Medical Device Locating and Tracking System

Abstract

To provide a medical device location and tracking system.SOLUTION: Methods (500) and systems (300, 400) for automatically ascertaining physical location information about a plurality of medical device controllers (100) and for tracking changes in the physical locations of the respective medical device controllers. One or more machine learning modules (426, 430, 434) infer the physical locations from computer network messages received from the medical device controllers, including information about computer network components (306, 308, 310, 312) that are proximate to the respective medical device controllers (100).SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. patent application Ser. No. 16 / 370,951, filed Mar. 30, 2019, entitled "Medical Device Location and Tracking System," the entire contents of which are incorporated herein by reference for all purposes.

[0002] Technical Field The present invention relates to a medical device location and tracking system, and more particularly to a machine learning-based system that automatically associates network identifiers used by medical devices to report status information with physical locations, thereby automatically detecting when a medical device has been moved to another physical location. [Background technology]

[0003] Related technologies Many medical devices, such as some implantable heart pumps, e.g., the Impella® 2.5 heart pump available from Abiomed, Inc. of Danvers, Massachusetts, connect to external controllers that collect and display operational data about the medical device, such as cardiac signal levels, battery temperature, blood flow, and tubing integrity. An exemplary medical device controller is available from Abiomed, Inc. under the trade name Automated Impella Controller®. These controllers issue alarms when operational data values ​​exceed predetermined values ​​or ranges, for example, when a leak or loss of suction is detected. These controllers include a video display screen as a human interface, on which operational data and / or alarms are displayed.

[0004] To facilitate remote monitoring by medical personnel to ensure effectiveness and patient safety, some of such control devices may be coupled, often via a computer network including a wireless segment, to a central server that may be accessed by a monitoring station that may display real-time and / or historical operating data and / or alarms on a display screen for viewing by medical personnel.

[0005] Many such controllers are expensive and / or in short supply in hospitals and other medical facilities. Thus, when these controllers become available, such as after a heart pump is removed from a patient, these organizations often move them to where they are needed, which may include moving them between floors of a building, between buildings on a campus, and between campuses. Additionally, these controllers may also move with the patient while the attached medical equipment is still connected to the patient, such as when the patient is moved from an operating room to an intensive care unit.

[0006] However, this movement creates problems for medical personnel remotely monitoring the control device and the medical device attached to the control device. While the user interface of some control devices facilitates input of location information, such information is not always entered when the control device is moved, and the information may be entered incorrectly. Thus, if a control device is moved, for example, from one room or floor or building to another, the medical personnel remotely monitoring the control device may not be aware of its new location.

[0007] Lack of or incorrect information about the physical location of a control device can jeopardize patient safety. For example, if medical personnel remotely monitoring an implanted heart pump become aware of a dangerous condition, such as when the corresponding control device emits an alarm, but the medical personnel do not know the (correct) location, such as the room number, of the patient in which the heart pump is implanted, the medical personnel may not be able to quickly dispatch a nurse, doctor, or technician to the patient. Summary of the Invention

[0008] Overview of Aspects One aspect of the present invention provides a medical device control device locating and tracking system that includes a first electronic data store, a second electronic data store, a user interface, and a first machine learning module.

[0009] The first electronic data store is configured to store a plurality of first entries, each of which includes information associating a respective medical device control device with a respective physical location. The second electronic data store is configured to store a plurality of second entries, each of which includes information associating a respective computer network device with a respective physical location.

[0010] The user interface is configured to receive information identifying the identified medical device controller. The information identifying the identified medical device controller may be entered by a human, or the information identifying the identified medical device controller may be automatically confirmed without human input to the user interface. The user interface is also configured to receive information from a human user identifying an entered physical location of the identified medical device controller. The user interface is configured to store a new first entry in the first electronic data store. The new first entry associates the identified medical device controller with the entered physical location.

[0011] The receiver is configured to receive messages from a plurality of medical device control devices. The receiver is configured to receive the messages via a computer network. Each message is sent by a respective source medical device control device of the plurality of medical device control devices. Each message includes an identifier of the source medical device control device. Each message also includes an identifier of a computer network device.

[0012] In response to receiving each message, the first machine learning module is configured to automatically determine whether an entry in the first electronic data store associates the source medical device control device with a respective physical location. In other words, the first machine learning module is configured to automatically determine whether the first electronic data store contains such an association, rather than whether the source medical device control device is associated with a particular physical location. If an entry in the first electronic data store is found that associates the source medical device control device with a respective physical location, the first machine learning module is configured to store a new second entry in the second electronic data store. The new second entry associates a computer network device with the physical location associated with the source medical device control device.

[0013] In any embodiment, the computer network device identifier may identify a computer network device with which the originating medical device controller has communicated. The computer network device identifier may identify a computer network device with which the originating medical device controller has directly communicated wirelessly. The computer network device identifier may identify a wireless access point with which the originating medical device controller has directly communicated wirelessly. The computer network device identifier may include a base station identifier for a cellular base station with which the originating medical device controller has directly communicated wirelessly. The computer network device identifier may identify a computer network device through which the message passed on its way to the receiver. The computer network device identifier may include an IP address.

[0014] In any embodiment, the medical device controller location and tracking system may include a second machine learning module. The second machine learning module may be configured to automatically determine, in response to receiving each of the messages, whether an entry in the first electronic data store associates the source medical device controller with the respective physical location. If no entry in the first electronic data store is found associating the source medical device controller with the respective physical location, the second machine learning module may be configured to determine whether an entry in the second electronic data store associates a computer network device with the respective physical location.

[0015] If an entry in the first electronic data store associating the source medical device control device with the respective physical location is not found and an entry in the second electronic data store associating the computer network device with the respective physical location is found, the second machine learning module may be configured to store a new first entry in the first electronic data store. The new first entry may associate the source medical device control device with the physical location associated with the computer network device.

[0016] In any embodiment, the medical device controller location and tracking system may include a third machine learning module. The third machine learning module may be configured to automatically determine, in response to receiving each of the messages, whether an entry in a first electronic data store associates the source medical device controller with the respective physical location. If an entry in the first electronic data store is found that associates the source medical device controller with the respective physical location, the third machine learning module may be configured to determine whether an entry in a second electronic data store associates a computer network device with the respective physical location.

[0017] If an entry in the first electronic data store is found associating the source medical device control device with a respective physical location and an entry in the second electronic data store is found associating the computer network device with a respective physical location, the third machine learning module may be configured to compare the physical location associated with the source medical device control device in the first electronic data store with the physical location associated with the computer network device in the second electronic data store.

[0018] If an entry in the first electronic data store is found associating the source medical device control device with a respective physical location and an entry in the second electronic data store is found associating a computer network device with a respective physical location, and the physical location associated with the source medical device control device in the first electronic data store is found to be different from the physical location associated with the computer network device in the second electronic data store, the third machine learning module may be configured to modify the entry in the first electronic data store to associate the source medical device control device with the physical location associated with the computer network device in the second electronic data store.

[0019] In any embodiment, the third machine learning module may be configured to temporarily modify the entry in the first electronic data store to associate the source medical device controller with a physical location associated with the computer network device in the second electronic data store. The third machine learning module may be further configured to automatically subsequently modify the entry in the first electronic data store to associate the source medical device controller with a default value.

[0020] Another aspect of the present invention provides a medical device control device locating and tracking system, the system including a first electronic data store, a second electronic data store, a receiver, and a second machine learning module.

[0021] The first electronic data store is configured to store a plurality of first entries, each of which includes information associating a respective medical device control device with a respective physical location. The second electronic data store is configured to store a plurality of second entries, each of which includes information associating a respective computer network device with a respective physical location.

[0022] The receiver is configured to receive messages from a plurality of medical device control devices. The receiver is configured to receive the messages via a computer network. Each message is sent by a respective source medical device control device of the plurality of medical device control devices. Each message includes an identifier of the source medical device control device. Each message also includes an identifier of a computer network device.

[0023] The second machine learning module is configured to automatically determine, in response to receiving each of the messages, whether an entry in the first electronic data store associates the source medical device controller with the respective physical location. If no entry in the first electronic data store is found associating the source medical device controller with the respective physical location, the second machine learning module is configured to automatically determine whether an entry in the second electronic data store associates a computer network device with the respective physical location.

[0024] If an entry in the first electronic data store associating the source medical device control device with the respective physical location is not found and an entry in the second electronic data store associating the computer network device with the respective physical location is found, the second machine learning module is configured to automatically store a new first entry in the first electronic data store, the new first entry associating the source medical device control device with the physical location associated with the computer network device.

[0025] Yet another aspect of the present invention provides a medical device control device locating and tracking system, the system including a first electronic data store, a second electronic data store, a receiver, and a third machine learning module.

[0026] The first electronic data store is configured to store a plurality of first entries, each of which includes information associating a respective medical device control device with a respective physical location. The second electronic data store is configured to store a plurality of second entries, each of which includes information associating a respective computer network device with a respective physical location.

[0027] The receiver is configured to receive messages from a plurality of medical device control devices. The receiver is configured to receive the messages via a computer network. Each message is sent by a respective source medical device control device of the plurality of medical device control devices. Each message includes an identifier of the source medical device control device. Each message also includes an identifier of a computer network device.

[0028] The third machine learning module is configured to automatically determine, in response to receiving each of the messages, whether an entry in the first electronic data store associates the source medical device controller with the respective physical location. If an entry in the first electronic data store is found associating the source medical device controller with the respective physical location, the third machine learning module is configured to determine whether an entry in the second electronic data store associates a computer network device with the respective physical location.

[0029] If an entry in the first electronic data store is found associating the source medical device control device with a respective physical location and an entry in the second electronic data store is found associating the computer network device with a respective physical location, the third machine learning module is configured to compare the physical location associated with the source medical device control device in the first electronic data store with the physical location associated with the computer network device in the second electronic data store.

[0030] If an entry in the first electronic data store is found associating the source medical device control device with a respective physical location and an entry in the second electronic data store is found associating a computer network device with a respective physical location, and the physical location associated with the source medical device control device in the first electronic data store is found to be different from the physical location associated with the computer network device in the second electronic data store, the third machine learning module is configured to modify the entry in the first electronic data store to associate the source medical device control device with the physical location associated with the computer network device in the second electronic data store.

[0031] One aspect of the present invention provides a method for locating and tracking medical device control devices. The method includes providing a first electronic data store and a second electronic data store. The first electronic data store is configured to store a plurality of first entries. Each first entry includes information associating a respective medical device control device with a respective physical location. The second electronic data store is configured to store a plurality of second entries. Each second entry includes information associating a respective computer network device with a respective physical location.

[0032] Information identifying the identified medical device controller is received.

[0033] Information identifying the entered physical location of the identified medical device is received from a human user via a user interface.

[0034] A new first entry is stored in the first electronic data store, the new first entry associating the identified medical device control device with the entered physical location.

[0035] A message is received from a source medical device controller. The message is received over a computer network. The message includes an identifier of the source medical device controller. The message also includes an identifier of a computer network device.

[0036] In response to receiving the message, a determination is automatically made to determine whether an entry in a first electronic data store associates the source medical device with a respective physical location. If an entry in the first electronic data store is found that associates the source medical device control device with a respective physical location, a new second entry is stored in a second electronic data store. The new second entry associates a computer network device with the physical location associated with the source medical device control device.

[0037] In any embodiment, receiving a message including a computer network device identifier may include receiving a message identifying a computer network device with which the originating medical device control device has communicated. In any embodiment, receiving a message including a computer network device identifier may include receiving a message identifying a computer network device with which the originating medical device control device has directly communicated wirelessly. In any embodiment, receiving a message including a computer network device identifier may include receiving a message identifying a wireless access point with which the originating medical device control device has directly communicated wirelessly. In any embodiment, receiving a message including a computer network device identifier may include receiving a message identifying a base station identifier of a cellular base station with which the originating medical device control device has directly communicated wirelessly. In any embodiment, receiving a message including a computer network device identifier may include receiving a message identifying a computer network device through which the message has passed on its way to the receiver. In any embodiment, receiving a message including a computer network device identifier may include receiving a message identifying an IP address.

[0038] In any embodiment, in response to receiving the message, a determination can be made automatically to ascertain whether an entry in a first electronic data store associates the source medical device controller with the respective physical location. If no entry in the first electronic data store is found associating the source medical device controller with the respective physical location, a determination can be made automatically to ascertain whether an entry in a second electronic data store associates a computer network device with the respective physical location.

[0039] If an entry in the first electronic data store associating the source medical device control device with a respective physical location is not found and an entry in the second electronic data store associating the computer network device with a respective physical location is found, a new first entry may be stored in the first electronic data store. The new first entry may associate the source medical device control device with the physical location associated with the computer network device.

[0040] In any embodiment, in response to receiving the message, a determination can be made automatically to ascertain whether an entry in a first electronic data store associates the source medical device controller with a respective physical location. If an entry in the first electronic data store is found associating the source medical device controller with a respective physical location, a determination can be made automatically to ascertain whether an entry in a second electronic data store associates a computer network device with the respective physical location.

[0041] If an entry is found in the first electronic data store associating the source medical device control device with a respective physical location and an entry is found in the second electronic data store associating the computer network device with a respective physical location, the physical location associated with the source medical device control device in the first electronic data store may be compared to the physical location associated with the computer network device in the second electronic data store.

[0042] If an entry in the first electronic data store is found associating the source medical device control device with a respective physical location and an entry in the second electronic data store is found associating a computer network device with a respective physical location, and the physical location associated with the source medical device control device in the first electronic data store is found to be different from the physical location associated with the computer network device in the second electronic data store, the entry in the first electronic data store may be modified to associate the source medical device control device with the physical location associated with the computer network device in the second electronic data store.

[0043] In any embodiment, modifying the entry in the first electronic data store to associate the source medical device controller with a physical location associated with the computer network device in the second electronic data store may include temporarily modifying the entry in the first electronic data store to associate the source medical device controller with a physical location associated with the computer network device in the second electronic data store, and then automatically modifying the entry in the first electronic data store to associate the source medical device controller with a default value.

[0044] Yet another aspect of the present invention provides a non-transitory computer-readable medium encoded with instructions that, when executed by a processor, establish processes for performing a computer-implemented method for locating and tracking a medical device control device, including a process configured to provide a first electronic data store and a process configured to provide a second electronic data store.

[0045] The first electronic data store is configured to store a plurality of first entries, each of which includes information associating a respective medical device control device with a respective physical location. The second electronic data store is configured to store a plurality of second entries, each of which includes information associating a respective computer network device with a respective physical location.

[0046] The process is configured to receive information identifying an identified medical device control device.

[0047] A process configured to receive information identifying an entered physical location of an identified medical device, the process configured to receive the information from a human user via a user interface.

[0048] The process is configured to store a new first entry in a first electronic data store, the new first entry associating the identified medical device controller with the entered physical location.

[0049] The process is configured to receive a message from a source medical device controller over a computer network, the message including an identifier for the source medical device controller, and the message also including an identifier for a computer network device.

[0050] The process is configured to automatically determine, in response to receiving the message, whether an entry in the first electronic data store associates the source medical device with the respective physical location.

[0051] and a process configured to, if an entry in the first electronic data store associating the source medical device control device with a respective physical location is found, store a new second entry in the second electronic data store associating the source medical device control device with the associated physical location and the computer network device. [Brief explanation of the drawings]

[0052] The present invention will be more fully understood from the following detailed description of specific embodiments taken in conjunction with the drawings.

[0053] [Figure 1] 1 is a perspective view of an exemplary conventional medical device control device and an exemplary conventional medical device, in this example a heart pump, coupled to the medical device control device, according to the prior art. [Figure 2] 2A-2C illustrate exemplary virtual display screen contents that may be displayed on the screen of the medical device control device of FIG. 1 according to the prior art. [Figure 3] FIG. 3 is a schematic block diagram of the main components of a medical device locating and tracking system for locating and tracking a medical device control device, such as the medical device control device of FIGS. 1 and 2, in accordance with one embodiment of the present invention. [Figure 4] 4 is a diagram illustrating schematically components of and operations performed by the server of FIG. 3 in accordance with one embodiment of the present invention. [Figure 5A] Figures 5A-5C (collectively Figure 5) form a flowchart that schematically illustrates operations performed by the server components of Figure 4, including operations performed by a first machine learning module (Figure 5A), an operation performed by a second machine learning module (Figure 5B), and an operation performed by a third machine learning module (Figure 5C), according to respective aspects of the present invention. [Figure 5B] See the legend to Figure 5A. [Figure 5C] See the legend to Figure 5A. [Figure 6] FIG. 6 illustrates an exemplary virtual user interface displayed on a display screen that may be implemented by the medical device control device of FIG. 1 to provide medical device location information to the server of FIGS. 3-5, according to one embodiment of the present invention. [Figure 7]FIG. 6 illustrates an exemplary virtual user interface displayed on a display screen that may be implemented by the monitoring station of FIG. 1 to provide medical device location information to the server of FIGS. 3-5, according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0054] Detailed Description of Specific Embodiments Aspects of the present invention provide methods and systems for automatically ascertaining physical location information for multiple medical device controllers and tracking changes in the physical location of each of the respective medical device controllers. These aspects utilize one or more machine learning modules to infer physical location from computer network messages received from the medical device controllers that include information about computer network components proximate to each of the medical device controllers.

[0055] context FIG. 1 is a perspective view of an exemplary conventional medical device controller 100 and an exemplary conventional medical device 102, in this example, a heart pump, coupled to the medical device controller 100. In the example shown in FIG. 1, the medical device controller 100 is an Automated Impella Controller® available from Abiomed, Inc. of Danvers, Massachusetts, and the heart pump 102 is an Impella® 2.5 heart pump, also available from Abiomed, Inc., although any suitable medical device and controller may be used. In some cases, the medical device and its associated medical device controller are combined. Such combinations are referred to herein simply as medical device controllers.

[0056] The medical device controller 100 includes a display screen 104 on which the medical device controller 100 displays operational data regarding the medical device 102, such as cardiac signal levels, battery temperature, blood flow, and tubing integrity. As discussed in more detail herein, the medical device controller 100 may be connected to a computer network, thereby transmitting images of the content displayed on the screen 104 to a remote server (not shown).

[0057] Figure 2 illustrates exemplary virtual display screen content 200 that may be displayed on the screen 104 of the medical device controller 100 of Figure 1. For example, the display screen content may include a heart pump type ("Impella 5.0") 202, a heart pump serial number ("120703") 204, warning / error messages 206, date and time 208, controller software version number 210, a power icon 212, a placement signal 214, a current heart pump speed (performance) setting ("P-0") 216, a heart pump motor current value 218, a current or average blood flow rate 220 and minimum and maximum blood flow rates 222, and various graphs 224. The display screen content 200 is typically pixelated.

[0058] Main components 3 is a schematic diagram of the major components of a medical device locating and tracking system 300. The system 300 may collect, store, and retrieve operational data from and relating to multiple medical device controllers 100. In addition, the system 300 locates and tracks each medical device controller 100 as it moves from one physical location to another.

[0059] For simplicity, only the medical device controller 100 is shown in FIG. 3 , not the individual medical devices. While only four medical device controllers 100 are shown, other numbers of medical device controllers 100 may be used. Each medical device controller 100 can optionally be connected to a computer network 302 via a remote link module 304. The computer network 302 may include wired and / or wireless segments and / or networks, such as a wireless network conforming to the IEEE 802.11x standard (wireless local area network (WLAN), commonly referred to as "Wi-Fi") represented by wireless access point 306 and / or a cellular network represented by cell site 308. The computer network 302 may include private and / or public networks, such as local area networks (LANs) 310, such as Ethernet networks, connected via routers 312, and / or wide area networks (WANs), such as metropolitan area networks (MANs) and / or the Internet (not shown).

[0060] Each medical device controller 100 is configured to automatically and repeatedly retrieve status information about connected medical devices and display the status information on a display screen 104 (FIG. 1). As noted above, FIG. 2 illustrates respective virtual display screen contents 200 that may be displayed on the screen 104 of any given medical device controller 100.

[0061] The server 314 is configured to automatically periodically or on an ad-hoc basis, typically about every 20 seconds, request and receive images of the content displayed on the display screen 104 of each medical device controller 100. The requests and images are transmitted over the computer network 302. The images may be transmitted in one or more messages encoded as a video frame or a sequence of video frames. The video frames may include, for example, a pixelated copy of the image displayed on the display screen 104 of the medical device controller 100.

[0062] The server 314 is configured to process the received frames (images). The server 314 parses the images and extracts text information, such as the heart pump serial number, blood flow rate, and warning message text, through an optical character recognition (OCR) portion of the image. The server 314 may also parse the images to extract graphical information, such as a power icon, and compare this graphical information to predetermined pixel patterns and / or colors. The server 314 may include an OCR engine or may communicate with an external OCR engine 316, such as via the computer network 302. The server 314 may then use the recognized text to automatically verify the serial numbers or other identifiers of the medical device controllers 100, the operating parameters of the medical device controllers 100, whether an alarm has been issued by one of the medical device controllers 100, and the like.

[0063] The data store 318 is configured to store frames (images) of one or more media files, particularly MP4 videos or other suitable types of media files, and the server 314 is configured to automatically store received frames (images) in the data store 318. The data store 318 records screen images received by the server 314 for later playback, such as in response to a request from one of several monitoring stations 320. For simplicity, only two monitoring stations 320 are shown, but any number of monitoring stations 320 may be included. The monitoring stations 320 may use cloud-based technology to securely and remotely display images of the screen 104 of the medical device controller 100 to physicians and hospital staff anywhere with an Internet connection. An exemplary remote monitoring system is available under the trade name Impella Connect® Online Device Management System from Abiomed, Inc. of Danvers, Massachusetts.

[0064] The data store 318 is configured to provide requested portions of stored media files in response to a request to provide them, thereby supporting playback of status information for the medical device controllers 100. For example, the data store 318 may provide one or more frames (images) of a video stored in a media file for display to a user by the monitoring stations 320. The server 314 may also be configured to provide status information regarding one or more of the medical device controllers 100 to each of the monitoring stations 320 based on images received by the server 314 in real time and / or based on historical information maintained in the data store 318.

[0065] Each monitoring station 320 may display information about multiple medical device controllers 100, including their respective physical locations. As noted above, each medical device controller 100 may be moved from one physical location to another, causing disruption to medical personnel viewing the monitoring station 320 if location information is missing or inaccurate. For example, a user of the monitoring station 320 may instruct the monitoring station 320 to display information about all medical device controllers 100 within a specified location. However, if location information is missing or incorrect for one or more of the medical device controllers 100, information about the incorrect set of medical device controllers 100 will be displayed to the user.

[0066] Automatic guessing of physical location To solve this problem, the server 314 includes components 400, shown generally in FIG. 4. Using these components 400, the server 314 automatically learns the physical locations of some or all of the medical device controllers 100 and automatically tracks changes in these physical locations. This process may begin with a user manually entering physical location information for a subset, such as one or more, of the medical device controllers 100. This information is stored in a first data store 402, associating the medical device controllers 100 with their respective physical locations. This process is referred to as seeding the first data store 402.

[0067] From this information, the server 314 infers the physical locations of components of the computer network 302. For example, if the server 314 communicates over the computer network 302 with a medical device controller 100 whose physical location is known, and the communication involves a network component such as a wireless access point 306 (FIG. 3) that is necessarily in close proximity to the medical device controller 100, the server 314 stores information in the second data store 404 that associates the network component with its respective physical location.

[0068] Necessary proximity does not require any particular proximity. The server 314 may use any available information, and the server 314 may replace known physical location information with more accurate physical location information as it becomes available. For example, the server 314 may initially store physical location information related to an Internet Protocol (IP) address, such as a physical location associated with an IP network to which the medical device controller 100 is connected, and then replace that location information with more accurate physical location information related to a wireless access point.

[0069] From the physical location information about the network components, the server 314 infers the physical location of a medical device controller 100 whose location is not yet known or whose physical location has changed from a previously known value. For example, if the server 314 communicates with a medical device controller 100 whose physical location is unknown, but the communication involves a network component that is necessarily proximate to the medical device controller 100 and whose location is known, the server 314 automatically infers the physical location of the medical device controller 100 from the physical location of the network component.

[0070] Similarly, if the server 314 communicates with a medical device control device 100 whose physical location is known, but the communication involves network components that are necessarily in close proximity to the medical device control device 100 and whose locations are known with greater accuracy than the physical location of the medical device control device 100, the server 314 automatically infers a more accurate physical location of the medical device control device 100 from the physical locations of the network components, and the server 314 updates the physical location of the medical device control device 100.

[0071] Similarly, if the server 314 communicates with a medical device controller 100 whose physical location is known, and the communication involves a network component that is necessarily proximate to the medical device controller 100, and the location of the network component is known, but the known location of the network component does not match the known location of the medical device controller 100, the server 314 automatically infers that the medical device controller 100 has been moved to a new physical location, and the server 314 infers the new physical location from the physical locations of the network components.

[0072] The server 314 may use other sources of physical location information 406. For example, some commercial vendors provide IP-based geographic location information that includes a physical location associated with an IP address. The server 314 may automatically ascertain or at least estimate the physical location of the medical device controller 100, or at least the address of the Internet Service Provider (ISP) that handles network traffic from the medical device controller 100, by querying such IP-based geographic location services or databases 408 using the IP address or a portion of the IP address from network messages from the medical device controller 100. Well-known Whois databases may also be used. Cell site databases may also be used. Thus, optionally or alternatively, the first data store 402 and / or the second data store 404 may be seeded with information from one or more geographic location service providers or databases 408.

[0073] 5 is a flowchart that generally illustrates operations performed by the server 314 to implement a method 500 for locating and tracking medical devices. At 502, a first electronic data store 402 is provided. The first data store 402 is configured to store a plurality of first entries. Each first entry includes information associating a respective medical device controller 100 with a respective physical location. Table 1 illustrates exemplary hypothetical contents of the first data store 402 in accordance with one aspect of the present invention. The left column lists identifiers for the medical device controllers 100, such as serial numbers. The right column lists physical location identifiers associated with each medical device controller 100 in the left column.

[0074] Table 1: Information Associating Medical Device Control Devices with Physical Locations [Table 1]

[0075] At 504 (FIG. 5), a second electronic data store 404 is provided. The second data store 404 is configured to store a plurality of second entries. Each second entry includes information associating a respective computer network component with a respective physical location. Table 2 illustrates exemplary hypothetical contents of the second data store 404 according to one embodiment of the present invention. The left column lists a network component identifier, such as an IP address or media access control (MAC) address of a network or router (e.g., local area network 310 or router 312), a service set identifier (SSID) of a wireless access point (e.g., wireless access point 306), a GSM cell identifier (CID) of a base transceiver station (BTS), or a sector of a BTS. The right column lists a physical location identifier associated with each network component in the left column.

[0076] (Table 1) Information relating computer network components to physical locations [Table 2]

[0077] At 506 (FIG. 5), information identifying the medical device controller (the "identified medical device controller") is received, and at 508, information identifying the physical location of the identified medical device (the "entered physical location") is received. As described above, the first data store 402 may be seeded with one or more user entries. The server 314 (FIG. 3) may include a user interface 410 (FIG. 4) through which a user may enter information identifying the physical location of the medical device controller 100, and optionally, information identifying the medical device controller 100.

[0078] One embodiment of such a user interface 410 is implemented by the medical device controller 100. FIG. 6 shows an exemplary user interface 600 displayed on the display screen 104 of the medical device controller 100. In this embodiment, the display screen 104 is a touch-sensitive screen capable of receiving user input, although in other embodiments, a physical keyboard may be connected to the medical device controller 100. The user interface 600 includes a prompt 602 and an area 604 where the user can enter text identifying the physical location of the medical device controller 100. The user interface 600 also includes a virtual keyboard 606 on the touch-sensitive display screen 104 where the user can make input. A virtual entry is shown at 608. The user's input constitutes the physical location identifying information 412 (FIG. 4) entered into the user interface 410.

[0079] The user does not need to enter information identifying the medical device controller 100 because the medical device controller 100 already stores information such as its serial number, as shown on the display screen 104 at 204. When the medical device controller 100 transmits the user's input 608 to the server 314, the medical device controller 100 also transmits its serial number or other identifying information. The serial number or other identifying information constitutes the information identifying the medical device controller 414 (FIG. 4).

[0080] In another embodiment, the user interface 410 is implemented by one of the monitoring stations 320 (FIG. 3). FIG. 7 shows an exemplary user interface 700 displayed on a display screen 702 of the monitoring station 320. In this embodiment, the display screen 702 may be a touch-sensitive screen, similar to the user interface 600 described with respect to FIG. 6. Optionally or alternatively, a physical keyboard may be connected to the monitoring station 320. The user interface 700 includes a prompt 704 and an area 708 where a user can enter text identifying the medical device controller 100, such as the serial number 710 of the medical device controller 100. The user interface 700 includes a prompt 712 and an area 714 where a user can enter text identifying the physical location of the medical device controller 100. A virtual entry is shown at 716. The user entries 710 and 716 constitute the medical device controller identifying information 414 (FIG. 4) and the physical location identifying information 412.

[0081] In yet another aspect, the user interface 410 is implemented via an administrative console (not shown) communicatively coupled to the server 314. The administrative console may be implemented by a physical or virtual display and keyboard, a telnet connection from another computer, or any other suitable interface.

[0082] Based on the information the user interface 410 collects, i.e., information 414 identifying the medical device controller 100 and information 412 identifying the physical location, the user interface 410 stores a new first entry 416 in the first electronic data store 402, as shown in operation 510 (FIG. 5). The new first entry associates the identified medical device controller 100 with the entered physical location, as discussed with respect to Table 1.

[0083] As described above, the medical device controller 100 sends messages to the server 314 via the computer network 302 to communicate images of the display screen 104 on the medical device controller 100. These messages include a "from" address that identifies the respective medical device controller 100. The medical device controller 100 may send additional messages to the server 314 via the computer network 302. These additional messages may include information about the network environment sensed by the medical device controller 100. From this information, the server 314 can infer which network components are in proximity to the medical device controller 100. The server 314 includes a receiver 418 (FIG. 4) configured to receive these network messages 420.

[0084] For example, if the medical device controller 100 is wireless network-enabled, the medical device controller 100 transmits to the server 314 information, such as an SSID, that identifies wireless access points 306 or other wireless infrastructure that are within wireless range of the medical device controller 100 and with which the medical device controller 100 can communicate wirelessly. Optionally, this information may include relative or absolute received signal strength indicators (RSSIs) of the in-range wireless access points 306 or other wireless infrastructure, as measured by the medical device controller 100. Based on the RSSIs, the server 314 can infer the relative proximity of the identified wireless access points 306 to the medical device controller 100, for example, based on the relative strength of the signals from the various wireless access points 306.

[0085] In another example, the medical device controller 100 sends a message to the server 314 identifying other network components, such as routers, switches, etc., with which the medical device controller 100 has communicated. The medical device controller 100 may use tools such as traceroute, ping, etc. to probe its network environment and automatically determine the relative proximity of the network components to the medical device controller 100. The medical device controller can then send this proximity information, as well as the identifiers of each network component, to the server 314.

[0086] Thus, any message received by server 314 may include information 422 (FIG. 4) identifying the originating medical device controller 100 and information 424 identifying the computer network component. This operation is summarized in operation 512 (FIG. 5), where server 314 receives message 420 from originating medical device controller 100 over computer network 302. The message includes (a) identifier 422 of the originating medical device controller 100 and (b) identifier 424 of the computer network component.

[0087] The first machine learning module infers the location of network components. At 514 (FIG. 5), in response to receiving message 420, server 314 automatically determines whether an entry in first electronic data store 402 associates source medical device controller 100 with a respective physical location. This test determines whether first electronic data store 402 contains such an association, not whether source medical device controller 100 is associated with a particular physical location. If, at 516, an entry in first electronic data store 402 is found associating source medical device controller 100 with a respective physical location, control proceeds to 518, where first machine learning module 426 in server 314 stores a new second entry 428 in second electronic data store 404. As discussed with respect to Table 2, new second entry 428 associates a computer network component with the physical location associated with source medical device controller 100.

[0088] The computer network device identifier 424 may identify a computer network component with which the originating medical device controller 100 has communicated or a computer network component with which the originating medical device controller 100 has directly communicated wirelessly. For example, the computer network device identifier 424 may identify a wireless access point 306 (FIG. 3) with which the originating medical device controller 100 has directly communicated wirelessly, or a base station identifier for a cellular base station 308 with which the originating medical device controller 100 has directly communicated wirelessly. The computer network component identifier 424 may identify a computer network component through which the message 420 has traveled on its way to the receiver 418. The computer network component identifier 424 may include, for example, an IP address or a MAC address.

[0089] A second machine learning module estimates the location of the medical device controller. The server 324 may include a second machine learning module 430 (FIG. 4) that may be configured to automatically determine, in response to receiving the message 420, whether an entry in the first electronic data store 402 associates the source medical device controller 100 (identified by ID 422) with a respective physical location, as shown at operation 520 (FIG. 5).

[0090] If no entry is found in the first electronic data store 402 associating the source medical device controller 100 with the respective physical location, control proceeds from operation 522 to operation 524, where the server 314 determines whether an entry in the second electronic data store 404 associates the computer network component (identified by ID 424) with the respective physical location. If no entry is found in the first electronic data store 402 associating the source medical device controller 100 with the respective physical location, and if an entry is found in the second electronic data store 404 associating the computer network component with the respective physical location at operation 524, control proceeds from operation 526 to operation 528, where the second machine learning module 430 stores a new first entry 432 in the first electronic data store 402. The new first entry 432 associates the source medical device controller 100 (identified by ID 422) with the physical location associated with the computer network component (identified by ID 424). The locations of the computer network components are copied from the second data store 404 as represented in the right column of Table 2.

[0091] The third machine learning module predicts the behavior of medical device controllers. The server 324 may include a third machine learning module 434 (FIG. 4), which may be configured to automatically determine, in response to receiving the message 420, whether an entry in the first electronic data store 402 associates the source medical device controller 100 (identified by ID 422) with a respective physical location, as shown at operation 530. If an entry in the first electronic data store 402 is found that associates the source medical device controller 100 with a respective physical location, control proceeds from operation 532 to operation 534, where the server 314 determines whether an entry in the second electronic data store 404 associates the computer network component (identified by ID 424) with the respective physical location.

[0092] If an entry is found in the first electronic data store 402 associating the source medical device controller 100 with a respective physical location, and if an entry is found in the second electronic data store 404 associating a computer network component with a respective physical location at operation 534, control passes from operation 536 to operation 538. At operation 538, the server compares the physical location associated with the source medical device controller 100 in the first electronic data store 402 with the physical location associated with the computer network component in the second electronic data store 404.

[0093] If an entry is found in the first electronic data store 402 associating the source medical device controller 100 with a respective physical location and an entry is found in the second electronic data store 404 associating a computer network device with a respective physical location, and if operation 540 determines that the physical location associated with the source medical device controller 100 in the first electronic data store 402 is different from the physical location associated with the computer network device in the second electronic data store 404, then in operation 542 the server modifies the entry 436 (FIG. 4) in the first electronic data store 402 to associate the source medical device controller 100 with the physical location associated with the computer network device in the second electronic data store 404.

[0094] In some embodiments, in operation 542, the server only temporarily modifies the entry 436 (FIG. 4) in the first electronic data store 402 to associate the source medical device controller 100 with the physical location associated with the computer network device in the second electronic data store 404. Subsequently, for example, after a predetermined time, the server modifies the entry 436 (FIG. 4) in the first electronic data store 402 to associate the source medical device controller 100 with a default location, as shown in operation 544.

[0095] In any embodiment, the third machine learning module may be configured to temporarily modify the entry in the first electronic data store to associate the source medical device controller with a physical location associated with the computer network device in the second electronic data store. The third machine learning module may be further configured to automatically subsequently modify the entry in the first electronic data store to associate the source medical device controller with a default value.

[0096] implementation The server 314, including the first, second, and third machine learning modules 426, 430, and 434, and the receiver 418, may be implemented by a processor executing instructions stored in a memory. The instructions may include instructions for implementing a process that implements the method 500 described with respect to FIG. 5 and the user interfaces described with respect to FIGS. 6 and 7.

[0097] The first data store 402 and the second data store 404 may be implemented using relational databases and may include a front end (load balancer) that distributes access requests across multiple copies of the database to support large volumes of requests.

[0098] As used herein and in the appended claims, phrases such as "automatically determining whether entries in a first electronic data store associate the source medical device controller (or network component) with a respective physical location" refer to determining whether the electronic data store contains such an association, not whether the source medical device controller (or network component, as the case may be) is associated with a particular physical location. In such phrases, "respective physical location" does not mean a particular physical location, but rather any physical location. Thus, the determination does not involve a comparison with a particular physical location. Instead, the determination simply checks whether an association currently exists.

[0099] Thus, if the data store contains information documenting such an association, the result of the determination is true; whereas, if the data store does not contain information documenting such an association, the result of the determination is false. The result of the determination may be referenced in a subsequent phrase such as, "If an entry in the electronic data store is found that associates the source medical device controller (or network component, as the case may be) with a respective physical location, then..." Because no specific physical location is referenced in such a phrase, "respective physical location" does not raise an antecedent or clarity issue. This phrase is equivalent to, "If the previous determination produced a true result, then..."

[0100] While the present invention has been described through the above exemplary embodiments, modifications to and variations of the exemplary embodiments may be made without departing from the inventive concepts disclosed herein. For example, while specific network component identifiers, such as IP addresses and SSIDs, may be described in connection with the disclosed embodiments within the scope of the present invention, the values ​​of all parameters may vary widely to suit various applications.

[0101] As used herein, including the appended claims, the term "and / or" when used in connection with a list of items means one or more of the items in the list, i.e., at least one of the items in the list, but not necessarily all of the items in the list. As used herein, including the appended claims, the term "or" when used in connection with a list of items means one or more of the items in the list, i.e., at least one of the items in the list, but not necessarily all of the items in the list. "Or" does not mean "exclusive or."

[0102] Although aspects of the embodiments may be described with reference to flowcharts and / or block diagrams, the functions, operations, decisions, etc. of all or part of each block, or combinations of blocks, may be combined, separated into separate operations, or performed in other orders. References to "modules" are for convenience only and are not intended to limit the implementation. All or part of each block, module, or combination thereof may be implemented as computer program instructions (e.g., software), hardware (e.g., combinational logic, application-specific integrated circuit (ASIC), field programmable gate array (FPGA), processor, or other hardware), firmware, or a combination thereof.

[0103] The first machine learning module 426, the second machine learning module 430, and the third machine learning module 434, the receiver 418, and the server 314, including portions thereof, may be implemented or controlled by one or more processors that execute instructions stored in memory. Each processor may be a general-purpose processor such as a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a special-purpose processor, or the like, or a combination thereof, as appropriate.

[0104] The memory may be random access memory (RAM), read-only memory (ROM), flash memory, or any other memory, or combination thereof, suitable for storing control software or other instructions and data. Instructions defining the functionality of the present invention may be provided to a processor in many forms, including, but not limited to, information persistently stored on a tangible, non-transitory, non-writable storage medium (e.g., a read-only memory device within the computer, such as a ROM, or a device readable by a computer I / O attachment, such as a CD-ROM or DVD disk), information revocably stored on a tangible, non-transitory, writable storage medium (e.g., a floppy disk, removable flash memory, and hard drive), or information transmitted to a computer via a communications medium, including a wired or wireless computer network. Furthermore, although aspects may be described with reference to various exemplary data structures, the system may be embodied using a variety of data structures.

[0105] Aspects of the disclosure, or portions thereof, may be combined in ways not described above and / or not expressly claimed. In addition, the embodiments disclosed herein may suitably be practiced in the absence of any element not specifically disclosed herein. Thus, the present invention should not be considered limited to the disclosed embodiments.

[0106] As used herein, numerical terms such as "first," "second," and "third" are used to distinguish elements from one another and are not intended to indicate a particular order or total number of elements in a particular embodiment. Thus, for example, a given embodiment may include only a second machine learning module and a third machine learning module.

Claims

1. 1. A system including one or more processors, the one or more processors: receiving a message from a medical device controller that includes operational data related to a medical device communicatively coupled to the medical device controller, the message having passed through a computer network device on its way to the one or more processors; determining whether an entry in a first electronic data store associates the medical device controller with a physical location; determining whether an entry in a second electronic data store associates said computer network device with a physical location; (a) if an entry in the first electronic data store is found associating the medical device control device with a physical location, and (b) if an entry in the second electronic data store is not found associating the computer network device with a physical location, storing a new entry in the second electronic data store, the new entry stored in the second electronic data store associating the computer network device with the physical location that was associated with the medical device control device in the first electronic data store; (a) if an entry in the first electronic data store associating the medical device control device with a physical location is not found, and (b) if an entry in the second electronic data store associating the computer network device with a physical location is found, storing a new entry in the first electronic data store, the new entry stored in the first electronic data store associating the medical device control device with the physical location that was associated with the computer network device in the second electronic data store; (a) an entry in the first electronic data store is found associating the medical device controller with a physical location, and (b) an entry in the second electronic data store is found associating the computer network device with a physical location, and (c) a comparison indicates that the physical location associated with the medical device controller in the first electronic data store is different from the physical location associated with the computer network device in the second electronic data store, modifying the entry in the first electronic data store to associate the medical device controller with the physical location associated with the computer network device in the second electronic data store; transmitting the physical location associated with the medical device controller by the one or more processors to a monitoring station for display; A system that is configured to:

2. The system of claim 1 , wherein the computer network device has communicated directly with the medical device controller.

3. The system of claim 1 or 2, wherein the computer network device has wireless communication with the medical device control device.

4. The system of any one of claims 1 to 3, wherein the computer network device comprises a base station.

5. after modifying the entry in the first electronic data store to associate the medical device control device with the physical location that was associated with the computer network device in the second electronic data store; 5. The system of claim 1, wherein the one or more processors are further configured to modify the entry in the first electronic data store to associate the medical device control device with a default value.

6. 6. The system of claim 1, wherein at least one entry in the first electronic data store is generated in response to a human user providing the physical location of the medical device control device via a user interface of the medical device control device.

7. The system of any one of claims 1 to 6, wherein the medical device communicatively coupled to the medical device control device is a heart pump.

8. 1. A method executed by one or more processors for locating and tracking a medical device controller, comprising: receiving, at the one or more processors, a message from a medical device controller that includes operational data related to a medical device communicatively coupled to the medical device controller, the message having passed through a computer network device on its way to the one or more processors; determining, by the one or more processors, whether an entry in a first electronic data store associates the medical device controller with a physical location; determining, by the one or more processors, whether an entry in a second electronic data store associates the computer network device with a physical location; and (b) if an entry in the second electronic data store associating the computer network device with a physical location is not found, storing, by the one or more processors, a new entry in the second electronic data store, the new entry stored in the second electronic data store associating the computer network device with the physical location that was associated in the first electronic data store with the medical device control device; and (b) if an entry is found in the second electronic data store associating the computer network device with a physical location, storing, by the one or more processors, a new entry in the first electronic data store, the new entry stored in the first electronic data store associating the medical device control device with the physical location that was associated with the computer network device in the second electronic data store; (a) an entry in the first electronic data store is found associating the medical device controller with a physical location, and (b) an entry in the second electronic data store is found associating the computer network device with a physical location, and (c) a comparison indicates that the physical location associated with the medical device controller in the first electronic data store is different from the physical location associated with the computer network device in the second electronic data store, modifying, by the one or more processors, the entry in the first electronic data store to associate the medical device controller with the physical location associated with the computer network device in the second electronic data store; transmitting, by the one or more processors, the physical location associated by the one or more processors with the medical device control device to a monitoring station for display; A method comprising:

9. The method of claim 8 , wherein the computer network device has communicated directly with the medical device controller.

10. 10. The method of claim 8 or 9, wherein the computer network device has communicated wirelessly with the medical device controller.

11. The method of any one of claims 8 to 10, wherein the computer network device is a wireless access point.

12. The method of any one of claims 8 to 11, wherein the computer network device is a cellular base station.

13. modifying the entry in the first electronic data store to associate the medical device control device with the physical location associated with the computer network device in the second electronic data store; temporarily modifying the entry in the first electronic data store to associate the medical device control device with the physical location associated with the computer network device in the second electronic data store; subsequently modifying the entry in the first electronic data store to associate the medical device control device with a default value; The method according to any one of claims 8 to 12, comprising:

14. The method of any one of claims 8 to 13, wherein the medical device communicatively coupled to the medical device controller is a heart pump.

15. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by one or more processors, cause the one or more processors to: receiving a message from a medical device controller that includes operational data related to a medical device communicatively coupled to the medical device controller, the message having passed through a computer network device on its way to the one or more processors; determining whether an entry in a first electronic data store associates the medical device controller with a physical location; determining whether an entry in a second electronic data store associates said computer network device with a physical location; (a) if an entry in the first electronic data store is found associating the medical device control device with a physical location, and (b) if an entry in the second electronic data store is not found associating the computer network device with a physical location, storing a new entry in the second electronic data store, the new entry stored in the second electronic data store associating the computer network device with the physical location that was associated with the medical device control device in the first electronic data store; (a) if an entry in the first electronic data store associating the medical device control device with a physical location is not found, and (b) if an entry in the second electronic data store associating the computer network device with a physical location is found, storing a new entry in the first electronic data store, the new entry stored in the first electronic data store associating the medical device control device with the physical location that was associated with the computer network device in the second electronic data store; (a) an entry in the first electronic data store is found associating the medical device controller with a physical location, and (b) an entry in the second electronic data store is found associating the computer network device with a physical location, and (c) a comparison indicates that the physical location associated with the medical device controller in the first electronic data store is different from the physical location associated with the computer network device in the second electronic data store, modifying the entry in the first electronic data store to associate the medical device controller with the physical location associated with the computer network device in the second electronic data store; transmitting the physical location associated with the medical device controller by the one or more processors to a monitoring station for display; A non-transitory computer-readable storage medium that causes

Images