A system for continuous monitoring of respiratory diseases

Abstract

This invention provides a system and method for determining the symptoms of respiratory diseases. [Solution] This system includes a transceiver capable of receiving data from a monitor attached to the patient. The monitor includes multiple sensors, each of which outputs physiological data related to the patient's respiration. The transceiver is connected to an analysis platform that analyzes the physiological data to determine the patient's respiratory status, impairment, or the onset of disease symptoms.

Description

Technical Field

[0001] Claim of Priority This application claims priority to and the benefit of U.S. Provisional Patent Application No. 62 / 881,330, filed Jul. 31, 2019, and U.S. Provisional Patent Application No. 62 / 941,185, filed Nov. 27, 2019. Each of these documents is hereby incorporated by reference in its entirety. Technical Field

[0002] The present disclosure generally relates to disease detection systems and, more particularly, to a continuous monitoring system for respiratory diseases such as asthma.

Background Art

[0003] Many people suffer from respiratory diseases such as asthma and chronic obstructive pulmonary disease (COPD). For example, asthma is a common chronic respiratory disease that constricts the airways and makes breathing difficult. In addition, asthma can cause wheezing, chest tightness, shortness of breath, coughing, etc. Asthma can be caused by hypersensitivity to inhaled substances, which constricts and tightens the airways of the bronchi. Also, the airways can swell and secrete mucus, further obstructing the airflow. During an asthma attack, the airways can narrow to a life-threatening level.

[0004] In the United States alone, more than 25 million people suffer from asthma, of which 7 million are children. There is no cure for asthma, but it can be managed with inhaled medications. Some patients can eliminate most asthma symptoms by taking medications regularly. Generally, asthma treatment can be subdivided into two categories: daily preventive treatment and emergency medications. Emergency medications are generally bronchodilators that rapidly relax the smooth muscles of the bronchi to expand the airways and improve breathing during an asthma attack. Typical examples of daily preventive treatment include anti-inflammatory agents such as steroids that reduce swelling and mucus production in the airways and, accordingly, reduce the patient's sensitivity to triggers. Preventive anti-inflammatory agents are effective not only in suppressing asthma symptoms but also in prevention.

[0005] When diagnosed with asthma, patients may be prescribed preventative anti-inflammatory medications that can be self-administered using inhalers. However, this treatment depends on whether asthma can be detected early, and currently, it is not possible to constantly monitor patients to predict asthma attacks and administer preventative treatment in response to symptom onset. Therefore, healthcare providers have no choice but to wait for patients to come in for regular checkups on their own. Healthcare professionals typically use a stethoscope to detect respiratory abnormalities during checkups. As a result, there is a higher possibility that impending asthma attacks may go undetected, worsen, and require emergency medication because preventative treatment has been delayed.

[0006] Therefore, there is a need for a system that can continuously monitor and determine the condition of respiratory diseases, disorders, and illnesses such as asthma. Furthermore, a system including a monitor that can continuously detect multiple physiological signals such as respiratory rate, heart rate, respiratory characteristics, breath sounds, and ventilation volume is also required to predict respiratory events such as asthma attacks and exacerbations. In addition, there is a need for a user-friendly physical monitor that can monitor respiratory status, disorders, or illnesses 24 hours a day. [Prior art documents] [Non-patent literature]

[0007] [Non-Patent Document 1] Seppa, V.-P., Pelkonen, AS, Kotaniemi-Syrjanen, A., Makela, MJ, Viik, J., & Malmberg, LP (2013). Tidal breathing flow measurement in awake young children by using impedance pneumography. J Appl Physiol, 1725-1731. [Overview of the project] [Means for solving the problem]

[0008] The disclosed respiratory disease monitoring system provides continuous signal measurements related to respiratory status, impairment, or disease. This disclosed system enables nighttime monitoring. The system includes an easy-to-use monitor with multiple types of sensors for determining data related to monitoring respiratory status, impairment, or disease. Based on such data, the system can determine symptoms of respiratory disease and predict respiratory events such as asthma attacks.

[0009] One disclosed example is a system for determining the symptoms of respiratory disease. This system includes a transceiver capable of receiving data from a monitor worn on the patient. The monitor includes multiple sensors, each of which outputs physiological data related to the patient's respiration. The transceiver is connected to an analysis platform that analyzes the physiological data to determine the patient's respiratory status, impairment, or the onset of disease symptoms.

[0010] In a further implementation of this system example, the multiple sensors include a heart rate sensor and a respiratory sensor. In another implementation, the system includes a portable computing device that receives physiological data from a transceiver and transmits that physiological data to an analysis platform. In another implementation, the analysis platform analyzes environmental data about the patient when determining the occurrence of symptoms of respiratory disease. In another implementation, the analysis platform analyzes demographic data about the patient when determining the occurrence of symptoms of respiratory disease. In another implementation, the multiple sensors further include an accelerometer. In another implementation, the multiple sensors further include a pressure sensor. In another implementation, the symptom is shortness of breath. In another implementation, the analysis platform is configured to determine shortness of breath using a combination of respiratory effort determined from the pressure sensor and accelerometer and respiratory rate determined from the respiratory sensor. In another implementation, the multiple sensors further include an audio sensor. In another implementation, the analysis platform distinguishes between mild wheezing and other external signals based on data from the audio sensor. In another implementation, the analysis platform runs on a remote server. In another implementation, the analysis platform is configured to apply a model to physiological data to determine the occurrence of respiratory disease symptoms. In another implementation, this model consists of machine learning based on collected physiological and respiratory disease outcome data. In another implementation, the analysis platform determines the occurrence of symptoms based on public health factors applicable to the patient. In another implementation, these public health factors include social health determinants. In another implementation, the analysis platform estimates social health determinants based on the geographical location of the patient's home. In another implementation, the public health factors include data collected from other patients in a similar patient cohort. In another implementation, the analysis platform analyzes physiological data to determine the risk assessment of respiratory disease events for the patient.In another implementation, the analysis platform compares the risk assessment to a threshold to predict respiratory events. In another implementation, the analysis platform initiates corrective action upon receiving the predicted respiratory event. In another implementation, these multiple sensors may include an impedance plethysmography sensor. In another implementation, the analysis platform determines the risk assessment by correlating impedance measurements from the impedance plethysmography sensor with vital capacity, plotting a flow-volume curve from the vital capacity, extracting one or more ventilation parameters from the flow-volume curve, deriving features from the ventilation parameters, and applying a model to the features to determine the risk assessment. In another implementation, these multiple sensors include an ECG sensor. In another implementation, the analysis platform removes noise generated by cardiac activity from the impedance measurements from the ECG sensor. In another implementation, these multiple sensors include an accelerometer. In another implementation, the analysis platform removes motion artifacts from the impedance measurements from the accelerometer. In another implementation, one or more tidal volume parameters are selected from a group consisting of the time to peak expiratory flow rate during expiratory time, the volume of peak expiratory flow rate relative to expiratory ventilation, and the slope of the post-peak expiratory flow rate curve. In yet another implementation, this model is constructed using machine learning based on collected physiological and respiratory disease outcome data.

[0011] Another disclosed example is a patient-wearable, continuous monitoring device. This monitoring device includes a housing having a surface that can be attached to the patient. This monitoring device includes a plurality of sensors, each of which continuously senses various physiological data of the patient regarding the patient's respiratory status, impairment, or disease. A memory stores this physiological data. A transceiver transmits the sensed data to an external device.

[0012] In a further implementation of this example monitoring device, the multiple sensors include a heart rate sensor and a respiratory sensor. In another implementation, the respiratory sensor is an impedance plethysmography sensor. In another implementation, the monitor includes a pair of electrode pads configured to sense the voltage between the electrode pads. In another implementation, a heart rate sensor is coupled to this pair of electrode pads. In another implementation, an impedance plethysmography sensor is coupled to this pair of electrode pads. In another implementation, the monitor includes a second pair of electrode pads to which an impedance plethysmography sensor is coupled for injecting a low-amplitude high-frequency current. In another implementation, the housing has a form factor that is one of a group consisting of a patch, a wristband, a necklace, and a vest. In another implementation, the multiple sensors further include an audio sensor. In another implementation, the multiple sensors include an accelerometer and a gyroscope. In another implementation, the multiple sensors further include a pressure sensor. In another implementation, the enclosure is made from a flexible, suitable material.

[0013] Another example is a system for monitoring respiratory illness in patients. This system includes a monitor that can be worn by the patient. The monitor includes multiple sensors, each of which outputs physiological data related to the patient's respiratory illness. The monitor includes a first transceiver configured to transmit this physiological data. This system includes an external device which includes a second transceiver for receiving physiological data from a second transceiver. The second transceiver is connected to an analysis platform that analyzes the physiological data received from the second transceiver to determine the occurrence of respiratory illness.

[0014] In a further implementation of this system example, the multiple sensors include a heart rate sensor and a respiratory sensor. In another implementation, the external device is a portable computing device. In another implementation, the analysis platform analyzes environmental data about the patient when determining the occurrence of respiratory disease symptoms. In another implementation, the analysis platform analyzes demographic data about the patient when determining the occurrence of respiratory disease symptoms. In another implementation, the multiple sensors further include an accelerometer. In another implementation, the multiple sensors further include a pressure sensor. In another implementation, the symptom is shortness of breath. In another implementation, the analysis platform determines shortness of breath using a combination of respiratory effort determined from the pressure sensor and accelerometer and respiratory rate determined from the respiratory sensor. In another implementation, the multiple sensors further include an audio sensor. In another implementation, the analysis platform distinguishes between mild wheezing and other external signals based on data from the audio sensor. In another implementation, the analysis platform runs on a remote server. In another implementation, the analysis platform applies a model to physiological data to determine the occurrence of respiratory disease symptoms. In another implementation, this model consists of machine learning based on collected physiological and respiratory disease outcome data. In another implementation, an analysis platform analyzes this physiological data to determine a risk assessment of respiratory events in respiratory disease. In another implementation, the analysis platform compares the risk assessment to a threshold to predict respiratory events. In another implementation, the analysis platform initiates corrective action upon receiving the predicted respiratory events. In another implementation, these multiple sensors may include impedance plethysmography sensors.In another implementation, the analysis platform is configured to determine risk assessment by correlating impedance measurements from an impedance plethysmography sensor with vital capacity, plotting a flow-volume curve from the vital capacity, extracting one or more tidal volume parameters from the flow-volume curve, deriving features from the tidal volume parameters, and applying a model to the features to determine risk assessment. In another implementation, these multiple sensors include an ECG sensor. In another implementation, the analysis platform removes noise generated by cardiac activity from the impedance measurements from the ECG sensor. In another implementation, these multiple sensors include an accelerometer. In another implementation, the analysis platform removes motion artifacts from the impedance measurements from the accelerometer. In another implementation, one or more tidal volume parameters are extracted from a group consisting of the time to peak expiratory flow rate during expiratory time, the volume of peak expiratory flow rate relative to expiratory ventilation, and the slope of the post-peak expiratory flow rate curve. In another implementation, this model is constructed using machine learning based on collected physiological and respiratory disease outcome data. In another implementation, the system includes a medication rule engine that modifies the treatment plan for respiratory diseases based on a determined risk assessment. In another implementation, the medication rule engine is configured to adjust the dosage of drugs that form part of the treatment plan. In another implementation, the medication rule engine is configured to adjust the type of drugs that form part of the treatment plan. In another implementation, an analytics platform issues alerts based on the risk assessment. In another implementation, the system includes an alert device that receives alerts issued by the analytics platform and alerts a person upon receiving an alert. In another implementation, the alert device wakes a person from sleep upon receiving an alert. In another implementation, the alert device is a wearable alert device.

[0015] Another example is a method for predicting respiratory disease events in patients. Various types of respiratory-related physiological data are collected from multiple sensors on a monitor attached to the patient. A model for predicting respiratory disease events is applied. This model is based on the physiological data collected from the multiple sensors.

[0016] In a further implementation of this example method, the multiple sensors include a heart rate sensor and a respiratory sensor. In another implementation, the multiple sensors further include an accelerometer. In another implementation, the multiple sensors further include a gyroscope. In another implementation, the model considers environmental data about the patient. In another implementation, the model considers demographic data about the patient. In another implementation, this method includes constructing the model by machine learning based on collected physiological and respiratory disease outcome data. In another implementation, this method includes issuing an alert to an alert device when an event is predicted, and the alert device is configured to draw the person's attention. In another implementation, the model includes input information of public health factors applicable to the patient. In another implementation, these public health factors include social health determinants. In another implementation, this method includes estimating social health determinants based on the geographical location of the patient's home. In another implementation, the public health factors include data collected from other patients in a patient cohort similar to that patient. In another implementation, this method includes initiating corrective action in response to a predicted respiratory event. In an alternative implementation, these multiple sensors may include an impedance plethysmography sensor. In another implementation, this method further includes determining the risk assessment by correlating impedance measurements from the impedance plethysmography sensor with vital capacity. A flow-volume curve based on vital capacity is created. One or more tidal volume parameters are extracted from this flow-volume curve. Features are derived from these tidal volume parameters. A model is applied to these features to determine the risk assessment. In an alternative implementation, these multiple sensors may include an ECG sensor. In another implementation, this method includes removing noise generated by cardiac activity from the impedance measurements from the ECG sensor. In an alternative implementation, these multiple sensors may include an accelerometer. In another implementation, this method includes removing motion artifacts from the impedance measurements from the accelerometer.In another implementation, one or more ventilation parameters are selected from a group consisting of the time to peak expiratory flow rate during expiratory time, the volume of peak expiratory flow rate relative to expiratory ventilation, and the slope of the post-peak expiratory flow rate curve.

[0017] Another disclosed example is a system for monitoring a patient's respiratory illness. This system includes a monitor that can be worn by the patient. The monitor has multiple sensors. Each of the multiple sensors is configured to output physiological data about the patient's respiratory illness. A first transceiver is configured to transmit this physiological data. An external device includes a second transceiver configured to receive physiological data from the first transceiver. An analysis platform is connected to the second transceiver. This analysis platform analyzes the physiological data received from the second transceiver to predict respiratory illness events.

[0018] In a further implementation of this system example, these multiple sensors include a heart rate sensor and a respiratory sensor. In another implementation, the multiple sensors further include an accelerometer.

[0019] In other implementations, the sensors further include accelerometers. In other implementations, the sensors further include gyroscopes. In other implementations, the model considers environmental data about the patient. In other implementations, the model considers demographic data about the patient. In other implementations, the model consists of machine learning based on collected physiological and respiratory disease outcome data. In other implementations, the analysis platform alerts an alert device configured to alert a person when an event is predicted. In other implementations, the model includes input information on public health factors applicable to the patient. In other implementations, these public health factors include social health determinants. In other implementations, the analysis platform estimates social health determinants based on the geographical location of the patient's home. In other implementations, the public health factors include data collected from other patients in a patient cohort similar to that patient. In other implementations, the analysis platform initiates corrective action in response to predicted respiratory events. In other implementations, these sensors may include impedance plethysmography sensors. In another implementation, the analysis platform is configured to determine risk assessment by correlating impedance measurements from an impedance plethysmography sensor with vital capacity. A flow-volume curve is created based on vital capacity. One or more ventilation parameters are extracted from this flow-volume curve. Features are derived from these ventilation parameters. A model is applied to these features to determine risk assessment. In another implementation, these multiple sensors include an ECG sensor. In another implementation, the analysis platform removes noise generated by cardiac activity from the impedance measurements from the ECG sensor. In another implementation, these multiple sensors include an accelerometer. In another implementation, the analysis platform removes motion artifacts from the impedance measurements from the accelerometer.In another implementation, one or more ventilation parameters are extracted from the group consisting of the time to peak expiratory flow rate during the expiratory time, the volume of the peak expiratory flow rate relative to the expiratory ventilation volume, and the slope of the expiratory flow rate curve after the peak.

[0020] The above summary is not intended to represent each embodiment or aspect of the present disclosure. That is, the above summary merely shows some examples of the novel aspects and features described herein. The above features and advantages, as well as other features and advantages of the present disclosure, will become readily apparent upon reading the following detailed description of representative embodiments and aspects for carrying out the invention in conjunction with the accompanying drawings and the appended claims.

[0021] The understanding of the present disclosure will be enhanced by referring to the following description of exemplary embodiments in conjunction with the accompanying drawings.

Brief Description of the Drawings

[0022] [Figure 1] FIG. 1 is a block diagram of a continuous monitoring system that monitors respiratory diseases, disorders, and illnesses, including an example of a patient's continuous monitoring device, and determines corresponding symptoms. [Figure 2] FIG. 2 is a block diagram showing the electronic components and other elements of the continuous monitoring device of the system of FIG. 1. [Figure 3] FIG. 3 is a flowchart showing an example of a machine learning process for training a prediction model for respiratory diseases such as asthma. [Figure 4] FIG. 4 is a flowchart of a routine for collecting and processing data from the continuous monitoring device of FIG. 1. [Figure 5A] FIG. 5 is a graph showing an example of signal data collected for the outputs of various sensors mounted on the continuous monitoring device of FIG. 1. [Figure 5B] FIG. 6 is a graph showing an example of signal data collected for the outputs of various sensors mounted on the continuous monitoring device of FIG. 1. [Figure 5C]A graph showing an example of collected signal data including body movement artifacts, derived from the analysis data analyzed from the continuous monitoring device of FIG. 1. [Figure 5D] A graph showing the state of removing cardiogenic noise from the data analyzed from the continuous monitoring device of FIG. 1. [Figure 6] A block diagram showing the data flow in a system for collecting data from the continuous monitoring device of FIG. 1. [Figure 7] A block diagram of a medical system incorporating and supporting the continuous monitoring system of FIG. 1. [Figure 8A] A perspective view showing an example of a continuous monitoring device used in the system of FIG. 1. [Figure 8B] A circuit diagram of an example of the monitoring device of FIG. 8A. [Figure 8C] A top perspective view of the internal components of an example of the monitoring device of FIG. 8A. [Figure 8D] A bottom perspective view of the internal components of an example of the monitoring device of FIG. 8A. [Figure 9] A block diagram of the components of an example of the monitoring device of FIG. 8A. [Figure 10A] A perspective view before attaching an example of an adhesive accessory component for applying an example of the monitoring device of FIG. 8A. [Figure 10B] Before attaching to the patient's skin, the continuous steps when attaching the adhesive of the adhesive accessory component of FIG. 10A to the monitoring device of FIG. 8A are shown. [Figure 11] A process flow diagram showing an example of data collection from a monitoring device and predictive analysis of such data. [Figure 12] Two graphs showing the flow volume curve and the ventilation volume parameter that can be extracted from such a curve.

MODE FOR CARRYING OUT THE INVENTION

[0023] This disclosure includes various variations and alternative forms. Several representative embodiments illustrated in the drawings are described in detail below herein. However, it should be understood that the present invention is not intended to be limited to any particular form disclosed, and rather this disclosure covers all variations, equivalents, and alternatives that fall within the spirit and scope of the invention as defined by the appended claims.

[0024] The present invention can be embodied in numerous different forms. Representative embodiments are shown in the drawings and are described in detail below in this specification. This disclosure is an example or illustration of the principles of this disclosure and is not intended to limit the broader aspects of this disclosure to the examples given. Therefore, elements or limitations disclosed in, for example, the sections “Abstract,” “Summary of the Invention,” and “Modes for Carrying Out the Invention,” but not expressed in the claims, should not be incorporated into the claims, individually or collectively, by suggestion, inference, or otherwise. In this specification, unless otherwise specified, singular nouns include plural nouns, and vice versa. The phrase “including” means “including but not limited to.” Furthermore, in this specification, approximation words such as “approximately,” “about,” “substantially,” and “around” may be used to mean, for example, “just,” “near,” “around,” “within 3-5%,” “within acceptable manufacturing tolerances,” or any logical combination thereof.

[0025] This disclosure relates to an ongoing monitoring system for monitoring a patient's respiratory status, impairment, or disease, such as asthma. The system includes an ongoing monitor worn by the patient. The monitor has sensors that acquire multiple physiological readings from the patient. The data obtained from these readings may be transmitted to an external device. The system includes a machine learning engine capable of analyzing and determining data indicating respiratory status, impairment, or disease symptoms. The system may use the data to predict respiratory events, such as asthma attacks. The patient or their family may be alerted to take preventative measures.

[0026] Figure 1 shows a patient 100 with a respiratory monitoring device 110 (monitor) continuously attached to the chest. As described below, the monitor 110 can be applied to any location on the patient 100's body where relevant physiological signals sent from the patient 100 can be detected. In this embodiment, the respiratory monitor 110 includes a transmitter for transmitting data, a sensor(s) for detecting respiratory-related signals, and an adhesive for attaching it to the patient 100. The monitor 110 may be replaced periodically, but because it is small, it may remain attached to the patient 100 for the duration of the monitoring period. The monitor 110 may also be reusable. Therefore, the monitor 110 can acquire continuous data from the patient to monitor respiratory status, impairment, or disease. The data detected by the monitor 110 can be transmitted to a remote external portable device 112, such as a smartphone. The portable device 112 can communicate with an external data server 114 via a network such as the internet or the cloud. The data server 114 may run applications for data analysis and machine learning related to predicting respiratory events, as well as determining respiratory status, disorders, or disease symptoms, as described below.

[0027] The monitor 110 generally includes a flat protective housing that houses electronic components such as a power supply, transceiver, memory, controller, sensor interface, and sensor electronics. In this embodiment, the housing is made from a material such as flexible silicone so as to conform to the user's skin. Sensor interface areas may be positioned to contact the patient's skin. Such sensor contact areas may include ECG electrode pads, impedance electrode pads, acoustic pads, or PPG sources and detectors. Some electrodes may be used by multiple sensors. The monitor 110 may have various wearable form factors, such as a patch, wristband, necklace, or vest.

[0028] Figure 2 is a block diagram of the electronic components of the monitor 110, portable device 112, and external server 114. The monitor 110 includes a controller 200, a sensor interface 202, a transceiver 204, a memory 206, and a battery 208. The sensor interface 202 communicates with an audio sensor 210, a heart rate sensor 212, a respiration sensor 214, a contact pressure sensor (strain gauge) 216, and an optional accelerometer 218.

[0029] The transceiver 204 enables data exchange between the monitor 110 and the remote external portable device 112 in Figure 1. The transceiver 204 in this embodiment is a wireless link that may incorporate any suitable wireless connectivity technology known in the art, including but not limited to Wi-Fi (IEEE 802.11), Bluetooth®, other radio frequencies, infrared (IR), GSM®, CDMA, GPRS, 3G, 4G, W-CDMA, EDGE or DCDMA200 and similar technologies.

[0030] Memory 206 may store computer modules or other software for configuring the controller 200 to implement the functions of the monitor 110 as described herein. In addition, memory 206 may store data collected by various sensors associated with the monitor 110. This data may be stored in memory 206 until it is continuously transmitted to an associated long-term storage device or downloaded by connecting another device to the monitor 110.

[0031] In this embodiment, the voice sensor 210 detects sounds from the lungs. Such sounds may indicate respiratory status, impairment, or symptoms of disease, and may predict respiratory events that may occur. For example, wheezing or coughing sounds may predict future asthma attacks. Such predictions may also be made from voice data combined with data such as heart rate. In this embodiment, the heart rate sensor 212 is a two-lead electrocardiogram (ECG) sensor. In this embodiment, the respiratory sensor 214 is an impedance plethysmography (IPG) sensor having two voltage leads and two current leads. Monitor example 110 includes an optional pressure sensor 216 and an optional accelerometer 218. In this embodiment, data from different sensors 210, 212, 214, 216, and 218 may be analyzed for the purpose of determining respiratory status, impairment, or symptoms of disease, and predicting respiratory events. For example, sensor data from the pressure sensor 216 and accelerometer 218 may be used to determine lung ventilation. Pressure data from the pressure sensor 216 can be used to measure respiratory effort. By considering tidal volume and respiratory effort, respiratory events such as asthma attacks can be predicted.

[0032] Other sensors may be part of monitor 110. Such sensors may include a Doppler radar motion sensor, a thermometer, a weighing scale, or a photoplethysmography (PPG) sensor, all of which are configured to provide further physiological data measured from patient 100 (biological movement, body temperature, weight, and oxygen saturation, respectively). Further sensors may be used to provide further types of data. This data may be analyzed alone or in conjunction with other types of data to determine respiratory status, impairment, or symptoms of disease and to predict respiratory events. Further sensors or sensors 210, 212, and 214 may also be used for other purposes, such as monitoring heart rate variability (HRV). There may also be data acquired from external sensors, such as an environmental sensor 130. Such an environmental sensor 130 may transmit data such as ambient temperature, humidity, or pollen count to a portable device 112 or server 114 to assist in predictive analysis.

[0033] The remote external portable device 112 may be a portable computing device such as a smartphone or tablet that can run applications for collecting, analyzing, and displaying data from the monitor 110. The remote external portable device 112 may include a CPU 230, a GPS receiver 232, a transceiver 234, and a memory 236. The memory 236 may include an application 240 for collecting and analyzing data. The memory 236 also stores the collected data 242 received from the monitor 110. Additional data, such as patient-specific data and environmental data, which can be used to determine respiratory status, impairment, or disease symptoms and to predict respiratory events, may also be stored in the memory 236. The additional data may be analyzed and compiled by the application 240. The remote external portable device 112 may have access to a database 250 containing “big data” from other monitors and corresponding patients. The patient application 240 may be able to operate to provide the patient or their family with actionable insights and recommendations for controlling respiratory events, such as predicting asthma attacks.

[0034] Server 114 may also access database 250. Server 114 may analyze data received from external portable devices 112 and run one or more analytical algorithms as part of an analytical platform 252 configured with machine learning to monitor patients' respiratory illnesses. Server 114 may also run machine learning modules 254 that comprise analytical algorithms(s) for both determining symptoms from collected data and predicting respiratory events.

[0035] Algorithms(s) for monitoring respiratory status, impairment, or disease may analyze data from sensors 210, 212, and 214, or data produced as a result of refining or combining data from sensors 210, 212, and 214. As described above, these algorithms determine the symptoms of respiratory status, impairment, or disease. These algorithms may be executed by the patient application 240 or by the analysis platform 252. The results of the analysis may be provided directly to the patient or their family via an interface generated by application 240 on the portable device 112. Application 240 may also provide the patient or their family with suggested corrective actions, such as taking medication, calling a healthcare professional, or discontinuing treatment efforts. Naturally, these decisions may also be provided to the server 114.

[0036] As described below, predictive algorithms for predicting respiratory events may also be executed by the server 114. Such algorithms may further analyze algorithms executed by the application 240 on the portable device 112. Predictive analysis may be provided to other stakeholders, such as healthcare providers, with the permission of the patient or their family. Predictive analysis may be used for various purposes, such as formulating actions for the patient. Such actions may include recommending medication, increasing or decreasing the frequency of medication, or advising on changes in activities, based on the severity of respiratory events predicted by the algorithm.

[0037] As shown in Figure 1, a family member 120, such as a parent, can operate a portable device 112 to receive information and recommendations regarding the patient 100. For example, a family member 120 may receive alerts regarding the patient's condition. Alternatively, a family member 120 may have a network-connected wearable alert device 122, such as a smartwatch, bracelet, necklace, or headband, which can receive alerts from either the portable device 112 or the server 114. For example, an alert may be issued to the family member 120 when a respiratory event is predicted or detected by the portable device 112 or determined by an algorithm run by the server 114. This alert may be sent to the portable device 112 associated with the family member 120. Alternatively or additionally, to ensure that the family member 120 receives alerts more reliably, the alert may be sent to the network-connected wearable alert device 122. This would ensure that the family member 120 receives notifications regarding the patient's condition, particularly at night, through an application running on the network-connected wearable alert device 122. This notification or alert may also be received by smart home devices or Internet of Things (IoT) network-connected devices (e.g., lights, alarm clocks, infant monitors, CPAP devices, smart mattresses) that are in close proximity to family member 120 and are configured to draw the family member's attention through visual, auditory, tactile or other similar means.

[0038] Therefore, an algorithm operating in either the external portable device 112 or the server 114 can determine respiratory status, impairment, or symptoms of disease, and predict respiratory events. For example, this algorithm may determine symptoms of shortness of breath using a combination of respiratory effort and respiratory rate. Respiratory effort can be determined from readings of the pressure sensor 216 and the intensity of chest movement obtained from the accelerometer 218, or from the respiratory sensor 214. Another example of a symptom is determining a change in the ratio of inhalation to exhalation, which can be an early indicator of respiratory events such as asthma attacks. Before an asthma attack occurs, the ratio of inhalation to exhalation decreases. That is, inhalation becomes shorter to increase the amount of air expelled from the inflamed lung, and the patient tends to lengthen their exhalation time. The ratio of inhalation to exhalation can be measured using the voice sensor 210 and the respiratory sensor 214.

[0039] Furthermore, these algorithms can determine changes in vital capacity to predict respiratory events. Changes in vital capacity may be related to speech signals, heart rate data, or respiratory data. Vital capacity may be measured using only heart rate and respiratory data, without using the speech sensor 210. Changes in vital capacity may correlate with changes in impedance determined by the IPG sensor 214.

[0040] The impedance signal from the IPG sensor 214 can be used to determine diaphragmatic breathing. Diaphragmatic breathing indicates that the airways of the lungs are narrowed compared to the movement of the upper chest, and the pattern is asynchronous. Therefore, diaphragmatic breathing is a sign that the patient is having difficulty breathing due to inflammation or congestion of the airways or lungs. This algorithm can also determine heart rate variability based on data from the heart rate sensor 212. Heart rate can be correlated as an indicator of the autonomic nervous system. Heart rate variability is an indicator of the state of the sympathetic and parasympathetic nervous systems and can be used to measure the degree of anxiety and stress. Since heart rate often increases with the use of bronchodilators, heart rate can also be used to detect medication use.

[0041] These algorithms can also determine indicators of sleep quality, such as nighttime awakenings, using combinations of movement, heart rate, and respiration. These algorithms can correlate readings from the accelerometer 218 that indicate movement, respiratory rate data from the respiration sensor 214, and heart rate variability determined from the heart rate sensor 212.

[0042] Furthermore, these algorithms can analyze the audio signal output from the audio sensor 210 to distinguish mild wheezing from other external signals. Therefore, these algorithms can determine the intensity and timing (inspiration or exhalation) of the wheezing. The intensity and timing of the wheezing sound may indicate a condition, disease, or minor illness. Changes in the intensity and timing of such sounds can also be used to predict respiratory events.

[0043] These algorithms can combine multiple sensor signals to detect "silent chest," a sign of severe asthma. A silent chest state is characterized by very high and volatile heart rate and respiratory rate readings from sensors 212 and 214, even though the voice sensor 210 detects no signal. By combining these signals, the algorithm can determine or predict the occurrence of respiratory events, such as severe asthma attacks. Furthermore, using multiple sensors, the algorithm can determine the symptoms of respiratory illness across the entire range of asthma, from mild to severe, based on a multi-sensor approach from voice, heart rate, and respiratory data collected from sensors 210, 212, and 214.

[0044] These algorithms and monitor 110 can be combined with therapeutic devices such as inhalers. These algorithms can, for example, detect whether the inhaler is being used correctly to ensure that medication is taken properly. For example, the algorithms can combine input information from an adherence monitor, such as Reciprocal Labs Patent No. 9,550,031, with the inhaler to compare the timing of the inhaler click with the exhalation / inhalation from the sensor of monitor 110.

[0045] The data output information from monitor 110 can also be combined with data collected from other sources, such as input information from other sensors that are external to monitor 110. For example, these algorithms may consider alerts for exposure to environmental triggers that correlate with data on local weather conditions, based on location information obtained from the GPS receiver 232 or the built-in GPS sensor of the portable device 112.

[0046] Based on the determined combination of symptoms, an individualized risk assessment can be generated, such as the probability of respiratory events occurring, including asthma attacks. Such a risk assessment may also take into account manually entered data, such as the patient's history and clinical recommendations. This risk assessment can then be converted into a set of ranges that can be used to output the risk assessment to the patient, their family, or healthcare professionals. The resulting ranges may be displayed, for example, on a user interface on a portable device 112.

[0047] This data, collected from monitor 110 and other monitors of similar patients, can serve as a predictive indicator of responses, treatment plans, and factors that trigger respiratory events in similar patients in response to similar environments. The analysis platform 252 uses a model to predict respiratory events based on various data inputs. This model may be a known model or a model constructed by the machine learning module 254. The predictive data may be used to enable the system to alert the patient or their family in the event of a high-priority respiratory event, such as an asthma attack. This predictive data may be provided to healthcare providers to evaluate and modify treatment plans or to recommend preventive medication for such respiratory events.

[0048] Figure 3 shows an example routine for training a respiratory disease model, such as a neural network, to predict respiratory events. This example routine may be part of a machine learning module 254 executed by server 114 in Figure 1. In this embodiment, the routine in Figure 3 is unsupervised learning based on data from sensors and patient-specific data, such as demographic data and outcome data based on the patient's respiratory disease. The routine collects sensor data as input information from each of the sensors, such as sensors 210, 212, and 214 of monitor 110 for monitoring multiple patients (300). The routine then collects corresponding patient-specific data, such as demographic data, as further input information and outcome data, such as respiratory events for the corresponding patients, as output information (302). Based on the collected data, the routine determines a potential set of input factors to predict respiratory events (304). The routine then assigns weights to these input factors (306). The routine then attempts to predict the output respiratory events based on these weighted input factors (308). This routine then evaluates the accuracy of the prediction (310). If the accuracy does not meet the desired level ("no" in 312), this routine adjusts the weights (314) and returns to the prediction step (308). If the accuracy meets the desired level ("yes" in 312), this routine stores its weights (316), and the resulting model can be deployed to provide analysis based on input sensor signals from a monitor such as monitor 110.

[0049] In this way, the neural network in this embodiment may be provided with respiratory-related data collected from each patient by a monitor such as monitor 110. In addition, patient-specific data may be collected from queries made on a patient computing device such as portable device 112 or imported from an electronic medical record database. Further information may be stored based on the data collected from monitors such as monitor 110. In addition, patient-specific data about other patients, such as demographic information, medical history, and genetic structure, may be provided to the neural network.

[0050] This sensor information can be processed by a neural network capable of determining patterns based on the received sensor data. In addition, other factors may be provided to this model. Furthermore, the neural network may determine patterns based on data relating to the patient's demographics regarding respiratory illness, disease, or disorder, such as geographical location, weather, medical history, and environmental factors. Additionally, the neural network may determine patterns indicating the effects of medication and treatment on the frequency and severity of respiratory events.

[0051] Once the neural network establishes patterns and creates a model, the data collected by the monitor 110, along with other information such as the patient's location data and patient-specific data, can be processed by the neural network. Thus, the neural network can provide a model that, based on multiple types of data, determines the symptoms of respiratory illness, disease, or disorder and predicts respiratory events. This output data can be used by healthcare professionals, the patient's family, or the patient themselves as guidance for preventative measures or treatment. For example, an application could use this output data to create a report highlighting high-risk factors for respiratory events in a particular patient. Such a report could be sent to an external portable device 112 or communicated to the patient by other means.

[0052] For example, a neural network may determine that a particular environment or location is likely to exacerbate a respiratory illness, disease, or disorder, or to trigger a respiratory event. For instance, suppose a patient is moving to a new location. Upon arrival at the destination, an associated external portable device 112 may send location data to the server 114 for input to the neural network. The neural network may then determine that a respiratory event is likely to occur, based on the fact that similar patients have experienced similar events in that region and under similar conditions. This model can be constantly updated with new input data from monitors such as monitor 110 and other sources, as well as with the respiratory symptoms that occur. Therefore, increased use of the analysis platform 252 can lead to improved accuracy of the model.

[0053] Figure 4 shows an example routine for data collection and analysis in the system shown in Figure 2. This routine first collects sensor data from monitor 110 (400). The collected sensor data may be in summary form, such as audio signals of lung sounds over time, heart rate over time, or respiratory rate over time. Further data is derived from one or more sensor outputs, such as actimetry, impedance plethysmography, or temperature. This routine collects patient-specific data from a medical record database (402). This routine then collects relevant environmental data such as humidity, altitude, and pollen count (404). Such environmental data may be obtained from a database or sensors located in either monitor 110 or portable device 112.

[0054] This related data is then input into a respiratory disease model (406). This model evaluates this related data according to the weights determined by the machine learning process in Figure 3. This model outputs a risk assessment of respiratory events (408). This routine then determines whether the risk assessment exceeds a predetermined threshold (410). If the risk assessment does not exceed the predetermined threshold ("No" in 410), this routine continues to collect data (400).

[0055] If the risk assessment exceeds a predetermined threshold ("yes" in 410), i.e., if a respiratory event is predicted, this routine stores the anomalous data that formed the basis of the analysis leading to that prediction (412). This anomalous data may be forwarded to healthcare professionals or other applications for further analysis or action. This anomalous data may also be added to the patient's health record. The routine then initiates corrective action (414). Corrective action may include alerts to the patient or their family, or to healthcare professionals.

[0056] The flowcharts in Figures 3 and 4 illustrate an example of machine-readable instructions for collecting and analyzing data to predict respiratory events. In this example, the machine-readable instructions include an algorithm executed by: (a) a processor, (b) a controller, and / or (c) one or more other suitable processing devices. The algorithm may be embedded in software stored on a tangible medium (e.g., flash memory, CD-ROM, floppy disk, hard drive, digital video (versatile) disk (DVD), or other memory device). However, those skilled in the art will understand that the entire algorithm and / or parts thereof may be executed by a device other than a processor and / or embedded in firmware or dedicated hardware in a well-known manner (e.g., this may be executed by application-specific integrated circuits [ASICs], programmable logic devices [PLDs], field-programmable logic devices [FPLDs], field-programmable gate arrays [FPGAs], or discrete logic). For example, any or all of the interface components may be executed by software, hardware, and / or firmware. Furthermore, some or all of the machine-readable instructions shown in the flowchart may be executed manually. In addition, although the exemplary algorithm is described with reference to the flowcharts shown in Figures 3 and 4, those skilled in the art will readily understand that many other methods may be used to execute the exemplary machine-readable instructions. For example, the order in which the blocks are executed may be changed and / or some of the described blocks may be modified, removed, or combined.

[0057] Figure 5A shows example waveforms from monitor 110 based on the outputs of various sensors 210, 212, and 214 in Figure 2, illustrating waveforms that can be used by an algorithm to predict respiratory events such as the onset of a severe asthma attack. The data shown in the waveforms of Figure 5A is an example of predicting a respiratory event based on multiple different sensor data. Figure 5A shows an initial lung voice waveform 500, an initial heart rate waveform 510, and an initial respiratory waveform 520. The initial output waveforms 500, 510, and 520 can be used in combination by the routine described above to determine the symptoms of a respiratory disease, illness, or disorder. The waveform data from the outputs of sensors 210, 212, and 214 is stored in monitor 110 so that an external client device, such as a portable device 112, can retrieve it, and the portable device 112 then transmits the data to a server, such as server 114, which performs an analysis routine.

[0058] In this embodiment, the initial lung voice waveform 500 shows peaks 502 and 504 indicating wheezing from the lungs. The later lung voice waveform 530 shows a lack of voice signal, suggesting the possibility of a "silent chest" indicating a severe asthma attack. The initial heart rate waveform 510 shows a relatively short, consistent peak. In contrast, the later heart rate waveform 540 shows a large pulsation and large heart rate variability, indicating high sympathetic nervous system activity, an indicator of stress due to a severe asthma attack. The initial respiratory waveform 520 shows relatively small variation in the magnitude between peaks. In contrast, the later respiratory waveform 550 shows large variation between large peaks, indicating that the patient is having difficulty breathing due to narrowed airways in the lungs. The combination of data from the later waveforms 530, 540, and 550 may allow the algorithm to more accurately predict the onset of an asthma attack. This data may also enable the determination of the severity of the attack, allowing for more advanced responses.

[0059] Figure 5B shows an example of an audio waveform 560. As described above, this learning algorithm can correlate various signals to predict respiratory events. For example, this learning algorithm may determine that specific signatures 562 and 564 represent wheezing and coughing, respectively. Signatures 562 and 564 may correlate with symptoms of respiratory distress. Therefore, this algorithm can also predict respiratory events using only a single type of data, or by combining a single type of data with other different types of data.

[0060] Other analyses may also be performed to measure respiratory rate and vital capacity. For example, vital capacity can be correlated with impedance measurements. Parameters can be determined from flow-volume curves plotted by diagramming respiratory flow rate against vital capacity, as detailed below.

[0061] Figure 5C is a graph showing an example of acquired signal data including motion artifacts derived from data analyzed from the continuous monitoring device 110. In this embodiment, impedance data 570 is acquired from the respiratory sensor 214 in Figure 2. The impedance data 570 may be processed to remove motion artifacts generated by motion detected by an accelerometer such as the accelerometer 218. A particular peak 572 indicates motion that can be ignored in the analysis of the impedance data 570.

[0062] Figure 5D is a graph illustrating how cardiogenic noise is removed from data analyzed from the continuous monitoring device 110. In this embodiment, impedance data acquired from the sensor 214 in Figure 2 is graphically represented as trace 580. This impedance data can be processed to remove noise generated by cardiac activity detected by an ECG sensor such as the heart rate sensor 212. In this way, specific peaks in the impedance waveform 580 can be filtered into a modified trace 582 to minimize cardiogenic noise detected by the heart rate sensor 212. In one implementation, the R peak from the ECG sensor can be used as a trigger.

[0063] Figure 6 is a block diagram of the data flow in a system 600 for monitoring respiratory diseases, illnesses, or disorders in patients such as patient 100. As shown in Figure 6, data from monitor 110 is collected by an application running on a portable device 112. Further patient-specific medical or demographic information may be manually entered into the portable device 112 by the patient or their family 120. Such information may also be obtained from a medical record database. As described above, the portable device 112 can provide information based on the collected data to the patient or their family through various interfaces.

[0064] The portable device 112 can directly transmit data collected from the monitor 110 and / or transmit analytical data via a network such as the internet or the cloud to an analytical platform running on a server such as the server 114. As described above, this analytical platform can provide predictive analytical data on respiratory diseases, illnesses, or disorders, and respiratory events. This output can be in the form of a data report that can be sent to the healthcare provider system 610. The healthcare provider system 610 can provide further insights directly to the patient or their family, or to healthcare professionals 620. In this embodiment, healthcare professionals 620 can prescribe preventive medications from a supply system 630 that can also ship preventive medications, such as anti-inflammatory drugs, to the patient 100, in addition to therapeutic devices such as inhalers.

[0065] Several interfaces may be displayed on the patient device 112. These interfaces may display determined symptoms and risk assessments for respiratory events. For example, one interface may display a traffic light system, where green indicates normal risk, orange indicates increased risk, and red indicates high risk, based on collected data. In this way, example interfaces can provide information in an easy-to-understand manner and reassure the family of patient 100. Other interfaces may allow the patient or their family to contact a healthcare professional or send analyzed data to the healthcare professional.

[0066] Figure 7 is a block diagram of an example healthcare system 800 for acquiring data from a patient having a monitor attached, such as the monitor 110 in Figure 1. The healthcare system 800 includes a data server 114, an electronic medical record (EMR) server 814, a health or home healthcare provider (HCP) server 816, an external portable device 112, and the monitor 110 in Figure 1. In this embodiment, the portable device 112 and the monitor 110 coexist with the patient 100. In system 800, all of these entities are connected to a wide area network 140 (e.g., the Internet) and are configured to communicate with each other via a wide area network 830. The connection to the wide area network 830 may be wired or wireless. The EMR server 814, the HCP server 816, and the data server 114 may all run on separate computing devices in different locations, or any partial combination of two or more of these entities may run together on the same computing device.

[0067] The portable device 112 may be a personal computer, smartphone, tablet computer, or other device. The portable device 112 is configured to mediate between the patient 100 and the remote entity of the system 800 via the wide-area network 830. In the embodiment shown in Figure 7, this mediation is achieved by a software application program or application 240 running on the portable device 112. The patient program 240 may be a dedicated application referred to as the “patient app,” or it may be a web browser that interacts with a website provided by a health provider or home healthcare provider. Alternatively, the monitor 110 may communicate with the portable device 112 via a local wired network or a wireless network (not shown) based on a protocol such as Bluetooth®. The system 800 may include other patients 820 who provide data through their respective monitors 822 and portable devices 824. All patients within the system 800 may be managed by the data server 114.

[0068] As described above, data from the monitor 110 and / or the portable device 112 may be collected via the analysis platform 252 on the data server 114 to predict respiratory events. As previously stated, family members such as parent 120 may receive alerts about patient 100 via a network-connected wearable alert device 122 similar to the portable device 112. Alternatively, family members 120 may wear the alert device 122 to receive alerts from the portable device 112 or the data server 114. The analysis platform 252 may provide analysis of the collected data using the routine in Figure 4 to determine symptoms and predict respiratory events. Further data may be collected from the monitor 110 for other purposes, such as tracking the effectiveness of preventive measures or treatments, or tracking sleep quality, anxiety, and stress. A combination of physiological signals from multiple sensors mounted on the monitor 110, such as respiratory rate, heart rate, and body position, can be used to detect sleep / wakefulness and classify sleep stages. These physiological signals can be further used to detect apnea and hypopnea, which can help in the diagnosis of sleep-disordered breathing. ECG signals from ECG sensors such as the heart rate sensor 212 can be further used to monitor sympathetic and parasympathetic nervous system responses through frequency analysis of heart rate variability (HRV). HRV is a promising biomarker for measuring mental resilience and is an indicator of flexibility and the ability to adapt to stress.

[0069] Such data can be transmitted to the data server 114 by either the monitor 110 or the portable device 112. The data server 114 can also run the machine learning module 254 to further refine the model for correlating the data with respiratory events and improve the accuracy of the predictions on the analysis platform 252.

[0070] In this embodiment, the monitor 110 is configured to transmit physiological data obtained from continuous monitoring of various respiratory-related sensors to a portable device 112 via a wireless protocol, which receives the data as part of the patient program 240. The portable device 112 then transmits the data to the data server 114 according to a pull-or-push model. The data server 114 may receive the physiological data from the portable device 112 according to a "pull" model, thereby causing the portable device 112 to transmit the physiological data in response to a query from the data server 114. Alternatively, the data server 114 may receive the physiological data according to a "push" model, causing the portable device 112 to transmit the physiological data to the data server 114 as soon as the physiological data becomes available after a predetermined period. The data server 114 may access a database, such as database 250, to store the collected and analyzed data.

[0071] Data received from the portable device 112 is stored and indexed by the data server 114 so that it can be distinguished from physiological data collected from any other patient 820 in the system 800 by being uniquely associated with patient 100. The data server 114 may be configured to calculate summary data from data received from the monitor 110. The data server 114 may also be configured to receive data from the portable device 112 (e.g., data entered by patient 100 or the patient's family, behavioral data about the patient, or summary data).

[0072] The EMR server 814 contains electronic medical records (EMRs) (i.e., both EMRs specific to patient 100 and comprehensive EMRs for a larger population of patients with similar conditions to patient 100). EMRs, also known as electronic health records (EHRs), typically contain a patient's medical history (e.g., previous condition, treatment, complications, and current condition). The EMR server 814 may be located, for example, in the hospital where patient 100 received previous treatment. The EMR server 814 is configured to send EMR data to the data server 114, possibly in response to queries received from the data server 114.

[0073] In this example, the HCP server 816 is associated with a health / home healthcare provider (which could be an individual healthcare professional or organization) responsible for the treatment and care of patient 100, for example, respiratory therapy. The HCP may also be called a DME or HME (National / Home Medical Equipment Provider). The HCP server 816 may host a process 854, which is described in more detail below. One function of the HCP server process 854 is to send data related to patient 100 to the data server 114 in response to receiving queries from the data server 114.

[0074] In some implementations, the data server 114 is configured to communicate with the HCP server 816 to trigger notifications or action recommendations to HCP agents (e.g., nurses) or to support various reporting. Details of the actions performed are stored by the data server 114 as part of the engagement data. The HCP server 816 hosts the HCP server process 854, which communicates with the analysis platform 252 and the patient program 240.

[0075] For example, HCP Server Process 854 may include monitoring patients using compliance rules that specify the required inhaler usage over a compliance period, such as 30 days, and the minimum number of doses, such as four, within a minimum of 21 days, within that compliance period, regarding the use of therapeutic drugs or devices such as inhalers. In post-processing of summary data, it may be determined whether recent figures represent a compliant session by comparing the usage data with the minimum duration from the compliance rules. The results of such post-processing are referred to as “compliance data.” Such compliance data may be used when healthcare providers individually tailor treatments, which may include inhalers and other devices. Other stakeholders (e.g., payers) may use compliance data to determine whether reimbursement is possible for a patient. HCP Server Process 854 may have other health management functions, such as determining overall drug use based on data collection from a large number of patients. For payers, compliance data can help support patients with phenotypic mismatches and recommend the use of alternative therapies, such as biologics.

[0076] As is understood, the data in data server 114, EMR server 814, and HCP server 816 is often sensitive data related to patient 100. Typically, permission to send sensitive data to another party is often required from patient 100 or a member of the patient's family 120. Such permission may be required for data transfer between servers 114, 814, and 816 (provided such servers are operated by different entities).

[0077] Continuous monitoring in the system shown in Figure 7 can be used for various respiratory disorders, including asthma, COPD, cystic fibrosis, and bronchiectasis. However, the above principles should be understood as not being limited to such applications.

[0078] Figure 8A is a perspective view of a patch-type monitor example 900 that can be used as the monitor 110 shown in Figure 1. Figure 8B is a circuit diagram of the monitoring device example 900. Figure 8C is a top perspective view of the internal components of the monitoring device example 900. Figure 8D is a bottom perspective view of the internal components of the monitoring device example 900. The monitoring device 900 has the same function as the monitor 110 in that it collects physiological data signals over time from the patient and sends that data to a portable device such as the portable device 112 in Figure 1. In this way, the monitor example 900 collects cardiopulmonary signals from the patient's chest and stores them in onboard memory. The stored data can be downloaded from that memory to a smartphone / tablet via Bluetooth®.

[0079] The monitoring device 900 includes a housing 910 having an upper surface 912 and a lower surface 914. In this embodiment, the housing 910 is a silicone shell casing, but other suitable flexible conforming materials that flex with skin movement may also be used. In this embodiment, the housing 910 is 90 mm long and 20 mm wide, but other suitable dimensions and shapes may also be used for this housing. As described later, the lower surface 914 is a contact surface attached to a layer 918 having an adhesive applied to the lower surface 914. The layer 918 also has an adhesive on its lower surface, configured to attach the layer 918 to the patient. As described below, the layer 918 is part of an adhesive accessory that may be used to attach the monitor housing 910 to the patient's chest in one implementation of this technology. The monitor 900 is envisioned to be mounted horizontally on the upper center of the patient's chest, but other orientations such as 45 degrees to the horizontal, or other locations such as the upper left or upper right side of the chest, or the ribs under the right or left armpit, are also envisioned. The upper surface 912 includes a cylindrical battery housing 916.

[0080] Figure 8B shows the circuit board 920 housed in the housing 910. The circuit board 920 includes all the electronic components described herein, such as sensors, memory, transceivers, microprocessors, and signal processors. Traces 922 are attached to annular electrode pads 930, 932, 934, and 936 formed on the bottom surface 914 of the housing 910. In one mounting configuration, the bottom surface 914 is coated with adhesive to hold the monitoring device 900 in place of skin. The four electrode pads 930, 932, 934, and 936 are connected to the skin through hydrogel patches in the adhesive. The battery housing 916 holds a coin cell battery 938 mounted on top of the circuit board 920, as shown in Figure 8C. In this embodiment, the battery 938 is a non-rechargeable coin cell battery (e.g., a CR-2032 battery). Of course, other power sources, such as rechargeable batteries, can also be used to power the monitor 900.

[0081] Figure 9 is a block diagram of the electronic components of an example monitoring device 900. The monitoring device 900 includes a microprocessor 960, two writable memories 962 and 964, a Bluetooth® transceiver / antenna 966, and a signal processor circuit 968. The monitor 900 further includes an electrocardiogram (ECG) sensor 970, an impedance sensor 972, an accelerometer 974, and a gyroscope 976. The microprocessor 960 includes an internal persistent memory that stores firmware for executing routines. Both memories 962 and 964 store data collected by the monitor 900. In this embodiment, these memories can store at least 80 hours' worth of data. The collected data can be transmitted from the transceiver 966. Alternatively, a docking station having a connection to a computing device may be provided. This docking station includes data contacts for sending data to the computing device, in addition to contacts for charging a rechargeable battery.

[0082] In this embodiment, the signal processor circuit 968 is a Maxim Integrated ASIC (MAX30001) and measures the patient's ECG and chest impedance using signals received from four electrode pads 930, 932, 934, and 936. In this embodiment, an ECG sensor 970 is coupled to pads 932 and 934 to determine the voltage signal for the ECG. An impedance sensor 972 is coupled to pads 932 and 934 to measure the voltage signal and is coupled to pads 930 and 936 to determine the impedance by injecting a low-amplitude (e.g., 92 microamperes) high-frequency (e.g., 80 kHz) AC current. Pads 932 and 934 are time-multiplexed between the ECG sensor 970 and the impedance sensor 972.

[0083] Data signals from sensors 970 and 972, accelerometer 974, and gyroscope 976 are collected by microprocessor 960. From this data, physiological signals such as heart rate, respiratory rate, tidal volume, body position, and body orientation can be extracted. Data extraction or processing can be performed by firmware installed on monitor 900 or by an external device such as a mobile device or cloud-based server. As described herein, the collected data can be used in various processes to analyze the patient's health status. In this embodiment, the collected physiological data can be used to determine tidal volume, respiratory rate, minute ventilation, the flow-volume curve for (non-forced) resting breathing, and parameters that can be derived from this curve. The collected impedance values ​​can correlate with vital capacity. This respiratory flow rate can be obtained from the time derivative of vital capacity. Tidal volume parameters indicating airway obstruction can be derived from the flow-volume curve plotted by diagramming the respiratory flow rate against vital capacity.

[0084] Figure 12 shows two graphs representing the flow-volume curve and the tidal volume parameters that can be extracted from such curves. Trace 1200 in the upper graph represents the flow-volume curve plotted from data collected from a monitor 900 attached to the patient. Trace 1250 in the lower graph represents the respiratory flow rate versus time profile plotted from the same data used to plot the flow-volume curve 1200. The flow-volume curve 1200 is plotted from the expiratory portion of the respiratory cycle, and, following the convention of vital capacity measurement, positive values ​​of respiratory flow rate (abbreviated as "flow rate" on the vertical axis) represent expiratory flow rate. Similarly, profile 1250 also represents expiratory flow rate as positive on the vertical axis. Profile 1250 shows that the expiratory flow rate increases sharply, reaching a peak value labeled PTEF at the time labeled TPTEF, then slowly decreases toward zero, reaching zero at the expiratory time labeled TE. The dashed line 1260 with slope S linearly approximates the decrease in expiratory flow rate after the peak. The flow-volume curve 1200 extends counterclockwise, starting at an extreme value where vital capacity is equal to the expiratory ventilation volume VE, and quickly reaching the peak value of expiratory flow rate PTEF. At this point, vital capacity has decreased to VPTEF, and then gradually decreases until the end of exhalation, which is defined as when vital capacity is zero.

[0085] Ventilation parameters can be extracted from traces 1200 and 1250. Three examples are shown below. Time to peak expiratory flow rate during exhalation (TPTEF / TE) Volume of peak expiratory flow rate relative to expiratory ventilation (VPTEF / VE) Slope (S) of the expiratory flow rate curve after the peak.

[0086] The ventilation parameters in the three examples above indicate the patient's respiratory disease, particularly the state of airway obstruction. In each of the ventilation parameter examples above, an increase in value is associated with bronchiectasis, and a decrease in value is associated with bronchial obstruction. Other parameters, such as vital capacity, can also be derived from this physiological data. Parameters that can distinguish between upper airway obstruction and lower airway obstruction, which cannot be done with conventional vital capacity measurements, can be derived.

[0087] Figure 10A is a perspective view of the adhesive accessory component example 1000 for attaching the monitoring device example 900 to a patient before attachment. Figure 10B shows the sequence of steps for attaching the adhesive in the adhesive accessory component 1000 to the monitoring device 900 before attachment to the patient's skin. The adhesive accessory component 1000 includes a protective bottom layer 1010 supporting an intermediate layer 1012 (shown in Figure 10B). The intermediate layer 1012 has four hydrogels corresponding to the positions of electrode pads 930, 932, 934, and 936 on the bottom surface 914 of the monitor 900 when properly attached to the intermediate layer 1012. An upper protective layer 1014, comprising a skirt portion 1018 and a cutout portion 1022 shaped like the monitor 900, covers the intermediate layer 1012.

[0088] As shown in step 1020 of the first step in Figure 10B, the cutout 1022 of the upper layer 1014 is peeled off to expose the intermediate layer 1012 having the hydrogel 1016 and the surrounding adhesive. The cutout 1022 is shaped like the monitor 900, leaving the skirt portion 1018 of the upper layer 1014 in place. As shown in step 1030 of Figure 10B, which is a lower view of the adhesive accessory 1000, the monitor 900 is placed where the cutout 1022 was removed and attached to the intermediate layer 1012 by adhesive. As a result, the hydrogel 1016 on the intermediate layer 1012 is in contact with the electrode pads 930, 932, 934, and 936 on the bottom surface 914 of the monitor 900 and is visible through the translucent bottom layer 1010. The bottom layer 1010 is then removed from the intermediate layer 1012 in step 1040, exposing the intermediate layer 1012 having the hydrogel 1016 and the surrounding adhesive. The intermediate layer 1012, with the exposed adhesive and hydrogel 1016, is then attached to the appropriate location on the patient's chest via the adhesive so that the hydrogel 1016, and thus the electrode pads 930, 932, 934, and 936, make electrical contact with the skin. After the intermediate layer 1012 is properly attached, the skirt portion 1018 of the upper layer 1014 may be peeled off, leaving the monitor 900 and the intermediate layer 1012, which can be identified as layer 918 in Figure 8A, on the skin.

[0089] Monitor 900 may also include other sensors, such as a voice sensor. Monitor 900 can be used in place of Monitor 110 in the data acquisition and analysis processes performed in the health management system 800 shown in Figure 7. An example processing flow for data acquisition from Monitor 900 for predictive analytics is shown in Figure 11. Data is collected by sampling and correlating readings from the ECG sensor 970, impedance sensor 972, accelerometer 974, and gyroscope 976. This data is stored in Monitor 900 and repeatedly transmitted to an external device, such as a portable device 112.

[0090] The collected data can be analyzed to create analytical data for predictive analysis. As shown in Figure 11, impedance data from the impedance sensor 972 can be used to determine respiratory rate, tidal volume, respiratory flow rate, and inspiration / expiration. ECG data from the ECG sensor 970 can be used to determine the patient's heart rate, heart rate variability, cardiac coupling, and movement. Accelerometer data from the accelerometer 974 can be used to determine body position and body movement. Data from the gyroscope 976 can be used to determine body orientation.

[0091] Analysis data from sensors mounted on the monitor 900, and optionally additional data from external sources, can be classified into one set of physiological data 1110, one set of activity data 1112, and one set of sleep data 1114. The classified data is input to a feature extraction module 1120 that derives statistical features such as mean, median, percentile, and standard deviation from this data. This set of features is then input to a machine learning classifier 1130 that outputs an event prediction 1140. As described above with respect to Figure 4, the event prediction 1140 may be the result of comparing a risk assessment with a predetermined threshold.

[0092] The event prediction 1140 may be a binary yes / no indicator (predicted / unpredicted event), or it may be graded based on the severity of the predicted respiratory event, such as mild, moderate, or severe. In one implementation, the event prediction 1140 may be converted into various zones that may lead to various corrective actions, such as "time to take medication," "seeking medical advice from a healthcare professional," or "going to the emergency room."

[0093] Further output information may include personalized medication reminders and dosage adjustments based on physiological data. Such reminders and adjustments based on a personalized, dynamic drug treatment plan can be determined based on continuous monitoring of the patient's health status, such as the system shown in Figure 1. Other functions for data collection include: In particular, to support clinicians in diagnosing and managing asthma in children under 5 years old who are unable to undergo regular lung capacity testing, To evaluate the effectiveness of medication in reliably controlling the disease, or the need to gradually increase or decrease the dosage and type of medication, This may include helping to reduce the readmission rate of patients who have been discharged after acute asthma.

[0094] Traditional drug treatment plans for asthma consist of two elements: a preventive medication element and an emergency medication element. The preventive medication element involves prescribing a fixed amount (e.g., one packet) of preventive medication (e.g., anti-inflammatory drugs) to be taken at regular intervals (e.g., once a day) regardless of symptoms. The emergency medication element involves taking a fixed amount (e.g., one packet) when symptoms such as shortness of breath or wheezing occur, and then, if the symptoms do not improve, prescribing emergency medication (e.g., bronchodilators) to be taken at regular intervals (e.g., every four hours). In this plan, if symptoms do not improve after taking emergency medication a certain number of times, the patient should consult a doctor or hospital.

[0095] An example of a personalized physiological signal might be readings from specific sensors, such as the lungs, heart, or exercise sensors, acquired from other sensors in the monitor 110 in Figure 1, or from other monitors attached to the patient 100. This data can be analyzed, as described above, to provide disease management and risk assessment for the patient. The determined risk assessment can be used by a medication rule engine and dosage calculator run by the data server 114 to provide personalized treatment to the patient. Such sensor readings may or may not be linked to data indicating administration status, collected from connected drug delivery devices, such as inhalers. In a similar manner, patient activity, such as exercise or other physical activity, can also be monitored. This information can be used, for example, to assess whether a respiratory illness is limiting the patient's activity level and whether medication needs to be increased to bring the patient to a normal activity level.

[0096] Examples of medication rule engines and dosage calculators may be applications run by a computing device such as an external portable device 112 or server 114 in Figure 1. The medication rule engine may include simple reminders and instructions for the patient or their family to check their medication management status. Alternatively, the medication rule engine may use sensor data to determine if medication was not taken or was not taken properly. In such embodiments, this can be determined by comparing the respiratory profile with the inhaler intake to confirm that the inhaler click was synchronized with the inhalation. The effectiveness of medication can be measured by comparing pre-medication physiological data with post-medication physiological data. The medication rule engine may instruct an increase or decrease in the frequency of administration based on data obtained from sensors indicating the effect or lack thereof of the medication. Similarly, the medication rule engine may instruct an increase or decrease in dosage and / or type of medication (e.g., preventive medicine, emergency medicine, another medicine, etc.) to address the effect or lack thereof of the current dosage.

[0097] Instructions to the patient or their family may be given with or without notification from the healthcare provider. For example, over-the-counter (OTC) or prescription drugs may be supervised and approved according to a medication rule engine that automatically adjusts the dosage within certain limits without intervention from the healthcare provider. This drug may be supervised by a device that provides any appropriate form of drug delivery, such as an inhaler, tablet, or drug delivery patch. The medication rule engine may also incorporate symptoms reported by the patient, such as shortness of breath, wheezing, cough, decreased activity, or nocturnal awakenings. In this embodiment, this medication and medication rule engine may only apply to respiratory diseases such as asthma and COPD, but other conditions may have other medication rule engines.

[0098] In contrast to current generic and static plans, the same process can be used in combination with other types of routines and plans that can be personalized. Examples of such plans include personalized dynamic activity and exercise plans, personalized dynamic cognitive and behavioral plans, personalized dynamic food and nutrition plans, and personalized air exposure plans. Through iterative adjustments of these routines and plans, personalized dynamic optimization can be achieved. Aspects of patient treatment, health, and quality of life can be customized to the individual patient and adapted to the patient's and environmental conditions. The causes of deviations from a healthy state can also be analyzed. For example, a patient may have their own standards and an adaptive algorithm that learns individual thresholds for those standards. In this case, deviations from the patient's own standards may be a greater concern than deviations from age-specific healthy normals.

[0099] An example of an analysis module performed by the data server 114 in Figure 1 may also include public health factors in asthma suppression and exacerbation prediction algorithms. Because respiratory diseases such as asthma have regional and seasonal variations, public health factors can provide more accurate predictions. As explained with respect to the example in Figure 1, physiological signals of interest are collected to determine symptoms and the individual's risk of deviating from asthma suppression or experiencing exacerbations such as attacks. Processing may consider environmental conditions (such as air quality including pollutants and allergens) based on patient history / health records, such as any data on medication adherence captured through connected inhalers, and geographic / home location-related data for individual members of a general patient population obtained from third parties. Such analysis may include dynamically capturing local environmental data through indoor air quality monitors or from outdoor sensors.

[0100] The analysis of respiratory disease exacerbations may also consider public health factors that can be stored in the patient records of the 250 databases shown in Figure 2. Such factors may include social health determinants (such as risks to food and housing hazards, economic troubles, and stress at home) that are captured on an individual basis or calculated / estimated based on geographical / home location. In addition, seasonality can be used to further refine the respiratory analysis. For example, there are known periods of asthma surges, such as when schools reopen. This analysis can be used to pre-stratify patients in order to quantify risk based on the various data described above.

[0101] This specific analysis of a particular patient can be compared to an analysis of a general population or a specific cohort similar to that patient. For example, individual patients may be dynamically grouped with other patients who have similar socioeconomic and ethnic characteristics. Any historical or new data collected about others within that group can then be used to influence the prediction of respiratory events for the individual patient. For example, shared EMR data, health data (signs and symptoms), and home addresses / zip codes of hospitalized patients may be used to determine similar patient groups and improve predictions.

[0102] Furthermore, the monitoring experience can be improved by providing incentives for both patients and their families to adhere to monitoring and related treatment practices. This can be achieved by gamifying the experience for both the patient and their family. For example, pediatric patients and their families may receive rewards such as points, badges, or money for using a monitoring device, such as monitor 110 in Figure 1. Such rewards may be earned for wearing the monitor, charging the monitor, or performing suggested treatment actions.

[0103] Children and parents can team up and compete against other teams to win prizes such as indoor air quality monitors. Such programs may involve other partners (ranging from governments to private companies and non-profit organizations) offering free or discounted services as incentives. These incentives do not have to be directly related to asthma and can be based on social health determinants such as free meals or counseling. For example, this gamified application could offer free meals at participating health food restaurants or allow patients to make donations when they complete treatment or adhere to daily routines such as exercise. A network of partners could also enable donations to welfare activities by allowing patients to adhere to their routines by wearing the Monitor 110. This system could provide insurance companies and HMEs with an incentive to underwrite patient populations. For example, when an insurance company / HME insures a patient population, a donation to a health-related charity or other welfare organization may be accounted for. Incentives for patients, their parents, or other entities such as insurance companies may change based on changes in social and environmental factors. For example, rewards may increase if the risk of non-compliance is high. For example, on a sunny day, a certain reward may be provided for engaging in outdoor activities when pollutants and allergens are low. On highly polluted days, when the risk of exacerbation is high, this reward may be reduced.

[0104] As used in this application, terms such as “component,” “module,” and “system” generally refer to computer-related entities that are either hardware (e.g., circuits), a combination of hardware and software, software, or entities relating to an operating machine having one or more specific functions. For example, a component may be, but is not limited to, a process executed on a processor (e.g., a digital signal processor), a processor, an object, an executable file, an execution thread, a program, and / or a computer. For example, both a controller and an application running on the controller may be components. One or more components may reside within a process and / or an execution thread, and some components may be localized on one computer or distributed across two or more computers. Furthermore, a “device” may take the form of specially designed hardware, generalized hardware specialized by the execution of software that enables the performance of a specific function, software stored on a computer-readable medium, or a combination thereof.

[0105] The terms used herein are intended solely to describe specific embodiments and are not intended to limit the invention. The singular forms “a,” “an,” and “the” used herein are intended to include the plural form unless otherwise evident from the context. Furthermore, the terms “include,” “have,” or their inflections are used in the embodiments for carrying out the invention and in the claims, and these terms are intended to be as comprehensive as the term “equipped with.”

[0106] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as those generally understood by those skilled in the art. Furthermore, terms defined in widely used dictionaries should be interpreted in accordance with their meaning in the context of the art in question, and not in an idealized or overly formal sense, unless explicitly defined herein.

[0107] While various embodiments of the present invention have been described above, they should be understood to be illustrative only and not limiting. Although the present invention has been illustrated and described in relation to one or more implementations, equivalent changes and modifications will occur or will be known to those skilled in the art in reading and understanding this specification and the accompanying drawings. In addition, certain features of the present invention may have been disclosed in relation to only one of several implementations, but such features may be combined with one or more other features of other implementations to be desirable and advantageous for any given or specific application. Therefore, the breadth and scope of the present invention should not be limited by any of the above embodiments. Rather, the scope of the present invention should be defined according to the following claims and their equivalents. Label list [Explanation of symbols]

[0108] 100 patients 110 Monitors 112 Portable Devices 114 Data Server 120 family members 122 Alert Devices 130 Environmental Sensors 200 controllers 202 Sensor Interface 204 Transceiver 206 memory 208 batteries 210 sensors 212 sensors 214 sensors 216 sensors 218 Accelerometer 230 CPU 232 GPS receivers 234 transceivers 236 memory 240 applications 242 data 250 databases 252 Analytics Platforms 254 Machine Learning Modules 300 steps 302 steps 304 steps 306 steps 308 steps 310 steps 312 steps 314 steps 316 steps 400 steps 402 402 406 steps 408 steps 410 steps 412 steps 414 steps 500 Early stage lung sound waveforms 502 Peak 510 Initial heart rate waveform 520 Initial stage respiratory waveform 530 Late-stage lung sound waveform 540 Late-stage heart rate waveform 550 Late-stage respiratory waveform 560 Audio Waveform Examples 562 Signature 570 data 572 Peak 580 traces 582 Trace 600 System 610 Healthcare Provider Systems 620 healthcare workers 630 Supply System 800 System 814 EMR Server 816 HCP Servers 820 patients 822 Each monitor 824 Portable Devices 830 Wide-area network 854 HCP server processes 900 monitors 910 cabinet 912 Top surface 914 Bottom surface 916 Battery Housing 918 layers 920 Circuit Board 922 Trace 930 Electrode Pads 932 Electrode Pads 934 Electrode Pads 936 Electrode Pads 938 Battery 960 microprocessor 962 memory 964 memory 966 Transceiver 968 Signal Processor Circuit 970 ECG sensor 972 Impedance Sensor 974 Accelerometer 976 Gyroscope 1000 Adhesive ancillary parts 1010 Bottom layer 1012 Middle Class 1014 Upper layer 1016 Hydrogel 1018 Skirt 1020 steps 1022 Cutout 1030 steps 1040 steps 1110 Physiological data 1112 Activity Data 1114 Sleep Data 1120 Feature Extraction Module 1130 Machine Learning Classifiers 1140 Event Predictions 1200 Flow-Volume Curve 1250 Profiles 1260 dashed line

Claims

1. A system for determining the onset of respiratory disease symptoms in a patient, A transceiver capable of receiving data from a monitor attached to a patient, wherein the monitor includes a plurality of sensors, each of which is configured to output physiological data relating to the patient's respiratory disease, and the transceiver capable of receiving data from a monitor attached to a patient, An analysis platform connected to the aforementioned transceiver, A system comprising: an analytical platform configured to analyze the physiological data in order to determine the occurrence of the symptoms of the respiratory disease.

2. The system according to claim 1, wherein the plurality of sensors include a heart rate sensor and a respiratory sensor.

3. The system according to any one of claims 1 to 2, further comprising a portable computing device capable of receiving the physiological data from the transceiver and transmitting the physiological data to the analysis platform.

4. The system according to any one of claims 1 to 3, wherein the analysis platform is further configured to analyze environmental data relating to the patient when determining the occurrence of the symptoms of the respiratory disease.

5. The system according to any one of claims 1 to 4, wherein the analysis platform is further configured to analyze demographic data relating to the patient when determining the occurrence of the symptoms of the respiratory disease.

6. The system according to claim 2, wherein the plurality of sensors further comprises accelerometers.

7. The system according to claim 6, wherein the plurality of sensors further comprises pressure sensors.

8. The system according to claim 7, wherein the symptom is shortness of breath.

9. The aforementioned analysis platform The respiratory effort determined from the pressure sensor and the accelerometer, The system according to claim 8, configured to determine shortness of breath using a combination of the respiratory rate determined from the respiratory sensor.

10. The system according to any one of claims 1 to 9, wherein the plurality of sensors include an audio sensor.

11. The system according to claim 10, wherein the analysis platform is further configured to distinguish between mild wheezing and other external signals based on data from the audio sensor.

12. The system according to any one of claims 1 to 11, wherein the analysis platform is executed on a remote server.

13. The system according to any one of claims 1 to 12, wherein the analysis platform is configured to apply a model to the physiological data in order to determine the occurrence of the symptoms of the respiratory disease.

14. The system according to claim 13, wherein the model is comprised of machine learning based on collected physiological data and respiratory disease outcome data.

15. The system according to any one of claims 1 to 14, wherein the analysis platform is configured to determine the occurrence of symptoms based on public health factors applicable to the patient.

16. The system according to claim 15, wherein the public health factors include social health determinants.

17. The system according to claim 16, wherein the analysis platform is further configured to estimate the social health determinants based on the geographical location of the patient's home.

18. The system according to claim 15, wherein the public health factors include data collected from other patients in a patient cohort similar to the patient.

19. The system according to any one of claims 1 to 18, wherein the analysis platform is further configured to analyze the physiological data to determine the risk assessment of the respiratory disease event in the patient.

20. The system according to claim 19, wherein the analysis platform is further configured to predict respiratory events by comparing the risk assessment with a threshold.

21. The system according to claim 20, wherein the analysis platform is further configured to initiate corrective action in response to the predicted respiratory event.

22. The system according to any one of claims 19 to 21, wherein the plurality of sensors include an impedance plethysmography sensor.

23. The aforementioned analysis platform Correlating the impedance measurements from the aforementioned impedance plethysmography sensor with lung capacity, To construct a flow-volume curve from the aforementioned lung capacity, Extracting one or more ventilation parameters from the aforementioned flow-volume curve, To derive feature quantities from the aforementioned ventilation parameters, The system according to claim 22, configured to determine the risk assessment by applying a model to the features in order to determine the risk assessment.

24. The system according to claim 23, wherein the plurality of sensors include an ECG sensor.

25. The system according to claim 24, wherein the analysis platform is further configured to remove noise generated by cardiac activity from the impedance measurements obtained by the ECG sensor.

26. The system according to any one of claims 23 to 25, wherein the plurality of sensors include accelerometers.

27. The system according to claim 26, wherein the analysis platform is further configured to remove motion artifacts from the impedance measurements by the accelerometer.

28. The one or more ventilation parameters mentioned above, Time to peak expiratory flow rate during exhalation, The volume of peak expiratory flow rate relative to expiratory ventilation, and A system according to any one of claims 23 to 27, selected from the group consisting of the slope of the exhalation flow curve after the peak.

29. The system according to any one of claims 23 to 28, wherein the model is comprised of machine learning based on collected physiological data and respiratory disease outcome data.

30. A continuous monitoring device that can be worn by a patient, A housing having a surface that can be attached to the patient, Multiple sensors, each configured to output physiological data relating to the patient's respiratory status, impairment, or disease, A memory configured to store the aforementioned physiological data, A monitoring device comprising a transceiver capable of transmitting the aforementioned physiological data to an external device.

31. The monitoring device according to claim 30, wherein the plurality of sensors include a heart rate sensor and a respiratory sensor.

32. The monitoring device according to claim 31, wherein the respiratory sensor is an impedance plethysmography sensor.

33. The monitoring device according to claim 32, further comprising a pair of electrode pads configured to sense the voltage between the electrode pads.

34. The monitoring device according to claim 33, wherein the heart rate sensor is connected to the pair of electrode pads.

35. The monitoring device according to any one of claims 33 to 34, wherein the impedance plethysmography sensor is connected to the pair of electrode pads.

36. The monitoring device according to claim 35, further comprising a second pair of electrode pads to which the impedance plethysmography sensor is connected for injecting a low-amplitude high-frequency current.

37. The monitoring device according to any one of claims 30 to 36, wherein the housing has a form factor of one of the group consisting of a patch, a wristband, a necklace, and a vest.

38. The monitoring device according to any one of claims 30 to 37, wherein the plurality of sensors include an audio sensor.

39. The monitoring device according to any one of claims 30 to 38, wherein the plurality of sensors include an accelerometer and a gyroscope.

40. The monitoring device according to any one of claims 30 to 39, wherein the plurality of sensors further include pressure sensors.

41. The monitoring device according to claim 30, wherein the housing is made from a flexible material.

42. A system for monitoring respiratory diseases in patients, A monitor that can be attached to the aforementioned patient, A plurality of sensors, each configured to output physiological data relating to the respiratory disease of the patient, A monitor wearable on the patient includes a first transceiver configured to transmit the physiological data, An external device including a second transceiver configured to receive the physiological data from the first transceiver, An analysis platform, which is connected to the second transceiver, A system for monitoring a patient's respiratory illness, comprising: an analysis platform configured to analyze the physiological data received from the second transceiver in order to determine the onset of symptoms of the respiratory illness.

43. The system according to claim 42, wherein the plurality of sensors include a heart rate sensor and a respiratory sensor.

44. The system according to any one of claims 42 to 43, wherein the external device is a portable computing device.

45. The system according to any one of claims 42 to 44, wherein the analysis platform is further configured to analyze environmental data relating to the patient when determining the occurrence of the symptoms of the respiratory disease.

46. The system according to any one of claims 42 to 45, wherein the analysis platform is further configured to analyze demographic data relating to the patient when determining the occurrence of the symptoms of the respiratory disease.

47. The system according to claim 43, wherein the plurality of sensors further comprises accelerometers.

48. The system according to claim 43, wherein the plurality of sensors further comprises pressure sensors.

49. The system according to claim 48, wherein the symptom is shortness of breath.

50. The aforementioned analysis platform The respiratory effort determined from the pressure sensor and the accelerometer, The system according to claim 49, configured to determine shortness of breath using a combination of the respiratory rate determined from the respiratory sensor.

51. The system according to any one of claims 42 to 50, wherein the plurality of sensors include an audio sensor.

52. The system according to claim 51, wherein the analysis platform is further configured to distinguish between mild wheezing and other external signals based on data from the audio sensor.

53. The system according to any one of claims 42 to 52, wherein the analysis platform is executed on a remote server.

54. The system according to any one of claims 42 to 53, wherein the analysis platform is configured to apply a model to the physiological data in order to determine the occurrence of the symptoms of the respiratory disease.

55. The system according to claim 54, wherein the model is comprised of machine learning based on collected physiological data and respiratory disease outcome data.

56. The system according to any one of claims 42 to 55, wherein the analysis platform is further configured to analyze the physiological data to determine the risk assessment of respiratory events of the respiratory disease.

57. The system according to claim 56, wherein the analysis platform is further configured to predict the respiratory event by comparing the risk assessment with a threshold.

58. The system according to claim 57, wherein the analysis platform is further configured to initiate corrective action in response to the predicted respiratory event.

59. The system according to any one of claims 56 to 58, wherein the plurality of sensors include an impedance plethysmography sensor.

60. The aforementioned analysis platform Correlating the impedance measurements from the aforementioned impedance plethysmography sensor with lung capacity, To construct a flow-volume curve from the aforementioned lung capacity, Extracting one or more ventilation parameters from the aforementioned flow-volume curve, To derive feature quantities from the aforementioned ventilation parameters, The system according to claim 59, configured to determine the risk assessment by applying a model to the features in order to determine the risk assessment.

61. The system according to claim 60, wherein the plurality of sensors include an ECG sensor.

62. The system according to claim 61, wherein the analysis platform is further configured to remove noise generated by cardiac activity from the impedance measurements obtained by the ECG sensor.

63. The system according to any one of claims 60 to 62, wherein the plurality of sensors include accelerometers.

64. The system according to claim 63, wherein the analysis platform is further configured to remove motion artifacts from the impedance measurements by the accelerometer.

65. The one or more ventilation parameters mentioned above, Time to peak expiratory flow rate during exhalation, The volume of peak expiratory flow rate relative to expiratory ventilation, and A system according to any one of claims 61 to 64, selected from the group consisting of the slope of the exhalation flow curve after the peak.

66. The system according to any one of claims 61 to 65, wherein the model is comprised of machine learning based on collected physiological data and respiratory disease outcome data.

67. The system according to any one of claims 56 to 66, further comprising a medication rule engine configured to modify the treatment plan for the respiratory disease based on the determined risk assessment.

68. The system according to claim 67, wherein the medication rule engine is configured to adjust the dosage of drugs that form part of the treatment plan.

69. The system according to claim 67, wherein the medication rule engine is configured to adjust the types of drugs that constitute part of the treatment plan.

70. The system according to any one of claims 56 to 69, wherein the analysis platform is further configured to issue alerts based on the risk assessment.

71. Upon receiving an alert issued from the aforementioned analysis platform, The system according to claim 70, further comprising an alert device configured to alert a person upon receiving the aforementioned alert.

72. The system according to claim 71, wherein the alert device is configured to wake the person when it receives the alert.

73. The system according to any one of claims 71 to 72, wherein the alert device is a wearable alert device.

74. A method for predicting respiratory disease events in patients, Collecting physiological data related to the respiratory disease of the patient from multiple sensors in a monitor attached to the patient, A method for predicting respiratory disease events in a patient, comprising applying a model for predicting respiratory disease events based on the physiological data collected from the plurality of sensors.

75. The method according to claim 74, wherein the plurality of sensors include a heart rate sensor and a respiratory sensor.

76. The method according to claim 75, wherein the plurality of sensors further comprise accelerometers.

77. The method according to claim 76, wherein the plurality of sensors further comprises a gyroscope.

78. The method according to any one of claims 74 to 77, wherein the model takes into account environmental data relating to the patient.

79. The method according to any one of claims 74 to 78, wherein the model takes into account demographic data relating to the patient.

80. The method according to any one of claims 74 to 79, wherein the model comprises machine learning based on collected physiological data and respiratory disease outcome data.

81. The method according to any one of claims 74 to 80, further comprising issuing an alert to an alert device when the aforementioned event is predicted, wherein the alert device is configured to draw the attention of a person.

82. The method according to any one of claims 74 to 81, wherein the model includes input information of public health factors corresponding to the patient.

83. The method according to claim 82, wherein the public health factors include social health determinants.

84. The method according to claim 83, further comprising estimating the social health determinants based on the geographical location of the patient's home.

85. The method according to any one of claims 82 to 84, wherein the public health factors include data collected from another patient in a patient cohort similar to the patient.

86. The method according to any one of claims 74 to 85, further comprising initiating a corrective action in response to a predicted respiratory event.

87. The method according to any one of claims 74 to 86, wherein the plurality of sensors include an impedance plethysmography sensor.

88. Correlating the impedance measurements from the aforementioned impedance plethysmography sensor with lung capacity, To construct a flow-volume curve from the aforementioned lung capacity, Extracting one or more ventilation parameters from the aforementioned flow-volume curve, To derive feature quantities from the aforementioned ventilation parameters, The method according to claim 87, further comprising applying a model to features in order to determine the risk assessment, and determining the risk assessment by means of the model.

89. The method according to claim 88, wherein the plurality of sensors include an ECG sensor.

90. The method according to claim 89, further comprising removing noise generated by cardiac activity from the impedance measurement value by the ECG sensor.

91. The method according to any one of claims 88 to 90, wherein the plurality of sensors include accelerometers.

92. The method according to claim 91, further comprising removing motion artifacts from the impedance measurement value by the accelerometer.

93. The one or more ventilation parameters mentioned above, Time to peak expiratory flow rate during exhalation, The volume of peak expiratory flow rate relative to expiratory ventilation, and The method according to any one of claims 88 to 92, selected from the group consisting of the slope of the expiratory flow rate curve after the peak.

94. A system for monitoring respiratory diseases in patients, A monitor that can be attached to the aforementioned patient, A plurality of sensors, each configured to output physiological data relating to the respiratory disease of the patient, A monitor wearable on the patient includes a first transceiver configured to transmit the physiological data, An external device including a second transceiver configured to receive the physiological data from the first transceiver, An analysis platform, which is connected to the second transceiver, A system comprising: an analysis platform configured to analyze the physiological data received from the second transceiver in order to predict the events of the respiratory disease.

95. The system according to claim 94, wherein the plurality of sensors include a heart rate sensor and a respiratory sensor.

96. The system according to claim 95, wherein the plurality of sensors further comprises accelerometers.

97. The system according to claim 96, wherein the plurality of sensors further comprises a gyroscope.

98. The model is the system according to any one of claims 94 to 97, which takes into account environmental data relating to the patient.

99. The model is the system according to any one of claims 94 to 98, which takes into account demographic data relating to the patient.

100. The system according to any one of claims 94 to 99, wherein the model is comprised of machine learning based on collected physiological data and respiratory disease outcome data.

101. The system according to any one of claims 94 to 100, wherein the analysis platform is further configured to issue an alert to an alert device when it predicts the event, and the alert device is configured to draw the attention of a person.

102. The system according to any one of claims 94 to 101, wherein the model includes input information of public health factors corresponding to the patient.

103. The system according to claim 102, wherein the public health factors include social health determinants.

104. The system according to claim 103, wherein the analysis platform is further configured to estimate the social health determinants based on the geographical location of the patient's home.

105. The system according to any one of claims 102 to 104, wherein the public health factors include data collected from other patients in a patient cohort similar to the patient.

106. The system according to any one of claims 94 to 105, wherein the analysis platform is further configured to initiate corrective action in response to the predicted respiratory event.

107. The system according to any one of claims 94 to 106, wherein the plurality of sensors include an impedance plethysmography sensor.

108. The aforementioned analysis platform Correlating the impedance measurements from the aforementioned impedance plethysmography sensor with lung capacity, To construct a flow-volume curve from the aforementioned lung capacity, Extracting one or more ventilation parameters from the aforementioned flow-volume curve, To derive feature quantities from the aforementioned ventilation parameters, The system according to claim 107, configured to determine the risk assessment by applying a model to features in order to determine the risk assessment.

109. The system according to claim 108, wherein the plurality of sensors include an ECG sensor.

110. The system according to claim 109, wherein the analysis platform is further configured to remove noise generated by cardiac activity from the impedance measurements obtained by the ECG sensor.

111. The system according to any one of claims 108 to 110, wherein the plurality of sensors include accelerometers.

112. The system according to claim 111, wherein the analysis platform is further configured to remove motion artifacts from the impedance measurements by the accelerometer.

113. The one or more ventilation parameters mentioned above, Time to peak expiratory flow rate during exhalation, The volume of peak expiratory flow rate relative to expiratory ventilation, and A system according to any one of claims 108 to 112, selected from the group consisting of the slope of the exhalation flow curve after the peak.

114. A device for monitoring respiratory diseases in patients, Multiple means for generating physiological data relating to the respiratory disease of the patient, Means for transmitting the aforementioned physiological data, An apparatus comprising means for analyzing the physiological data received from the means for transmitting in order to predict the events of the respiratory disease.

Images