Systems and methods for remote patient screening and triage

Abstract

A system for short-term screening and triage of subjects includes a smart device owned by the subject and an application on the smart device, the application being programmed to provide the subject with instructions to begin the screening process, the application being programmed to have multiple screening processes and record sensor data obtained from sensors located in the smart device.

Description

Technical Field

[0001] This disclosure relates, as a non-limiting example, to remote monitoring of biosignals in subjects, including cardiac and respiratory monitoring. More specifically, this disclosure relates to systems and methods for short-term and long-term patient screening, citing symptoms of disease, bacterial or viral infection, cardiac-related complications, or respiratory-related complications. This disclosure also relates to the use of such systems for patient triage to determine risk levels and priorities for further evaluation.

[0002] background

[0003] Traditionally, monitoring, diagnosing, and assessing patients who may develop symptoms of infection or cardiopulmonary complications requires visits to an office or clinic. This process carries the risk of increased exposure to the public and clinical teams and can overwhelm hospital systems during crises or pandemics. Furthermore, soldiers on the battlefield may not have caregivers nearby. Currently, there are far too many patients requiring monitoring given the existing healthcare infrastructure, yet no high-capacity, accurate remote monitoring tools are available that can be easily used or deployed without physical contact with caregivers. Unlike persistent conditions, sudden or intermittent paroxysmal conditions require a home screening solution that can be used immediately and continuously.

[0004] Overview

[0005] This paper discloses a system that uses optical, audio, radio, and sensors (such as accelerometers, gyroscopes, pressure sensors, load sensors, weight sensors, force sensors, motion sensors, or vibration sensors) to capture mechanical vibrations of the body and physiological movements of the heart and lungs, and converts them into biosignal information that can be used to screen for and identify disease conditions. The systems and methods presented herein can be used by subjects experiencing symptoms of complications or conditions, or under the guidance of a physician in telemedicine applications.

[0006] These systems are used for both short-term and long-term screening. Short-term screening systems may include mobile phones, tablets, wearable watches, or any patient-accessible accessory with one or more sensors capable of capturing mechanical vibrations of the body, heart, and lungs, such as accelerometers, gyroscopes, pressure sensors, load sensors, weight sensors, force sensors, motion sensors, or vibration sensors. Such devices may be placed near sources in the body's physiological systems, such as the heart and lungs, including but not limited to placement on the chest, abdomen, sides, back, or similar areas. Long-term screening systems may include sensors that can be mounted in or under the legs of a bed and capture mechanical vibrations of the body, heart, and lungs (such as accelerometers, gyroscopes, pressure sensors, load sensors, weight sensors, force sensors, motion sensors, or vibration sensors). Short-term screening is designed for testing of limited duration (seconds to minutes), while long-term screening can be used continuously for any duration (seconds, minutes, days, months, etc.). Short-term and long-term screening systems may operate independently or synchronously and collaboratively to exchange data, such as historical trend data or baseline data of the subjects.

[0007] This system can be used as a patient triage tool to help assess the urgency of situations. The system can include a smartphone app for screening and assessing patient conditions.

[0008] Various aspects of this disclosure may be implemented in one or more of the embodiments described below.

[0009] 1) A system for at least short-term screening and triage of subjects, said system comprising:

[0010] The smart device, which is owned by the subject; and

[0011] An application is provided on the smart device, and the application and the smart device are configured to:

[0012] The application provides instructions to the subject to begin the screening process, and the application is programmed with multiple screening procedures.

[0013] Recording short-term sensor data obtained from one or more sensors located in the smart device; and

[0014] The short-term sensor data, trend data, and general population data were compared for use in screening and triage of subjects.

[0015] 2) According to the system described in 1), wherein the application and the smart device are further configured to:

[0016] Analyze the short-term sensor data;

[0017] Obtain trend data from long-term screening;

[0018] Based on the analyzed short-term sensor data and trend data, the status is identified; and

[0019] In response to the identified situation, perform an action.

[0020] 3) The system according to 2), wherein the action includes one or more of the following:

[0021] Generate audible tones for emergency situations;

[0022] In response to a crisis, a message is sent to the cloud entity;

[0023] The short-term sensor data and the identified conditions are sent to the entity rather than the subject.

[0024] 4) The system according to 2), wherein the application and the smart device are further configured to:

[0025] In response to the identified condition, a long-term screening is initiated to generate the trend data, wherein the long-term screening system includes one or more sensors mounted near the base where the subject is located, each sensor being configured to capture mechanical vibrations from the subject's movements relative to the base, the mechanical vibrations indicating the subject's biosignal information.

[0026] 5) The system according to 4), wherein the long-term screening system is further configured to access the short-term sensor data and the identified conditions.

[0027] 6) The system according to 2), wherein the application and the smart device are further configured to:

[0028] In response to the identified condition, further short-term screening is initiated.

[0029] 7) The system according to 2), wherein the application and the smart device are further configured to:

[0030] Analyze the subjects' cardiac information;

[0031] Based on the cardiac information, determine the heart rhythm and rate information;

[0032] The subject's health status is determined based on the heart rhythm and rate information; and

[0033] Identify the onset or progression of a heart condition.

[0034] 8) The system according to 2), wherein the application and the smart device are further configured to:

[0035] Analyze the subjects' respiratory information;

[0036] The respiratory rhythm and rate information are determined based on the respiratory information;

[0037] The subject's health status is determined based on the respiratory rhythm and rate information; and

[0038] Identify the onset or progression of respiratory conditions.

[0039] 9) The system according to 2), wherein the application and the smart device are further configured to:

[0040] Analyze the cough information of the subjects;

[0041] The cough rhythm and rate information are determined based on the cough information;

[0042] The subject's health status is determined based on the cough rhythm and rate information; and

[0043] Identify the onset or progression of cough or respiratory flow.

[0044] 10) The system according to 2), wherein the application and the smart device are further configured to determine the severity or progression of the identified situation.

[0045] 11) The system according to 1), wherein the smart device is one of a mobile phone, a tablet computer, a smartwatch or an accessory, and one of the mobile phone, the tablet computer, the smartwatch or the accessory has one or more of an accelerometer, a gyroscope, a pressure sensor, a load sensor, a weight sensor, a force sensor, a motion sensor, a microphone or a vibration sensor.

[0046] 12) The system according to 1), wherein the screening process includes instructions to move the subject to an appropriate location, stay in the location for a limited time, and place the smart device at one or more locations on the subject's body.

[0047] 13) A system for screening and triaging subjects, the system comprising:

[0048] A smart device equipped with an application, wherein the application and the smart device are configured together to:

[0049] Instruct the subject to begin the screening process;

[0050] Record short-term sensor data obtained from at least one sensor located in the smart device; and

[0051] Identify the situation from the short-term sensor data and the acquired trend data;

[0052] A substrate, on which sensors are deployed, the sensors being configured to capture mechanical vibrations from the subject's movements relative to the substrate, the mechanical vibrations indicating the subject's biosignal information; and

[0053] A processor, connected to the sensor, is configured to:

[0054] In response to a condition identified by the smart device, sensor data is captured from the sensor;

[0055] Based on sensor data captured from the sensors and short-term sensor data obtained, the status is identified; and

[0056] Based on the identified situation, perform the action.

[0057] 14) The system according to 13), wherein the application and the smart device are further configured to:

[0058] Analyze the short-term sensor data;

[0059] Obtain trend data from the memory associated with the processor; and

[0060] In response to the condition identified by the smart device, an action is performed.

[0061] 15) The system according to 14), wherein the application and the smart device are further configured to:

[0062] The short-term sensor data is transmitted to the entity for analysis against trend data;

[0063] Obtain the analysis results; and

[0064] In response to the state identified by the entity, perform an action.

[0065] 16) The system according to 15), wherein the action in response to a condition recognized by the smart device or the action in response to a condition recognized by the entity includes one or more of the following:

[0066] Generate audible tones for emergency situations;

[0067] In response to a crisis, a message is sent to the cloud entity;

[0068] The short-term sensor data and the identified conditions are sent to the entity rather than the subject.

[0069] 17) The system according to 13), wherein the application and the smart device are further configured to:

[0070] In response to the condition identified by the smart device, further smart device screening is initiated.

[0071] 18) The system according to 13), wherein the application and the smart device are further configured to perform at least one of the following:

[0072] Analyze the subjects' cardiac information;

[0073] Based on the cardiac information, determine the heart rhythm and rate information;

[0074] The subject's health status is determined based on the heart rhythm and rate information; and

[0075] To identify the onset or progression of a heart condition; or

[0076] Analyze the subjects' respiratory information;

[0077] The respiratory rhythm and rate information are determined based on the respiratory information;

[0078] The subject's health status is determined based on the respiratory rhythm and rate information; and

[0079] Identify the onset or progression of a respiratory condition; or

[0080] Analyze the cough information of the subjects;

[0081] The cough rhythm and rate information are determined based on the cough information;

[0082] The subject's health status is determined based on the cough rhythm and rate information; and

[0083] Identify the onset or progression of cough or respiratory flow.

[0084] 19) A method for at least short-term screening and triage of subjects, the method comprising:

[0085] Subjects are instructed to initiate the screening process via smart devices;

[0086] As the subject follows the screening process, short-term sensor data from the subject is recorded via sensors on the smart device;

[0087] Analyze the short-term sensor data;

[0088] Obtain trend data from long-term screening equipment;

[0089] Identifying subject conditions based on the analyzed short-term sensor data and the aforementioned trend data; and

[0090] In response to the identified situation, perform an action.

[0091] 20) The method according to 19) further includes:

[0092] In response to the identified condition, the capture of sensor data at the long-term screening device is initiated.

[0093] 21) The method according to 20) further includes:

[0094] Analyze sensor data from long-term screening equipment;

[0095] Obtain data from smart devices;

[0096] The subject's condition is identified based on the analyzed long-term screening device sensor data, general population data, and the aforementioned short-term sensor data; and

[0097] It takes action in response to conditions identified by long-term screening equipment.

[0098] 22) The method according to 21) further includes:

[0099] Short-term sensor data, conditions identified by smart devices, and conditions identified by long-term screening devices are sent to at least the physical entity rather than the subject.

[0100] 23) The method according to 19) further includes:

[0101] In response to the identified condition, an additional smart device screening is initiated. Brief description of the attached diagram

[0103] This disclosure is best understood from the following detailed description when read in conjunction with the accompanying drawings. It is emphasized that, in accordance with common practice, the various features in the drawings are not drawn to scale. Instead, for clarity, the dimensions of the various features have been arbitrarily enlarged or reduced.

[0104] Figure 1A-1D An example system for short-term screening and triage using smart devices for subjects, as disclosed herein, is shown.

[0105] Figure 1E It is a collection of data streams recorded during short-term screenings using the subjects' smart devices, as disclosed in this article.

[0106] Figure 2A This is a flowchart of another example system for short-term screening and triage, as disclosed in this article.

[0107] Figure 2B This is a flowchart of an example system for short-term and long-term screening and triage, as disclosed in this article.

[0108] Figure 2CIt is a system architecture used to implement short-term and long-term screening and triage.

[0109] Figure 3 This is a flowchart of an example process for collecting sensor data.

[0110] Figure 4 This is a flowchart of an example process for short-term analysis of sensor data.

[0111] Figure 5 This is a flowchart of an example procedure for short-term cardiac analysis.

[0112] Figure 6 This is a flowchart of an example procedure for short-term respiratory analysis.

[0113] Figure 7 This is a flowchart of an example procedure used for short-term cough analysis.

[0114] Figure 8 This is a flowchart of an example process for short-term screening and triage based on a machine learning classifier.

[0115] Detailed description

[0116] Methods for developing remote screening processes and triaging subjects' health status using sensor data from such systems are disclosed. In implementations, the system can analyze a subject's cardiac information and determine heart rhythm, morphology, and rate information. This heart rhythm, morphology, and rate information can be used to identify the onset or worsening of cardiac conditions such as atrial fibrillation, atrial flutter, ventricular fibrillation, ventricular flutter, bundle branch block, valvular stenosis, myocardial ischemia, and supraventricular tachycardia. In implementations, the system can analyze a subject's respiratory information and determine respiratory rhythm and rate information. This respiratory rhythm and rate information can be used to identify the onset or worsening of respiratory conditions such as tachypnea, apnea, or hypopnea. In implementations, the system can analyze a subject's cough information and determine cough rhythm and rate information. This cough rhythm and rate information can be used to identify the onset or worsening of cough conditions or respiratory flow (such as wheezing, rales, snoring, and rhonchi). The system can determine the severity of the condition and / or changes and trends in the condition. This system can generate remote screening reports. It can collect data, and the generated reports can be stored, sent to doctors for review, or analyzed using AI technology.

[0117] In practice, screening systems can be used to monitor the body's response to bacterial or viral infections. Specifically, sensor data can be used to monitor symptoms that may be directly or indirectly related to elevated body temperature. These symptoms can include changes in respiratory flow and depth, respiratory rate, heart rate, heart rate variability, movement and agitation, weight, and fluid retention. The system can also create a baseline for patients and continuously track and detect these changes over time, helping them become aware of their body's immune system response and enabling them or caregivers to monitor their condition.

[0118] In implementation, the screening system can be used in conjunction with a ventilator to remotely monitor its effectiveness. Furthermore, the system can be used as a data relay along with other sensors to relay local data from pulse oximeters, thermometers, blood pressure monitors, or other sensors to the cloud, enabling remote monitoring of these additional sensors to enhance screening.

[0119] In its implementation, the system will include two-way audio, text, and video communication with patients.

[0120] In practice, the screening system can also be used to screen cardiovascular and autonomic indices. For example, the system can be used for home stress testing, where sensor data can be used to monitor heart rate variability to quantify dynamic autonomic regulation or heart rate recovery.

[0121] In its implementation, the system can be used to create events based on life-based analytics. These events could be audible tones for critical situations or messages sent to the cloud for critical situations. The system also enables data convergence between short-term and long-term monitoring systems, allowing, for example, one system to establish a baseline using historical data collected by another system, or to use this information to determine disease progression or condition deterioration.

[0122] In implementation, additional bed-based sensor data can be combined to remove or cancel common-mode or other noise sources. Mobile data acquisition sensors can be used in conjunction with other monitoring systems with fixed locations, allowing for the combination of data from different monitoring sources to increase overall monitoring coverage as someone moves.

[0123] Figures 1A-1D An example system for short-term screening and triage using smart devices for test subjects is shown. Figure 1AThis is a flowchart of an example method 100 for using a smart device on a subject to employ a screening and triage system. In implementation, the smart device may include a mobile phone, tablet, wearable watch, or any accessory available to the subject, having one or more sensors capable of capturing mechanical vibrations of the body, heart, and lungs, such as accelerometers, gyroscopes, pressure sensors, load sensors, weight sensors, force sensors, motion sensors, or vibration sensors. These figures illustrate a mobile phone as a non-limiting example.

[0124] Screening can be triggered by the onset of symptoms of an illness or condition (e.g., when the subject feels unwell) or initiated upon request from a physician (101). The subject will receive a screening instruction (102). In implementation, this can be given by a physician. In implementation, the instruction can be provided by an app installed on a smartphone or other mobile device. The instruction is condition-specific; therefore, a screening process for an infection may differ from a screening process for a cardiac condition. Figures 1B-1D Here is an example of a screening instruction (103), in which the app instructs the subject to perform a screening procedure. In the implementation, the app may instruct the subject to lie on a bed and remain still for a given time (a counter may be used to display the time or play a countdown tone), such as Figure 1B As shown. In its implementation, the app can instruct the subject to place the phone at different locations on his / her chest, such as... Figure 1C As shown. In its implementation, the app can instruct the subject to lie on their side, as... Figure 1D As shown. In the implementation, other placements are possible, such as on the back, stomach, abdomen, etc. The app records sensor data, analyzes the sensor data (104), and generates a health report (105). In the implementation, the report may include physiological measurements such as heart rate, respiratory rate, heart rate variability, etc. In the implementation, the report may also include a list of identified or suspected problems, as well as the urgency level (severity level). In the implementation, the app may send the data to a doctor or caregiver, or may suggest subsequent testing using the same or a different system.

[0125] Figure 1E This is a graph of the data stream recorded during a short-term screening using the subject's smart device. Figure 1E This shows an example data stream when the subject was lying in bed, with his smartphone placed on his chest (as shown). Figure 1B(As shown), and the smartwatch is worn on his wrist. The (X, Y, Z) data stream from the phone's accelerometer is plotted in the top panel. The (X, Y, Z) data stream from the watch's accelerometer is plotted in the middle panel. The (X, Y, Z) data stream from the phone's gyroscope is plotted in the bottom panel. The phone's accelerometer data captures heart and respiratory activity. In this example, respiratory signals are strongly seen in the X and Y components, while heart activity is strongest in the Z direction. The watch's accelerometer data does not capture respiratory signals. The watch only captures heart activity. The gyroscope data captures both respiratory and heart activity. The effect of breath-holding is visible in the data streams recording breathing (phone accelerometer and gyroscope). Coughing episodes are visible in all recorded data streams.

[0126] Figure 2A This is a flowchart illustrating an example of a method 200 for short-term screening and triage using a smart device for a subject. In this implementation, the smart device may include a mobile phone, tablet, wearable watch, or any accessory available to the patient, having one or more sensors capable of capturing mechanical vibrations of the body, heart, and lungs, such as accelerometers, gyroscopes, pressure sensors, load sensors, weight sensors, force sensors, motion sensors, or vibration sensors.

[0127] Screening can be triggered by the onset of symptoms of a disease or condition (e.g., when the subject feels unwell) or initiated upon request from a physician (201). After screening begins, sensor data is acquired from the sensors (202). The sensor data is analyzed (203). The analyzed metrics are used to identify the subject's condition (204). In implementation, to quantify the body's response to bacterial or viral infection, changes in respiratory flow and depth, respiratory rate, heart rate, heart rate variability, movement and agitation, weight, and fluid retention are analyzed. Values ​​outside the normal range can define an abnormal condition, or, if the system has access to the patient's baseline, a sudden change compared to the baseline can be detected as an abnormal condition. In implementation, the normal range or abnormal condition can be relative to data representing the general population. Once the condition is identified, it is determined whether immediate action is required (208). Immediate action is taken if necessary (209). In implementation, immediate action could be notification to the patient, notification to the patient's physician, a call to a health center, etc. If immediate action is not required, it is determined whether follow-up testing is needed to confirm the results or provide new insights (210). If follow-up is required, additional or new sensor data is collected, and the process is restarted. Otherwise, the screening process is terminated (211). In the implementation, sensor data, analyzed data, and identified data can be stored locally in a local database 206 or a cloud database 207 for future access (205).

[0128] Figure 2B Example methods 220 for short-term and long-term screening and triage are shown. Short-term screening may use the subject's smart device. In implementation, the smart device may include a mobile phone, tablet, wearable watch, or any accessory available to the patient, having one or more sensors capable of capturing mechanical vibrations of the body, heart, and lungs, such as accelerometers, gyroscopes, pressure sensors, load sensors, weight sensors, force sensors, motion sensors, or vibration sensors. Long-term screening may use sensors that can be mounted in or under the legs of a bed (an example of a base on which the subject may reside), which can capture mechanical vibrations of the body, heart, and lungs (such as accelerometers, gyroscopes, pressure sensors, load sensors, weight sensors, force sensors, motion sensors, or vibration sensors). If short-term screening determines that long-term screening is required (229), the system may recommend adding a long-term screening system. Long-term screening may be added for enhanced continuous biosignal tracking.

[0129] The data exchange process 231 enables data exchange between short-term and long-term screening, where trend data (i.e., baseline and historical data of the subjects) can be accessed by either process. The data exchange process 231 also enables long-term screening to access short-term screening sensor data to be synchronized and added to the data stream set for enhanced monitoring. In implementation, data from acquired sensor data 222, acquired sensor data 232, stored data 226 (including local and cloud-based storage), and stored data 236 (including local and cloud-based storage) can be input into the data exchange process 231. In implementation, the data exchange process 231 outputs data to acquire trend data 224 and acquired trend data 234. That is, both initial and processed short-term and long-term data can be exchanged between short-term and long-term screening.

[0130] Figure 2CThis describes system 250 and its architecture for implementing short-term and long-term screening and triage. System 250 includes one or more devices 260 connected to or communicating with computing platform 270 (collectively, "connected to" computing platform 270). In an implementation, machine learning training platform 280 may be connected to computing platform 270. In an implementation, a user can access data via connected device 290, which can receive data from computing platform 270 or device 260. The connection between one or more devices 260, computing platform 270, machine learning training platform 280, and connected device 290 can be wired, wireless, optical, or a combination thereof. System 250 is illustrative and may include additional, fewer, or different devices, entities, etc., which may be similarly or differently architected without departing from the scope of this specification and claims. Furthermore, the illustrated devices may perform other functions without departing from the scope of this specification and claims.

[0131] In implementation, system 250, sensors, and data processing may be as described, for example, in U.S. Patent Application No. 16 / 777,385, filed January 30, 2020; U.S. Patent Application No. 16 / 595,848, filed October 8, 2019; and U.S. Provisional Patent Application No. 62 / 804,623, filed February 12, 2019 (collectively, the “Applications”), the entire disclosures of which are incorporated herein by reference.

[0132] In implementation, device 260 may include one or more sensors 261, a controller 262, a database 263, and a communication interface 264. In implementation, device 260 may include a classifier 265 for applicable and suitable machine learning techniques as described herein. One or more sensors 261 may detect and capture sensor data related to vibration, pressure, force, weight, presence, and motion in relation to the subject.

[0133] In its implementation, controller 262 can provide information about the topic described in this article. Figure 1A , Figure 2A , Figure 2B and Figures 4-8 The described processes and algorithms are applied to sensor data to determine short-term and long-term screening biosignal information and data as described in this paper. In the implementation, classifier 265 can classify the information in this paper regarding… Figure 1A , Figure 2A , Figure 2B and Figures 4-8The described processes and algorithms are applied to sensor data to determine short-term and long-term screening biosignal information and data. In the implementation, classifier 265 may be implemented by controller 262. In the implementation, the captured sensor data, as well as short-term and long-term screening biosignal information and data, may be stored in database 263. In the implementation, the captured sensor data, as well as short-term and long-term screening biosignal information and data, may be transmitted or sent to computing platform 270 via communication interface 264 for processing, storage, and / or combinations thereof. Communication interface 264 may be any interface and may use any communication protocol to communicate or transmit data between the source and destination endpoints. In the implementation, device 260 may be any platform or structure that collects data from subjects using one or more sensors 261 for use by controller 262 and / or computing platform 270 as described herein. Device 260 and its elements may include other elements that may be desired or necessary for implementing the devices, systems, and methods described herein. However, since such elements and steps are well known in the art, and since they do not contribute to a better understanding of the disclosed embodiments, a discussion of such elements and steps may not be provided herein.

[0134] In implementation, computing platform 270 may include processor 271, database 272, and communication interface 273. In implementation, computing platform 270 may include a classifier 274 for applicable and suitable machine learning techniques as described herein. Processor 271 may acquire sensor data from sensor 261 or controller 262, and may process data related to the machine learning techniques described herein. Figure 1A , Figure 2A , Figure 2B and Figures 4-8 The described processes and algorithms are applied to sensor data to determine short-term and long-term screening biosignal information and data as described herein. In the implementation, processor 271 can obtain short-term and long-term screening biosignal information and data as described herein from controller 262 for storage in database 272 for time analysis and other types of analysis. In the implementation, classifier 274 can classify the information and data regarding short-term and long-term screening biosignals as described herein. Figure 1A , Figure 2A , Figure 2B and Figures 4-8The described processes and algorithms are applied to sensor data to determine short-term and long-term screening biosignal information and data as described herein. A classifier 274 can be applied to the sensor data to determine short-term and long-term screening biosignal information and data as described herein via machine learning. In an implementation, classifier 274 can be implemented by processor 271. In an implementation, the captured sensor data, as well as the short-term and long-term screening biosignal information and data, can be stored in database 272. Communication interface 273 can be any interface and can use any communication protocol to communicate or transfer data between the source and destination endpoints. In an implementation, computing platform 270 can be a cloud-based platform. In an implementation, processor 271 can be a cloud-based computer or an off-site controller. Computing platform 270 and its components may include other components that may be desired or necessary for implementing the devices, systems, and methods described herein. However, because such components and steps are well known in the art and because they do not contribute to a better understanding of the disclosed embodiments, a discussion of such components and steps may not be provided herein.

[0135] In the implementation, the machine learning training platform 280 can access and process sensor data to train and generate classifiers. The classifiers can be transmitted or sent to classifier 265 or classifier 274.

[0136] exist Figure 2B In the process, sensor data is obtained from the sensor (232). In the implementation, the sensor data can be analyzed, for example, as shown in Applications (233). Long-term processing obtains instantaneous or near-instantaneous data from short-term processing via exchange data processing 231 (234). The analyzed data and the obtained data are used to identify conditions relevant to the subject (235). The identified conditions and data are stored in local memory or cloud-based memory (236). As described herein, the identified conditions and data are also input into exchange data processing 231. It is determined whether the identified condition requires immediate action (237). If not, nominal long-term processing continues. If immediate action is required, a response action is performed (238).

[0137] exist Figure 2BIn this method, the process begins at step 221, where sensor data 222 is obtained from the sensor. In implementation, the sensor data can be analyzed (223), for example, similar to that shown in Applications. Short-term processing obtains trend data from long-term processing via exchange data processing 231 (224). The analyzed and obtained data are used to identify conditions relevant to the subject (225). The identified conditions and data are stored in local memory or cloud-based memory (226). As described herein, the identified conditions and data are also input into exchange data processing 231. It is determined whether the identified condition requires immediate action (227). If immediate action is required, a response action is performed (228). If not, it is determined whether long-term processing is required (229). If so, long-term processing is performed. If long-term processing is not required, it is determined whether short-term processing is required (230). If short-term processing is not required, the current short-term processing is terminated. If so, data is obtained and another short-term processing is performed.

[0138] Figure 3 This is a processing pipeline 300 for acquiring sensor data (such as, but not limited to, accelerometer data, gyroscope data, pressure, load, weight, force, motion, or vibration). Analog sensor data stream 302 is received from sensor 301. Digitizer 303 digitizes the analog sensor data stream into digital sensor data stream 304. Framing unit 305 generates digital sensor data frames 306 based on the digital sensor data stream 304, which includes all digital sensor data stream values ​​within a fixed or adaptive time window. Figure 3 The processing pipeline 300 shown is illustrative and may include... Figure 3 The blocks or modules shown may include any, all, none, or a combination thereof. Figure 3 The processing order shown is illustrative and may vary without departing from the scope of this specification or the claims.

[0139] Figure 4A preprocessing pipeline 400 is used to process sensor data. The preprocessing pipeline 400 processes digital force sensor data frames 401. A noise reduction unit 402 removes or attenuates noise sources that may have the same or different levels of impact on each sensor. The noise reduction unit 402 can use various techniques, including but not limited to subtraction, combination of input data frames, adaptive filtering, wavelet transform, independent component analysis, principal component analysis, and / or other linear or nonlinear transforms. A signal enhancement unit 403 can improve the signal-to-noise ratio of the input data. The signal enhancement unit 403 can be implemented as a linear or nonlinear combination of input data frames. For example, the signal enhancement unit 403 can combine signal deltas to increase signal strength for higher resolution algorithm analysis. Subsampling units 404, 405, and 406 sample the digitally enhanced sensor data and may include downsampling, upsampling, or resampling. Subsampling can be implemented as multi-level or multi-stage sampling, and the same or different sampling rates can be used for cardiac analysis 407, respiratory analysis 408, and cough analysis 409. Figure 4 The processing order shown is illustrative and may vary without departing from the scope of this specification or the claims.

[0140] Figure 5 This is an example procedure 500 for performing cardiac analysis 407 using preprocessed and subsampled data 501. Filtering is used to remove unwanted components from the input sensor data or to preserve content useful for cardiac processing (502). In implementation, filtering can use an infinite impulse response (IIR) filter, a finite impulse response (FIR) filter, or a combination of both. The filter can be low-pass, high-pass, band-pass, band-stop, notch, or a combination thereof. In implementation, filtering can include sources from other sensors to remove common-mode or other noise, and adaptive filtering techniques can be used to remove unwanted signals. The filtered sensor data is transformed to enhance the cardiac components by modeling the input signal as a set of waveforms of a specific form (sine waves for Fourier transform, mother wavelets for wavelet transform, and / or periodic basis functions for periodic transform) (503). In implementation, this processing can be Fourier transform, wavelet transform, cosine transform, or mathematical operations (such as root mean square, absolute, moving average, moving median, etc.).

[0141] Envelope detection is performed on the transformed sensor data, taking a relatively high-frequency amplitude-modulated signal as input, and providing an output 530 that is equivalent to the input data profile described by connecting all local peaks in that signal. In implementation, envelope detection can use a low-pass filter, Hilbert transform, or other envelope detection methods. Peak detection is performed to find the local maxima and minima of the input signal 540. In implementation, peak detection can return all peaks and valleys or only the most predominant peaks and valleys.

[0142] Correlation analysis is performed using linear and nonlinear methods to measure the strength of the relationship between different segments of the input signal (504). Correlation analysis and peak locations can be used to identify individual beats in the input signal (505). The identified individual beats are enhanced (506). In implementation, this may include applying windows, factors, or transforms to enhance specific characteristics of the signal. Time-domain, frequency-domain, or time-frequency-domain analysis can be performed to determine the heart rate using the enhanced individual beats (507). Time-domain, frequency-domain, or time-frequency-domain analysis can be performed to determine a measure of heart rate variability using the enhanced individual beats (508). In implementation, the measure of heart rate variability may include SDNN, RMSSD, PNN50, LF, HF, and the LF / HF exponent. Time-domain, frequency-domain, or time-frequency-domain analysis can be performed to determine the heartbeat components (509). For cardiac signals, the beat components can be P, Q, R, S, and T waveforms, or atrial / ventricular depolarization and repolarization. Irregular rates or rhythms can be detected in cardiac data using HR, HRV, beat component, and subject trend data 510 (i.e., baseline and historical data).

[0143] Figure 5 The processing order shown is illustrative and may vary without departing from the scope of this specification or the claims.

[0144] Figure 6This is an example procedure for performing respiratory analysis 408 using preprocessed and subsampled data 601. Filtering is used to remove unwanted components from the input sensor data or to preserve content useful for respiratory processing (602). In implementation, the filter can use IIR, FIR, or a combination thereof. In implementation, the filter can be low-pass, high-pass, band-pass, band-stop, notch, or a combination thereof. In implementation, the filter can include sources from other sensors to remove common-mode or other noise, and adaptive filtering techniques can be used to remove unwanted signals. The filtered data is transformed to enhance the respiratory components by modeling the input signal as a set of waveforms of a specific form (sine waves for Fourier transform, mother wavelets for wavelet transform, periodic basis functions for periodic transform) (603). The transform can be Fourier transform, wavelet transform, cosine transform, or mathematical operations (such as root mean square, absolute, moving average, moving median, etc.). Peak detection is performed to find local maxima and minima of the input signal (605). In implementation, peak detection can return all peaks and valleys or only the most significant peaks and valleys.

[0145] Correlation analysis uses linear and nonlinear methods to measure the strength of the relationship between different segments of the input signal (604). Correlation analysis and peak locations can be used to identify individual breaths in the input signal (606). The identified individual breaths are then enhanced (607). In implementation, this may include applying windows, factors, or transformations to enhance specific characteristics of the signal.

[0146] Respiratory rate can be determined using enhanced individual respiration using time-domain, frequency-domain, or time-frequency-domain analysis (608). A measure of respiratory rate variability can be determined using enhanced individual respiration using time-domain, frequency-domain, or time-frequency-domain analysis (609). In implementation, respiratory rate variability measures may include DNN, RMSSD, PNN50, LF, HF, and the LF / HF index. Respiratory components can be determined using time-domain, frequency-domain, or time-frequency-domain analysis (610). For a respiratory signal, respiratory components can be inhalation (inspiration) and exhalation (expiration). Irregular rates or rhythms can be identified in respiratory data using RR, RRV, respiratory components, and subject trend data 611 (i.e., baseline and historical data) (612).

[0147] Figure 6 The processing order shown is illustrative and may vary without departing from the scope of this specification or the claims.

[0148] Figure 7This is an example procedure for performing cough analysis 409 using preprocessed and subsampled data 701. Filtering is used to remove unwanted components from the input sensor data or to preserve content useful for cough processing (702). In the implementation, the filter can be IIR, FIR, or a combination of both. In the implementation, the filter can be low-pass, high-pass, band-pass, band-stop, notch, or a combination thereof. In the implementation, filtering can include sources from other sensors to remove common-mode or other noise, and adaptive filtering techniques can be used to remove unwanted signals. The filtered sensor data is transformed to enhance the cough component by modeling the input signal as a set of waveforms of a specific form (sine waves for Fourier transform, mother wavelets for wavelet transform, periodic basis functions for periodic transform) (703). In the implementation, the transformation can be Fourier transform, wavelet transform, cosine transform, or mathematical operations (e.g., root mean square, absolute, moving average, moving median, etc.). Envelope detection can be performed to take a relatively high-frequency amplitude-modulated signal as input and provide an output equivalent to the input data profile described by connecting all local peaks in that signal (704). In implementation, envelope detection can use a low-pass filter, Hilbert transform, or other envelope detection methods. Patterns matching the morphological or spectral signature of a cough can be detected in the processed sensor data (705).

[0149] Variation analysis can be performed to measure the level of change in data compared to baseline (706). In implementation, this can be done by estimating standard deviation, coefficient of variation, etc. Variation analysis and cough features can be used to identify isolated cough episodes in the input signal (707). Cough rate can be determined using time-domain, frequency-domain, or time-frequency-domain analysis (708). Cough severity can be determined using time-domain, frequency-domain, or time-frequency-domain analysis (709). Irregular cough can be identified using cough rate, cough severity, and trend data 710 of the subjects (i.e., baseline data and historical data) (711).

[0150] Figure 7 The processing order shown is illustrative and may vary without departing from the scope of this specification or the claims.

[0151] Figure 8 This is an example process for short-term screening and triage based on machine learning classifiers. Swimlane 800 includes device 801, local database 802, cloud server 803, classifier factory 804, and configuration server 805. Device 801 includes a first set of devices 806 and a second set of devices 807.

[0152] The first set of devices 806 generates sensor data, which is received (808) and stored (809) by a local database 802 and received by a cloud server 803. The cloud server 803 retrieves the sensor data (812), and the classifier factory 804 generates or retrains a classifier (814). The generated or retrained classifier is stored by the classifier factory 804 (815). The generated or retrained classifier is used by the classifier factory 804 to classify the sensor data (816) and automatically detect different arrhythmias, diseases, or abnormal conditions. The classified data is stored (813) and subject trend data is stored (810). The configuration server 805 obtains the generated or retrained classifier and generates an update for device 801 (817). In the implementation, the update can be an app update for smart devices or a software update for remote devices. Configuration server 805 sends updates to (818) the first group of devices 806 and the second group of devices 807, where the second group of devices 807 can be a new device. When more data input becomes available from more devices, the system can be used to provide new or updated classifiers to older devices (such as the first group of devices 806). The system can also be used to provide software updates with improved accuracy and to learn personalized patterns and add personalization to the classifier or data.

[0153] Figure 8 The processing order shown is illustrative and may vary without departing from the scope of this specification or the claims.

[0154] Typically, a system for at least short-term screening and triage of subjects includes a smart device owned by the subject; an application provided on the smart device, the application and the smart device being configured to provide the subject with instructions to begin the screening process, the application being programmed with multiple screening processes, recording short-term sensor data obtained from one or more sensors located on the smart device, and comparing the short-term data, trend data and general population data for the purpose of screening and triage of the subject.

[0155] In the implementation, the application and smart device are also configured to analyze short-term sensor data, obtain trend data from long-term screening, identify conditions based on the analyzed short-term sensor data and trend data, and perform actions in response to the identified conditions. In the implementation, these actions include one or more of the following: generating an audible tone for a critical condition, sending a message to a cloud entity for a critical condition, or sending sensor data and the identified condition to the entity instead of the subject. In the implementation, the application and smart device are also configured to initiate long-term screening to generate trend data in response to the identified condition, wherein the long-term screening system includes one or more sensors mounted near a basement on which the subject sits, each sensor configured to capture mechanical vibrations from the subject's movements relative to the basement, which indicate the subject's biosignal information. In the implementation, the long-term screening system is also configured to access short-term sensor data and the identified condition. In the implementation, the application and smart device are also configured to initiate further short-term screening in response to the identified condition. In the implementation, the application and smart device are also configured to analyze the subject's cardiac information, determine heart rhythm and rate information based on the cardiac information, determine the subject's health status based on the heart rhythm and rate information, and identify the onset or progression of a cardiac condition. In the implementation, the application and smart device are also configured to analyze the subject's respiratory information, determine respiratory rhythm and rate information based on the respiratory information, determine the subject's health status based on the respiratory rhythm and rate information, and identify the onset or progression of a respiratory condition. In the implementation, the application and smart device are also configured to analyze the subject's cough information, determine cough rhythm and rate information based on the cough information, determine the subject's health status based on the cough rhythm and rate information, and identify the onset or progression of a cough condition or respiratory flow. In the implementation, the application and smart device are also configured to determine the severity or progression of a condition. In the implementation, the smart device is a mobile phone, tablet, smartwatch, or accessory having one or more of an accelerometer, gyroscope, pressure sensor, load sensor, weight sensor, force sensor, motion sensor, microphone, or vibration sensor. In practice, the screening process includes instructions to move the subject to a suitable location, stay in that location for a limited time, and place a smart device on one or more locations on the subject's body.

[0156] Generally, a system for screening and triaging subjects includes: smart devices equipped with an application, collectively configured to: instruct a subject to begin a screening process, record short-term sensor data obtained from at least one sensor located in the smart device, and identify a condition from the short-term sensor data and the obtained trend data; a substrate with a sensor deployed thereon, the sensor being configured to capture mechanical vibrations from the subject's movements relative to the substrate, the mechanical vibrations indicating the subject's biosignal information; and a processor connected to the sensor, the processor being configured to: capture sensor data from the sensor in response to a condition identified by the smart device, identify the condition based on the sensor data captured from the sensor and the obtained short-term sensor data, and perform an action based on the identified condition.

[0157] In the implementation, the application and smart device are also configured to: analyze short-term sensor data, obtain trend data from memory associated with the processor, and perform actions in response to conditions identified by the smart device. In the implementation, the application and smart device are also configured to: transmit short-term sensor data to an entity for analysis against the trend data, obtain analysis results, and perform actions in response to conditions identified by the entity. In the implementation, actions in response to conditions identified by the smart device or by the entity include one or more of the following: generating an audible tone for a critical situation, sending a message to a cloud entity for a critical situation, and sending short-term sensor data and the identified condition to the entity instead of the subject. In the implementation, the application and smart device are also configured to initiate further smart device screening in response to conditions identified by the smart device. In its implementation, the application and smart device are also configured to perform at least one of the following: analyzing the subject's cardiac information, determining cardiac rhythm and rate information based on the cardiac information, determining the subject's health status based on the cardiac rhythm and rate information and identifying the onset or progression of a cardiac condition; or analyzing the subject's respiratory information, determining respiratory rhythm and rate information based on the respiratory information, determining the subject's health status based on the respiratory rhythm and rate information and identifying the onset or progression of a respiratory condition; or analyzing the subject's cough information, determining cough rhythm and rate information based on the cough information, determining the subject's health status based on the cough rhythm and rate information and identifying the onset or progression of a cough condition or respiratory flow.

[0158] Typically, a method for at least short-term screening and triage of a subject includes: instructing the subject to initiate a screening process via a smart device; recording short-term sensor data from the subject via sensors on the smart device while he / she follows the screening process; analyzing the short-term sensor data; obtaining trend data from a long-term screening device; identifying the subject's condition based on the analyzed short-term sensor data and trend data; and performing an action in response to the identified condition.

[0159] In one implementation, the method includes initiating the capture of sensor data at a long-term screening device in response to an identified condition. In another implementation, the method includes analyzing the long-term screening device sensor data to obtain smart device data, identifying a subject's condition based on the analyzed long-term screening device sensor data, general population data, and short-term sensor data, and performing an action in response to the condition identified by the long-term screening device. In yet another implementation, the method includes sending the short-term sensor data, the condition identified by the smart device, the long-term screening device sensor data, and the condition identified by the long-term screening device to at least an entity, but not a subject. In yet another implementation, the method includes initiating additional smart device screening in response to the identified condition.

[0160] Although this disclosure has been described in conjunction with certain embodiments, it should be understood that this disclosure is not limited to the disclosed embodiments. Rather, this disclosure is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims, which should be interpreted in the broadest possible sense to include all such modifications and equivalent structures permitted by law.

Claims

1. A system for at least short-term screening and triage of subjects, said system comprising: The smart device is owned by the subject. as well as An application is provided on the smart device, and the application and the smart device are configured to: The application provides instructions to the subject to begin the screening process, and the application is programmed with multiple screening procedures. Record short-term sensor data obtained from one or more sensors located in the smart device; The short-term sensor data, trend data, and general population data are compared for use in screening and triage of subjects; Analyze the short-term sensor data; The trend data is obtained from a long-term screening system; The status is identified based on the analyzed short-term sensor data and the trend data; as well as In response to the identified situation, perform an action. The long-term screening system includes one or more sensors installed near the basement where the subject is located, each sensor being configured to capture mechanical vibrations from the subject's movements relative to the basement, the mechanical vibrations indicating the subject's biosignal information.

2. The system of claim 1, wherein, The action includes one or more of the following: Generate audible tones for emergency situations; In response to a crisis, a message is sent to the cloud entity; The short-term sensor data and the identified conditions are sent to the entity rather than the subject.

3. The system according to claim 1, wherein, The application and the smart device are also configured to: In response to the identified conditions, a long-term screening is initiated to generate the trend data.

4. The system according to claim 1, wherein, The long-term screening system is also configured to access the short-term sensor data and the identified conditions.

5. The system according to claim 1, wherein, The application and the smart device are also configured to: In response to the identified condition, further short-term screening is initiated.

6. The system according to claim 1, wherein, The application and the smart device are also configured to: Analyze the subjects' cardiac information; Based on the cardiac information, determine the heart rhythm and rate information; The subject's health status is determined based on the heart rhythm and rate information; and Identify the onset or progression of a heart condition.

7. The system according to claim 1, wherein, The application and the smart device are also configured to: Analyze the subjects' respiratory information; The respiratory rhythm and rate information are determined based on the respiratory information; The subject's health status is determined based on the respiratory rhythm and rate information; as well as Identify the onset or progression of respiratory conditions.

8. The system according to claim 1, wherein, The application and the smart device are also configured to: Analyze the cough information of the subjects; Based on the cough information, determine the cough rhythm and rate information; The subject's health status is determined based on the cough rhythm and rate information; and Identify the onset or progression of cough or respiratory flow.

9. The system according to claim 1, wherein, The application and the smart device are also configured to determine the severity or progression of the identified situation.

10. The system according to claim 1, wherein, The smart device is one of a mobile phone, a tablet computer, a smartwatch, or an accessory, and one of the mobile phone, the tablet computer, the smartwatch, or the accessory has one or more of an accelerometer, a gyroscope, a pressure sensor, a load sensor, a weight sensor, a force sensor, a motion sensor, a microphone, or a vibration sensor.

11. The system according to claim 1, wherein, The screening process includes instructing the subject to move to an appropriate location, remain in that location for a limited period of time, and place the smart device at one or more locations on the subject's body.

12. A system for screening and triaging subjects, the system comprising: A smart device equipped with an application, wherein the application and the smart device are configured together to: Instruct the subject to begin the screening process; Record short-term sensor data obtained from at least one sensor located in the smart device; as well as Identify the situation from the short-term sensor data and the acquired trend data; A substrate, on which sensors are deployed, the sensors being configured to capture mechanical vibrations from the subject’s movements relative to the substrate, the mechanical vibrations indicating the subject’s biosignal information; as well as A processor, connected to the sensor deployed on the substrate, is configured to: In response to a condition identified by the smart device, sensor data is captured from the sensor; The status is identified based on sensor data captured from the sensors and short-term sensor data obtained. as well as Based on the identified situation, perform the action.

13. The system according to claim 12, wherein, The application and the smart device are also configured to: Analyze the short-term sensor data; Obtain trend data from the memory associated with the processor; and In response to the condition identified by the smart device, an action is performed.

14. The system according to claim 13, wherein, The application and the smart device are also configured to: The short-term sensor data is transmitted to the entity for analysis against trend data; Obtain the analysis results; and In response to the state identified by the entity, perform an action.

15. The system according to claim 14, wherein, The action in response to a condition recognized by the smart device or the action in response to a condition recognized by the entity includes one or more of the following: Generate audible tones for emergency situations; In response to a crisis, a message is sent to the cloud entity; The short-term sensor data and the identified conditions are sent to the entity rather than the subject.

16. The system according to claim 12, wherein, The application and the smart device are also configured to: In response to the condition identified by the smart device, further smart device screening is initiated.

17. The system according to claim 12, wherein, The application and the smart device are also configured to perform at least one of the following: Analyze the subjects' cardiac information; Based on the cardiac information, determine the heart rhythm and rate information; The subject's health status is determined based on the heart rhythm and rate information; as well as Identify the onset or progression of a heart condition; or Analyze the subjects' respiratory information; The respiratory rhythm and rate information are determined based on the respiratory information; The subject's health status is determined based on the respiratory rhythm and rate information; as well as Identify the onset or progression of respiratory conditions; or Analyze the cough information of the subjects; Based on the cough information, determine the cough rhythm and rate information; The subject's health status is determined based on the cough rhythm and rate information. as well as Identify the onset or progression of cough or respiratory flow.

18. A method performed by a smart device, the method comprising: The subject is instructed to initiate the screening process via the aforementioned smart device; As the subject follows the screening process, short-term sensor data from the subject is recorded via sensors on the smart device; Analyze the short-term sensor data; Obtain trend data from long-term screening equipment; The subject's condition is identified based on the analyzed short-term sensor data and the trend data; as well as In response to the identified situation, perform an action. The long-term screening device includes one or more sensors installed near the basement where the subject is located, each sensor being configured to capture mechanical vibrations from the subject's movements relative to the basement, the mechanical vibrations indicating the subject's biosignal information.

19. The method of claim 18, further comprising: In response to the identified condition, the capture of sensor data at the long-term screening device is initiated.

20. The method of claim 19, further comprising: Analyze sensor data from long-term screening equipment; Obtain data from smart devices; The subject's condition is identified based on the analyzed long-term screening device sensor data, general population data, and the aforementioned short-term sensor data; as well as It takes action in response to conditions identified by long-term screening equipment.

21. The method of claim 20, further comprising: Short-term sensor data, conditions identified by smart devices, and conditions identified by long-term screening devices are sent to at least the physical entity rather than the subject.

22. The method of claim 18, further comprising: In response to the identified condition, an additional smart device screening is initiated.

Images