods provide several advantages over existing monitoring and prediction techniques. In addition to measuring by combining physiological measurements from multiple sensor sources and verifying changes in physiological signals using various types of analysis, the present disclosure more robustly and accurately analyzes a patient's current symptoms and the likelihood that the patient's symptoms will change. Based on such information, an individualized treatment plan can be created for the patient and periodically updated while periodically monitoring the patient's symptoms as they change for better or for worse.

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

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

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

[0068] Despite long-term wear, the use of a wearable medical device can include continuous or near-continuous wear by the patient as described above. For example, continuous use can include both the monitoring period and the period during which the device may not be monitoring the patient but is still being worn by the patient for other reasons or is attached to the patient for other reasons. For example, continuous wear or attachment of the wearable medical device to the patient through one or more electrodes described herein may be included. The wearable medical device can be configured to continuously monitor the patient for heart-related information (e.g., electrocardiogram (ECG) information including arrhythmia information, heart vibrations, lung vibrations, etc.) and / or non-heart information (e.g., blood oxygen, patient body temperature, blood glucose level, tissue fluid volume, and / or lung vibrations). The wearable medical device can perform its monitoring at periodic or aperiodic time intervals, or periodically or aperiodically. For example, the monitoring during such intervals or times can be triggered by the user's actions or another event.

[0069] 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, in particular, lung vibrations (e.g., using a microphone and / or accelerometer), respiratory vibrations, sleep-related parameters (e.g., snoring, sleep apnea), and tissue fluid (e.g., using a radio frequency transmitter and radio frequency sensor).

[0070] Other exemplary wearable medical devices include automatic heart monitors and / or defibrillators for use in specific special situations and / or environments such as within a combat zone or inside an emergency vehicle. Such devices can be configured to be used quickly (or substantially quickly) in first aid. In some examples, the wearable medical devices described herein can be made pacer-capable, for example, capable of performing pacing pulse therapy on a patient.

[0071] In an implementation, an exemplary therapeutic medical device can include an in-hospital continuous monitoring defibrillator and / or an in-hospital continuous monitoring pacing device, such as an in-hospital wearable defibrillator. In that example, the electrodes can be attached to the patient's skin by adhesion. For example, the electrodes can include disposable adhesive electrodes. For example, the electrodes can include sensing components and treatment components disposed in separate adhesive patches for the sensing electrode and the treatment electrode. In some implementations, both the sensing components and the treatment components can be integrated and disposed in the same electrode adhesive patch that is then attached to the patient. In an exemplary implementation, the electrodes can include a front treatment electrode attachable by adhesion, a rear treatment electrode attachable by adhesion, and a plurality of sensing electrodes attachable by adhesion. For example, attach the front treatment electrode attachable by adhesion to the front of the patient's torso to perform pacing treatment or defibrillation treatment. Similarly, attach the rear treatment electrode attachable by adhesion to the rear of the patient's torso. In an exemplary scenario, at least three ECG sensing electrodes attachable by adhesion can be attached at least above the chest near the patient's right arm, above the chest near the patient's left arm, and towards the lower part of the patient's chest in a manner directed by a trained professional.

[0072] Patients monitored by an in-hospital defibrillator and / or an in-hospital pacing device may be confined to a hospital bed or room for a significant amount of time (e.g., more than 90 percent of patients stay in the hospital). As a result, the user interface can be configured to interface with non-patient users, such as nurses, for device-related functions, such as initial device baseline, patient parameter setting and adjustment, and battery change of the device.

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

[0074] In some implementations, the medical device may be a patient monitoring device without a treatment method or treatment function. For example, such patient monitoring devices may include a cardiac monitoring device or cardiac monitor configured to monitor one or more cardiac physiological parameters of a patient to remotely monitor and / or diagnose the patient's symptoms. For example, the cardiac physiological parameters may include the patient's ECG information, cardiac vibrations (e.g., using an accelerometer or microphone), and other related cardiac information. The cardiac monitoring device is a portable device that a patient can carry around during daily life. The cardiac monitor may be configured to detect the patient's ECG via a plurality of cardiac sensing electrodes. For example, the cardiac monitor may be attached to the patient via at least three adhesive cardiac sensing electrodes disposed around the patient's torso. Such cardiac monitors are used in patient populations reporting cardiac event monitoring, such as irregular cardiac symptoms and / or heart diseases. Exemplary heart diseases may include atrial fibrillation, bradycardia, tachycardia, atrioventricular block, Wolff-Parkinson-White syndrome, atrial flutter, sinoatrial node dysfunction, cerebral ischemia, syncope, atrial standstill, and / or palpitations. For example, the patient may be prescribed a cardiac monitor for a long period of time, such as 10 to 30 days or more. In some mobile cardiac event monitoring applications, the portable cardiac monitor may be configured to substantially continuously monitor patients with heart malformations, and when such abnormalities are detected, the monitor may automatically transmit data regarding the abnormality to a remote server. The remote server may be located within a monitoring center that operates 24 hours a day, where the data is interpreted by reviewers and / or caregivers trained in cardiac matters who meet the eligibility requirements, and feedback is provided to the patient and / or designated caregiver via regular detailed reports or event trigger reports. In certain cardiac event monitoring applications, the cardiac monitor may be configured such that the patient can manually press a button on the cardiac monitor to report symptoms. For example, the patient may report symptoms such as constipation, shortness of breath, dizziness, rapid heartbeat, fatigue, fainting, chest discomfort, weakness, dizziness, and / or vertigo.The cardiac monitor can record a patient's predetermined physiological parameters (e.g., ECG information) for a certain period of time (e.g., from 1 minute to 30 minutes before the reported symptoms and from 1 minute to 30 minutes after the reported symptoms). The cardiac monitor can be configured to monitor a patient's physiological parameters other than cardiac-related parameters. For example, the cardiac monitor can be configured to monitor, for example, in particular, cardiac vibrations (e.g., using an accelerometer or a microphone), lung vibrations, respiratory vibrations, sleep-related parameters (e.g., snoring, sleep apnea), and tissue fluid.

[0075] Figure 1 shows an exemplary medical device 100 that is external to, portable, wearable by, and configured to implement one or more of the configurations described herein for patient 102. For example, medical device 100 can be a non-invasive medical device configured to be disposed substantially outside of the patient. The medical device 100 can be, for example, a portable medical device designed to move with and move along with the patient as the patient goes about daily life. For example, a medical device 100 described herein, such as a LifeVest® wearable defibrillator available from ZOLL® Medical Corporation, can be attached to the patient's body. Such wearable defibrillators are generally worn for approximately two to three months at a time, almost continuously or substantially continuously. During the period that the patient wears the wearable defibrillator, the wearable defibrillator can be configured to continuously or substantially continuously monitor the patient's vital signs and, when a need for treatment is determined, the wearable defibrillator can be configured to send one or more therapeutic electrical pulses to the patient. For example, such therapeutic shocks can be pulses for pacing, defibrillation, or transcutaneous electrical nerve stimulation (TENS).

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

[0077] Medical device controller 120 can be operably coupled to sensing electrodes 112, which can be attached to clothing 110, for example, using a hook-and-loop fastener, incorporated into clothing 110, or removably attached to the clothing. In some implementations, sensing electrodes 112 can be permanently integrated into clothing 110. Medical device controller 120 can be operably coupled to treatment electrodes 114. For example, treatment electrodes 114 can be further incorporated into clothing 110, or in some implementations, treatment electrodes 114 can be permanently integrated into clothing 110.

[0078] Configurations other than the configuration of the components shown in FIG. 1 are possible. For example, sensing electrodes 112 can be configured to be attached at various positions around the body of patient 102. Sensing electrodes 112 can be operably coupled to medical device controller 120 via connection pod 130. In some implementations, sensing electrodes 112 can be attached to patient 102 by adhesion. In some implementations, at least one of sensing electrodes 112 and treatment electrodes 114 can be included in a single integrated patch and adhered to the patient's body.

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

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

[0081] In some implementations, the medical devices described herein may be configured to switch between a therapeutic medical device and a monitoring medical device configured to only monitor a patient (e.g., not provide or perform any therapeutic functions). For example, therapeutic components and associated circuitry, such as the therapeutic electrode 114, can be disconnected (or connected) from the medical device as needed, or switched off (or on) from the medical device. For example, the medical device may have optional therapeutic elements (e.g., defibrillation electrodes and / or pacing electrodes, components, and associated circuitry) configured to operate in a therapeutic mode. As a means of converting the therapeutic medical device into a monitoring medical device for a particular use (e.g., operating only in a monitoring mode) or for a patient, the optional therapeutic elements can be physically disconnected from the medical device. Alternatively, the optional therapeutic elements can be deactivated (e.g., by physical switching or software switching) to substantially turn the therapeutic medical device into a monitoring medical device for a particular physiological purpose or for a particular patient. As an example of software switching, to deactivate the therapeutic elements of the medical device, an authorized person can access the protected user interface of the medical device and select a preconfigured option or perform some other user action via the user interface.

[0082] Figure 2 shows a sample component-level diagram of the medical device controller 120. As shown in Figure 2, the medical device controller 120 may include a therapy supply circuit 202, a data storage 204, a network interface 206, a user interface 208, at least one battery 210, a sensor interface 212, an alarm manager 214, and at least one processor 218. A patient monitoring medical device may include a medical device controller 120 that includes components similar to those described above, but does not include the therapy supply circuit 202 (shown in dashed lines).

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

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

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

[0086] For example, each defibrillation pulse can supply energy within the range of 60 to 180 joules. In some implementations, the defibrillation pulse can be a biphasic truncated exponential waveform, whereby the signal can switch between a positive portion and a negative portion (e.g., in the charging direction). This type of waveform can be effective in defibrillating a patient at a lower energy level compared to other types of defibrillation pulses (e.g., monophasic pulses, etc.). For example, the amplitudes and widths of the two phases of the energy waveform can be automatically adjusted to supply an accurate amount of energy (e.g., 150 joules) regardless of the patient's body impedance. The therapy supply circuit 202 can be configured to perform switching and pulse supply operations, for example, under the control of the processor 218. When energy is supplied to the patient, the amount of energy supplied can be tracked. For example, the energy amount can 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 whom the pulse is being supplied.

[0087] The data storage 204 can include, for example, one or more of flash memory, solid state memory, magnetic memory, optical memory, cache memory, combinations thereof, and other non-transitory computer-readable media. The data storage 204 can be configured to store executable instructions and data used in the operation of the medical device controller 120. In certain implementations, the data storage can include executable instructions that, when executed, are configured to cause the processor 218 to perform one or more functions.

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

[0089] In certain implementations, user interface 208 can include one or more physical interface devices, such as input devices, output devices, and combination input / output devices, and a software stack configured to drive the operation of the device. These user interface elements can display visual, auditory, and / or tactile content. Thus, user interface 208 can receive input or perform output, thereby enabling a user to interact with medical device controller 120.

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

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

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

[0093] The biovibration sensor 224 can detect, for example, the vibrations of a patient related to the activities of the heart and lungs. For example, the biovibration sensor 224 can be configured to detect the vibration values of the heart or chest including any one or all of S1, S2, S3, and S4. From these heart vibration values, specific heart vibration metrics or combined metrics including any one or more of the electromechanical activation time (EMAT), left ventricular systolic time (LVST), or left ventricular systolic time ratio (%LVST) can be calculated. The biovibration sensor 224 can include a vibration sensor configured to detect vibrations from the patient's heart system and supply an output signal corresponding to the detected heart vibrations. The biovibration sensor 224 can further include a multi-channel accelerometer, such as a three-channel accelerometer, configured to sense motions within each of three orthogonal axes so as to detect patient motion / body position and associate it with the detected heart vibration information. The biovibration sensor 224 can transmit information describing the heart vibration information to the sensor interface 212 for subsequent analysis.

[0094] The tissue fluid monitor 226 can use radio frequency-based technology to evaluate the fluid volume and fluid retention within the patient's body tissues. For example, the tissue fluid monitor 226 can be configured to measure the liquid content in the lungs, which is typical for the diagnosis and follow-up of pulmonary edema or pulmonary congestion in patients with heart failure. The tissue fluid monitor 226 can include one or more antennas configured to direct radio frequencies at the patient's tissue and measure an output radio frequency signal in response to the radio frequencies passing through the tissue. In a particular implementation, the output radio frequency signal includes parameters indicating the fluid volume within the patient's tissue. The tissue fluid monitor 226 can transmit information indicating the tissue fluid volume to the sensor interface 212 for subsequent analysis. Examples of radio frequency sensors are further described in FIG. 3 below.

[0095] The patient motion sensor 228 may include one or more accelerometers configured to measure motion data regarding patient motion. In certain implementations, the patient motion sensor 228 may be configured to measure the number of steps a patient takes over a particular period of time. For example, a patient may be instructed to perform a particular exercise such as a walking test. The patient motion sensor 228 may be configured to measure step count and pace information during the particular exercise. Note, however, that the patient motion sensor 228 is shown as an individual component for illustrative purposes only. In certain implementations, the one or more accelerometers included within the patient motion sensor 228 may be integrated with other components such as the biovibration sensor 224 or the tissue fluid monitor 226.

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

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

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

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

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

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

[0102] Wireless frequency information corresponding to reflected electromagnetic energy from a patient's chest cavity can indicate lung fluid volume (absolute value and volume change), chest impedance, blood pressure measurements, heart rate measurements, and / or a specific heart condition, based on monitoring of the patient's heart wall motion. Examples of wireless frequency transceivers are described, for example, in U.S. Patent No. 8,989,837 entitled "Methods and Systems for Determining Fluid Content of Tissue," U.S. Patent No. 7,122,012 entitled "Detection of Fluids in Tissues," U.S. Patent 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. 9,002,427 entitled "Apparatus and Method for Continuous Noninvasive Measurement of Respiratory Function and Events," the contents of which are incorporated herein by reference. As described above, wireless frequency information corresponding to reflected electromagnetic energy from a patient's chest cavity can similarly indicate changes in the patient's chest impedance values.

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

[0104] The radio frequency device 430 includes at least two antennas, a transmit antenna 432a and a receive antenna 432b, that transmit radio frequency energy to and receive radio frequency energy from a patient's chest cavity. In some implementations, antennas 432a and 432b may have a flatter and / or more flexible profile that more closely conforms to the shape and outer contour of the patient's body. The transceiver 436 is configured to generate drive signals that transmit and / or receive radio frequency energy with antennas 432a and 432b. The transceiver 436 is further configured to receive and process reflected electromagnetic energy received by antennas 432a and 432b from the patient's body. In certain implementations, the active background cancellation circuit 434 cancels background components from reflected signals, 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 below. The processor 438 may monitor one or more radio frequency signal path characteristics and generate a depth of selected tissue (e.g., within a range of 1 cm to 20 cm) and / or radio frequency information corresponding to the tissue of interest, such as an effective path length of the radio frequency path, and one or more phase and / or amplitude changes of the reflected radio frequency relative to the transmitted radio frequency. The processor 438 may process this radio frequency information and convert the information into interpretable physiological metrics such as chest fluid content information (TFC), heart wall motion data, and / or arterial pulsation information. In some implementations, the radio frequency device 430 may be configured to transmit its radio frequency information to a remote server via a communication interface 448. In that implementation, the remote server may be configured to process the received radio frequency information and perform the conversion to the physiological metrics described above. A power module 444, such as a thin battery, supplies power to the components of the patch unit.

[0105] In some implementations, the radio frequency device 430 may further include an ECG electrode 440 that makes electrical contact with the patient's skin, and an ECG acquisition circuit 450 that filters and digitizes an ECG signal for input to the processor 438. The ECG signal may be used to gate the operation of radio frequency transmission to and reception from the patient's chest. For example, the transceiver 436 may trigger radio frequency transmission based on the timing of the R-wave of the ECG signal.

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

[0107] The communication interface 448 communicates with a remote console to transmit radio frequency data and ECG measurement data and, optionally, to receive operation commands. For example, the communication interface 448 may generally include a wireless link such as a Bluetooth® or WiFi link. For example, since the remote console can be placed in the vicinity of the patient, it can directly receive and process data from the communication interface 448. Alternatively, the communication interface 448 may communicate with a local gateway such as a personal computer, a smartphone device, or a dedicated “hotspot” device that communicates with a remote server on a network such as the Internet or a telephone network. In these implementations, the console may be a network server configured to connect to one or more databases and store radio frequency data and ECG data for subsequent reference, processing, and analysis. For example, access and / or tools for performing data analysis may be provided to a physician or other expert. In some situations, that data may be available to another diagnostic computer system via a wired or wireless communication link. These system configurations are particularly useful for performing portable monitoring of multiple patients over long periods of time at various geographical locations.

[0108] As noted above, a radio frequency device such as device 430 may be used to monitor various metrics and parameters of a patient. For example, the radio frequency device may be configured to monitor interstitial fluid metrics, blood pressure, chest wall movement, and other similar patient parameters.

[0109] To measure interstitial fluid metrics, a radio frequency device may be configured to direct electromagnetic energy into a tissue region (e.g., a lung cavity or thoracic cavity) and measure the amplitude and delay of the return / reflected electromagnetic energy. For example, FIG. 5A illustrates a schematic plot 500 showing amplitude, and FIG. 5B illustrates a schematic plot 505 showing the propagation delay of radio frequencies reflected from a patient's heart. Note that the scales of plots 500 and 505 are arbitrary as shown in FIGS. 5A and 5B. The delay and amplitude vary periodically with each cycle of the heartbeat, as particularly indicated by the sharp peak of line 507 shown in FIG. 5B and the overall downward shift in amplitude at line 502 shown in FIG. 5A, although to a relatively lesser extent.

[0110] The recesses of both line 502 and line 507 from tick mark 250 to tick mark 260 correspond to the inhalation period during the respiratory cycle. When the lungs are filled with air, the effective radio frequency path length through the lungs decreases, as shown by this recess in FIG. 5B, because the physical distance between the antenna and the heart remains approximately the same while the average dielectric constant along that path decreases. Exhalation empties the air from the lungs, increasing the effective radio frequency path length. Further, the amplitude of the reflected wave in FIG. 5A decreases during inhalation, probably because the dielectric constant fluctuations increase, and thus there are more reflections along the radio frequency path through the lungs when the lungs are filled with air.

[0111] In the case of lungs with a large liquid content, the average dielectric constant is generally higher compared to healthy lungs, and thus the radio frequency path delay across the lungs is greater. When radio frequency traverses the lungs, there are fewer reflections, so the overall amplitude may also be larger. On the other hand, during the respiratory cycle, the difference between the air-filled lungs and the lungs emptied of air is expected to be smaller in both amplitude and delay than the differences shown in FIGS. 5A and 5B. Thus, to monitor the tissue fluid content, the processing device can compare, for example, the delay and possibly the amplitude of the reflected wave to the criteria provided by healthy and unhealthy lungs, or previous measurements taken on the same patient. Additionally or alternatively, the processing device can evaluate the amount of fluid in the lungs by analyzing changes in the amplitude and / or delay of the reflected wave during one or more respiratory cycles. In a particular implementation, to quantify the assessment of fluid retention, the actual physical distance traversed by the radio frequency passing through the lungs can be measured, and the relationship (such as a ratio) between the effective radio frequency path length and that physical distance can be calculated.

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

[0113] For example, during the cardiac cycle, a radio frequency device may generate and transmit radio frequency towards an artery that may be located at a specific depth from the radio frequency device. In some examples, some or all of the transmitted radio frequency may bounce back to the radio frequency device. In some cases, the radio frequency device may transmit the radio frequency continuously or discontinuously. During the cardiac cycle, the diameter of the artery may vary over time, and the radar cross section (RCS) of the artery obtained by the radio frequency device may similarly change over time. In some implementations, from various RCS measurements, a pulse waveform of the artery (e.g., pulse waveform 600) indicating a pulse wave propagating through the artery may be determined. Then, from the pulse waveform of the artery, various clinical information such as, but not limited to, arterial stiffness, pulse wave velocity, cardiac output, (continuous or discontinuous) measurements of blood pressure, etc. can be obtained. In some embodiments, the reflected echo may be modulated by the artery during the cardiac cycle process, and the information from the reflected echo may be utilized to determine / evaluate the pulse waveform of the artery. For example, the measurement range may change during the cardiac cycle process, resulting in a change in the phase of the reflected wave. In such cases, that information may be utilized to determine / evaluate the pulse waveform of the artery.

[0114] In a particular implementation, the radio frequency device may be calibrated to include basic measurements of the patient's blood pressure and pulse transit time (PTT) in order to more accurately determine the patient's blood pressure. The PTT can be obtained by using a plurality of sensors attached at known positions on the patient and measuring the pulse arrival time (PAT) at each position. The processing device can calculate the PTT by calculating the difference in PAT at each position and knowing the distance between the sensors. This information can further be utilized to determine the patient's pulse wave velocity (PWV).

[0115] In a particular implementation, the linear transformation associating the systolic blood pressure (SBP) and the diastolic blood pressure (DBP) with the PTT may be represented as follows. SBP = (a × PTT) + b, DBP = (c × PTT) + d The coefficients a, b, c, and d can be calibrated for each patient. In some embodiments, other types of transformations may be used to calculate blood pressure. For example, in the case of a model assuming a constant arterial thickness and a constant radius, the blood pressure P may be represented as P = a × ln(PTT) + b, where again a and b are constants calibrated for each patient. In some embodiments, in any case, obtaining the PTT of the pulse in the artery, and on the other hand the PWV, can be utilized to determine the blood pressure value in the artery. An additional example regarding determining blood pressure using a radio frequency device is described, for example, in U.S. Patent Application Publication No. 2016 / 0345845 entitled "Systems, Apparatuses and Methods for Determining Blood Pressure," the content of which is incorporated herein by reference.

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

[0117] Heart vibrations are the noise generated by the heartbeat and the resulting blood flow due to the heartbeat. Specifically, the vibrations reflect the turbulent flow generated when the heart valves close. During heart monitoring, for example, these unique and distinct vibrations that provide important auditory data regarding heart conditions can be detected using one or more heart vibration sensors.

[0118] In the case of adult healthy individuals, there are at least two normal heart vibrations that occur successively with each heartbeat, often expressed as thump-thump (or thud-thud). For example, the first heart vibration (S1) and the second heart vibration (S2) are generated by closing the atrioventricular valve (AV valve) and the semilunar valve (SL valve), respectively. More specifically, the vibration of S1 indicates the closing of the AV valve, which includes 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 vibration of S2 indicates the closing of the SL valve, which includes the pulmonary valve located between the right ventricle and the pulmonary artery to pump blood to the lungs to obtain oxygen, and the aortic valve located between the left ventricle and the aorta to pump the oxygen-containing blood to the body.

[0119] The cardiac systolic phase refers to a part of the cardiac cycle when the ventricles contract. The cardiac diastolic phase is a part of the cardiac cycle when the ventricles relax and blood is replenished after the cardiac systolic phase. Similarly, the atrial diastolic phase is the period when the atria relax. During the ventricular diastolic phase, the pressures in the left and right ventricles decrease from the peak reached during the cardiac systolic phase (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, allowing the stored blood from the atrium to flow into the ventricle.

[0120] When the small upper atrial cavity contracts during the late cardiac diastolic phase, the atrial cavity pumps blood into the larger lower ventricular cavity. When the lower ventricular cavity is filled and the valve to the atrium is closed, the ventricle undergoes isovolumetric contraction (contraction of the ventricle while all valves are closed), indicating the first stage of the cardiac systolic phase. The second stage of the cardiac systolic phase pumps blood from the left ventricle to the aorta and the limbs of the body, and from the right ventricle to the lungs. Therefore, the atria and ventricles contract in an alternating order. The left and right atria supply blood to the ventricles simultaneously. Then, the left and right ventricles contract simultaneously as well.

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

Table 1

[0122] In addition to the S1 and S2 vibrations, the S3 and S4 vibrations may be detected by a high-sensitivity sensor such as a vibration sensor. Generally, an examining physician performing auscultation (e.g., listening to internal heart vibrations using a stethoscope) will not hear the S3 vibration in an adult healthy subject.

[0123] The third heart vibration S3 is a vibration that occurs immediately after two normal heart vibrations, namely, "dokun dokun" (i.e., S1 and S2). The S3 vibration generally occurs at the beginning of the middle one-third of the cardiac diastole, i.e., approximately 0.12 to 0.18 seconds after S2. This produces a classical rhythm that is compared to the tone of the word "Kentucky" whose final syllable indicates the S3 vibration. Since the S3 vibration does not originate from the heart valves, it has a lower pitch than the S1 or S2 vibration. The S3 vibration in young people, some trained athletes, and in some cases pregnant women is generally harmless, but if the S3 vibration reappears later in life, it may indicate a heart disorder such as left ventricular failure as seen in congestive heart failure (CHF). The S3 vibration is thought to be caused by the reciprocating vibration of blood between the ventricular wall caused by the blood pushing in from the atrium. The reason why the third heart vibration does not occur until the middle one-third of the cardiac diastole may be that perhaps during the initial stage of the cardiac diastole, the ventricle may not be filled sufficiently to generate enough pressure to resonate. Generally, in an indirect examination using a stethoscope, S3 is associated with heart failure. This is because the fact that S3 can be detected by this joint examination method means that the ventricle is stiffer than the ventricle of a normal heart where the vibration of the blood hitting the ventricular wall is audible.

[0124] The intensity of the third heart vibration (intensity of S3) is based on the intensity and duration of that vibration. For example, a high-sensitivity vibration sensor configured to detect the S3 vibration may provide an intensity value of the S3 vibration within the range of 0 to 10. In some implementations, when this intensity value is equal to or exceeds 5.0, the reporting process may indicate the presence of S3.

[0125] The fourth heart vibration S4 is generated by the vibration of blood pushing against a hardened or hypertrophied ventricle. When the S4 vibration is auscultated, it is a sign of pathological conditions such as generally left ventricular insufficiency or left ventricular hypertrophy as seen in systemic hypertension, severe aortic valve stenosis, and hypertrophic cardiomyopathy. The vibration occurs immediately after atrial contraction at the end of diastole and immediately before the S1 vibration, and in some cases produces a rhythm called the "Tennessee" gallop.

[0126] As described above, the wearable medical device can be configured to monitor other physiological parameters of the patient in addition to cardiac-related parameters. In a particular implementation, the wearable medical device can be configured to monitor using vibration sensors such as, for example, a microphone and / or an accelerometer located on the patient's chest region. In some implementations, the vibration sensor can be configured to detect cardiac vibrations (S1 vibration, S2 vibration, S3 vibration, and S4 vibration, heart murmurs), lung vibrations, respiratory movement / chest wall movement, sleep-related parameters (e.g., snoring, sleep apnea), and other similar vibration-based parameters.

[0127] Figure 7 shows a sample schematic diagram including a vibration sensor 700. In an implementation, the vibration sensor 700 can include a high-fidelity diaphragm 705, for example, a dynamic electret condenser, ribbon-based or piezoelectric crystal-based diaphragm. A plurality of motion sensors 710 (e.g., at least 2, 4, 6, or more) can be separately arranged around the periphery of the diaphragm 705. The vibration signals from the diaphragm 605 and the plurality of motion sensors 710 can be digitized by an analog-to-digital converter (ADC) 715 from a series of analog converters and processed via a digital signal processing unit 720. For example, the digital signal processing unit can include a series of digital filters.

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

[0129] Signals from one or more of the plurality of motion sensors 710 can be used to monitor low-frequency vibrations. For example, the low-frequency vibrations include respiratory motion and / or chest wall motion.

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

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

Table 2

[0132] In certain implementations, information regarding characteristic patterns of vibrations can be provided by vibration analysis of vibrations detected via a chest vibration sensor such as the sensor 700 described above. Vibration analysis can include monitoring vibrations ranging from one-tenth of a hertz to approximately one hertz to monitor low-frequency thoracic movements such as respiratory movements, chest wall movements, and, in some cases, cardiac wall movements. For example, when the sensor is substantially aligned with the patient's ventricular apex, the sensor implementing the vibration analysis can detect and monitor ventricular wall movements. Similarly, other vibration patterns can be monitored.

[0133] In certain implementations, multiple frequency ranges of lung vibrations can be monitored at once. For example, an obstruction can produce chest vibration movements such as paradoxical breathing. Upon inhalation, the diaphragm descends to its limit, abdominal contents are pushed down and out, and a negative pressure is generated. This negative pressure pulls the chest wall inward, causing the abdomen to expand and the chest to drop during inspiration as a result. This is the opposite movement of normal breathing. During exhalation in paradoxical breathing, the chest expands and the abdomen drops. Again, this movement is the opposite of normal breathing. As the chest wall becomes more compliant, as seen in infants, the chest movements become more visible. During paradoxical breathing, the tongue is pulled down toward the airway and the jaw is further pulled backward with each breath, often making breathing noisy. The patient may exhibit, for example, wheezing, snoring, and / or grunting sounds. Thus, wheeze-related frequencies (>500 Hz) can be monitored with ultra-low-frequency vibrations (<2 Hz) of the chest wall and / or abdomen that can indicate paradoxical breathing movements.

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

[0135] Frequencies associated with heart vibrations and heart murmurs are generally in the range of approximately 20 Hz to 500 Hz. Low-frequency heart vibrations are vibrations with a dominant frequency of less than approximately 100 Hz such as S3, S4, and diastolic murmurs of mitral stenosis. Specific heart murmurs have high-frequency components such as aortic valve regurgitation with a dominant frequency of approximately 400 Hz. Patient metric analysis for tracking a patient's health status

[0136] As described above, in various scenarios related to the present disclosure, a patient monitoring system may include sensors configured to collect a patient's physiological signals other than ECG signals. For example, a vibration sensor may be configured to collect bio-vibration signals such as cardiac vibration signals and pulmonary vibration signals. Further, a radio frequency sensor such as an ultra-wideband transceiver circuit may be configured to collect information corresponding to radio frequency electromagnetic energy reflected from within a patient's thoracic cavity and / or heart. In the implementations described herein, the processing device may further process various signals and associated information collected from various underlying physiological sensors to generate one or more combined physiological parameters, e.g., physiological parameters determined based on two or more of the various underlying physiological sensors and associated information. At least one of predictive analytics (e.g., utilizing a machine learning process or an artificial neural network) and trend analysis (e.g., correlation analysis) may be performed on the collected signals and received information, as well as on the combined metrics, to determine a patient's current condition and one or more clinically actionable events.

[0137] More specifically, in certain implementations, the patient monitoring system can include 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, and one or more radio frequency antennas coupled to the patient, wherein the one or more radio frequency antennas direct radio frequency electromagnetic energy towards the patient's chest cavity and generate radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the patient's chest cavity received via the one or more radio frequency antennas, and one or more processors. The one or more processors can be configured to process a) the one or more ECG signals, b) the one or more cardiac vibration signals, and c) 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 can further perform at least one of predictive analysis and trend analysis of the plurality of physiological parameters including the combined physiological parameters to determine the patient's current clinical condition, wherein the trend analysis includes determining the existence of a substantial relationship of changes in the plurality of physiological parameters, comparing the patient's current clinical condition with a predetermined clinically usable criterion to determine one or more clinically usable events, and being configured to cause an output device to output an output regarding the one or more clinically usable events.

[0138] In another implementation, the patient monitoring system may include at least one vibration sensor coupled to the patient and configured to detect one or more cardiac vibration signals, at least one ultra-wideband radio frequency transceiver coupled to the patient, and one or more processors. The at least one ultra-wideband radio frequency transceiver may be configured to direct radio frequency electromagnetic waves towards the patient's lungs and detect radio frequency information responsive to the radio frequency electromagnetic waves passing through the lungs. The one or more processors may be configured to process the detected one or more cardiac vibration signals over a predetermined period to determine at least one cardiac vibration metric of the patient, process the patient's radio frequency information over a predetermined period to determine at least one lung fluid metric of the patient, determine an output regarding one or more clinically usable events based on the determined at least one cardiac vibration metric and the determined at least one lung fluid metric, and cause the output to be output to an output device.

[0139] In another implementation, a patient monitoring system can 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 the patient and configured to detect one or more cardiac vibration signals of the patient, an ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and coupled to the patient, and one or more processors. The ultra-wideband radio frequency transceiver can be configured such that one or more radio frequency antennas direct radio frequency electromagnetic energy towards the patient's chest cavity and receive, via the one or more radio frequency antennas, radio frequency information corresponding to reflected radio frequency electromagnetic energy reflected from within the patient's chest cavity. The one or more processors can 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 one or more combined physiological parameters, perform a trend analysis of the plurality of physiological parameters including the combined physiological parameters to produce a trend result, update a monitoring schedule of the patient based on the trend result, determine a current clinical condition of the patient based on the trend result, compare the current clinical condition of the patient with a predefined clinically usable criterion to determine one or more clinically usable events, and cause an output device to output an output regarding the one or more clinically usable events.

[0140] In another implementation, a patient monitoring system can 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 the patient and configured to detect one or more cardiac vibration signals of the patient, an ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and disposed over at least one aorta of the patient, and one or more processors. The ultra-wideband radio frequency transceiver circuit can be configured such that the one or more radio frequency antennas direct radio frequency electromagnetic energy towards at least a portion of the patient and receive, via the one or more radio frequency antennas, radio frequency information corresponding to reflected radio frequency electromagnetic energy reflected from within at least a portion of the patient. The one or more processors can 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 one or more combined physiological parameters, perform at least one of predictive analysis and correlation 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 to a predetermined clinically available criterion to determine one or more clinically available events, and cause an output device to output an output regarding the one or more clinically available events.

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

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

[0143] Note that the overviews shown in FIGS. 9 and 10 are shown as just examples. For example, three metrics are shown in both overviews as an example of the number of metrics that may be used. In actual practice, a variety of other numbers of input metrics may be used in both the predictive analytics process and the trend analysis process.

[0144] In one implementation of the general concept shown in FIGS. 9 and 10, metric 1 is an ECG metric, metric 2 is a biovibration metric (including heart vibrations, lung vibrations, and low-frequency patient movement data), and metric 3 is a radio-frequency-based physiological metric. Alternatively or additionally, one or more of metrics 1, 2, and 3 may include combined metrics obtained from one or more of the ECG metric, the biovibration metric, and the radio-frequency-based physiological metric.

[0145] Figures 11 and 12 show a patient monitoring system that indicates clinically actionable events based on changes in a patient's physiological information. The system can make decisions, perform analysis, and / or classification, and provide notifications regarding clinically actionable events according to a predetermined clinically actionable criterion.

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

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

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

[0149] Referring again to FIG. 11, in some examples, physiological metric 1145 may span with patient demographic information and patient medical history information 1140. For example, patient demographic value information may include age, gender, race, etc. For example, patient medical history information includes previous medical conditions, diagnoses, previous hospital stays, etc. A sample patient medical history record may include the information shown below, and a sample input to the patient monitoring system is further shown in Table 3 below. Table 3 [Table 3]

[0150] In some implementations, an additional set of physiological metrics may be obtained based on patient activity test data 1142 from one or more physical activity tests performed by a patient wearing a wearable medical device. For example, as shown below, this device may monitor one or more activity tests performed by the patient. In one example, the physical activity may be a physician-directed physical assessment, such as the activity assessment of WalkTest (registered trademark) performed by the WCD of LifeVest (registered trademark). The purpose of the assessment is to monitor the patient's process during the assessment by monitoring parameters such as the number of steps the patient takes while walking for approximately six minutes, the distance traveled during the assessment, and the movement speed.

[0151] Before and after walking, the patient may be asked to perform a health survey answering one or more questions regarding the patient's overall health. For example, the patient may be asked to indicate a shortness of breath level (e.g., an exemplary scale where 0 = normal sensation, 0.5 = able to maintain conversation while walking, 1 = may need to stop immediately). Another query may be regarding the patient's fatigue level (e.g., how much fatigue the patient is feeling). After the evaluation, the patient may be prompted to answer the same series of questions again or additional questions. Responses to these questions can be normalized to a series of physiological parameters, e.g., stored as values in a range from 0 to 1, 0 to 10, 0 to 100, or any other suitable range of values and input into predictive analytics and / or trend analysis. Numerical ranges are described herein, but other scales, ranges, and / or methods of quantifying the patient's responses to the health survey may be used. The patient's prescribing physician may repeat the evaluation for the patient once a day or once a week. The device may remind the patient via the user interface when the patient is scheduled to perform the next evaluation. The health surveys described herein are in the context of performing a physical assessment, but in some implementations, apart from the physical assessment, health surveys may be administered to the patient wearing the device. For example, the device may periodically (e.g., daily, weekly, or other schedule) prompt the patient to perform a health survey. In some examples, the patient's physician may configure the device to perform a health survey as needed. In such cases, the patient's physician may instruct a technician to send one or more operation commands to the wearable medical device to a remote server to cause the health survey to be performed.

[0152] The distance walked over an evaluation duration (e.g., 6 minutes) can indicate the patient's current clinical state. For example, in the case of a patient who walks less than a pre-set duration (e.g., 350 meters), this patient may be scored as having a relatively higher risk of death compared to a patient who has advanced more than 350 meters. In some examples, the input to predictive analytics and / or trend analysis may be the raw distance the patient has advanced. In other examples, the distance may be normalized according to a given scale. For example, a normalized scale indicating the distance advanced by the patient during the activity may be generated. For example, a scale from 0.0 to 1.0 indicating the distance advanced is shown in Table 4 below. Table 4

Table 4

[0153] In some examples, when a clinician enters the step length into the device via a user interface and the measured distance change can occur when using the step length provided by the clinician. In some implementations, a normalized step length (e.g., based on similar patient population data) can be implemented when calculating the travel distance.

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

Table 5

[0155] In some examples, the input to predictive analytics and / or trend analysis may be the raw number of steps the patient has advanced. In other examples, the number of steps may be normalized according to a given scale.

[0156] Another parameter that can be tracked includes the pace being evaluated, such as the number of steps per minute and / or the distance traveled per minute. As described above, in some examples, the input to the predictive analysis and / or trend analysis may be the raw pace information of the patient. In other examples, the pace may be normalized according to a predetermined scale. For example, during the normalization process, these metrics may be converted and stored as values in the range from 0 to 1, from 0 to 10, from 0 to 100, or any other suitable range of values, and can be input into the predictive analysis and / or trend analysis. Although numerical ranges are described herein, other scales, ranges, and / or methods for quantifying the patient's metrics may be used. Additional patient metrics may include · Heart rate during evaluation (average value, maximum value, expected value, mode) · Respiratory rate during evaluation · Whether the patient has completed the test (completed / not completed), or what percentage of the test has been completed · Whether the patient has performed a walking test, which can be an indicator that the patient has symptoms of the problem / deteriorated symptoms may be included.

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

[0158] In some implementations, additionally or alternatively to the above, the overall performance of the patient regarding physical evaluation, such as WalkTest (registered trademark), may be scored on a normalization scale. The overall performance score may be based on, for example, the individual scores for each component of the physical evaluation as described above, as well as information regarding health evaluation. For example, the overall performance may be graded on a scale ranging from 0 to 1 as shown in the following table. Table 6

Table 6

[0159] Referring again to FIG. 11, the entire dataset of the physiological metric 1145 is sent to the predictive analytics classifier or trend analysis classifier 1150, and an output 1155 is generated. Referring now to FIG. 12, as shown in system 1200, the output 1155 of the predictive analytics classifier or trend analysis classifier 1150 may include a score indicating the patient's current overall clinical symptoms 1205. If the patient's grade is deteriorating, e.g., the clinical symptom score has a deteriorating trend and / or exceeds a threshold, the system may prompt a specific action. In one example, the classifier may output a score from 0 to 1 indicating the patient's overall symptoms, where a score at the lower end of the scale (e.g., from 0.0 to 0.25) may indicate a stable patient with no cause for concern, and a score at the upper end of the scale (e.g., 0.50 or higher) may indicate an unstable patient requiring intensive monitoring (e.g., indicating the likelihood of an adverse event). For example, such adverse events may include one or more of arrhythmia events (VT / VF), seizure events, syncope events, and hospitalization events. Based on the patient's current health status 1205, system 1200 may generate a clinically usable event such as a treatment plan adjustment 1210 for the patient and send the generated recommendation to a caregiver such as a physician 1220.

[0160] In a particular implementation, information regarding changes to the treatment plan may be fed back to the predictive analytics classifier or trend analysis classifier 1150, as shown in FIG. 11. Such a feedback loop may provide an improvement to the predictive analytics classifier or trend analysis classifier 1150 that includes information regarding changes to the treatment plan and the patient's response to those changes.

[0161] Additionally or alternatively, to observe the trend of the output score, the score may be dependent on one or more threshold conditions. For example, the threshold condition(s) may trigger one or more clinically usable events. Table 7 below provides an exemplary set of patient health status score categories, threshold ranges, and the patient's current health status information. Table 7

Table 7

[0162] In some implementations, the score categories above may be part of a proprietary scoring system implemented with a proprietary device according to the embodiments described herein. In other particular implementations, this process may classify patients according to the heart failure classes adopted by a physician or a hospital group, association, or other regulatory authority. For example, such authorities may be the American College of Cardiology (ACC), the American Heart Association (AHA), and the New York Heart Association (NYHA). In this regard, the device may automatically classify patients into appropriate heart failure classes and / or stages based on the similar scoring systems above. In some implementations, the user may configure, via a user parameter set in advance, which grading system the device implements. For example, when setting, the user may be prompted to indicate the grading system according to one or more of the following options. The user may do so via a user interface (e.g., either locally on the device or remotely via configuration parameters sent to the device and then to a server). Those options, · Proprietary scoring system (described above) · ACC / AHA system · NYHA system may be indicated.

[0163] The ACC / AHA system may be implemented as follows.

[0164] Stage A are patients at risk of heart failure in whom structural heart changes have not yet developed (i.e., patients with diabetes without previous infarction, patients with coronary heart disease).

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

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

[0167] Stage D includes patients with refractory heart failure who require advanced intervention therapy (i.e., biventricular pacemaker, left ventricular assist device, transplantation surgery).

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

Table 8

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

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

[0171] Grade III heart failure patients feel clear limitations during physical activity. Patients may maintain a pain-free state at rest, but most physical activities will cause excessive fatigue. Under the circumstances of the doctor, the patient's diet and exercise may be monitored. Diuretics may be prescribed to suppress fluid retention.

[0172] Patients with class IV heart failure perform all physical activities with substantial discomfort. There may be significant signs of heart failure even while at rest. Surgical options will be considered in conjunction with the same considerations given to classes I through III treatment.

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

Table 9

[0174] At any given time, one or more events may be triggered depending on the patient's class and / or score. Such events may be any of the automatic events that are triggered without user input. For example, the system may automatically instruct an external medical device (e.g., a wearable defibrillator) connected to the patient to increase the sensitivity of the detection process during periods when the patient may be at high risk of a sudden arrhythmia event. Or, the system may output information regarding the patient's current symptoms and issue instructions to the caregiver and / or other people who should take action. Such actions may include recommendations to change the patient's treatment plan, such as changing the dosage of a drug, or to place the patient under heightened surveillance or admit the patient to the hospital.

[0175] For example, clinically actionable events, including but not limited to, triggering a change in the controller to shorten the time from detection to treatment of sudden cardiac arrest, may be relevant for external medical devices (e.g., wearable defibrillators). Further, by detecting categories of high risk scores, the system may be prompted to notify patients, physicians, responsible third parties, medical teams, and / or technical support of a change in risk. Thus, patients in categories of high risk scores may be observed more frequently in the future and / or given attention to change treatment plans.

[0176] In some implementations, when a patient's clinical condition deteriorates, caregivers and / or technical support personnel may initiate a real-time or substantially real-time streaming delivery of the patient's ECG data (and / or other physiological data) to a remote server for additional monitoring and analysis to an external medical device of the patient. For example, as shown in FIG. 12, when the patient's current health state 1205 indicates a worsening of symptoms, the system may send a sign to the remote server to perform various notification and / or analysis actions 1215.

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

[0178] In some implementations, if the patient's symptoms are worsening but have not yet reached a predetermined critical threshold, i.e., if a subsequent rapid action cannot be considered necessary (e.g., when the classifier is 0.5 or more in the above example but scores the patient's current health status as 0.65 or less), the physician or technical support people may start reporting the patient's physiological state more frequently (e.g., reporting the patient's symptoms medically), or may start streaming the ECG data. Further, if the patient reaches score category 3 (e.g., 0.5 or more), the physician or technical support people may take additional actions including, for example, instructing to check external medical devices more frequently and / or ensuring that the downtime of continuous monitoring is kept to a minimum.

[0179] For a patient in score category 4 who has a high level of systolic dysfunction, actions that may be taken include, but are not limited to, notifying the patient and the responsible third party to obtain a physician's diagnosis, and notifying the responsible medical team of the patient's critical condition.

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

[0181] According to the implementation, the patient monitoring device and / or the patient monitoring system may recommend one or more of the following actions. These actions may be recommended 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 recommended to the patient's primary caregiver and / or attending physician.

[0182] The general ACC / AHA Stage A is considered early heart failure. At this stage, the patient is monitored for signs of hypertension, diabetes, coronary artery disease, metabolic syndrome, a history of alcohol dependence, a history of rheumatic fever, a family history of cardiomyopathy, a history of taking drugs that can damage the myocardium such as some anticancer drugs. Exemplary Stage A treatment plans that the patient monitoring system may recommend include the following. · Performing only ECG monitoring The monitoring device does not have to initiate biovibration and / or radio frequency-based TFC monitoring of the patient · Regular exercise, being active, daily walking · Smoking cessation · Hypertension treatment (pharmacotherapy, low-salt diet, active lifestyle) · Hypercholesterolemia treatment · Abstaining from alcohol or not using energy recovery drugs · Pharmacotherapy: If the patient has coronary artery disease, diabetes, hypertension, or other vascular or heart diseases, an angiotensin-converting enzyme inhibitor (ACE-I) or an ARB-type antihypertensive drug (ARB) If the patient has hypertension, a beta blocker

[0183] ACC / AHA Stage B is considered early heart failure. This means that the patient has been diagnosed with at least left ventricular systolic dysfunction, but has never had symptoms of heart failure. Most people with heart failure at Stage B may have an echocardiogram (echo) showing an ejection fraction (EF) of less than 40%. This category can include people with heart failure and low EF (HF-rEF) due to any cause. An exemplary Stage B treatment plan that a patient monitoring system may recommend includes the following. · Continue or modify the treatments listed in the Stage A list For example, the monitoring device may initiate biometric vibration and / or radio frequency-based TFC monitoring of the patient. For example, the TFC measurement frequency may be increased. If TFC was previously measured on a weekly basis, it may be changed to measurements every two or three days. For example, the monitoring device may initiate physical assessments and / or physical tests on the patient. · (If the patient has not yet advanced a treatment plan as part of their Stage A) Add an angiotensin-converting enzyme inhibitor (ACE-I) or an ARB-type antihypertensive (ARB) · If the patient has had a heart attack and the patient's EF is 40% or less (if the patient has not yet advanced a treatment plan as part of their Stage A), add a beta blocker · If the patient has had a heart attack, or the patient has diabetes and the EF is less than 35% (to reduce the risk of the patient's myocardium hypertrophying and the pump function of the myocardium becoming insufficient), add an aldosterone antagonist · Enable wearable defibrillator treatment · Consider surgery or interventional treatment that may be possible as treatment for coronary artery occlusion, heart attack, valvular disease (where the patient may require valve repair or replacement surgery), or congenital heart disease.

[0184] Patients in stage C of the ACC / AHA have generally been diagnosed with heart failure and have currently or previously shown signs and symptoms of the disease. There are many possible symptoms of heart failure. The most common ones are, · Shortness of breath · Feeling tired (fatigue) · Inability to exercise · Weak legs · Waking up due to urge to urinate · Swelling in the feet, ankles, lower legs, and abdomen (edema) which are.

[0185] An exemplary stage C treatment plan that a patient monitoring system may recommend includes the following. · Continuing or modifying the treatments listed in the stage A and stage B lists. For example, the monitoring device may initiate biovibration and / or radio frequency-based TFC monitoring of the patient (if not already monitoring). For example, the TFC measurement frequency may be increased. If TFC was previously measured on a two- to three-day basis, it may be changed to daily measurements. For example, the monitoring device may initiate frequent physical evaluations and / or physical tests on the patient. · Adding a beta blocker (if the patient is not already taking the drug) · Adding an aldosterone antagonist if vasodilators (e.g., ACE-I, ARB, or a combination of angiotensin receptor / neprilysin inhibitors) and beta blockers do not relieve the patient's symptoms (if the patient is not already taking the drug) · Adding a hydralazine / nitrate combination if other treatments do not relieve the patient's symptoms · Adding a drug that can lower the heart rate, for example, if the patient's heart rate is more than 70 beats per minute and the patient still has symptoms · Adding a diuretic (a "water pill") if the chest fluid content and / or S3 intensity continue to worsen · Advising sodium (salt) restriction in the diet · Recommendations for daily patient weight tracking · As much fluid restriction as possible if chest fluid content and / or S3 intensity continue to deteriorate · As much cardiac resynchronization therapy as possible (e.g., biventricular pacemaker) · As much implantable cardioverter-defibrillator (ICD) therapy as possible · If treatment improves or arrests the patient's symptoms, the patient may still need to continue treatment to delay progression to stage D.

[0186] Patients in stage D and with low EF (HF-rEF patients) generally have advanced symptoms that are less responsive to treatment. This is generally considered the final stage of heart failure. Exemplary stage D treatment plans that a patient monitoring system may recommend include the following. · Continuation and / or modification of treatments listed in the stage A, stage B, and stage C lists · Heart transplantation · Assistive artificial heart · Heart surgery · Continuous infusion of intravenous inotropic agents · Palliative care or hospice care · Treatment research Evaluation for more advanced treatment options, including

[0187] One or more physiological measurements extracted from the ECG signal may include one or more of heart rate, heart rate variability, PVC burden or PVC count, activity level, noise quantification, atrial fibrillation, transient apnea, cardiac arrhythmia, QRS height, QRS width, change in size or shape of morphology, cosine R-T, artificial pacing, corrected QT interval, QT variability, T wave width, T wave alternans, T wave variability, ST segment change, early repolarization, delayed potential, fractionated QRS / HF content, and fractionated T wave / HF content.

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

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

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

[0191] HRV measurement quantifies the variation of the RR intervals over time within the electrocardiogram signal of a patient. The R wave of a specific beat corresponds to a point in the cardiac cycle at the initial systolic phase, and from the signal processing point in the figure, a reliable reference time for measuring the cardiac cycle intervals is provided. 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 an indicator of the dynamic interaction and balance between the SNS and PNS, and provides a measure of the nervous system's ability. HRV is affected by the autonomic nervous system and functions as an indicator for diagnosing and evaluating various symptoms ranging from congestive heart failure to sleep apnea. For example, it has been found that a decreased HRV is a precursor to an increased mortality rate in the elderly with coronary heart disease. A decreased HRV is also seen after sudden cardiac arrest.

[0192] The variability measurement related to HRV is T-wave alternans, and T-wave alternans is a variability measurement during myocardial recovery in the cardiac relaxation (diastolic) phase, and measures the variation in the amplitude of the T wave of the ECG.

[0193] In one example, extracting HRV data can include filtering the ECG signal to remove noise and artifacts, placing the QRS complex within the filtered ECG signal, finding the RR intervals between consecutive R peaks, and processing the RR intervals to obtain HRV. For example, the ECG signal is filtered using a band-pass filter and the QRS complex is placed. It is necessary to use a band-pass filter with an operating frequency range wider than the frequency components of the QRS complex. The frequency components of the QRS complex are between 10 Hz and 25 Hz. Therefore, in one embodiment of the present disclosure, the operating frequency range of the band-pass filter is approximately from 5 Hz to approximately 28 Hz.

[0194] In one example, the R wave may be arranged as follows. The maximum peak data value that first occurs within the filtered ECG signal is arranged. An upper amplitude threshold and a lower amplitude threshold are determined from the arranged maximum peak value. The peak value, and the minimum values on both sides of the peak value are arranged. In this embodiment of the present disclosure, both sides refer to the left side and the right side of the peak value. It is verified whether the condition that the peak value exceeds the upper amplitude threshold and the minimum value is below the lower amplitude threshold is satisfied. If the condition is satisfied, the position of the peak value is displayed as the R position. The position of the minimum value that occurs closest to the left side of the R position is displayed as the Q position, and the position of the minimum value that occurs closest to the right side of the R position is shown as the S position. Regarding the time scale for displaying the filtered ECG signal, the Q position occurs at the location where the minimum value first occurs before the R position, and the S position occurs at the location where the minimum value first occurs after the R position. Thus, the positions of the QRS peaks within the filtered ECG signal are determined.

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

[0196] The positions of other R waves within the filtered ECG signal may be arranged by repeating a process of arranging another peak value and other minimum values on both sides of another peak value. When another peak value exceeds an upper amplitude threshold and both other minimum values fall below a lower threshold, the position of the peak value is displayed as the R position. The position of the minimum value that occurs closest to the left side of the R position is shown as the Q position, and the position of the minimum value that occurs closest to the right side of the R position is displayed as the S position. In this way, the positions of other QRS peaks are determined.

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

[0198] The time domain data may include information regarding any one or more of the following parameters: the average value of the RR intervals (average RR), the standard deviation of the RR intervals (STD), the average value of the instantaneous heart rate (average HR), the standard deviation of the instantaneous heart rate (STD_HR), the root mean square of the differences between adjacent RR intervals (RMSSD), the number of consecutive RR intervals that differ by 50 ms or more (NN50), and the ratio of consecutive RR intervals that differ by 50 ms or more (pNN50).

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

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

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

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

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

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

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

[0206] An overview of how a random forest tool may be applied to a given dataset may indicate how a grading tool may function when interpreting given parameters or metrics. A random forest is a collection of decision trees. A decision tree is a flowchart-like structure where each node represents a test on a metric and each branch represents the result of the test. The tree ends with a class label, such as a decision made at the end after calculating each of the metrics, for example. Each tree in a random forest tool obtains one "vote" when classifying a given set of metrics. There are two components to the randomness involved in constructing a random forest. The first is that in generating each tree, a random subsample of the total dataset is selected to grow the tree. The second is that at each node of the tree, a "splitter variable" is selected and the original patients are divided into two classes. For example, patients in one class (e.g., response or occurrence of sudden cardiac arrest) may be separated from patients in another class (e.g., non-response). The tree grows with additional splitter variables until all terminal nodes (leaves) of the tree are completely in one class or the other. The tree is "tested" against previously placed patient records. Each patient test record traverses the tree, going down one branch or the other according to the metrics included in the record of each splitter variable. A predicted result (one vote) is assigned to the patient test record based on where in the tree the record ends up. The entire process may be repeated with new random assignments of the original dataset to generate additional trees and ultimately a "forest". In any case, different subsets of patients may be used to construct the trees and test their performance.

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

[0208] As described above, a machine learning tool can train a classifier on a first percentage of the original dataset and can validate the classifier on a second percentage of the dataset or on another separate dataset. When evaluating the performance of each classifier, the performance of the basic decisions within the decision trees of a random forest can be evaluated based on specificity and sensitivity parameters. For example, the sensitivity parameter can be based on a measure of the classifier's ability to correctly predict whether a patient is at risk of needing treatment according to an appropriate score category. For example, the sensitivity parameter can be based on the percentage of patients who are appropriately treated so that the model correctly predicts, and patients who are at risk of being treated. The specificity parameter can be based on the percentage of patients who are not treated and patients who are predicted by the associated classifier as not being at risk of needing treatment. It may be advantageous to optimally balance individual performance variables such as high levels of sensitivity and specificity. For example, by setting the specificity to a relatively high value, e.g., 95%, the basic threshold within the classifier model can be adjusted for a minimum number of false positives. After the specificity is defined, the measurement of sensitivity can be treated as a type of performance measurement, e.g., generally in the range of 15% to 35% of a given model. However, smaller or larger sensitivity values are also possible.

[0209] For example, as described below, a validation protocol can be utilized to validate the prediction performance of a training model. In an implementation, the validation stage can be used to ascertain an appropriate threshold score for classifying future patients (whose results are currently unknown and for whom prediction of the results is desired), and to determine the prediction performance of each classifier model generated by a machine learning tool. To validate various classifiers and associated threshold scores, for example, a second population of individuals such as a validation population (or cohort) can be used. For example, the validation population used can be a new validation population. The results of the patients in the validation cohort are ultimately learned as these patients progress towards the end of device use. In one embodiment, the patients in the validation population can be different from the training and test populations of patients described above for training the classifier. For example, the patient validation population and associated metrics (validation metrics) can be independent from the patient training population and associated metrics (training metrics). In some implementations, there may be an overlap between the validation metrics and the training metrics.

[0210] In some implementations, the validation population can be updated based on at least one of: 1) adjusting one or more of the metrics in the validation metric, and 2) expanding the validation metric by adding one or more additional patients to the population of patients that make up the validation population. A threshold for classifying future patients can be refined based on the updated validation metric. For example, the metrics of patients currently being treated or monitored, or otherwise not yet at the end of device use, can be used to adjust one or more of the metrics in the validation metric, or the metrics of the patients can be added to the validation population as metrics from new patients. When new metrics for a patient are determined during monitoring or treatment of the patient, the validation metric can be adjusted. In some examples, when a monitored patient progresses to the end of device use, the metrics of the patient can be added to the validation population and / or can be used to adjust the metrics in the validation metric after the patient has progressed to the end of device use.

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

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

[0213] The training dataset 1405 may be supplied to a training module 1410. The training module 1410 may include one or more non-training data structures such as a series of data trees (organized, for example, using the random forest tool described above). Using the known input variables and known results from the training dataset 1405, the training module 1410 may train that data structure by repeatedly processing each data point in the training set to generate more accurate expected (and known) results.

[0214] When the training module 1410 empties the training dataset 1405, the training module may output one or more trained classifier models 1415. The one or more trained classifier models 1415 may represent a model set, and the model set provides the most accurate grades and generates the results of a known set of input variables that can be generated from the training data 1405. The verification module 1420 may further be configured to refine the trained classifier model 1415 using additional patient records. For example, the verification dataset 1425 may be input to the verification module 1420 to verify one or more trained classifier models 1415. Continuing with the above example, the verification dataset 1425 may include 200 patient records. Generally, there is no advantage in running the same dataset twice, so there is no overlap between the training dataset and the verification dataset.

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

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

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

[0218] In an artificial neural network, a node includes a plurality of artificial neurons, and each artificial neuron has at least one input with an associated weight. The artificial neural network can be trained using its physiological parameters such that the associated weights of at least one input of each artificial neuron of the plurality of artificial neurons are adjusted in response to the first, second, and third respective parameters of different data sets from the patient's physiological parameters. This results in an artificial neural network that is trained to generate a health status score for the patient.

[0219] An artificial neural network may be a mathematical model or a computational model that simulates the structure 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 artificial neuron, and at least one output. The neuron may be present in a single hidden layer of the artificial neural network and may receive two or more inputs. In an example where the artificial neural network has a plurality of neurons, the plurality of neurons may be distributed throughout one or more hidden layers. If there are multiple layers, each layer may be interconnected with the previous layer and the subsequent layer.

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

[0221] In an example, a first parameter (e.g., S3 vibration intensity), and a second parameter (e.g., interstitial 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 parameters. The artificial neural network may be trained with the feature vector. The artificial neural network may be implemented as instructions stored in a memory that cause a processor to perform the functions of the artificial neural network when executed by the processor. In an embodiment of the present disclosure, the artificial neural network may be based on a support vector machine architecture, and the weights associated with at least one input of each artificial neuron of the plurality of artificial neurons are initialized from a library used by the support vector machine.

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

[0223] For example, the artificial neural network may be based on an extreme learning machine architecture, and the weights associated with at least one input of each artificial neuron of a plurality of artificial neurons are initialized through random selection by the extreme learning machine. The artificial neural network may be realized as a single-layer feedforward network, and the prediction about the patient's viability is derived from the following function. [Number] In the formula, xj is the input vector to one of the inputs of a plurality of neurons for N input vectors of j = 1, 2,..., N, wi is the weight associated with the input of the neuron that receives the input vector of xj, g(wi·xj + bi) is the output of the neuron that receives the input vector of xj for i = 1, 2,..., N artificial neurons, βi is the output weight vector that associates the i-th hidden neuron with each output neuron, and bi is the bias for the i-th hidden neuron.

[0224] The training of the artificial neural network may be based on error backpropagation learning. For example, the error backpropagation learning may use the Levenberg-Marquardt process. Each of the plurality of neurons of the artificial neural network may have an activation function, and the activation function is selected from a group of functions including hardlim, sigmoid, sine, radial basis, and linear.

[0225] In an example, the result of the artificial neural network may be only two possible values, and the two possible values are whether the patient's health condition is stable and good (no adverse events are expected), or whether the patient is hospitalized (adverse events are expected).

[0226] In another example, the physiological parameter data may be divided into many parts. The first parameter set may relate to the patient's ECG metric, the second parameter set may relate to the patient's heart vibration metric, and the third parameter set may relate to the patient's demographics and medical history. The first parameter set, the second parameter set, and the third parameter set are then provided as a set of normalized data values to be input into a scoring system. For example, the scoring system may assign each category to each parameter of the first parameter set, the second parameter set, and the third parameter set. Each category may have a plurality of predetermined value ranges, and each of the plurality of value ranges has a predetermined score. The score for each parameter of the first parameter set, the second parameter set, and the third parameter set is determined by assigning the normalized data set to each predetermined value range and including the set of normalized data values among the plurality of value ranges of the category associated with each parameter of the first parameter set, the second parameter set, and the third parameter set. The total score may be obtained based on the sum of the scores of each parameter of the first parameter set, the second parameter set, and the third parameter set as an indication of the patient's symptoms. The scoring system may be any suitable process or process and may be implemented in an electronic database capable of assigning scores to each value range 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 system may be based on a mathematical model using logistic regression such as univariate analysis.

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

[0228] In addition to using a learning process such as an artificial neural network or a machine learning process as described above, trend analysis can further be utilized to monitor patients whose symptoms are changing and to produce outputs such as changing a patient's treatment plan. In certain implementations, trend analysis can include determining the existence of a substantial relationship between changes in two or more physiological parameters. For example, as described above in connection with FIG. 7, detecting a change in a particular metric can trigger the monitoring of another metric. This additional monitoring can be performed to confirm the trend of the monitored metric and to provide additional information regarding the overall patient's symptoms.

[0229] An example of trend analysis is correlation analysis. Correlation analysis is the quantification of the linear relationship between two variables, and the correlation analysis can be represented by a value from -1.0 to 1.0, collectively referred to as the Pearson product-moment correlation coefficient and denoted as r. As the correlation coefficient approaches 1.0, the correlation coefficient indicates a strong positive correlation between the two variables. As the correlation coefficient approaches -1.0, the correlation coefficient indicates a weak negative correlation between the two variables. A correlation value close to zero indicates no linear relationship between the two variables.

[0230] In certain examples, there may be two sets of data samples, X and Y. For example, the data set of X may be data sampled from curve X, such as the S3 intensity curve of heart vibrations, and the data set of Y may be data samples from curve Y, such as the curve of chest fluid content measurement. In certain implementations, the correlation analysis may be performed using Pearson's product-moment correlation coefficient, Fisher transformation, or other similar correlation functions. For example, using Pearson's product-moment correlation coefficient, the correlation of n data pairs (X, Y) can be calculated, where X and Y are samples over a certain period of time. Continuing with the above example, X can be measured from the S3 intensity curve and Y can be measured from the TFC measurement curve. The above Pearson's product-moment correlation coefficient r can be obtained by exchanging the variance-covariance-based samples of the data sets of X and Y. The resulting value of r is a value from -1.0 to 1.0. In this example, a value of 1.0 would indicate a perfect correlation between X and Y, i.e., as the S3 vibration intensity increases, then the TFC measurement value increases accordingly. A value of -1.0 would indicate a negative perfect correlation. For example, as the S3 vibration intensity increases, then the TFC measurement value decreases. Conversely, as the S3 vibration intensity decreases, then the TFC measurement value increases. A value of 0.0 indicates that there is no linear relationship between the variables.

[0231] As described herein, multiple metrics can be correlated to determine a patient's condition. For example, when a patient may be at risk of experiencing a cardiac adverse event such as arrhythmia, there may be a high correlation between chest fluid content (TFC) and S3 vibration intensity. When using the process described in FIG. 10, TFC can be considered as metric 1 and can be shown on a normalized scale from 0 to 1000. Other normalized linear or non-linear scales may be used. For example, the scale may be from 0 to 1, or from 0 to 10, or from 0 to 100. For example, the non-linear scale may be a logarithmic scale. The processing device can monitor the TFC to detect any changes or trends in the patient's TFC value.

[0232] For example, as shown in FIG. 16A, the processing device may record the patient's TFC measurement values over a period of several weeks. As shown in FIG. 16A, the TFC measurement values are indicated by line 1600. For example, the initial measurement value of the patient's TFC may include a TFC measurement value of 120 TFC units. In some examples, the TFC unit may be measured on a normalized scale from 0 to 200 TFC units. However, as shown in FIG. 16A, the plot is adjusted to focus on the range of 100 to 160 TFC units. In the first week, the TFC measurement value may increase to 130 TFC units. However, in the second week, the TFC measurement value may decrease to 125 TFC units. In the third week, the TFC measurement value may increase to 150 TFC units, and in the fourth week, the TFC measurement value may increase to 155 TFC units. Depending on the programming of the processing device, the processing device may trigger a second metric measurement value based on the change in the TFC measurement value. For example, the TFC measurement value may exceed a predetermined threshold (e.g., 150 TFC units), or a threshold for a predetermined period (e.g., the second week when the TFC units have been continuously increasing, or the third week to the fourth week when the TFC units have been increasing). These changes may trigger the processing device to monitor at least one additional metric. For example, as shown in FIG. 16A, in the fourth week, the processing device may similarly begin to measure the S3 vibration intensity indicated by line 1602.

[0233] As described above, the S3 vibration intensity can be measured on a normalized scale of S3 intensity units from 0 to 10, and an S3 intensity unit of 5.0 indicates a threshold where a patient may feel heart disease and / or may require additional treatment. Other normalized linear or non-linear scales may be used. For example, the scale may be in S3 intensity units from 0 to 1, or from 0 to 10, or from 0 to 100 S3 intensity units. For example, the non-linear scale may be a logarithmic scale. As shown in FIG. 16A, the initial reading shown can be adjusted to focus on the range of S3 intensity units from 3 to 9. At the 4th week, the patient's S3 vibration intensity is measured as 4.5 S3 intensity units. However, at the 5th week, the patient's S3 vibration intensity rises to 5.0 S3 intensity units, and by the 6th week, the patient's S3 vibration intensity rises to 6.0 S3 intensity units. During the same period, the patient's TFC measurement also continued to rise, to 155 TFC units at the 5th week and 165 TFC units at the 6th week.

[0234] In certain implementations, the processing device may perform trend analysis to determine the correlation coefficient between both the TFC measurement and the S3 vibration intensity. As shown in FIG. 16A, there may be an approximate linear relationship between the two metrics, and in such cases, the correlation coefficient may indicate a strong positive correlation between the two variables. Such a correlation may be interpreted by the processing device as indicating a specific cardiac adverse event characterized by a high correlation coefficient between the TFC measurement and the S3 vibration intensity. In certain implementations, a high correlation coefficient may further indicate a change in the patient's symptoms over a period of time, for example, 6 weeks as shown in FIG. 16A.

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

[0236] FIG. 16C shows a six-week trend analysis that includes the patient's overall grade score. As shown in FIG. 16C, the patient's TFC measurements over the first two weeks, shown as line 1620, can trend upward, which produces an overall increase in the patient's overall grade score, shown as line 1626. As described above, after a certain trend in the second week, additional monitoring can be triggered. In this example, at the second week, monitoring of both the S3 vibration intensity and the %EMAT can be initiated. As shown in FIG. 16C, the S3 vibration intensity is shown as line 1622 and the %EMAT is shown as line 1624. As further shown in FIG. 16C, each of the TFC measurements, S3 vibration intensity, and %EMAT continues to increase from the second week to the sixth week.

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

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

[0239] For example, at week 4, the patient's LVST can be measured at approximately 250 ms. However, at week 5, the patient's LVST rises to 290 ms, and by week 6, the patient's LVST has risen to 325 ms. During this same period, the patient's TFC measurements similarly continue to rise, e.g., to 160 TFC units at week 5 and to 165 TFC units at week 6. This increase in LVST can be utilized to confirm the interpretation that the accumulation of pleural effusion within the patient has worsened and that in such cases, an interventional treatment is recommended. Conversely, if the TFC measurement substantially drops from week 1 to the next week, e.g., shows a downward trend from high TFC units to low TFC units, the patient's LVST is similarly expected to drop over the same period. The drop in LVST can be utilized to confirm the interpretation that one or more interventional treatments for managing the pleural effusion appear to be improving the patient's symptoms.

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

[0241] FIG. 17 shows a sample process flow of the patient monitoring system described herein. For example, a series of sensors may be configured to detect 1705 the patient's vital signals. In certain implementations, an ECG sensor may be configured to detect one or more ECG signals of the patient, a vibration sensor may be configured to detect one or more bio-vibration signals of the patient, and an ultra-wideband radio frequency transceiver may be configured to direct radio frequency electromagnetic energy towards the patient with one or more antennas and receive, via one or more antennas, radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from a part of the patient such as the aorta or the thoracic cavity.

[0242] In certain implementations, one or more processors may be configured to process raw signals to determine a set of a patient's physiological parameters 1710. For example, as described herein, physiological parameters may include ECG metrics, biometric vibration metrics, radio frequency metrics, and / or combined physiological metrics. In some examples, physiological parameters may be collected over a particular previous period. For example, the 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 previous period corresponds to a period during which the patient's medical history is available to the patient.

[0243] One or more processors may further be configured to perform at least one of predictive analytics 1715 or trend analysis 1720 using the physiological parameters. In certain implementations, one or more processors may be configured to perform both predictive analytics 1715 and trend analysis 1720.

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

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

[0246] One or more processors may generate an output based on a clinically actionable event 1735. In certain implementations, clinically actionable events may include automated events that are triggered without user input, such as increasing the monitoring and / or analysis of one or more physiological signals. Similarly, clinically actionable events may include manual events that are triggered based on a user response to a generated output, and may include one or more instructions to perform one or more actions, such as an order to admit the patient to a hospital.

[0247] Various validations have been performed to analyze and verify the concepts and techniques described in this specification. For example, in heart failure analysis, validations have been performed to evaluate the values of the heart disease-based biovibration information described in this specification, as well as combinations of the heart disease-based biovibration information and one or more ECG metrics. In the validation, a patient population including patients with a heart ejection fraction of <35% and admitted with decompensated heart failure was enrolled in a prospective observational protocol. All patients were fitted with a WCD equipped with an accelerometer. The WCD had the ability to record biovibrations as well as measure ECG signals. Each patient was to wear the WCD in an outpatient setting. The patient population was monitored for heart failure events and emergency department visits for heart failure symptoms, and such information was collected for the patient population. Univariate and multivariate analyses were performed on the collected information to identify a model that optimally predicted the occurrence of readmission or emergency department visits in early heart failure.

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

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

[0250] Each patient in the population underwent a chest CT scan while lying supine to determine the initial fluid volume. After this, RF was read while lying supine from a wearable patch device placed at the midaxillary line on the left side. Using the reflected RF signal measured by the patch device and anthropometric data, an RF-based lung fluid model was constructed for each patient. The lung fluid was reported as a percentage of the lung air volume. Then, grading analysis techniques were utilized to compare the results and performance of the RF patch device with those of the chest CT scan.

[0251] As a result of the above verification, it was shown that all acute heart failure patients were measured to have a higher lung fluid volume than non-acute heart failure patients. Based on statistics, an RF patch design as well as a chest CT scan were performed to identify acute heart failure patients from non-acute heart failure patients. Sample data showing various determined statistical results from this verification can be referred to in Table 10 below. Table 10

Table 10

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

[0253] In an example, a patient may complain of chest pain when performing certain activities such as sitting in a reclining position or lying supine. The patient's physician may prescribe a wearable radio frequency sensing device to the patient, and the device is configured to measure the patient's TFC. The patient may wear the device over the course of several weeks. Over that period, the device may measure a steady increase in the fluid content within the patient's thoracic cavity. When returned to the physician, the physician may download the data recorded by the radio frequency sensing device into a trend analysis process. That process may detect a trend indicating that the patient's TFC is steadily increasing. The physician may want to obtain additional physiological information for the patient and may further prescribe a mobile cardiac monitoring device that includes a vibration sensor configured to measure body vibrations. The patient wears both the radio frequency sensing device and the mobile cardiac monitoring device for a period of time. When returned to the physician, the recorded information from both monitoring devices may be input into a trend analysis process. That process may confirm a trend indicating that the patient's TFC is increasing by analyzing information regarding the patient's S3 vibration intensity. That process may determine a correlation between the TFC increase and the patient's S3 vibration intensity and may provide an indication that the patient may be suffering from a heart disease such as congestive heart failure. That process may provide such an indication to the physician along with a recommended action to make a change to the patient's prescribed medications and the like.

[0254] In another example, a patient during hospitalization may wear at least one ECG sensor, at least one bio-vibration 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, in other examples, another similar machine learning technique described above). The artificial neural network can transform the input information to provide clinical symptom information of the patient. Such clinical symptom information can be further analyzed to determine the patient's current health status, whether the patient's discharge should be approved, and what risks, if any, there are for the patient to be readmitted within a specific period, for example, within 30 days. In some examples, even if the patient meets all the conditions necessary for discharge, the process may indicate that the patient has a high risk of being readmitted in the near future. In such an example, a physician or other similar caregiver may decide to keep the patient hospitalized for additional monitoring, change the patient's treatment plan, or otherwise change the treatment provided to the patient.

[0255] Even though the subject matter contained herein has been described in detail for purposes of illustration, such detail is solely for that purpose and the disclosure 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 disclosure contemplates that, to the extent possible, one or more features of any embodiment can be combined with one or more features of any other embodiment.

[0256] Other examples are within the scope of the description and spirit of the claims. Further, the specific functions described above can be implemented using software, hardware, firmware, hardwiring, or any combination thereof. The features implementing the functions can be physically located in various positions and can include distributing a portion of the functions to be implemented at various physical locations. Examples of embodiments of the present invention are shown as items below. [Item 1] A patient monitoring system, an ECG sensor connected to a patient and configured to detect one or more ECG signals of the patient, a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals of the patient, an ultra-wideband radio frequency transceiver circuit having one or more radio frequency antennas and connected to the patient, directing radio frequency electromagnetic energy to the chest cavity of the patient through the one or more radio frequency antennas, receiving through the one or more radio frequency antennas and generating radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from within the chest cavity an ultra-wideband radio frequency transceiver circuit configured as such; one or more processors, a) processing the one or more ECG signals, b) the one or more cardiac vibration signals, and c) the radio frequency information to generate a plurality of physiological parameters of the patient comprising one or more combined physiological parameters; performing at least one of predictive analysis and trend analysis of the plurality of physiological parameters comprising the one or more combined physiological parameters to determine the current clinical condition of the patient, wherein the trend analysis determines the existence of a substantial relationship of changes in the plurality of physiological parameters; comparing the current clinical condition of the patient with a clinically usable criterion determined in advance to determine one or more clinically usable events; and causing an output device to provide an output regarding the one or more clinically usable events one or more processors configured to perform the above; A patient monitoring system including the above. [Item 2] The patient monitoring system according to item 1, wherein the trend analysis has a correlation analysis. [Item 3] The patient monitoring system according to item 1, wherein at least one of the prediction analysis and the trend analysis is performed on physiological parameters collected over a previous period having one or more of at least 24 hours, at least 48 hours, at least one week, at least two weeks, at least one month, at least six weeks, at least two months, at least four months, at least six months, at least one year, and at least two years. [Item 4] The patient monitoring system according to item 1, wherein at least one of the prediction analysis and the trend analysis is performed on physiological parameters collected over a previous period corresponding to at least the available medical history of the patient. [Item 5] The one or more clinically usable events include at least one of an automatic event triggered without user input and a manual event triggered based on a user response to the output and having one or more instructions to perform one or more actions. The patient monitoring system according to item 1. [Item 6] The output regarding the one or more clinically usable events is based on the plurality of physiological parameters or one or more thresholds defined for the results of the at least one prediction analysis and the trend analysis and exceeds the one or more thresholds. The patient monitoring system according to any one of the preceding items 1 to 5. [Item 7] Performing the prediction analysis includes inputting the plurality of physiological parameters into an artificial neural network and determining the current clinical symptoms of the patient based on the output of the artificial neural network. The patient monitoring system according to any one of the preceding items 1 to 5. [Item 8] Performing the prediction analysis Inputting the plurality of physiological parameters into a deep learning process; Determining the current clinical symptoms of the patient based on the output of the deep learning process; The patient monitoring system according to any one of the preceding items 1 to 5, comprising: [Item 9] Performing the predictive analysis includes: Inputting the plurality of physiological parameters into a machine learning process; Determining the current clinical symptoms of the patient based on the output of the machine learning process; The patient monitoring system according to any one of the preceding items 1 to 5, comprising: [Item 10] The current clinical symptoms of the patient include a prediction score based on the output of the machine learning process, and the prediction score indicates the possibility of the occurrence of an adverse event. The patient monitoring system according to Item 9. [Item 11] The adverse event includes one or more of an arrhythmia event, a seizure event, a syncope event, and a hospitalization event. The patient monitoring system according to Item 10. [Item 12] Performing the trend analysis includes: determining whether at least one of the plurality of physiological parameters exceeds a threshold; correlating the at least one of the plurality of physiological parameters that exceeds the threshold with at least one additional physiological parameter selected from the plurality of physiological parameters to generate a correlation score; and determining the current clinical symptoms of the patient based on the correlation score. The patient monitoring system according to any one of the preceding items 1 to 5, comprising: [Item 13] The patient monitoring system according to Item 12, wherein the correlation score indicates a change in the patient's symptoms. [Item 14] The vibration sensor is further configured to sense one or more lung vibrations of the patient, and the one or more lung vibrations include at least one of bronchial vibrations, wheezing, crackles, whistling sounds, bubbling sounds, pleural friction rubs, squawks, glottal sounds, pharyngeal sounds, or other vibrations, the patient monitoring system of claim 1. [Item 15] The one or more ECG signals include at least one of heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, respiration, cardiac arrhythmia, QRS height, QRS width, change in size or shape of the morphology of the one or more ECG signals, cosine R-T, artificial pacing, QT interval, QT variability, T wave width, T wave alternans, T wave variability, and ST segment change, the patient monitoring system of claim 1. [Item 16] The one or more cardiac vibration signals include at least one of S1 vibration, S2 vibration, S3 vibration, S4 vibration, and heart murmur vibration, the patient monitoring system of claim 1. [Item 17] The radio frequency information includes a measurement of the liquid content in the thoracic cavity of the patient, the patient monitoring system of claim 1. [Item 18] The plurality of physiological parameters includes one or more of left ventricular systolic time (LVST), electromechanical activation time (EMAT), %LVST, and left ventricular end diastolic pressure (LVEDP), the patient monitoring system of claim 1. [Item 19] The one or more processors are incorporated into a heart monitoring device adapted to be worn by the patient, the patient monitoring system of claim 1. [Item 20] The one or more processors are incorporated into a remote processing device, the patient monitoring system of claim 1. [Item 21] The one or more processors are incorporated into a wearable defibrillator device adapted to be worn by the patient, the patient monitoring system of claim 1. [Item 22] A patient monitoring system, at least one vibration sensor configured to be coupled to a patient and detect one or more cardiac vibration signals, at least one ultra-wideband radio frequency transceiver coupled to the patient, directing radio frequency electromagnetic waves towards the lungs of the patient, detecting radio frequency information in response to the radio frequency electromagnetic waves passing through the lungs of the patient and being configured as at least one ultra-wideband radio frequency transceiver, one or more processors, processing the detected one or more cardiac vibration signals over a predetermined period to determine at least one cardiac vibration metric of the patient, processing the radio frequency information of the patient over a predetermined period to determine at least one lung fluid metric of the patient, determining an output regarding 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 causing the output to be provided to an output device and being configured as one or more processors, and a patient monitoring system including the same. [Item 23] wherein the one or more clinically actionable events include at least one of an automatic event triggered without user input, and a manual event triggered based on a user response to the output and comprising one or more instructions to perform one or more actions, for the patient monitoring system according to item 22. [Item 24] Determining the output includes performing a predictive analysis of the determined value or trend of the at least one cardiac vibration metric and the determined value or trend of the at least one lung fluid metric, for the patient monitoring system according to the preceding item 22 or 23. [Item 25] Performing the prediction analysis includes inputting the determination value or its trend of the at least one cardiac vibration metric and the determination value or its trend of the at least one pulmonary fluid metric into a machine learning process determining a prediction score based on the output of the machine learning process, wherein the prediction score indicates the likelihood of a harmful event occurring determining the output based on the prediction score The patient monitoring system according to item 24, comprising [Item 26] Determining the output includes performing trend analysis of changes in the at least one cardiac vibration metric and the at least one pulmonary fluid metric to determine the existence of a substantial relationship between changes in the at least one cardiac vibration metric and the at least one pulmonary fluid metric, as described in the preceding item 22 or 23, of the patient monitoring system [Item 27] Detecting the existence of a substantial relationship between changes in the at least one cardiac vibration metric and the at least one pulmonary fluid metric by performing the trend analysis of the changes includes performing a correlation analysis, as described in item 26, of the patient monitoring system [Item 28] Determining the output includes performing a correlation analysis, and the correlation analysis includes processing 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 correlating at least one of the plurality of physiological parameters exceeding a threshold with at least one additional physiological parameter selected from the plurality of physiological parameters to generate a correlation score, wherein the correlation score indicates a change in the patient's symptoms determining the output based on the correlation score The patient monitoring system according to the preceding item 22 or 23, comprising [Item 29] The patient monitoring system according to item 22, wherein the one or more cardiac vibration signals include at least one of S1 vibration, S2 vibration, S3 vibration, S4 vibration, ventricular wall movement, and heart noise vibration. [Item 30] The patient monitoring system according to item 22, wherein the radio frequency information includes a measurement value of the liquid content in the chest cavity of the patient. [Item 31] A patient monitoring system, an ECG sensor connected to the patient and configured to detect one or more ECG signals of the patient; a vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals of the patient; a ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and connected to the patient, directing radio frequency electromagnetic energy to the chest cavity of the patient by the one or more radio frequency antennas, generating radio frequency information corresponding to the reflected radio frequency electromagnetic energy reflected from the chest cavity of the patient and received via the one or more radio frequency antennas a ultra-wideband radio frequency transceiver circuit configured as such; one or more processors, processing 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, performing a trend analysis of the plurality of physiological parameters including the one or more combined physiological parameters to generate a trend result, updating the monitoring schedule of the patient based on the trend result, determining the current clinical symptoms of the patient based on the trend result, comparing the current clinical symptoms of the patient with a predetermined clinically usable criterion to determine one or more clinically usable events, Causing an output device to provide an output related to the one or more clinically usable events one or more processors configured to: A patient monitoring system comprising: [Item 32] The one or more processors are further configured to process the one or more ECG signals, the one or more heart vibration signals, and the radio frequency information according to the updated monitoring schedule to generate updated physiological parameters of the patient; perform a trend analysis of the updated physiological parameters including the one or more combined physiological parameters to generate an updated trend result; The patient monitoring system according to item 31, wherein the updated clinical condition of the patient is determined based on the updated trend result. [Item 33] The one or more clinically usable events include: an automatic event triggered without user input; and a manual event triggered based on a user response to the output and including one or more instructions to perform one or more actions. The patient monitoring system according to the preceding item 31 or 32, including at least one of the above. [Item 34] The one or more ECG signals include at least one of heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, respiration, arrhythmia, QRS height, QRS width, change in size or shape of the morphology of the one or more ECG signals, cosine R-T, artificial pacing, QT interval, QT variability, T wave width, T wave alternans, T wave variability, and ST segment change. The patient monitoring system according to item 31. [Item 35] The one or more heart vibration signals include at least one of S1 vibration, S2 vibration, S3 vibration, S4 vibration, and heart murmur vibration. The patient monitoring system according to item 31. [Item 36] The patient monitoring system according to item 31, wherein the radio frequency information includes a measurement value of the liquid content in the thoracic cavity of the patient. [Item 37] A patient monitoring system, comprising: An ECG sensor connected to the patient and configured to detect one or more ECG signals of the patient; A vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals of the patient; An ultra-wideband radio frequency transceiver circuit including one or more radio frequency antennas and disposed on at least one aorta of the patient, directing radio frequency electromagnetic energy from the one or more radio frequency antennas to at least a part of the patient, configured to receive, via the one or more radio frequency antennas, and generate radio frequency information corresponding to reflected radio frequency electromagnetic energy reflected from within at least a part of the patient; an ultra-wideband radio frequency transceiver circuit; One or more processors, processing 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; performing at least one of predictive analysis and trend analysis of the plurality of physiological parameters including the one or more combined physiological parameters to determine the current clinical condition of the patient; comparing the current clinical condition of the patient with a predetermined clinically usable criterion to determine one or more clinically usable events; One or more processors configured to provide an output related to one or more clinically usable events to an output device; and a patient monitoring system. [Item 38] The patient monitoring system according to item 37, wherein the at least one main artery includes at least one of a radial artery, a brachial artery, a main artery, and one or more pulmonary arteries. [Item 39] The patient monitoring system according to the preceding item 37 or 38, wherein 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.

Claims

1. 1. A patient monitoring system comprising: a plurality of electrocardiogram electrodes coupled to the patient and configured to detect electrocardiogram signals; at least one vibration sensor connected to the patient and configured to detect one or more cardiac vibration signals; at least one ultra-wideband radio frequency transceiver coupled to the patient, directing radio frequency electromagnetic waves at the patient's lungs; Detecting radio frequency information in response to the radio frequency electromagnetic waves passing through the lungs of the patient. At least one ultra wideband radio frequency transceiver configured to One or more processors, processing the detected electrocardiogram signal and the detected one or more cardiac vibration signals to determine an electromechanical activation time parameter of the patient; processing the radio frequency information to determine thoracic fluid parameters of the patient; monitoring the thoracic fluid parameter of the patient over a first period of time; responsive to detecting a trend in the thoracic fluid parameter of the patient during the first time period, monitoring the thoracic fluid parameter of the patient and the electromechanical activation time parameter over a second time period; determining an overall rating score for the patient based on the monitoring during the second period of time; determining an output related to one or more clinically actionable events in response to the overall grade score exceeding a threshold; Causes an output device to perform said output. one or more processors configured to Including, Determining an overall grade score for the patient includes: determining a score for each of the thoracic fluid parameters of the patient and the electromechanical activation time parameters of the patient; and determining the overall rating score for the patient based on a sum of the scores for each of the parameters.

4. A patient monitoring system comprising:

2. Determining a score for each of the thoracic fluid parameters of the patient and the electromechanical activation time parameters of the patient includes: assigning each category to each parameter; each of the categories having a plurality of predetermined value ranges; The patient monitoring system of claim 1 , wherein each of the plurality of predetermined value ranges has a predetermined score.

3. an automatic event, where the one or more clinically actionable events are triggered without user input; a manual event triggered based on a user response to the output and comprising one or more instructions to perform one or more actions; 3. The patient monitoring system of claim 1, further comprising at least one of:

4. 4. The patient monitoring system of claim 1, wherein the one or more cardiac vibration signals include at least one of S1 vibrations, S2 vibrations, S3 vibrations, S4 vibrations, ventricular wall motion, and heart murmur vibrations.

5. 5. The patient monitoring system of claim 1, wherein the radio frequency information includes a measurement of the patient's lung fluid content.

6. 6. The patient monitoring system of claim 1, wherein the electrocardiogram signal includes at least one of heart rate, heart rate variability, PVC load or PVC count, atrial fibrillation load, breathing, heart rate turbulence, QRS height, QRS width, changes in size or shape of the electrocardiogram signal morphology, cosine R-T, artificial pacing, QT interval, QT variation, T wave width, T wave alternans, T wave variation, and ST segment changes.

Images