Detection of patient health condition changes based on peak patient activity data and off-peak patient activity data

Abstract

The present disclosure relates to systems and techniques for detecting changes in a patient's health condition based on peak patient activity data and non-peak patient activity data. In some examples, the peak patient activity data and the non-peak patient activity data correspond to one or more peak periods (time periods) and one or more non-peak periods, respectively, with at least one peak period and at least one non-peak period corresponding to a highest activity level and a lowest activity level of a day, respectively. If a change in the patient's health condition is detected, the techniques described herein can direct a medical device to generate an output indicating the detection of the change in the patient's health condition for display.

Description

[0001] This application claims priority to U.S. Patent Application No. 17 / 014,843, filed September 8, 2020, and titled “DETECTION OF CHANGES IN PATIENT HEALTH BASED ON PEAK AND NON-PEAK PATIENT ACTIVITY DATA,” the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present disclosure relates generally to medical systems, and more particularly, to medical systems configured to monitor patient activity to understand changes in patient health. BACKGROUND

[0003] Some types of medical systems can monitor various data (e.g., electrocardiogram (EGM) and activity) of a patient or a group of patients to detect changes in health. In some examples, a medical system can monitor cardiac EGMs to detect one or more types of arrhythmias, such as bradycardia, tachycardia, fibrillation, or cardiac arrest (e.g., caused by a sinus pause or AV block). In some examples, a medical system can include one or more of an implantable medical device or a wearable device to collect various measurements for detecting changes in patient health. SUMMARY

[0004] Medical systems and techniques as described herein detect changes in health of a patient based on patient activity (e.g., level of physical movement) during peak and non-peak time periods (e.g., daily peak and non-peak time periods). Generally, there is a well-defined relationship between a patient’s daily activity and that patient’s overall physical health. As demonstrated herein, peak and non-peak time periods of patient activity (e.g., aggregated over multiple days) are relevant to an accurate assessment of patient health, and monitoring those time periods can provide an improved indication of changes in patient health.

[0005] Various medical devices (e.g., implantable devices, wearable devices, etc.) can be configured to monitor patient activity and detect changes in patient health status correlated with changes in data recording daily activities over multiple days. Peak and off-peak time periods for patients provide highly accurate data for calculating abstractions to represent the recorded patient activity data (e.g., daily activity metrics). The techniques described herein include performing detection analytics to detect changes in patient health status by comparing daily activity metrics over at least two days. This comparison not only generally simplifies detection analytics but also achieves complementary goals of reducing operational resource requirements and overall resource utilization by utilizing peak and off-peak time periods of daily activity metrics. Both of these conserve resource capacity, thereby saving time and money. Lower resource consumption enables smaller and less complex implementations (e.g., wearables) to implement these techniques. Medical devices with large resource capacities are no longer necessary; instead, medical devices with fewer processing, networking, and storage resources can be configured to detect changes in patient health status according to any of the techniques described herein.

[0006] Furthermore, by identifying each patient's individual peak and off-peak periods, the techniques described herein take into account the unique behaviors of each patient in the analysis of their health status. No two people share exactly the same behaviors, and therefore, a patient's peak and off-peak periods are typically unique, providing highly accurate data only for that patient. Additionally, the fact remains that most people cannot maintain a fixed daily schedule and frequently change their peak and off-peak activity periods. For example, the techniques described herein, which can identify different peak and off-peak periods each day, further improve the detection analysis described herein. Differences between patients' daily habits can be offset by identifying each patient's peak and off-peak periods. Therefore, focusing the healthcare system on peak and off-peak periods mitigates or completely eliminates problems associated with other methods, such as the tendency for false positives and false negatives. In light of the foregoing, this disclosure describes a technological development or solution for integration into practical applications.

[0007] In one example, a medical system includes: one or more sensors configured to sense patient activity; a sensing circuitry configured to provide patient activity data based on the sensed patient activity; and a processing circuitry configured to: for each day of a multi-day period, determine an activity level for each of a plurality of time periods within that day based on the activity data; determine one or more peak periods and one or more off-peak periods from the plurality of time periods based on the activity level, the one or more peak periods and the one or more off-peak periods corresponding to one or more highest activity levels and one or more lowest activity levels, respectively; determine daily values ​​of one or more activity metrics from the patient activity data corresponding to each of the one or more peak periods and the one or more off-peak periods, wherein the processing circuitry is further configured to: detect changes in patient health status based on comparisons between the daily values ​​of the one or more activity metrics for at least some days of the multi-day period; and generate an output indicating the detection of changes in patient health status for display.

[0008] In another example, a method includes, for each day of a multi-day period: determining an activity level for each of a plurality of time periods during that day based on activity data from one or more sensors configured to sense patient activity; determining one or more peak periods and one or more non-peak periods from the plurality of time periods based on the activity level, the one or more peak periods and the one or more non-peak periods corresponding to one or more highest activity levels and one or more lowest activity levels, respectively; and determining daily values ​​of one or more activity measures from the patient activity data corresponding to each of the one or more peak periods and the one or more non-peak periods, the method further including: detecting changes in patient health status based on comparisons between the daily values ​​of the one or more activity measures for at least some days of the multi-day period; and generating an output indicating the detection of changes in patient health status for display.

[0009] In another example, a non-transitory computer-readable storage medium includes program instructions that, when executed by processing circuitry of a medical system, cause the processing circuitry to: for each day of a plurality of days: determine, based on activity data, an activity level for each time period of a plurality of time periods during the day; determine, based on the activity level, one or more peak time periods and one or more non-peak time periods from the plurality of time periods, the one or more peak time periods and the one or more non-peak time periods corresponding to one or more highest activity levels and one or more lowest activity levels, respectively; and determine, from the patient activity data corresponding to each of the one or more peak time periods and the one or more non-peak time periods, daily values of one or more activity metrics; detect a patient health condition change based on a comparison between the daily values of the one or more daily activity metrics for at least some of the plurality of days; and generate an output indicating the detection of the patient health condition change for display.

[0010] This summary is intended to provide an overview of the subject matter described in this disclosure. It is not intended to provide an exclusive or exhaustive explanation of the systems, devices, and methods described in detail within the accompanying drawings and the specification. Further details of one or more examples are set forth in the accompanying drawings and the specific embodiments summarized below. Other features, objects, and advantages will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 An example environment of an example medical system according to one or more examples of the present disclosure is shown in connection with a patient.

[0012] Figure 2 is a functional block diagram illustrating an example configuration of a medical device according to one or more examples of the present disclosure.

[0013] Figure 3 is a conceptual side view of an example configuration of an IMD of Figure 1 and Figure 2 is a conceptual side view of an example configuration of an external device of

[0014] Figure 4 is a functional block diagram illustrating an example configuration of an external device of Figure 1 according to one or more examples of the present disclosure.

[0015] Figure 5 is a block diagram illustrating an example system including an access point, a network, an external computing device such as a server, and one or more other computing devices that can be coupled to Figures 1 to 4 a medical device and an external device of

[0016] Figure 6 is a flowchart illustrating example operations for determining peak and non-peak periods to enable accurate detection of patient health condition changes, in accordance with one or more examples of the present disclosure.

[0017] Figure 7 is a flowchart illustrating example operations for detecting patient health condition changes by analyzing daily activity metric values, in accordance with one or more examples of the present disclosure.

[0018] Like reference numbers in the specification and drawings indicate like elements. DETAILED DESCRIPTION

[0019] Generally, medical systems in accordance with the present disclosure implement techniques for detecting patient health condition changes based on peak and non-peak patient activity data. Daily activity metric values are computed from each of the peak and non-peak patient activity data, and each value represents the patient’s activity level for that full day. Examples of peak and non-peak periods correspond to the highest and lowest activity levels, respectively, in terms of patient activity data over a day. Techniques described herein can detect patient health condition changes by comparing (to each other) daily activity metric values determined from patient activity data corresponding to peak (e.g., daytime) and non-peak (e.g., nighttime) periods of each day. In one example, if the comparison indicates a deviation between two daily values or between a daily value and a baseline value that exceeds a threshold, is statistically significant, or is otherwise correlated with a patient health condition decline, a medical system as described herein generates an output indicating a patient health condition decline for display. As described herein, identification of peak and non-peak periods for a patient provides highly accurate data for computing daily activity metric values and establishing a baseline (e.g., mean, median, maximum, or any other statistical value) from which patient health condition changes can be detected.

[0020] Example medical devices from which patient activity data can be collected can include implantable or wearable monitoring devices, pacemakers / defibrillators, or ventricular assist devices (VADs). Implantable or wearable devices with accelerometers that continuously measure patient activity and record such measurements as patient activity data are described herein as example medical devices. One example medical device implements systems and techniques involving identification of daily peak and non-peak (e.g., sleep) patient activity for monitoring and trend analysis based on the highest and lowest daily activity levels. One example technique for identifying daily peak and non-peak activity can involve identifying 4 individualized peak time hours and 4 individualized non-peak time hours, the activity data for which is used to monitor and track a decline in a patient’s health condition.

[0021] Example medical devices can transmit patient activity data to other devices, such as computing devices, which can further analyze the patient activity data and then provide reports on the patient's activity and health status. These reports can compare various specific implementations of the techniques described herein, for example, comparing corresponding daily activity measures provided by different selections of peak and off-peak time periods for the same patient. Activity measures based on activity data during peak and off-peak time periods can provide information to the patient or caregiver about important aspects of the patient's health status.

[0022] In this way, the technology of this disclosure can advantageously achieve improved accuracy in detecting changes in a patient's health condition, and thus enable a better assessment of the patient's condition.

[0023] Figure 1 An example medical system 2 incorporating one or more technologies according to this disclosure is illustrated in the environment of a patient 4. The example technologies can be used with an IMD 10, which can be used with an external device 12 and... Figure 1 At least one of the other devices not shown in the diagram communicates wirelessly. In some examples, the IMD 10 can be implanted outside the chest cavity of patient 4 (e.g., subcutaneously). Figure 1 (As described in the pectoral muscle location). IMD 10 can be positioned near the sternum at or just below the patient's heart level, for example, at least partially within the heart contour. IMD 10 contains multiple electrodes ( Figure 1 (Not shown in the image), and is configured to sense cardiac EGM via multiple electrodes. In some examples, the IMD 10 may employ LINQ. TM The ICM is available from Medtronic, Inc. of Minneapolis, MN. The IMD 10 includes one or more sensors, such as one or more accelerometers, configured to sense patient activity.

[0024] External device 12 may be a computing device having a user-viewable display and an interface for receiving user input. In some examples, external device 12 may be a laptop computer, tablet computer, workstation, one or more servers, cellular phone, personal digital assistant, or another computing device that can run an application that enables the computing device to interact with IMD 10.

[0025] External device 12 is configured to communicate wirelessly with IMD 10 and optionally with another computing device. Figure 1(Not specified in the text) Communication. For example, external device 12 can communicate via near-field communication technology (e.g., inductive coupling, NFC, or other communication technology that can operate within a range of less than 10cm-20cm) and far-field communication technology (e.g., according to 802.11 or The standard set of radio frequency (RF) telemetry or other communication technologies that can operate at a range greater than that of near-field communication technologies can be used for communication.

[0026] External device 12 can be used to configure the operating parameters of IMD 10. External device 12 can be used to retrieve data from IMD 10. The retrieved data may include values ​​of physiological parameters measured by IMD 10, indications of arrhythmias or other disease episodes detected by IMD 10, and physiological signals recorded by IMD 10. For example, external device 12 can retrieve cardiac EGM segments recorded by IMD 10, since IMD 10 determines that cardiac arrest or another disease episode occurred during said segment. As another example, external device 12 may receive activity data, daily activity measurements, or other data related to the techniques described herein from IMD 10. The following will discuss... Figure 5 In more detail, one or more remote computing devices may interact with IMD 10 via a network in a manner similar to external device 12, for example, to program IMD 10 and / or retrieve data from IMD 10.

[0027] The processing circuitry of medical system 2, such as the processing circuitry of IMD 10, external device 12, and / or one or more other computing devices, can be configured to perform the example techniques of this disclosure for detecting changes in a patient's health status. The processing circuitry of IMD 10 can be communicatively coupled to one or more sensors, each configured to sense patient activity in some form, and communicatively coupled to a sensing circuitry configured to generate patient activity data. The processing circuitry of IMD 10 (possibly in combination with the processing circuitry of external device 12) can calculate daily activity metrics based on the patient activity data and, after several days, analyze daily values ​​of indicators of the patient's health status (including non-trivial changes in the patient's health status). To facilitate successful analysis, the processing circuitry can identify peak and off-peak periods of the day for calculating daily values.

[0028] Although described in the context of an example in which IMD 10 senses patient activity, example systems including any type of implantable, wearable, or external device configured with one or more sensors to sense patient activity can be configured to implement the techniques of the present disclosure. In some examples, processing circuitry in a wearable device can execute the same or similar logic as that executed by processing circuitry of IMD 10 and / or other processing circuitry as described herein. In this manner, a wearable device or other device can perform some or all of the techniques described herein in the same manner as described herein with respect to IMD 10. In some examples, a wearable device operates with IMD 10 and / or external device 12 as a potential provider of computing / storage resources and sensors for monitoring patient activity and other patient parameters. For example, a wearable device can transfer patient activity data to external device 12 for storage in non-volatile memory and for use in calculating daily activity metric values from peak patient activity data and non-peak patient activity data. Similar to processing circuitry of IMD 10, processing circuitry of external device 12 can analyze patient activity data to determine which peak and non-peak periods to use in calculating daily activity metric values.

[0029] Figure 2 is an example configuration of IMD 10 that illustrates an example implementation of techniques in accordance with one or more techniques described herein. Figure 1 is a functional block diagram of an example configuration of IMD 10. In the illustrated example, IMD 10 includes electrodes 16A and 16B (collectively, “electrodes 16”), antenna 26, processing circuitry 50, sensing circuitry 52, communication circuitry 54, storage 56, switching circuitry 58, and sensor 62. Although the illustrated example includes two electrodes 16, in some examples, IMDs including or coupled to more than two electrodes 16 can implement techniques of the present disclosure.

[0030] Processing circuitry 50 can include fixed function circuitry and / or programmable processing circuitry. Processing circuitry 50 can include any one or more of a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or equivalent discrete or analog logic circuitry. In some examples, processing circuitry 50 can include multiple components, such as any combination of one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or one or more FPGAs, as well as other discrete or integrated logic circuitry. The functions attributed to processing circuitry 50 herein can be embodied as software, firmware, hardware or any combination thereof.

[0031] The sensing circuitry 52 can be selectively coupled to the electrodes 16 via the switching circuitry 58, for example, to sense electrical signals of the heart of the patient 4. As an example, the sensing circuitry 52 can monitor signals from a sensor 62, which can include one or more accelerometers, pressure sensors, and / or optical sensors. In some examples, the sensing circuitry 52 can include one or more filters and amplifiers for filtering and amplifying the signals received from the electrodes 16 and / or the sensors 62. The sensing circuitry 52 can capture signals from any of the sensors 62, for example, to produce patient activity data 64 to facilitate monitoring of patient activity and detecting patient health condition changes.

[0032] The sensing circuitry 52 can generate the patient activity data 64 from sensor signals received from the sensors 62 that encode patient activity. The sensing circuitry 52 and the processing circuitry 50 can store the patient activity data 64 in the storage device 56.

[0033] The processing circuitry 50 executing logic configured to perform detection analysis on the patient activity data 64 can be operable to detect any patient health condition changes (e.g., a decline). The processing circuitry 50 can control one or more sensors 62 to sense patient activity in some form; examples of the one or more sensors 62 that sense patient activity include accelerometers (e.g., three-axis accelerometers), gyroscopes, thermometers, torque transducers, etc. There are multiple methods for converting patient activity data into an activity level, which can be a quality (e.g., high activity, low activity, etc.) or a quantity (e.g., activity minutes or fractional activity minutes (e.g., 10-second blocks)). The activity level enables differentiation between multiple time periods (e.g., two or more consecutive time periods, two or more consecutive time periods, etc.) of patient activity data.

[0034] One example peak period can be the hour corresponding to the highest activity level in a 24-hour day, and an example off-peak period can be the hour corresponding to the lowest activity level in the same 24-hour day. Another example peak period includes the hour corresponding to the highest activity level in a 24-hour day in addition to one or more of the second highest activity level hour, third highest activity level hour, fourth highest activity level hour, etc. in a 24-hour day. The complementary off-peak period can include the hour corresponding to the lowest activity level in addition to one or more of the second hour, third hour, fourth hour, etc. in a 24-hour day corresponding to the second lowest activity level hour, third lowest activity level hour, fourth lowest activity level hour, etc. The first, second, third, fourth, etc. peak and first, second, third, fourth, etc. off-peak provide the best evidence of the amount of activity of the patient in the context of a day and its impact on the overall patient health condition.

[0035] In this example, processing circuitry 50 is configured to determine the activity level per hour in a day by using the 10-second 23 method or similar algorithm on the activity minute count. Generally, the 10-second 23 method checks whether the integral count of the front-facing (z-axis) accelerometer reaches a 23 count threshold within each of consecutive 10-second windows, called epochs. Processing circuitry 50 stores 24-hour data associated with 10-second activity epochs, where any activity epoch that reaches or exceeds the 23 count threshold counts as a fractional activity minute. Combining multiple activity epochs results in a count of activity minutes; for example, each activity minute can represent sixty seconds of six (e.g., consecutive) activity epochs that satisfy the 23 count threshold. When processing circuitry 50 stores the 24-hour activity minutes in a memory buffer in storage 56, each hour corresponds to a stored data entry that indicates how many minutes in that hour included six activity epochs in which the 23 count threshold was satisfied. These minutes can include six consecutive or non-consecutive 10-second epochs. Processing circuitry 50 orders the buffer from highest to lowest to identify peak periods as the hours with the highest activity minute numbers and off-peak periods as the hours with the lowest activity minute numbers. In this way, IMD 10 or any other medical device that implements the techniques for identifying patient peak periods and off-peak periods can do so regardless of whether the patient is in a patient group or as an individual. When IMD 10 is used for multiple patients in a group study, each patient can have the attribute of individualized peak periods and individualized off-peak periods rather than arbitrary and / or static supplements (e.g., fixed or predefined periods) of them in other group studies.

[0036] The hourly resolution provides an opportunity to the detection analysis performed by IMD 10 to distinguish between daytime activity and nighttime activity without actually knowing which time of day the patient is asleep or awake or whether the patient is asleep or awake. One goal of this opportunity is to identify simple daily measures of nighttime sleep disturbance (which can be indicative of sleep quality) and / or peak daytime activity. Peak activity is most likely to occur during the daytime and reflects the patient's best effort. Daily values will provide overall activity for trend analysis and long-term analysis. A sudden increase or decrease in sleep disturbance or a sudden decrease in daytime activity can be indicative of an acute change in health condition.

[0037] Once suitable peak and non-peak periods are identified, processing circuitry 50 of IMD 10 can determine daily values for one or more activity metrics from peak and non-peak patient activity data. In one example activity metric, an example daily activity metric value is calculated from a weighted average that is calculated by applying a weight to an average of peak activity minutes from a peak N (e.g., four) hour window and an average of non-peak activity minutes from a non-peak N (e.g., four) hour window and then combining the weighted numbers (e.g., determining a difference or ratio of the numbers). The formula can apply one or more parameters / coefficients to the weighted average before completing the daily activity metric value calculation. In some examples, processing circuitry can determine multiple daily activity metric values, such as a first daily activity metric value based on an average of activity minutes for an N peak hour window and a second daily activity metric value based on an average of activity minutes for an N non-peak hour window.

[0038] The processing circuitry 50 of the IMD 10 can execute the logic programmed with the above example activity metric; when under control of the executed logic, the processing circuitry 50 of the IMD 10 applies the formula to the peak and non-peak patient activity data for a particular day and computes a daily activity metric value. The processing circuitry 50 of the IMD 10 tracks the daily activity metric values over time to detect patient health condition changes. In one example, the processing circuitry 50 compares the daily activity metric values for two or more days to one another and identifies at least one activity value difference that is indicative of any indication of a patient health condition change worth analyzing. Over time, the example daily activity metric values can form a range, and the range corresponds to a baseline that is representative of a normal patient health condition. A deviation from the range that is statistically significant or otherwise noteworthy indicates a patient health condition change. If the patient is known to be healthy, the processing circuitry 50 of the IMD 10 can establish the range as a health condition baseline, such that a significant (negative) deviation from the range can indicate a patient health condition decline. Substantial or otherwise noteworthy deviations include deviations from the established baseline that violate a guideline, exceed a threshold difference, cross a maximum activity value, etc. Note that other activity metrics can implement different formulas, etc., and the present disclosure does not limit application to any one activity metric.

[0039] The communication circuitry 54 can include any suitable hardware, firmware, software, or any combination thereof for communicating with another device, such as the external device 12, another networked computing device, or another IMD or sensor. Under the control of the processing circuitry 50, the communication circuitry 54 can receive downlink telemetry from, as well as send uplink telemetry to, the external device 12 or another device with the aid of an internal or external antenna, e.g., the antenna 26. In addition, the processing circuitry 50 can communicate with the external device 12 and the Medtronic Carelink® network via the internet or other computer network. The antenna 26 and the communication circuitry 54 can be configured to transmit and / or receive signals via inductive coupling, electromagnetic coupling, near-field communication (NFC), radio frequency (RF) communication, Bluetooth, WiFi, or other proprietary or non-proprietary wireless communication schemes. A computer network, such as the Medtronic Carelink® network, communicates with networked computing devices. The antenna 26 and the communication circuitry 54 can be configured to transmit and / or receive signals via inductive coupling, electromagnetic coupling, near-field communication (NFC), radio frequency (RF) communication, Bluetooth, WiFi, or other proprietary or non-proprietary wireless communication schemes.

[0040] In some examples, the storage 56 includes computer-readable instructions that, when executed by the processing circuitry 50, cause the IMD 10 and processing circuitry 50 to perform various functions attributed to the IMD 10 and processing circuitry 50 herein. The storage 56 can contain any volatile, nonvolatile, magnetic, optical, or electrical media, such as a random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically-erasable programmable ROM (EEPROM), flash memory, or any other digital media. As examples, the storage 56 can store programmed values of one or more operational parameters of the IMD 10 and / or data collected by the IMD 10 for transmission to another device using the communication circuitry 54. The data stored by the storage 56 and transmitted by the communication circuitry 54 to one or more other devices can include patient activity data indicative of suspicious changes in daily activity metric values and / or indications of changes in patient health status.

[0041] Figure 3 is illustrated Figure 1 and Figure 2 conceptual side view of an example configuration of the IMD 10. Although different examples of the IMD 10 can include leads, in the example shown in Figure 3 the IMD 10 can include a leadless subcutaneously implantable monitoring device having a housing 15 and an insulating cover 76. Electrodes 16A and 16B can be formed or placed on an outer surface of the cover 76. The circuitry 50-62 described above with respect to Figure 2 may be formed or placed on an inner surface of the cover 76 or within the housing 15. In the illustrated example, the antenna 26 is formed or placed on an inner surface of the cover 76, but in some examples, can be formed or placed on the outer surface. In some examples, the insulating cover 76 can be positioned over the open housing 15 such that the housing 15 and the cover 76 enclose the antenna 26 and the circuitry 50-62 and protect the antenna and circuitry from fluids, such as body fluids.

[0042] One or more of the antenna 26 or circuitry 50-62 can be formed on an inner side of an insulative cover 76, such as by using flip-chip technology. The insulative cover 76 can be flipped onto the housing 15. When flipped and placed onto the housing 15, the components of the IMD 10 formed on the inner side of the insulative cover 76 can be positioned in a gap 78 defined by the housing 15. The electrodes 16 can be electrically connected to the switching circuitry 58 through one or more vias (not shown) formed through the insulative cover 76. The insulative cover 76 can be formed of sapphire (i.e., corundum), glass, parylene, and / or any other suitable insulative material. The housing 15 can be formed of titanium or any other suitable material (e.g., biocompatible material). The electrodes 16 can be formed of any of stainless steel, titanium, platinum, iridium, or alloys thereof. Additionally, the electrodes 16 can be coated with a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes can be used.

[0043] Figure 4 is a block diagram illustrating an example configuration of components of the external device 12. In Figure 4 In an example, the external device 12 includes processing circuitry 80, communication circuitry 82, a storage device 84, and a user interface 86.

[0044] The processing circuitry 80 can include one or more processors configured to implement functionality and / or process instructions for execution within the external device 12. For example, the processing circuitry 80 can be capable of processing instructions stored in the storage device 84. The processing circuitry 80 can include, among other things, a microprocessor, a DSP, an ASIC, an FPGA, or equivalent discrete or integrated logic circuitry, or a combination of any of the foregoing devices or circuitry. Accordingly, the processing circuitry 80 can include any suitable structure, whether in hardware, software, firmware, or any combination thereof, to

[0045] The communication circuitry 82 can include any suitable hardware, firmware, software, or any combination thereof for communicating with another device, such as the IMD 10. Under the control of the processing circuitry 80, the communication circuitry 82 can receive downlink telemetry from, as well as send uplink telemetry to, the IMD 10 or another device. The communication circuitry 82 can be configured to transmit and / or receive signals via inductive coupling, electromagnetic coupling, NFC, RF communication, Bluetooth, WiFi, or other proprietary or non-proprietary wireless communication schemes. The communication circuitry 82 can also be configured to communicate with devices other than the IMD 10 via any of a variety of forms of wired and / or wireless communication and / or network protocols.

[0046] The storage device 84 can be configured to store information during operation of the external device 12. The storage device 84 can include a computer-readable storage medium or computer-readable storage devices. In some examples, the storage device 84 includes one or more of a short-term memory or a long-term memory. The storage device 84 can include, for example, RAM, DRAM, SRAM, magnetic discs, optical discs, flash memory, or various forms of EPROM or EEPROM. In some examples, the storage device 84 is used to store data indicative of instructions executed by the processing circuitry 80. The storage device 84 can be used by software or applications running on the external device 12 to temporarily store information during program execution.

[0047] Data exchanged between the external device 12 and the IMD 10 can include operational parameters. The external device 12 can transmit data including computer-readable instructions that, when implemented by the IMD 10, can control the IMD 10 to change one or more operational parameters and / or to export collected data. For example, the processing circuitry 80 can transmit instructions to the IMD 10 requesting that the IMD 10 export collected data (e.g., cardiac arrest episode data) to the external device 12. In turn, the external device 12 can receive the collected data from the IMD 10 and store the collected data in the storage device 84. The data received by the external device 12 from the IMD 10 can include activity data 64. The processing circuitry 80 can implement any of the techniques described herein to analyze peak patient activity data 64 and non-peak patient activity data 64 from the patient of the IMD 10 to determine a daily activity metric value, for example, to determine whether the patient is experiencing a health condition change.

[0048] A user, such as a clinician or the patient 4, can interact with the external device 12 through a user interface 86. The user interface 86 includes a display (not shown), such as a liquid crystal display (LCD) or light emitting diode (LED) display or other type of screen, with which the processing circuitry 80 can present information related to the IMD 10, such as a daily activity metric value, an indication of a change in the daily activity metric value, and an indication of a patient health change related to the change in the daily activity metric value. Additionally, the user interface 86 can include input mechanisms configured to receive input from the user. The input mechanisms can include, for example, any one or more of buttons, a keypad (e.g., an alphanumeric keypad), a peripheral pointing device, a touch screen, or another input mechanism that allows the user to navigate through and provide input to a user interface presented by the processing circuitry 80 of the external device 12. In other examples, the user interface 86 also includes audio circuitry for providing audible notifications, instructions, or other sounds to the user, receiving voice commands from the user, or both.

[0049] Figure 5 is a block diagram illustrating an example system incorporating an access point 90, a network 92, an external computing device such as a server 94, and one or more other computing devices 100A-100N (collectively, “computing devices 100”) that can be coupled with IMD 10 and external device 12 via network 92 in accordance with one or more techniques described herein. In this example, IMD 10 can use communication circuitry 54 to communicate with external device 12 via a first wireless connection and with access point 90 via a second wireless connection. In Figure 5 In the example of FIG. 9, access point 90, external device 12, server 94, and computing devices 100 are connected to one another and can communicate through network 92.

[0050] Access point 90 can comprise a device connected to network 92 via any of a variety of connections, such as a telephone dial-up, digital subscriber line (DSL), or cable modem connection. In other examples, access point 90 can be coupled to network 92 through different forms of connections, including wired or wireless connections. In some examples, access point 90 can be a user device, such as a tablet computer or smartphone, that can be co-located with the patient. IMD 10 can be configured to transmit data, such as patient activity data 64, peak patient activity data 64 and non-peak patient activity data 64, an indication of a daily activity metric, and / or an indication of a change in patient health, to access point 90. Access point 90 can then communicate the retrieved data to server 94 via network 92.

[0051] In some cases, server 94 can be configured to provide a secure storage site for data that has been collected from IMD 10 and / or external device 12. In some cases, server 94 can assemble data in a web page or other document for viewing by a trained professional, such as a clinician, via computing devices 100. Figure 5 One or more aspects of the illustrated system can be implemented with general network technology and functionality that can be similar to that provided by Medtronic CareLink® Network. Networks.

[0052] In some examples, one or more computing devices in computing device 100 may be tablets or other smart devices located with a clinician, which the clinician may program to receive alerts and / or query IMD 10. For example, the clinician may access data collected by IMD 10 and / or indications of the patient's health status, such as when patient 4 is between clinician visits, to check the status of the medical condition. In some examples, the clinician may input instructions for medical interventions for patient 4 into an application executed by computing device 100, such as based on the status of the patient's condition determined by IMD 10, external device 12, server 94, or any combination thereof, or based on other patient data known to the clinician. Device 100 may then transmit the instructions for medical interventions to another computing device in computing device 100 located with patient 4 or patient 4's caregiver. For example, such instructions for medical interventions may include instructions to change medication dosage, timing, or selection, instructions to schedule a clinician visit, or instructions to seek medical care. In another example, computing device 100 can generate alerts to patient 4 based on the status of patient 4's medical condition, enabling patient 4 to proactively seek medical attention before receiving instructions for medical intervention. In this way, patient 4 can be authorized to take action as needed to address his or her medical condition, which can help improve patient 4's clinical outcomes.

[0053] In the Figure 5 In the illustrated example, server 94 includes, for example, a storage device 96 and a processing circuitry system 98 for storing data retrieved from IMD 10. Although Figure 5 Unless otherwise specified, computing device 100 may similarly include storage devices and processing circuitry. Processing circuitry 98 may include one or more processors configured to implement functions and / or processing instructions for execution within server 94. For example, processing circuitry 98 may be able to process instructions stored in storage device 96. Processing circuitry 98 may include, for example, a microprocessor, DSP, ASIC, FPGA, or equivalent discrete or integrated logic circuitry system, or a combination of any of the foregoing devices or circuitry systems. Therefore, processing circuitry 98 may include any suitable structure, whether hardware, software, firmware, or any combination thereof, to perform the functions of processing circuitry 98 as described herein. The processing circuitry 98 of server 94 and / or the processing circuitry of computing device 100 may implement any of the techniques described herein to analyze activity data 64 received from IMD 10, for example, to determine whether a patient's health status has changed.

[0054] The storage 96 can include computer-readable storage media or computer-readable storage devices. In some examples, the storage 96 includes one or more of short-term memory or long-term memory. The storage 96 can include, for example, RAM, DRAM, SRAM, magnetic disks, optical disks, flash memory, or various forms of EPROM or EEPROM. In some examples, the storage 96 is used to store data indicative of instructions executed by the processing circuitry 98.

[0055] Figure 6 is a flowchart illustrating example operations for determining peak and non-peak periods to enable accurate detection of patient health condition changes, in accordance with one or more examples of the present disclosure. According to Figure 6 the instructions of FIG. 6, the processing circuitry 50 of the IMD 10 monitors patient activity data generated by the sensing circuitry 52 of the IMD 10 (120). For example, as discussed in more detail with respect to Figures 1 to 2 As discussed in more detail with respect to the instructions of FIG. 6, the processing circuitry 50 can monitor patient activity data over several days and each day initiate a method of identifying peak and non-peak periods of the patient activity data to compute an activity metric value for that day.

[0056] In the example operations of Figure 6 it is noted that there is a range of predetermined options that can be programmed into the example of the IMD 10: the number of time periods in a day (e.g., 24-hour time periods), the length of each peak and non-peak period, the total amount of time for each peak and non-peak period, the number of peak / non-peak periods, a Boolean indicating whether peak periods need to be contiguous (e.g., abut or adjacent to each other in time order) time periods, a selection of statistical processes to apply, a selection as to which class of patient health conditions to detect, etc.

[0057] In the example of the instructions of FIG. 6, the processing circuitry 50 of the IMD 10 determines whether the IMD 10 is programmed to use fixed time periods to compute daily activity metric values (122). By “fixed,” each time period can be predetermined and / or arbitrary (e.g., randomly selected). The fixed time periods can be any time period within a 24-hour day and, by happenstance rather than design, can be peak and / or non-peak periods. Based on determining that the IMD 10 is programmed to use fixed time periods (122 is true), the processing circuitry 50 of the IMD 10 proceeds to compute daily activity metric values of one or more activity metrics using patient activity corresponding to the fixed time periods.

[0058] Based on a determination that IMD 10 is not programmed to use a fixed time period (NO of 122), processing circuitry 50 of IMD 10 continues to determine whether IMD 10 is programmed to use multiple consecutive time periods for peak and non-peak time periods (124). Having two or more consecutive time periods as peak time periods (e.g., rather than two or more non-consecutive (e.g., non-contiguous) time periods) provides a more accurate assessment of the patient’s health condition based on the individual patient and / or the circumstances of the patient’s health condition. There can be alternative definitions of peak and non-peak time periods to consider, such as having only one time period as a peak time period and (possibly) only one time period as a non-peak time period. Each time period can be one hour long or more than one hour long.

[0059] Based on a determination that IMD 10 is not programmed to use consecutive time periods (NO branch of 124), but is programmed to identify peak and non-peak time periods over any time period, processing circuitry 50 of IMD 10 continues to determine an activity level for each hour and determines peak and non-peak time periods as having the highest and lowest activity levels, respectively (126). There are a variety of mechanisms for determining an activity level for a time period (e.g., an hour), such as a 10-second 23-count method, which checks whether the integral count of the frontal (z-axis) accelerometer reaches a 23-count threshold within each consecutive 10-second window. Processing circuitry 50 of IMD 10 can apply the 10-second 23-count method to each hour of the 24 hours in a day to determine the active minutes (or fractional active minutes (e.g., with 10-second resolution)) for that hour; ultimately, after applying the method to the patient activity data for a day, processing circuitry 50 of IMD 10 selects the hour of the day with the highest active minutes as the first peak time period and selects the hour of the day with the lowest active minutes as the first non-peak time period. Processing circuitry 50 of IMD 10 can continue to select at least one additional hour as supplemental peak and non-peak time periods. Since IMD 10 does not need to maintain consecutive time periods as peak and non-peak time periods, processing circuitry 50 of IMD 10 can select four non-consecutive hours with the four highest activity levels in a day for peak time periods. Processing circuitry 50 of IMD 10 can also select four non-consecutive hours with the four lowest activity levels as non-peak time periods. After selecting one or more hours as peak time periods (e.g., a set of non-consecutive peak hours) and one or more other hours as non-peak time periods (e.g., a set of non-consecutive non-peak hours), processing circuitry 50 of IMD 10 continues to determine daily activity metric values for one or more activity metrics from patient activity data at the peak and non-peak time periods, where two or more peak time periods or two or more non-peak time periods are not consecutive time periods (130).

[0060] Based on the determination that IMD 10 is programmed to use continuous time periods (124 is), the processing circuitry system 50 of IMD 10 continues to determine the activity level of the moving window, and identifies peak periods and non-peak periods as having the highest and lowest activity levels, respectively (128). In addition to the requirement that peak periods are continuous time periods, this disclosure specifies a flexible definition of the moving window to include two or more continuous time periods, such as a four-hour window where each hour is a time period. As the moving window traverses the 24-hour time span (advancing one hour at a time), the processing circuitry system 50 of IMD 10 applies a 10.23 counting method to calculate the number of active minutes per hour, and then combines the number of active minutes from two or more consecutive hours of the moving window. In one example where the moving window is a four-hour window, the processing circuitry system 50 of IMD 10 calculates the average activity level for each moving window, and then selects the four-hour window with the highest average activity level and the four-hour window with the lowest average activity level. When defining peak and non-peak periods as two moving windows corresponding to the highest and lowest activity levels, the processing circuitry system 50 of the IMD 10 continues to determine daily activity metrics based on patient activity data at the peak and non-peak periods, where both the peak and non-peak moving windows comprise consecutive time periods (130). In some examples, the processing circuitry system 50 of the IMD 10 determines well-defined peak and non-peak periods only after monitoring patient activity for a sufficient number of days.

[0061] This article is aimed at Figure 7 Provides information on determining one or more daily activity metrics by utilizing identified peak and off-peak periods (which may follow...). Figure 6 The example operation shown includes further details on determining whether daily activity measures are associated with changes in patient health status (e.g., decline). It should be noted that while some changes in daily activity measures over short periods may be associated with overall changes in patient health status, other changes in daily activity measures (e.g., fluctuations) may be associated with changes in specific categories of patient health status (e.g., cardiac health status).

[0062] Figure 7 This is a flowchart illustrating example operations for detecting changes in patient health status based on the analysis of peak and non-peak patient activity data, according to one or more examples of this disclosure. Figure 6 As an example of the illustration, the processing circuitry system 50 of the IMD 10 determines one or more peak periods and one or more non-peak periods of patient activity data generated by the sensing circuitry system 52 of the IMD 10. According to... Figure 7As an example of the illustration, the processing circuitry system 50 of the IMD 10 detects changes in the patient's health status based on daily activity metrics calculated from peak and non-peak patient activities generated by the sensing circuitry system 52 of the IMD 10.

[0063] exist Figure 7 In the illustrated example, the processing circuitry system 50 of the IMD 10 utilizes one or more peak periods and one or more off-peak periods to focus detection analysis on accurate patient activity data for detecting changes in patient health status. At least one or more peak periods correspond to highly accurate patient activity data; when combined with patient activity data associated with the same one or more off-peak periods, very accurate activity values ​​can be computed as an example abstraction of patient activity data throughout the day. Depending on which activity measures the processing circuitry system 50 of the IMD 10 uses for computation, daily activity measures also provide some insight into patient activity data throughout the day. Example activity measures may refer to mathematical functions (e.g., formulas), data structures (e.g., models), standardization methods / mechanisms, and measurements and other data configured to enable the computation of daily activity measures by analyzing peak and off-peak patient activity data. This analysis can be qualitative and / or quantitative, for example, to gain insights into patient health status by expressing as many relevant features as possible within the context of given patient activity.

[0064] In order to Figure 7 In an example operation, such detection analysis is initiated, with the processing circuitry system 50 of the IMD 10 processing patient activity data (140) at one or more peak periods and one or more off-peak periods. Patient activity data is provided daily by implementing one or more sensors configured to sense patient activity in some form. This patient activity data can be divided into time periods (e.g., 24 one-hour periods), and activity levels can be determined for each time period. This disclosure describes various mechanisms for determining activity levels within a specific time period. In addition to hourly activity levels and / or the number of minutes of activity, each peak or off-peak period can be correlated with other patient activity data.

[0065] The IMD 10 can be programmed with at least one peak period and non-peak period determination mechanism, examples of which include: 1) a fixed 4-hour time window, 2) an individualized 4-hour time window, and 3) all hourly activity windows. Each option identifies which hourly activity measure to use for a peak period or non-peak period. For example, for a fixed 4-hour time window, the medical device calculates a daily activity average during a first predetermined 4-hour time window and a nightly daily average during a second predetermined 4-hour time window. The first and second predetermined 4-hour time windows are selected by calculating hourly activity averages of moving four-hour windows and then identifying the 4-hour time windows with the highest activity average and the lowest activity average across the patient group. The individualized 4-hour time window accounts for differences in individualized habits by identifying, for each patient, the time windows with the highest activity average and the lowest activity average for that patient. All hourly activity windows is an option in which a one-hour moving window is used to identify one or more hourly windows to use for the baseline activity average. These methods can be mixed; for example, one mixed option can be to use the highest activity of any four hours (e.g., four non-consecutive hours) and the lowest activity of any four hours for the highest activity average and the lowest activity average, respectively.

[0066] For example, as discussed with respect to Figures 1 to 2 and Figure 6 As discussed in more detail, the processing circuitry 50 can determine that one or more peak periods are periods of time that typically have the highest activity levels, and one or more non-peak periods are periods of time that typically have the lowest activity levels. By relying on these periods of time (and possibly ignoring other periods of time), the techniques described herein enable highly accurate assessment of patient health conditions that are readily detected as acute changes. Daily activity metric values computed from peak patient activity data and non-peak patient activity data will provide overall activity for trend analysis and long-term analysis. A sudden increase or decrease in sleep disturbance or a sudden decrease in daytime activity can indicate an acute change in health condition.

[0067] The processing circuitry 50 of the IMD 10 computes at least one daily activity metric value from peak activity levels and non-peak activity levels, as well as other patient activity data (141). In some examples, the processing circuitry 50 of the IMD 10 computes a daily activity metric value for one or more activity metrics of the patient activity data within a day (e.g., the current day). Each activity metric as described herein can be configured to quantify some aspect of patient activity, such that combining one or more metrics can provide a comprehensive view or assessment of patient health condition.

[0068] After calculating the daily activity metric value, the processing circuitry 50 of the IMD 10 compares the daily activity metric value to a baseline value (142). In some examples, the baseline value can be another (e.g., previous) daily activity metric value that represents the highest or average activity metric / level of daily patient activity. Thus, the processing circuitry 50 of the IMD 10 can compare the calculated daily activity metric value to other daily activity metric values and then use the comparison to detect a patient health condition change. In other examples, the baseline value can be predetermined, or as an alternative, calculated by other means than one or more activity metrics, while retaining the same data model to facilitate comparison to daily activity metric values. In some examples, the baseline value represents a normal health condition for that particular patient, and any deviation from that baseline value should be evaluated. The baseline value can represent a boundary for the patient, as the baseline value is the highest activity value / level while still indicating that the patient’s health condition has not declined; any deviation beyond the baseline value can indicate an acute change or decline in the patient’s health condition.

[0069] Activity metrics as described herein include any number of formulas, methods, and mechanisms for determining daily activity metric values from patient activity data. The processing circuitry 50 of the IMD 10 can apply one or more activity metrics to peak patient activity data and non-peak patient activity data for each day, and calculate daily activity metric values for several days. Over time, example daily activity metric values can form a range, and the range corresponds to a baseline that represents a normal patient health condition. A deviation from the range that is statistically significant or exceeds a predetermined threshold indicates a patient health condition change.

[0070] One example peak (e.g., daytime) activity metric is the average activity of the four highest activity hours during the last 24 hours. One example non-peak activity metric (e.g., for night-time sleep disturbance (sleep quality)) is the average of the four lowest activity hours during the last 24 hours.

[0071] Other example activity metrics can employ different peak period / non-peak period selection mechanisms, different formulas, etc. For example, the example activity metrics described above can be modified to allow for non-consecutive one-hour time periods. Some activity metrics are configured to utilize features that correspond to overall patient health condition. Other activity metrics can be configured with a more granular set of features to identify changes in different categories of patient health conditions, such as heart health condition.

[0072] In some examples, after comparing the daily activity metric value to the baseline value, processing circuitry 50 of IMD 10 determines whether the comparison satisfies a threshold (143). In some examples, the baseline value can be predetermined or one of the daily activity metric values. If the difference / variation between the calculated daily activity metric value and the baseline value does not exceed the threshold (NO of 143), processing circuitry 50 of IMD 10 returns to processing patient activity for peak and non-peak periods of different days (140). If the difference / variation between the calculated daily activity metric value and the baseline value exceeds the threshold (YES of 143), processing circuitry 50 of IMD 10 proceeds to generate output data indicating a change in patient health (144).

[0073] As one example of output data, processing circuitry 50 of IMD 10 can combine the two metrics for trend analysis and analysis. The daily activity metric values can be plotted over time to visually see changes and trends. A linear regression line for the last 2 weeks can be displayed to show overall trends. Statistical process control (SPC) can be used to provide an alert for acute decreases in daytime activity or acute changes in sleep unrest. The alert would indicate a significant decrease in health that would require further evaluation, which can involve taking temperature, measuring oxygen, and asking the caregiver or clinician about symptoms. Such and other medical measurements would be used to determine a specific etiology (e.g., flu, depression).

[0074] In response to detecting a variation that exceeds the threshold, processing circuitry 50 of IMD 10 can proceed to generate a report describing the patient’s health over time (145). IMD 10 can leverage additional processing capabilities of a remote computing device, such as external device 12, to generate the report. IMD 10 can provide patient activity data to external device 12 over a sufficient number of days (e.g., a trial period). In turn, processing circuitry 80 of external device 12 can generate a report to include a plot of the daily activity metric over the sufficient number of days (e.g., the trial period). Processing circuitry 80 of external device 12 can apply different peak period determination mechanisms and non-peak period determination mechanisms and / or different activity metrics to the patient activity data for comparison. If IMD 10 is programmed to use a fixed 4-hour time window, the remote computing device can generate a plot of the daily activity metric with application of individualized 4-hour time windows and all hourly activity window mechanisms. In this way, the effectiveness of each determination mechanism can be evaluated. Each mechanism can be applied to an individual or can be group-based.

[0075] The report can describe results from applying different activity metrics and different peak / non-peak periods. An example report can show patient activity data for several days, where the patient activity data for each day is divided into one-hour long periods. The example report can indicate which one-hour long periods are peak periods and which are non-peak periods; especially when different selection methods are applied, the example report can distinguish between peak / non-peak periods determined by these selection methods. For example, the example report can indicate the following as having the highest and lowest activity levels for at least one day: 1) non-consecutive peak and non-peak periods, 2) a window of adjacent or consecutive peak and non-peak periods; 3) fixed peak and non-peak periods.

[0076] Figure 6 and Figure 7 The order and flow of operations illustrated are examples. In other examples in accordance with the present disclosure, more or fewer thresholds can be considered. Further, in some examples, the processing circuitry can or can not perform the methods of Figure 6 and Figure 7 or any of the techniques described herein, as directed by a user. For example, a patient, clinician, or other user can turn on or off the functionality for identifying patient health condition changes (e.g., using Wi-Fi or cellular services) or locally (e.g., using an application provided on a patient cell phone or using a medical device programmer).

[0077] The techniques described in this disclosure can be implemented, at least in part, in hardware, software, firmware or any combination thereof. For example, various aspects of the techniques can be implemented within one or more processors, DSPs, ASICs, FPGAs or any other equivalent integrated or discrete logic QRS circuitry as well as any combinations of such components, embodied in external devices, such as physician or patient programmers, simulators, or other devices. The terms "processor" and "processing circuitry" can generally refer to any of the foregoing logic circuitry, alone or in combination with other logic circuitry, or any other equivalent electrical circuitry, alone or in combination with other digital or analog circuitry.

[0078] For aspects implemented in software, at least some of the functionality attributed to the systems and devices described in this disclosure can be embodied as instructions on a computer-readable storage medium such as RAM, DRAM, SRAM, magnetic disks, optical disks, flash memory, or various forms of EPROM or EEPROM. The instructions can be executed by one or more processing units to support one or more aspects of the functionality described in this disclosure.

[0079] Additionally, in some aspects, the functionality described herein can be provided within dedicated hardware and / or software modules. Depiction of different features as modules or units is for illustrative purposes, and does not necessarily mean that such modules or units must be realized by separate hardware or software components. Rather, functionality associated with one or more modules or units can be performed by separate hardware or software components, or integrated within common or separate hardware or software components. Also, the techniques of this disclosure can be fully implemented in one or more circuits or logic elements. The techniques of this disclosure can be implemented in a variety of devices, including an IMD, an external programmer, a combination of an IMD and external programmer, an integrated circuit (IC), or a set of one or more ICs and / or discrete circuitry resident in an IMD and / or external programmer.

Claims

1. A medical system, the medical system comprising: One or more sensors, the one or more sensors being configured to sense patient activity; A sensing circuit system configured to provide patient activity data based on sensed patient activity; and Processing circuitry system, the processing circuitry system being configured to: For each day of the multiple days: The activity level is determined based on the activity data for each of the multiple time periods during the day; Based on the activity level, one or more peak periods and one or more off-peak periods are determined according to the plurality of time periods, wherein the one or more peak periods and the one or more off-peak periods correspond to one or more highest activity levels and one or more lowest activity levels, respectively. Determine the weighted average of the parameters for the one or more peak periods; Determine the weighted average of the parameters for the one or more non-peak periods; as well as Based on the patient activity data, daily values ​​of one or more activity metrics are determined using a weighted average of parameters from the one or more peak periods and a weighted average of parameters from the one or more non-peak periods. The processing circuit system is further configured to: Changes in a patient’s health status are detected by comparing daily values ​​of one or more activity measures over at least some of the days. as well as The output of the detection, which indicates changes in the patient's health status, is generated for display.

2. The medical system of claim 1, wherein the medical system comprises at least one of an implantable device, a wearable device, a pacemaker / defibrillator, or a ventricular assist device (VAD) comprising the one or more sensors and the sensing circuitry system therein.

3. The medical system according to any one of claims 1 to 2, wherein the processing circuitry is configured to detect a decline in a patient's health condition based on the comparison between the daily values ​​of the one or more activity measures.

4. The medical system according to any one of claims 1 to 2, wherein, in order to detect changes in the patient's health condition, the processing circuitry is configured to: A baseline value for at least one of the one or more activity metrics is determined based on a first or more daily value among the daily values ​​of the activity metrics; and Determine whether a second or more daily values ​​of the activity metric deviate from the baseline.

5. The medical system according to any one of claims 1 to 2, wherein the processing circuitry is configured to determine the one or more peak periods and the one or more non-peak periods based on the activity level in a moving window comprising a plurality of consecutive time periods.

6. The medical system according to any one of claims 1 to 2, wherein the one or more peak periods are discontinuous periods, and the one or more non-peak periods are discontinuous periods.

7. The medical system according to any one of claims 1 to 2, wherein the one or more sensors comprise one or more accelerometers.

8. The medical system according to any one of claims 1 to 2, wherein the activity level of each of the time periods includes the amount of time during which patient activity meets a threshold.

9. A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising program instructions that, when executed by a processing circuitry of a medical system, cause the processing circuitry to: For each day of the multiple days: Activity levels are determined based on activity data for each of the multiple time periods throughout the day. Based on the activity level, one or more peak periods and one or more off-peak periods are determined according to the plurality of time periods, wherein the one or more peak periods and the one or more off-peak periods correspond to one or more highest activity levels and one or more lowest activity levels, respectively. Determine the weighted average of the parameters for the one or more peak periods; Determine the weighted average of the parameters for the one or more non-peak periods; as well as Based on the activity data, daily values ​​of one or more activity metrics are determined using the weighted average of parameters during the one or more peak periods and the weighted average of parameters during the one or more off-peak periods. Changes in a patient’s health status are detected by comparing daily values ​​of one or more daily activity measures over at least some of the days. as well as The output of the detection, which indicates changes in the patient's health status, is generated for display.

10. The non-transitory computer-readable storage medium of claim 9, wherein the instructions for causing the processing circuitry system to detect changes in the patient's health status further include instructions for causing the processing circuitry system to perform the following operations: A baseline value for at least one of the one or more activity metrics is determined based on a first or more daily value among the daily values ​​of the activity metrics; and Determine whether a second or more daily values ​​of the activity metric deviate from the baseline.

Images