Detection of User Infection Using Wearable Sensor Data

Abstract

A method for reporting a user's risk of infection, comprising: (i) receiving user cardiac data from sensors of a wearable device worn by the user; (ii) determining, for a first period, a user's heart rate variability phase acceleration value from the received user cardiac data by a heart rate variability phase acceleration algorithm; (iii) determining, for the first period, a user's heart rate variability phase deceleration value from the received user cardiac data by a heart rate variability phase deceleration algorithm; (iv) using the user's heart rate variability phase acceleration value and the user's heart rate variability phase deceleration value to determine, for the first period, the user's current infection risk by a trained infection risk prediction algorithm that uses the user's heart rate variability phase deceleration value; and (v) providing the determined user's current infection risk via the user's interface.

Description

Technical Field

[0001] This patent application claims priority under 35 U.S.C. § 119(e) to U.S. Provisional Application No. 63 / 351,516, filed on June 13, 2022, the content of which is incorporated herein by reference.

Background Art

[0002] The present disclosure generally relates to methods and systems for detecting, reporting, and / or treating individual infections detected by wearable device sensor data.

[0003] The detection of infections is an important aspect of personal healthcare. Early detection of infections leads to both improved treatment and improved public health from an epidemiological perspective. However, it is particularly difficult to detect an individual's infection outside of a healthcare facility, especially if the individual is not experiencing significant symptoms or, otherwise, is not aware that they may have an infectious disease. There are many ways for users to actively monitor their own health and detect infections, but passive monitoring or detection systems that detect infections without requiring active input from the user would significantly improve early infection detection and public health surveillance, among other scenarios, including nosocomial infections due to hospital staff infections or outbreaks on military aircraft carriers, but not limited to these.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Accordingly, there is a continuing need for methods and systems for detecting patient infections or the risk of infection using various data inputs, particularly via passive monitoring.

Means for Solving the Problems

[0005] Various embodiments and implementations of this specification are directed to methods and systems configured to detect and report a patient's infection or risk of infection based on sensor data from a wearable device worn by the patient. The system receives user heart data from sensors of a wearable device worn by the user. The system then determines the user's heart rate for a first period from the received user heart data. The system determines both (i) the user's heart rate variability phase acceleration value for the first period and (ii) the user's heart rate variability phase deceleration value for the first period from the received user heart data using a heart rate variability phase acceleration algorithm and a heart rate variability phase deceleration algorithm, respectively. A trained infection risk prediction algorithm of the system uses the user's heart rate variability phase acceleration value and the user's heart rate variability phase deceleration value for the first period to determine the user's current risk of infection. The determined current risk of infection for the user is provided via a user interface. According to one embodiment, a medical professional prescribes an antibiotic and / or antiviral treatment to treat the user's current infection in response to receiving the provided determined current risk of infection for the user.

[0006] Generally, in one aspect, a method for reporting a user's risk of infection is provided. The method includes (i) receiving user heart data from sensors of a wearable device worn by the user, (ii) determining, using a heart rate variability phase acceleration algorithm, a heart rate variability phase acceleration value for the user for a first period from the received user heart data, (iii) determining, using a heart rate variability phase deceleration algorithm, a heart rate variability phase deceleration value for the user for the first period from the received user heart data, (iv) determining, using a trained infection risk prediction algorithm, the current risk of infection for the user using the heart rate variability phase acceleration value and the heart rate variability phase deceleration value for the first period for the user, and (v) providing, via a user interface, the determined current risk of infection for the user.

[0007] According to one embodiment, the method further includes prescribing, by a medical expert, an antibiotic and / or antiviral treatment for treating the user's current infection according to the provided determined current risk of infection of the user.

[0008] According to one embodiment, the method further includes transmitting the received user heart data to a remote server, and the determining step is performed at the remote server.

[0009] According to one embodiment, the user interface includes a web portal.

[0010] According to one embodiment, the method further includes receiving, by a medical expert via the user interface, the determined risk of the current infection of the user.

[0011] According to one embodiment, the method is performed at regular intervals for the user by a remote service.

[0012] According to one embodiment, (i) the sensor is a heart rate sensor, the user heart data is heart rate sensor data, and / or (ii) the sensor is an electrocardiography sensor, and the user heart data is ECG data.

[0013] Also provided is a method for treating a patient's infection. The method includes a medical professional receiving the patient's determined current infection, where the patient's current infection is determined by (i) receiving the patient's cardiac data from a sensor of a wearable device worn by the patient, (ii) determining, from the received patient cardiac data, the patient's cardiac fluctuation phase acceleration value for a first period by a cardiac fluctuation phase acceleration algorithm, (iii) determining, from the received patient cardiac data, the patient's cardiac fluctuation phase deceleration value for the first period by a cardiac fluctuation phase deceleration algorithm, (iv) determining, by a trained infection risk prediction algorithm, that the patient is experiencing a current infection using the patient's cardiac fluctuation phase acceleration value and the patient's cardiac fluctuation phase deceleration value for the first period, and (v) providing the determination that the patient is experiencing a current infection to the medical professional via a user interface. The method also includes a medical professional prescribing an antibiotic and / or antiviral treatment for treating the patient's current infection according to the provided risk of the patient's current infection.

[0014] Also, a system for reporting the predicted risk of infection of a user, a wearable device worn by the user, the wearable device comprising a sensor configured to acquire user cardiac data, a trained infection risk prediction algorithm configured to determine the current risk of infection of the user based on the user's cardiac fluctuation phase acceleration value and the user's cardiac fluctuation phase deceleration value for a first period, By means of the heart rate fluctuation phase acceleration algorithm, from the received user heart data, (i) determining the user's heart rate fluctuation phase acceleration value for the first period; and (ii) by means of the heart rate fluctuation phase deceleration algorithm, from the received patient heart data, determining the user's heart rate fluctuation phase deceleration value for the first period; and (iii) using the user's heart rate fluctuation phase acceleration value and the user's heart rate fluctuation phase deceleration value for the first period, determining the risk of infection of the current user by means of a trained infection risk prediction algorithm, a processor configured to perform the steps; a user interface configured to provide population-based assessment and ranking so that the determined risk of infection of the current user, and personnel responsible for infection control, efficiently monitor the cohort and respond to population outbreaks; A system is provided that has.

[0015] It should be understood that all combinations of the foregoing concepts and additional concepts, to be discussed in more detail below (provided such concepts are not mutually inconsistent), are intended to be part of the subject matter of the invention disclosed herein. In particular, the subject matter of the claims at the end of this disclosure is intended to be part of the subject matter of the invention disclosed herein. Similarly, of course, any technical terms that are explicitly used herein and incorporated by reference will have the meaning that most closely matches the particular concepts disclosed herein.

[0016] These and other aspects of the various embodiments will be apparent from and will be explained with reference to the embodiments described hereinafter.

[0017] In the drawings, like reference numerals generally refer to the same parts throughout the different drawings, as in the literature. The figures showing the features and methods implementing the various embodiments should not be construed as being limited to other possible embodiments that fall within the scope of the appended claims. Also, the figures are not necessarily drawn to scale, and instead, emphasis is placed on illustrating the principles of the various embodiments.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Modes for Carrying Out the Invention

[0019] The present disclosure describes various embodiments of systems and methods configured to detect individual infections and / or determine the likelihood of an individual having a risk or current infection. More generally, the Applicants have recognized and appreciated that it would be beneficial to provide a method or system for improving infection detection using heart rate data obtained from sensors of wearable devices. Accordingly, an infection detection system receives user heart data from sensors of a wearable device worn by a user. The system then determines the user's heart rate for a first period from the received user heart data. The system determines from the received user heart data both (i) the user's heart rate variability phase acceleration value for the first period by a heart rate variability phase acceleration algorithm and (ii) the user's heart rate variability phase deceleration value for the first period by a heart rate variability phase deceleration algorithm. A trained infection risk prediction algorithm of the system uses the user's heart rate variability phase acceleration value and the user's heart rate variability phase deceleration value for the first period to determine the risk of the user having a current infection. The determined risk of the user having a current infection is provided via a user interface. According to one embodiment, a medical professional prescribes antibiotics and / or antiviral treatment to treat the user's current infection in response to receiving the provided determined risk of the user having a current infection.

[0020] According to one embodiment, the systems and methods described herein or contemplated herein can be implemented as elements of commercially available products for patient analysis or monitoring, such as in some non-limiting embodiments, Philips(R) telehealth products, Connected Care platforms, HealthBand, and / or HealthDot(R) (available from Koninklijke Philips NV, the Netherlands), or any suitable system.

[0021] According to another embodiment, the systems and methods described or contemplated herein can be implemented as elements for cohort monitoring in some non-limiting embodiments. For example, the systems and methods can be utilized by a system in infection control in a hospital to monitor staff and / or patients in order to minimize the rate of nosocomial infections. As another example, the systems and methods can be utilized by a system by institutions responsible for public safety in their communities, such as military education or higher education, and thus, they can monitor and respond to potential outbreaks. Many other embodiments are possible.

[0022] Referring to FIG. 1, in one embodiment, it is a flowchart of a method 100 for detecting and reporting individual infections or the likelihood of infection using an infection detection system. The method described in connection with the figure is provided by way of example only and should be understood not to limit the scope of the present disclosure. The infection detection system can be any of the systems described herein or otherwise contemplated. The infection detection system can be a single system or multiple different systems.

[0023] In step 110 of the present method, an infection detection system is provided. Referring to an embodiment of the infection detection system 200 shown in FIG. 2, for example, the system includes one or more of a processor 220, a memory 230, a user interface 240, a storage 260, and a sensor 280 interconnected via one or more system buses 212 and / or via one or more communication interfaces 250, which is a wearable device 270. It will be understood that FIG. 2 constitutes an abstraction in some respects, and the actual arrangement of the components of system 200 may be more complex than that shown. Further, the infection detection system 200 can be any of the systems described herein or otherwise contemplated. Other elements and components of the infection detection system 200 are disclosed and / or contemplated elsewhere in this specification. According to one embodiment, the infection detection system 200 includes a wearable device or other sensor device that communicates with a local or remote processor, such as a cloud-based processing system.

[0024] According to one embodiment, the user wears a wearable device comprising a sensor configured to obtain sensor data regarding the user. The wearable device may be the infection detection system 200, or the wearable device may be a component of the infection detection system 200. The user may be any individual who can wear the wearable device. According to one embodiment, the user is a patient. For example, the patient may be discharged from the hospital with a prescription or order to purchase and / or use the wearable device or wearable device, or may be provided in another way. As another example, the user may be a member of the military or any other organization for which it is advantageous to monitor the user's health. As yet another example, the user may be any individual interested in monitoring their own health.

[0025] The infection detection system 200 may be provided as software as a service (SAAS), and the wearable device may be sold to the user together with the service, or as an offer to use or purchase the service. For example, the user may purchase a wearable device to monitor an aspect of health such as activity level, or to provide other monitoring or notification services. The wearable device may be accompanied by user access to the infection detection system 200 as a free or paid service.

[0026] The wearable device can be any device that can be worn, carried, or communicated with the user so that the sensors of the device can obtain sensor data about the user. The wearable device can be a ring, a watch, a necklace, or any other device. Examples of wearable devices include, for example, Apple(R) Watch, Garmin(R) Watch, Oura(R) Ring, Empatica(R) Bracelet, etc. These devices typically monitor activity levels and / or provide notifications or other communication options, and typically can monitor vital signals including photoplethysmography (PPG), skin temperature, acceleration, oxygen saturation, and other vital signs.

[0027] In step 120 of the method, the infection detection system 200 receives sensor data from the sensor 210 of the wearable device 270. According to one embodiment, the wearable device is the infection detection system, and thus the processor of the wearable device receives sensor data from the sensors of the wearable device. According to another embodiment, the wearable device is a component of the infection detection system, and the local and / or remote processors (such as a remote server) of the infection detection system receive sensor data from the sensors transmitted by wired and / or wireless communication.

[0028] According to one embodiment, the sensor data may be any data that can be used by the methods and systems described herein or otherwise contemplated to determine the likelihood, risk, or presence of an infection. For example, the sensor data may be an electrocardiogram obtained from one or more electrode sensors. The sensor data may be heart rate or heart rate data from a photoplethysmography (PPG) sensor or other cardiac sensor. Other sensors are also suitable.

[0029] According to one embodiment, the sensor data may be continuously acquired or received by the infection detection system, or may be acquired or received periodically, such as at a predetermined request rate. For example, the sensor data may be used immediately, or may be stored in local or remote memory for use in further steps of the method. Thus, the infection detection system can receive sensor data continuously or at a predetermined request rate from the sensor and / or memory device, or can request sensor data from the sensor and / or memory device. For example, in optional step 122 of the method, sensor data and / or other data is transmitted to a remote server or other component of the infection detection system.

[0030] In step 130 of the method, a processor of the infection detection system analyzes the received sensor data to determine the user's heart rate during a first period. The first period can be any period during which sufficient sensor data can be acquired and analyzed by the system. For example, in a scenario where the infection detection system analyzes data continuously, the first period may be one minute, less than one minute, or several / dozens of minutes, and the first period and subsequent periods may or may not overlap. In a scenario where the infection detection system analyzes data periodically, the first period may be any selected period, such as one minute, less than one minute, or several / dozens of minutes. The user's heart rate during the first period can be determined using any method, algorithm, or process for extracting or calculating or determining the heart rate from the received sensor data type.

[0031] According to one embodiment, before or after step 130, or at any other point in the method, the infection detection system can prepare the sensor data received for analysis. For example, referring to FIG. 3, it is a flowchart of a method for detecting or predicting an infection. At 310, the sensor data is acquired by sensors of a wearable device and transmitted to an infection detection system (which can be the wearable device and / or other components of the system) for detecting or predicting an infection, thereby being received or otherwise utilized thereby. At 320 and 330, the received sensor data is prepared for analysis. For example, at 320, the sensor data is formatted for processing. Since the infection detection system can be configured to utilize sensor data from a wide variety of different wearable devices, the format of the sensor data can vary from wearable device to wearable device. Thus, the infection detection system can be configured, designed, programmed, or otherwise set up to process two or more different types of sensor data from two or more different wearable device types or brands, etc., to generate standardized sensor data utilized by downstream steps of the method. This can include removing outlier sensor data, reformatting or otherwise reorganizing the sensor data, and other processing steps.

[0032] At step 330, the received sensor data (which may or may not require formatting or reformatting at 320) can be preprocessed so as to be readily utilizable by downstream steps of the method. The preprocessing can include any data analysis or modification required to transform the sensor data into appropriate input data. For example, the preprocessing can include cleaning the data, such as removing noise or outliers, for example, by replacing the top and bottom 1% of the data with random uniform values generated from adjacent data, among many other options.

[0033] The formatted and processed sensor data may be used immediately or stored in the local or remote storage of the infection detection system, such as the memory of the wearable device or other components of the system, for use in further steps of the method.

[0034] In step 140 of the method, the processor of the infection detection system uses a heart rate variability phase acceleration algorithm to analyze the received sensor data to determine the heart rate variability phase acceleration value of the user during the first period. The heart rate variability phase acceleration algorithm is any algorithm configured to analyze the received sensor data and generate phase rectified heart rate acceleration data. For example, the heart rate variability phase acceleration algorithm averages the noise affecting the heart rate acceleration. According to one embodiment, information such as the heart rate can be obtained from the sensor data including the inter-beat interval, along with the heart rate variability. Since the heart rate and the variation of the heart rate can be changed by infection, the heart rate and the variation of the heart rate can be converted into the variation of the heart rate for processing by the system.

[0035] The heart rate variability phase acceleration value of the user during the first period may be used immediately or stored in the local or remote storage of the infection detection system, such as the memory of the wearable device or other components of the system, for use in further steps of the method.

[0036] In step 150 of the present method, the processor of the infection detection system uses a heart rate variability phase deceleration algorithm to analyze the received sensor data in order to determine the heart rate variability phase deceleration value of the user during the first period. The heart rate variability phase deceleration algorithm is any algorithm configured to analyze the received sensor data and generate phase rectified heart rate deceleration data. For example, the heart rate variability phase deceleration algorithm averages the noise that affects heart rate deceleration. According to one embodiment, information such as heart rate can be obtained from the sensor data including the interbeat interval, along with the heart rate variability. Since the heart rate and the variability of the heart rate can be changed by infection, the heart rate and the variability of the heart rate can be converted into the variability of the heart rate for processing by the system.

[0037] The heart rate variability phase deceleration value of the user during the first period may be used immediately, or may be stored in the local or remote storage of the infection detection system, such as the memory of a wearable device or other components of the system, for use in further steps of the method.

[0038] According to one embodiment, the heart rate variability phase acceleration algorithm and / or the heart rate variability phase deceleration algorithm can be an algorithm derived from, based on, or otherwise obtained from the algorithms described in Kamath et al. (Eds.), "Heart Rate Variability (HRV) Signal Analysis: Clinical Applications," (2012). However, other heart rate variability phase acceleration and / or deceleration algorithms are possible.

[0039] In step 160 of this method, the trained infection risk prediction algorithm of the infection detection system uses at least the user's heart rate fluctuation phase acceleration value and the user's heart rate fluctuation phase deceleration value for the first period as inputs to generate a determination of the current infection and / or the risk or likelihood of the current infection. The infection risk prediction algorithm of the infection detection system can be any algorithm configured to use these inputs to generate a determination of the current infection and / or the risk or likelihood of the current infection. For example, the algorithm can be any type of machine learning algorithm, as well as other types of algorithms. The algorithm can be trained using known mechanisms for training machine learning algorithms.

[0040] According to one embodiment, the infection detection system uses the trained infection risk prediction algorithm to determine the user's current infection and / or the risk or likelihood of the current infection according to the following process. However, this is provided only as a non-limiting example, and other methods can be used to determine the user's current infection and / or the risk or likelihood of the current infection by the algorithm.

[0041] According to this embodiment, the infection detection system receives sensor data such as the inter-beat interval (IBI) from the sensor during a first time period such as the entire sleep episode (e.g., 8 hours). The infection detection system divides the sleep episode IBI into 5-minute windows, or windows of any other size. The size of the window can be a predetermined size or a learned size.

[0042] For each window, the infection detection system calculates the heart rate fluctuation phase acceleration value and the heart rate fluctuation phase deceleration value using the sensor data. According to one embodiment, in order to generate the heart rate fluctuation phase acceleration value (and similarly to generate the heart rate fluctuation phase deceleration value), the system creates a buffer called an anchor to store all the beats whose values increase (decrease). This buffer stacks horizontally all the beats that result in an increase in the heart rate. The dimensions of this buffer are N×L, where N is the number of beats that resulted in an increase (decrease) in the heart rate. L is the window length, which means that the system stores all the IBI values of the L / 2 beats before the selected beat and the L / 2 beats after the selected beat in row N. According to one embodiment, since L = 4, the system stores the 2 IBI values after the beat, the current IBI value before the current beat, and 1 IBI value after the current beat.

[0043] According to one embodiment, for each beat within the window, if the IBI causes the value to increase (or decrease, during analysis by the deceleration algorithm), the system adds the IBI of the window, along with the IBI of the previous and subsequent beats, to the anchor buffer. In optional filtering, if the IBI changes by more than 5%, the system rejects the beat and does not input it into the anchor buffer.

[0044] According to one embodiment, if there are at least 20 beats stored in the anchor buffer (i.e., N is 20 or more), the system calculates the average over all the anchor beats by calculating the average across the rows. This results in the dimensions of the anchor buffer being 1×4. According to one embodiment, the resulting phase rectified acceleration and deceleration for the window period (5 minutes, in this non-limiting example) are given by the average difference between pairs of beats before and after the reference beat, according to the following equation. Output = (Average[2] + Average[3] - Average[0] - Average[1] / 4) (Equation 1)

[0045] According to one embodiment, the infection detection system aggregates all window values into a single one-day statistic, including but not limited to minimum, average, maximum, standard deviation, quantiles, and more.

[0046] According to one embodiment, the infection detection system aggregates all information over multiple times (such as over 10 days, according to a non-limiting example), stacks them into a vector, and inputs the information into a machine learning algorithm to generate an infection prediction score or decision.

[0047] The infection prediction score or decision can be a binary score indicating infection (e.g., yes / no, 1 / 0), risk of infection (e.g., low risk, medium risk, high risk), and / or prediction of infection (e.g., percentage of likelihood of infection), or any other indicator of the user's infection, risk of infection, or likelihood of infection.

[0048] According to one embodiment, the infection prediction score or decision may be used immediately or stored in local or remote storage of the infection detection system, such as in the memory of a wearable device or other components of the system, for use in further steps of the method.

[0049] In step 170 of the method, the determined infection, infection score, risk of infection, and / or prediction of infection are provided via the user interface of the infection detection system. The system can display or otherwise provide information to a user, such as the wearer of a wearable device, a caregiver, or another individual, via the user interface. The display can include information about the patient, input data related to the patient, or any other information. The infection information can be communicated to another device via wired and / or wireless communication. For example, the system can communicate the infection information and other information to a mobile phone, computer, laptop, wearable device, and / or any other device configured to enable display and / or other communication of the infection information and other information. The user interface can be any device or system that enables information to be transmitted and / or received and can include a display, mouse, and / or keyboard for receiving user commands. According to one embodiment, the user interface is a web portal that a user or other individual accesses to obtain infection information and / or other information.

[0050] According to one embodiment, the user interface can comprise a warning system. For example, the system or user interface can be configured to provide or otherwise generate a warning if the infection detection system detects an infection or detects a risk or likelihood of infection that meets or exceeds a predetermined threshold. A moderate risk or a likelihood of infection exceeding 50% can trigger the system or user interface to generate a warning. The warning can be, for example, a noise, a tactile response, a text message, or any other mechanism that warns the user or other individual of the information.

[0051] In optional step 180 of the method, a user or individual who is a medical professional or other professional receives, via a user interface, a determined infection, risk of infection, or likelihood of infection of the wearer of the wearable device. The user or individual who is a medical professional or other professional can be anyone who utilizes the information provided for management or care decisions. For example, the individual can be the wearer's physician. As another example, the individual can be a manager of an organization or other group that is monitoring one or more wearers for potential infections.

[0052] According to one embodiment, a user or individual who is a medical professional or other professional can receive, via a user interface, a determined infection, risk of infection, or likelihood of infection using any mechanism. For example, the individual can receive a warning or other information indicating the determined infection, risk of infection, or likelihood of infection. Alternatively, the user can log in to a web portal to receive or otherwise access the information. As yet another option, the user can have an app installed on their smartphone or other device to access the information, and the app can further include a notification or warning mechanism.

[0053] In optional step 190 of the method, a user or individual, such as a medical professional or other professional, can receive information and act based on that information. For example, a medical professional can receive and review a determined infection, risk of infection, or likelihood of infection for a wearer of a wearable device. After reviewing the information, the medical professional can make a treatment or treatment decision. Since the infection detection system has identified an infection or risk of infection, the treatment or treatment is designed or selected to treat that infection or prevent the infection. For example, the treatment can include an antibiotic to treat an infection from a bacterial agent, the treatment can include an antiviral to treat an infection from a viral agent, and / or the treatment can include an antifungal to treat an infection from a fungal agent, and the treatment can include an antiparasitic to treat an infection from a parasitic agent among other possible treatments.

[0054] The selected antibiotic, antiviral, antifungal, or antiparasitic can be selected to broadly treat an infection or more narrowly treat a very specific bacterial agent, virus, fungus, or parasite. The selected antibiotic, antiviral, antifungal, or antiparasitic can also be based on information about the wearer of the wearable device, including but not limited to recent movement history, exposure history, medical history, demographic information, and / or any other information. Any or all of this information can be stored by the infection detection system or otherwise be accessible to the infection detection system so that all of this information can be available to the medical professional and thus inform the selected therapy or treatment. The selected treatment or treatment can be communicated directly or indirectly to the wearer of the wearable device via, for example, electronic communication, a prescription, a phone call, voicemail, text message, or any other mechanism.

[0055] Referring to FIG. 2, it is a schematic diagram of an infection detection system 200. The system 200 may be any of the systems described herein or envisioned by other methods, and may include any of the components described herein or envisioned by other methods. It should be understood that FIG. 2 constitutes an abstraction in some respects, and the actual arrangement of the components of the system 200 may be more complex than that shown, and different from what is illustrated.

[0056] According to one embodiment, the system 200 includes a processor 220 capable of executing instructions stored in a memory 230 or a storage device 260, or otherwise processing data to perform, for example, one or more steps of a method. The processor 220 may be formed from one or more modules. The processor 220 may take any suitable form, including but not limited to a microprocessor, a microcontroller, multiple microcontrollers, a circuit, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a single processor, or multiple processors.

[0057] The memory 230 may take any suitable form including non-volatile memory and / or RAM. The memory 230 may include various memories such as, for example, L1, L2, or L3 cache or system memory. Thus, the memory 230 may include static random access memory (SRAM), dynamic RAM (DRAM), flash memory, read only memory (ROM), or other similar memory devices. The memory can store, among other things, an operating system. The RAM is used by the processor for temporary storage of data. According to one embodiment, the operating system can include code that controls the operation of one or more components of the system 200 when executed by the processor. It will be apparent that in embodiments where the processor implements one or more of the functions described herein in hardware, the software described as corresponding to such functions in other embodiments may be omitted.

[0058] The user interface 240 may include one or more devices for enabling communication with the user. The user interface can be any device or system that enables information to be transmitted and / or received, and may include a display, a mouse, and / or a keyboard for receiving user commands. In some embodiments, the user interface 240 may include a command line interface or a graphical user interface that can be presented to a remote terminal via the communication interface 250. The user interface may be disposed together with one or more other components of the system, or may be disposed remotely from the system and communicate via a wired and / or wireless communication network.

[0059] The communication interface 250 may include one or more devices for enabling communication with other hardware devices. For example, the communication interface 250 may include a network interface card (NIC) configured to communicate according to the Ethernet (registered trademark) protocol. Further, the communication interface 250 may implement a TCP / IP stack for communicating according to the TCP / IP protocol. Various alternative or additional hardware or settings for the communication interface 250 will be apparent.

[0060] The storage device 260 may include one or more machine-readable storage media such as read-only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, or similar storage media. In various embodiments, the storage device 260 can store instructions for execution by the processor 220, or data on which the processor 220 can operate. For example, the storage 260 can store an operating system 261 for controlling various operations of the system 200.

[0061] It will be apparent that the various information described as being stored in the memory device 260 may be additionally or alternatively stored in the memory 230. In this regard, the memory 230 may be regarded as constituting a storage device, and the memory device 260 may be regarded as a memory. Various other devices will be apparent. Further, both the memory 230 and the memory device 260 may be regarded as non-transitory machine-readable media. As used herein, the term non-transitory excludes transient signals and is understood to include all forms of storage devices, including both volatile and non-volatile memory.

[0062] The system 200 is shown as including one of each of the components described, but the various components may be replicated in various embodiments. For example, the processor 220 may include a plurality of microprocessors configured to independently execute the methods described herein or configured to execute steps or subroutines of the methods described herein, such that the plurality of processors cooperate to achieve the functions described herein. Further, if one or more components of the system 200 are implemented in a cloud computing system, the various hardware components may belong to separate physical systems. For example, the processor 220 may include a first processor in a first server and a second processor in a second server. Many other variations and configurations are possible.

[0063] According to one embodiment, system 200 includes a wearable device 270 having one or more sensors 280 configured to obtain sensor signals or sensor data regarding a patient, i.e., regarding the patient's heartbeat data. The wearable device may include, but is not limited to, rings, wristwatches, bracelets, necklaces, clothing, and other devices, and can be any device equipped with sensors and capable of obtaining sensor data. Although shown in FIG. 2 as a component of system 200, system 200 may be a component of wearable device 270. Sensor 280 can be any sensor capable of generating the sensor data described herein or envisioned by other means.

[0064] According to one embodiment, the storage device 260 of system 200 can store one or more algorithms, modules, and / or instructions for performing one or more functions or steps of the methods described herein or otherwise envisioned. For example, the system can include, among other instructions or data, a heart rate variability phase acceleration algorithm instruction 262, a heart rate variability phase deceleration algorithm instruction 263, a trained infection risk prediction algorithm 264, and a reporting instruction 265.

[0065] According to one embodiment, the heart rate variability phase acceleration algorithm instruction 262 instructs the system to analyze the received sensor data to determine the heart rate variability phase acceleration value of the user for a first period. The heart rate variability phase acceleration algorithm is any algorithm configured to analyze the received sensor data and generate phase rectified heart acceleration data. For example, the heart rate variability phase acceleration algorithm averages the noise affecting the heart acceleration. The heart rate variability phase acceleration value of the user for the first period may be used immediately or stored in local or remote storage of the infection detection system, such as in the memory of the wearable device or other components of the system, for use in further steps of the method.

[0066] According to one embodiment, the heart rate fluctuation phase deceleration algorithm instruction 263 instructs the system to analyze the received sensor data to determine the heart rate fluctuation phase deceleration value of the user during the first period. The heart rate fluctuation phase deceleration algorithm is any algorithm configured to analyze the received sensor data and generate phase-rectified heart rate deceleration data. For example, the heart rate fluctuation phase deceleration algorithm averages the noise affecting the heart rate deceleration. The heart rate fluctuation phase deceleration value of the user during the first period may be used immediately or stored in local or remote storage of the infection detection system, such as in the memory of the wearable device or other components of the system, for use in further steps of the method.

[0067] According to one embodiment, the trained infection risk prediction algorithm 264 instructs the system to utilize at least the heart rate fluctuation phase acceleration value of the user and the heart rate fluctuation phase deceleration value of the user during the first period as inputs for generating a determination of a current infection and / or the risk or likelihood of a current infection. The infection risk prediction algorithm of the infection detection system can be any algorithm configured to utilize these inputs and generate a determination of a current infection and / or the risk or likelihood of a current infection. For example, the algorithm can be any type of machine learning algorithm, as well as other types of algorithms. The algorithm can be trained using known mechanisms for training machine learning algorithms.

[0068] According to one embodiment, the reporting instruction 265 instructs the system to provide the determined infection, infection score, risk of infection, and / or prediction of infection to the user via the user interface of the infection determination system. The system can display or otherwise provide the infection information to the user, such as a healthcare provider or a wearer of a wearable device, via the user interface. The infection information can include the determined infection, infection score, risk of infection, and / or prediction of infection, as well as other information such as information about the wearer of the wearable device. The information can be communicated to another device by wired and / or wireless communication. For example, the system can communicate the information to a mobile phone, computer, laptop, wearable device, and / or any other device configured to enable the display and / or other communication of instructions and other information. The user interface can be any device or system that enables the transmission and / or reception of information and can include a display, mouse, and / or keyboard for receiving user commands.

[0069] Referring to FIG. 4, in one embodiment, it is a flowchart of a method 400 for training the infection prediction algorithm 264 of the infection detection system 200. In step 410 of the method, the system receives a training data set including heart rate data and infection status data of a plurality of individuals. The training data can include any information or data necessary for training the infection prediction algorithm, including labeled heart rate data and infection status data indicating the presence or absence of infection. The training data can be stored in and / or received from one or more databases. The databases can be local and / or remote databases. For example, the infection detection system can include a database of training data.

[0070] According to one embodiment, the infection detection system may include a data preprocessor or similar component or algorithm configured to process the received training data. For example, the data preprocessor analyzes the training data to remove noise, bias, errors, and other potential problems. The data preprocessor may also analyze the input data to remove low-quality data. Many other forms of data preprocessing or identification and / or extraction of data points are possible.

[0071] In step 420 of the method, the system processes the received information to extract location-specific features regarding heart rate and infection status data. The heart rate and infection status features can be any features used to train an infection prediction algorithm, e.g., features that can be used by or are used by an algorithm trained for infection analysis of future heart rate data, or any heart rate and infection status features. Feature extraction can be achieved by various embodiments for feature identification, extraction, and / or processing, including any method for extracting features from a dataset. The result of the feature processing step or module of the ultrasonic system is a set of heart rate and infection status features for a plurality of wearers of the wearable device, and thus comprises a training dataset that can be used to train a classifier.

[0072] In step 430 of the method, the system trains a machine learning algorithm, which is the algorithm used when analyzing heart rate information, as described or otherwise assumed. The machine learning algorithm is trained using the extracted features according to known methods for training machine learning algorithms. According to one embodiment, the algorithm is trained using the processed training dataset to generate determined infections, infection scores, risks of infection, and / or predictions of infection, as described herein or otherwise assumed. The generated information or report can include any of the information described herein or otherwise assumed, including, but not limited to, determined infections, infection scores, risks of infection, and / or predictions of infection for the wearer of the wearable device.

[0073] In step 440 of the method, the trained infection prediction algorithm is stored for future use. According to one embodiment, the trained model can be stored in a local storage device or a remote storage device.

[0074] According to one embodiment, the infection detection system is configured to process thousands or millions of data points in the input data used to train a classifier and to process and analyze the received plurality of heart rate and infection state features. For example, using automated processes such as feature identification and extraction and subsequent training to generate a functional and proficient classifier requires processing millions of data points from the input data and the generated features. This can require millions or billions of calculations to generate a new trained classifier from these millions of data points and millions or billions of calculations. As a result, each trained classifier is new and distinct based on the input data and parameters of the machine learning algorithm, thus improving the functionality of the infection detection system. Therefore, generating a functional and proficient trained classifier involves a process with a volume of calculations and analysis that the human brain cannot achieve in a lifetime or multiple lifetimes.

[0075] Furthermore, the infection detection system may be configured to continuously receive heart rate and infection state characteristics, perform analysis, and provide periodic or continuous updates via a report provided to the user for the wearer of the wearable device. This requires continuous analysis of thousands or millions of data points to optimize the report and requires a large amount of computation and analysis that the human brain cannot achieve in a lifetime.

[0076] By providing improved infection prediction or detection, this novel infection detection system has a very large positive effect on patient care compared to prior art systems. As just one example, by providing a system that can improve user analysis by detecting infection at an early stage, the system facilitates early treatment decisions, improves survival outcomes, and thereby can save lives.

[0077] All definitions are to be understood as governing, to the extent defined and used herein, dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of defined terms.

[0078] The indefinite articles "a" and "an" are to be understood as meaning "at least one" as used herein in the specification and claims, unless clearly indicated to the contrary.

[0079] The phrase "and / or" as used herein in the specification and claims is to be understood to mean "either or both" of the elements so conjoined, i.e., elements that in some cases co-exist and in other cases do not co-exist. Multiple elements listed in "and / or" are to be construed in the same manner, i.e., as "one or more" of the elements so conjoined. Other elements may optionally exist outside of those specifically identified by the "and / or" clause, whether or not related to those specifically identified elements.

[0080] In the specification and claims, as used herein, "or" should be understood to have the same meaning as the previously defined "and / or". For example, when separating items in a list, "or" or "and / or" is inclusive, i.e., it should be interpreted to include at least one, and more than one, of the elements in the list of elements and, optionally, further unlisted items. Terms such as "only one of" or "exactly one of", or when used in the claims, terms such as "consisting of", refer only to exactly one element of the list of elements, unless explicitly indicated to the contrary. In general, the term "or" as used herein should be interpreted simply to indicate an exclusive alternative (i.e., "one or the other, but not both") when preceded by an exclusive term such as "either", "one of", "only one of" or "exactly one of".

[0081] As used herein in the specification and claims, the phrase "at least one" should be understood to mean at least one selected from any one or more of the elements in a list of one or more elements, but not necessarily including at least one of each and every element specifically listed in the list of elements, and not excluding any combination of elements in the list of elements. This definition allows for the possibility that elements may optionally exist outside of the specifically recited elements in the list of elements referred to by the phrase "at least one", whether or not related to the specifically recited elements.

[0082] Also, it should be understood that in any method claimed herein that includes more than one step or act, unless clearly indicated to the contrary, the order of the steps or acts of the method is not necessarily limited to the order in which the steps or acts of the method are recited.

[0083] The claims, as well as all transitional phrases such as "comprising", "including", "carrying", "having", "containing", "relating to", "maintaining", "consisting of", etc. in the above specification are open-ended, that is, they are not limiting but should be understood to mean including. Only the transitional phrases "consisting of" and "consisting essentially of" are closed or semi-closed transitional phrases, respectively.

[0084] Although several embodiments of the present invention have been described and illustrated herein, those skilled in the art can readily envision various other means and / or structures for performing the functions described herein and / or obtaining one or more of the results described herein, and each such variation and / or modification is considered to be within the scope of the embodiments of the present invention described herein. More generally, those skilled in the art will readily recognize that all parameters, dimensions, materials, and configurations described herein are intended to be exemplary, and that the actual parameters, dimensions, materials, and / or configurations will depend on the specific application or the application in which the teachings of the invention are used. Those skilled in the art will be able to recognize or confirm many equivalents to the specific inventive embodiments described herein using only routine experimentation. Therefore, the embodiments presented so far are presented by way of example only, and within the scope of the appended claims and their equivalents, inventive embodiments can be practiced differently from those specifically described and claimed. The inventive embodiments of the present disclosure are directed to each individual feature, system, product, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, products, materials, kits, and / or methods, if such features, systems, products, materials, kits, and / or methods are not mutually inconsistent, is included within the scope of the invention of the present disclosure.

Claims

1. A method for reporting the risk of infection for users, The steps include receiving user heart data from a sensor of a wearable device worn by the user, The steps include determining the user's heart rate variability phase acceleration value for a first period from the received user cardiac data using a heart rate variability phase acceleration algorithm, The steps include determining the user's heart rate variability phase deceleration value for the first period from the received user cardiac data using a heart rate variability phase deceleration algorithm, A step of determining the current user's infection risk using a trained infection risk prediction algorithm, using the user's heart rate variability phase acceleration value and the user's heart rate variability phase deceleration value for the first period, The steps include providing the determined infection risk of the current user via the user interface and A method having

2. The method according to claim 1, further comprising the step of transmitting the received user cardiac data to a remote server, wherein the determination step is performed on the remote server.

3. The method according to claim 2, wherein the user interface includes a web portal.

4. The method according to claim 1, further comprising the step of receiving the current user's infection risk determined by a medical professional via the user interface.

5. The method according to claim 1, wherein the method is performed for the user at regular intervals via a remote service.

6. The method according to claim 1, wherein (i) the sensor is a heart rate sensor and the user cardiac data is heart rate sensor data, and / or (ii) the sensor is an electrocardiogram recording sensor and the user cardiac data is ECG data.

7. A system for reporting the predicted risk of infection for users, A wearable device worn by the user, comprising a sensor configured to acquire user cardiac data, A trained infection risk prediction algorithm configured to determine the current infection risk of a user based on the user's heart rate variability phase acceleration value and the user's heart rate variability phase deceleration value for a first period, A processor configured to perform the following steps: (i) determine the user's heart rate variability phase acceleration value for a first period from the received user cardiac data using a heart rate variability phase acceleration algorithm; (ii) determine the user's heart rate variability phase deceleration value for a first period from the received patient cardiac data using a heart rate variability phase deceleration algorithm; and (iii) determine the current user's infection risk using a trained infection risk prediction algorithm, using the user's heart rate variability phase acceleration value and the user's heart rate variability phase deceleration value for a first period. A user interface configured to provide the infection risk of the current user as determined above, A system that has

8. The system according to claim 7, wherein the user interface includes a web portal.

9. The system according to claim 7, wherein the received user cardiac data is transmitted to a remote server.

10. The system according to claim 7, wherein the processor performs the steps for the user at regular intervals.

11. (i) The sensor is a heart rate sensor, and the user cardiac data is heart rate sensor data, and / or (ii) The sensor is an electrocardiogram recording sensor, and the user cardiac data is ECG data, according to claim 7.

Images