Method and apparatus for determining device dose

Abstract

The technology described herein relates to computerized methods and apparatus for determining a dose injected into a user by one or more drug delivery devices. Data indicative of a set of injection events is accessed, the set of injection events including one or more injection events associated with one or more drug delivery devices. The set of injection events is processed to determine a dose injected into the user based on one or more of: whether the injection event is associated with a change in the drug delivery device, a dose size of the one or more injection events, a location of the one or more injection events in the set of injection events, and a dose size of the one or more injection events. And / or a time period between the one or more injection events and a next injection event in the group of injection events.

Description

Background Art

[0001] Drug delivery devices include injection-type delivery devices that inject a drug dose. Reusable injection devices typically include a reservoir that holds the drug, and a dose setting mechanism that allows a user to set a desired dose size for each injection. An insulin pen is an example of a reusable injection device. The insulin pen includes a reservoir of insulin sufficient for multiple doses over an extended period of time (e.g., over several days or weeks). The insulin pen also allows the user to specifically adjust the unit amount to be delivered with each injection.

[0002] Patients using a drug delivery device (e.g., an insulin pen) typically need to follow a prescribed dose schedule, which may include multiple injections throughout the day, and the dose size for each injection. The patient must manually track each injection and the dose size, which can be cumbersome, tedious, and prone to human error. Summary of the Invention

[0003] The present disclosure relates to techniques for determining injection dose information. In some embodiments, the techniques can process multiple injection events to distinguish non-events (e.g., priming events) from actual injection doses. In some embodiments, the techniques can incorporate change information (e.g., cartridge change and / or switching drug delivery devices) into the analysis to determine injection doses taking into account change events.

[0004] Various aspects are described in the present disclosure, including but not limited to the following aspects: 1. A computerized method for determining a dose injected into a user by one or more drug delivery devices, the method comprising: Accessing data indicative of a group of injection events, the group of injection events including one or more injection events associated with one or more drug delivery devices, wherein each of the one or more drug delivery devices includes: A dose adjustment mechanism that allows a user to adjust the amount of the dose for an injection of the drug delivery device; a reservoir sized to hold a drug for multiple doses; One or more sensors for detecting the amount of the dose allocated for each injection; and A wireless communication unit that conveys the amount of the dose allocated and the time at which it is allocated; Determining whether the group of injection events is associated with a drug delivery device change; When determining that the group of injection events is not associated with the drug delivery device change, analyzing the group of injection events based on a first dose detection algorithm to determine the dose administered to the user; and When determining that the injection event group is associated with a drug delivery device change, analyze the injection event group based on a second dose detection algorithm to determine the dose administered to the user.

[0005] 2. The computerized method according to aspect 1, wherein: The one or more drug delivery devices include a previous drug delivery device and a new drug delivery device; and Determining whether the injection event group is associated with a drug delivery device change includes: determining whether the user switches from using the previous drug delivery device to using the new drug delivery device within a predetermined time window of the injection event group.

[0006] 3. The computerized method according to aspect 1, wherein: The one or more drug delivery devices include one drug delivery device; and Determining whether the injection event group is associated with a drug delivery device change includes: determining whether there is a change in a replaceable cartridge of the one drug delivery device within a predetermined time window of the injection event group.

[0007] 4. The computerized method according to aspect 1, wherein analyzing the injection event group based on a first dose detection algorithm includes: Determining that the number of injection events in the injection event group is greater than two; and Determining that the dose is equal to the injection amount associated with the latest injection event in the injection event group, wherein the latest injection event occurs later in time than any other injection event in the injection event group.

[0008] 5. The computerized method according to aspect 4, wherein the latest injection event is designated as a true injection event, and all other injection events in the injection event group are each designated as a fill injection event.

[0009] 6. The computerized method according to aspect 1, wherein analyzing the injection event group based on a first dose detection algorithm includes: Determining that the number of injection events in the injection event group is equal to two, wherein the injection event group includes: A first injection event associated with a first time; and A second injection event associated with a second time later than the first time; and Determining whether a first injection amount associated with the first injection event is greater than a second injection amount associated with the second injection event.

[0010] 7. The computerized method according to aspect 6 further includes, when determining that the first injection event is greater than the second injection event, determining the dose based on the sum of the first injection amount and the second injection amount.

[0011] 8. The computerized method according to aspect 6 further includes, when determining that the first injection event is not greater than the second injection event, determining that the dose is equal to the second injection amount.

[0012] 9. The computerized method according to aspect 8, wherein the first injection event is designated as a priming injection event.

[0013] 10. The computerized method according to aspect 1, wherein analyzing the set of injection events based on a second dose detection algorithm includes: determining whether a change time associated with a change of the drug delivery device is (i) later than or earlier than each time associated with each injection event in the set of injection events, or (ii) later than a time associated with at least one injection event in the set of injection events and earlier than another time associated with at least one other injection event in the set of injection events.

[0014] 11. The computerized method according to aspect 10 further includes: when determining that the change time is later than or earlier than each time associated with each injection event in the set of injection events, determining that the dose is equal to the injection amount associated with the latest injection event in the set of injection events, wherein the latest injection event occurs later in time than any other injection event in the set of injection events.

[0015] 12. The computerized method according to aspect 11, wherein the remaining injection events are designated as priming injection events.

[0016] 13. The computerized method according to any one of aspects 10 or 11 further includes: when determining that the change time is later than a time associated with at least one injection event in the set of injection events and earlier than another time associated with at least one other injection event in the set of injection events, determining: a first subset of injection events, the first subset of injection events including each injection event in the set of injection events associated with a time that occurs before the change time; and a second subset of injection events, the second subset of injection events including each injection event in the set of injection events associated with a time that occurs after the change time.

[0017] 14. The computerized method according to aspect 13 further includes determining the dose based on the sum of the following: The most recent injection event in the first sub-injection event group, wherein the most recent injection event occurs later in time than any other injection event in the first sub-injection event group; and The most recent injection event in the second sub-injection event group, wherein the most recent injection event occurs later in time than any other injection event in the second sub-injection event group.

[0018] 15. The method according to aspect 14, wherein the remaining injection events in the first sub-injection event group and the remaining injection events in the second sub-injection event group are designated as fill injection events.

[0019] 16. The method according to aspect 1, further comprising determining the injection event group.

[0020] 17. The method according to aspect 16, wherein: Determining the injection event group includes determining that a plurality of injection events meet a predetermined criterion; and Determining that a plurality of injection events meet a predetermined criterion includes: for each injection event in the plurality of injection events, determining that the time associated with the injection event is within a predetermined time period of the previous injection event in the plurality of injection events.

[0021] 18. A non-transitory computer-readable medium including instructions that, when executed by one or more processors on a computing device, are operable to cause the one or more processors to perform the method according to any one of aspects 1-17.

[0022] 19. A system including a memory storing instructions and a processor, the processor being configured to execute the instructions to perform the method according to any one of aspects 1-17.

[0023] 20. A computerized method for determining a dose injected into a user by one or more drug delivery devices, the method comprising: Accessing data indicating an injection event group, the injection event group including one or more injection events associated with one or more drug delivery devices, wherein each of the one or more injection events occurs within a predetermined time period, and wherein each of the one or more drug delivery devices includes: A dose adjustment mechanism that allows a user to adjust the amount of the dose for an injection of the drug delivery device; a reservoir sized to accommodate a plurality of doses of the drug; One or more sensors for detecting the amount of the dose allocated for each injection; and A wireless communication unit that conveys the amount of the dispensed dose and the dispensed time; Determining the dose administered to a user, including: Determining whether the set of injection events includes a first injection event and a second injection event that occurs after the first injection event; and When determining that the set of injection events includes the first injection event and the second injection event, determining whether the first injection event is associated with a dose administered to the user or a priming dose not administered to the user based on the time period between the first injection event and the second injection event.

[0024] 21. The computerized method according to aspect 20, wherein the predetermined time period is between four minutes and six minutes.

[0025] 22. The computerized method according to aspect 20, wherein determining the dose administered to a user includes: determining whether the injection event is associated with a dose administered to the user or a priming dose not administered to the user based on the dose magnitude of the injection event in the set of injection events.

[0026] 23. The computerized method according to aspect 22, further comprising: Determining whether the dose magnitude is greater than a first predetermined threshold; When determining that the dose magnitude is greater than the first predetermined threshold, determining that the injection event is associated with a dose administered to the user; and When determining that the dose magnitude is not greater than the first predetermined threshold, determining the dose administered to the user based on whether there is a next injection event that occurs after the injection event in the set of injection events.

[0027] 24. The computerized method according to aspect 23, wherein the first predetermined threshold is a dose magnitude between nine units and eleven units.

[0028] 25. The computerized method according to aspect 23, further comprising: when determining that the dose magnitude is not greater than the first predetermined threshold: Determining whether there is a next injection event that occurs after the injection event in the set of injection events; When determining that there is no next injection event in the set of injection events, determining that the injection event is associated with a dose administered to the user; and When determining that there is a next injection event in the set of injection events, determining the dose administered to the user based on the time period between the injection event and the next injection event in the set of injection events.

[0029] 26. The computerized method according to aspect 20, wherein determining the dose administered to the user based on the time period between the first injection event and the second injection event comprises: determining whether the time period is less than a second predetermined threshold; when determining that the time period is less than the second predetermined threshold, determining that the first injection event is associated with a priming dose not administered to the user; and when determining that the time period is not less than the second predetermined threshold, determining the dose administered to the user based on the dose magnitude of the first injection event.

[0030] 27. The computerized method according to aspect 26, wherein the second predetermined threshold is a time period between 75 seconds and 85 seconds.

[0031] 28. The computerized method according to aspect 26, wherein determining the dose administered to the user based on the dose magnitude of the first injection event comprises: determining whether the dose magnitude is greater than a third predetermined threshold; when determining that the dose magnitude is greater than the third predetermined threshold, determining that the first injection event is associated with the dose administered to the user; and when determining that the dose magnitude is not greater than the third predetermined threshold, determining that the first injection event is associated with a priming dose not administered to the user.

[0032] 29. The computerized method according to aspect 28, wherein the third predetermined threshold is a dose magnitude between four units and five units.

[0033] 30. A non - transitory computer - readable medium comprising instructions that, when executed by one or more processors on a computing device, are operable to cause the one or more processors to perform the method according to any one of aspects 20 - 29.

[0034] 31. A system comprising a memory storing instructions and a processor, the processor being configured to execute the instructions to perform the method according to any one of aspects 20 - 29. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Additional embodiments of the present disclosure, as well as their features and advantages, will become more apparent by reference to the description herein in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale. Further, in the drawings, like reference numerals denote corresponding parts in different views.

[0036] Figure 1 is an illustrative example of a drug delivery device according to some examples; Figure 2is a flowchart showing an exemplary computerized process for determining a group of injection events according to some embodiments; Figures 3A - 3B is a table showing an example of a group of injection events according to some embodiments; Figures 4A - 4B is a flowchart showing an exemplary computerized process for determining a dose based on a group of injection events according to some embodiments; Figures 5A - 5C is a table showing an example of dose determination for a group of injection events not associated with a change in a drug delivery device according to some embodiments; Figures 6A - 6B is a table showing an example of dose determination for a group of injection events associated with a change in a drug delivery device according to some embodiments; Figure 7 is a flowchart showing an exemplary computerized process for determining a dose based on a group of injection events including one or more injection events occurring within a predetermined time period according to some embodiments; Figures 8A - 8E is a table showing an example of dose determination for an exemplary group of injection events in which the injection events occur within a predetermined time period of five minutes according to some embodiments; Figure 9 is a flowchart showing an exemplary computerized process for determining a dose based on a group of injection events according to some embodiments; Figures 10A - 10C is a table showing an example of dose determination for an exemplary group of injection events according to some embodiments; and Figure 11 is a diagram of an exemplary system for implementing the computerized processes described herein according to some embodiments. DETAILED DESCRIPTION

[0037] For purposes of facilitating an understanding of the principles of the present disclosure, reference will now be made to the embodiments illustrated in the drawings, and specific language will be used to describe these embodiments. However, it should be understood that no limitation of the scope of the invention is thereby intended.

[0038] This disclosure relates to techniques for accurately determining dose injection information. A drug delivery device (e.g., an insulin pen) can be disposable or reusable. When a user depletes the insulin in the reservoir, the disposable pen is discarded and replaced as a whole. The reusable pen has a port for receiving an insulin cartridge. Once the cartridge is used up, the user can discard the old cartridge and insert a new one. For example, U.S. Patent No. 7,195,616, entitled MEDICATION INJECTOR APPARATUS WITH DRIVE ASSEMBLY THAT FACILITATES RESET, issued on March 27, 2007, describes an example of a reusable insulin pen, which is incorporated herein by reference in its entirety.

[0039] Insulin pens typically need to be primed regularly before use. Priming generally involves the user deliberately injecting a small amount of insulin (e.g., injecting into the air) in order to clear excess air remaining in the needle or elsewhere in the fluid path between the insulin reservoir of the pen and the needle tip. If the pen is not properly primed before use, air in the needle and / or fluid path may cause the pen to inject less insulin than the requested amount.

[0040] Since it can be cumbersome and error-prone for a user to manually track injections and doses, a drug delivery device can include wireless capabilities (e.g., WiFi, Bluetooth, NFC, etc.) that can wirelessly report injection event information, including the time and dose size of an insulin injection. As used herein, an "injection event" can refer to a discrete dose of insulin delivered at a particular time. The injection event information can be transmitted to a remote device, such as a smart phone (e.g., running a mobile app) or a cloud server. It is necessary to distinguish between the actual injection dose of insulin injected into a patient's body and the priming dose that is not injected into the patient's body. If the priming dose is mistaken for the actual dose, the remote device and / or cloud server may incorrectly determine that the user has injected more insulin than he / she actually has. This incorrect determination may in turn affect the validity of the user's insulin dose log, as well as the calculation of the amount of insulin on board (e.g., the amount of effective, unused insulin circulating through the user's body). The incorrect on-board insulin calculation may in turn affect the validity of subsequent bolus calculations.

[0041] There is also a need to identify split doses, where a user splits a single dose between two or more pens (e.g., disposable insulin pens) or replaces the insulin cartridge of a reusable pen in the middle of a dose.

[0042] The following example illustrates the need for detecting both fill doses and dispensed doses. Assume a user needs to take 15 units of insulin, but only 7 units remain in her pen. The user can fill her pen by expelling 2 units of a small dose into the air. The user then injects the remaining 5 units. The user then discards the empty pen and selects a new pen (or, if the pen is a reusable pen, replaces the used insulin cartridge). The user fills the new pen (or new insulin cartridge) by expelling 3 small doses of 2 units each until the user feels there is no air left in the needle. Once the new pen or cartridge is properly filled, the user injects the remaining 10 units.

[0043] In the case of this example, a device receiving injection event data will receive data indicating the following order of injection doses: 2, 5, 2, 2, 2, and 10 units of insulin. If the device assumes all of these doses are actual doses, it will overestimate the amount of insulin the user actually ingested (e.g., it will determine the user injected 23 units of insulin when in fact the user only injected 15 units). Thus, there is a need to distinguish between the actual dose injected into the patient and the fill dose, and also to identify when doses are dispensed on two separate pens or cartridges.

[0044] The techniques described herein provide computer-implemented techniques (e.g., computer applications such as mobile phone applications or cloud-based applications) that provide for accurately determining the dose injected into a patient by a drug delivery device. In some embodiments, the techniques can be configured to, for example, determine groups of injection events based on the injection event times (e.g., by grouping injection events that occur within five minutes of each other). Such groups of injection events can include any group of one or more injection events. In some embodiments, the techniques can be configured to process a group of injection events based on whether the group of injection events is associated with a device change (e.g., a user switching to a new disposable drug delivery device and / or changing the cartridge of a reusable drug delivery device). If the group of injection events is not associated with a device change, the techniques can process the group of injection events according to a first algorithm that is configured to determine dose information for a group of injection events not associated with a device change. If the group of injection events is associated with a device change, the techniques can use a second algorithm to process the group of injection events, the second algorithm being configured to determine dose information for a group of injection events associated with a device change.

[0045] In some embodiments, the technology may be configured to determine a group of injection events that occur within a certain time period (e.g., injection events that occur within a five-minute period). In some embodiments, the dose administered to the user may be determined by determining whether each injection event is associated with a dose administered to the user or a fill dose not administered to the user. This determination may include determining whether the group of injection events includes a first injection event and a second injection event that occurs after the first injection event. When it is determined that the group of injection events includes the first injection event and the second injection event, the determination may also be based on the time period between the first injection event and the second injection event.

[0046] Although various embodiments have been described, it will be apparent to those of ordinary skill in the art that more embodiments and implementations are possible. Accordingly, the embodiments described herein are examples and not the only possible embodiments and implementations. Additionally, the above advantages are not necessarily the only advantages, and it is not necessarily expected that all of the described advantages will be achieved by each embodiment.

[0047] Figure 1 is an illustrative example of a drug delivery device 20 according to some examples. The drug delivery device 20 is a reusable drug injection pen. As is known in reusable devices of its type, the injection pen 20 includes a cartridge or reservoir 22 filled with a drug as part of a cartridge assembly generally designated by 24, which cartridge assembly is connected to a reusable pen base generally designated by 26. The cartridge or reservoir 22 is sized to hold a plurality of doses of the drug. The pen base 26 preferably includes a dose setting and injection mechanism that functions to allow selection of an amount of the drug and then expel it from the cartridge assembly 24 through an injection needle assembly 27 shown connected thereto. As shown, an exposed knob 28 having a rotatable button 30 thereon at the rear or proximal end of the pen base 26 is a manually operable part of the dose setting and injection mechanism otherwise housed within the pen base 26. During the dose setting process, the knob 28 is designed to be rotatable to set the dose, and when the knob 28 is rotated in this way to increase the selected dose, the knob 28 and button 30 translate out of the pen base 26 from Figure 1 the axial position shown, or translate to the right from the Figure 1 perspective of an observer. During the dose injection process that occurs after the dose setting process, when a thrust is applied to the button 30 that is free to rotate relative to the knob 28, the button 30 and knob 28 are designed to shift leftward and return to Figure 1 the axial position shown, causing the injection mechanism assembly housed within the pen base to operate so that the drug in the cartridge is injected.

[0048] In some embodiments, a drug delivery device may include one or more sensors for detecting the dose dispensed for each injection. For example, the drug delivery device may include one or more sensors configured to detect movement and / or changes of components of the drug delivery device. Examples of such sensors may include magnetic field sensors, switches, accelerometers, gyroscopes, etc. As another example, the drug delivery device may include sensors for determining the setting of a dose setting member. U.S. Patent No. 7,195,616, which is incorporated herein by reference in its entirety, includes some non-limiting examples of such sensors.

[0049] In some embodiments, the drug delivery device may include one or more sensors for detecting when a user changes the cartridge (e.g., when the user changes reservoir 22). For example, the drug delivery device may include one or more switches and / or pressure sensors for detecting removal and / or insertion of the cartridge into the drug delivery device.

[0050] In some embodiments, the drug delivery device may include a processing unit (or processing units), such as a central processing unit (CPU), a microcontroller unit (MCU), an application specific integrated circuit (ASIC), etc. In some embodiments, the processing unit may be configured to use data generated from the sensors to determine the injection dose and / or the insertion / removal of the cartridge. In some embodiments, the processing unit may be configured to perform the techniques described herein, including determining the dose of the injection.

[0051] In some embodiments, the drug delivery device may include a communication unit. The communication unit may be a wired communication unit (e.g., Universal Serial Bus (USB), FireWire, Serial, etc.) and / or a wireless communication unit (e.g., Bluetooth, WiFi, Near Field Communication (NFC), etc.). For example, the communication unit may be a WiFi transceiver, a Bluetooth transceiver, an RFID transceiver, a USB transceiver, a Near Field Communication (NFC) transceiver, a combination chip, etc. The processing unit may be configured to use the communication unit to send injection event information (e.g., including the dispensed dose and the time of dispensing), cartridge change information, and / or other information to a separate device.

[0052] Figure 2 is a flow chart showing an exemplary computerized process 200 for determining a group of injection events according to some embodiments. Process 200 may be performed by, for example, a drug delivery device, a smart phone, a server, etc. In step 202, the device accesses data indicative of injection events. For example, the device may receive a set of injection events from the drug delivery device substantially simultaneously (e.g., in a batch report), or the device may receive each injection event individually from the drug delivery device as each injection event occurs.

[0053] In step 204, the device adds the received injection event to the currently open injection event group. If there is no currently open injection event group, the device creates a new currently open injection event group.

[0054] In step 206, the device opens an injection event window. The injection event window can include a time period during which the device will add any newly received injection events to the currently open injection event group. In some embodiments, opening the injection event window can include starting a timer.

[0055] In step 208, the device determines whether it has accessed data indicating a new injection event within the injection event window (e.g., before the timer expires). If so, the device returns to step 204 (where it adds the new injection event to the currently open injection group), to step 206 (where it restarts the injection event window), and to step 208 (where it determines whether it has accessed data indicating a new injection event within the newly restarted injection event window). If no new injection event is received within the injection event window, the device proceeds to step 210 and closes the injection event group. If an additional new injection event is received within the newly restarted injection event window, the device returns to step 204. Thus, the device repeats steps 204, 206, and 208 until no new injection event is received within the current injection event window.

[0056] In operation, for example, if each injection is delivered within 5 minutes (in this example, the injection event window has a duration of 5 minutes) of the previous injection (e.g., less than or equal to it), the device can group one or more injection events into a single injection event group. Thus, for example, if the injection event data shows that the pen delivered a second injection 4 minutes after the first injection and then a third injection 3 minutes after the second injection, the device groups all three injections into the same injection event group (e.g., even though the elapsed time between the first and third injection events is 7 minutes).

[0057] Process 200 can be modified in various ways. For example, in some embodiments, the device may not restart the injection event window every time a new injection event is received. In such embodiments, all injection events must be received within a certain time period of the first injection event in order to be grouped into the same injection event group. In some embodiments, the device may optionally determine whether an injection event meets a certain predetermined criterion before adding the injection event to the currently open injection event group. For example, the device may be configured to add only injection events that are greater than a particular minimum dose size (e.g., 1 unit), have a duration greater than a particular minimum duration, or have a duration less than a particular maximum duration to the currently open injection event group. Any injection event that does not meet the predetermined criterion may not be added to the currently open injection event group.

[0058] Figures 3A - 3B Tables 300, 350 are examples showing injection event groups according to some embodiments. As shown in Table 300, an injection event 302 occurred at 4:42:03 PM, with a dose of two units, and five minutes later at 4:47:03 PM, no additional injection event occurred, so injection event 302 is the only injection event in the injection event group. In this example, injection event 302 was determined to be an injection event (e.g., as opposed to a filling event) because it was the only injection event in the injection event window. As shown in Table 350, the injection event group (group 1 in this example) includes five different injection events 352 - 360. As shown, each injection event is within five minutes of the previous injection event. For example, injection event 354 occurred at 4:55:19 PM, which is within five minutes of injection event 352, which occurred at 4:55:14 PM.

[0059] Figure 4A Is a flowchart showing an exemplary computerized process 400 for determining a dose based on an injection event group according to some embodiments. In step 402, the device (e.g., a drug delivery device, a smart phone, a server, etc.) accesses an injection event group that includes one or more injection events. As described herein, the injection event group may include injection events associated with (e.g., delivered by) one or more drug delivery devices.

[0060] At step 404, the device determines whether the injection event group is associated with a drug delivery device change. In some embodiments, the device change may include switching from one single-use drug delivery device to another single-use drug delivery device and / or changing the cartridge of a reusable drug delivery device. In some embodiments, the drug delivery device may store and / or report data indicating when the cartridge is changed, when the single-use drug delivery device runs out of the drug in the reservoir, and / or when a new single-use drug delivery device replaces the previous single-use drug delivery device. In some embodiments, the device change may be determined based on other information. For example, when the user selects a new single-use drug delivery device, the user may need to first pair the drug delivery device with another device (such as an attachable module, an application running on a smart phone, a server, etc.). When the new drug delivery device is paired with the device and / or paired with another device in the system, the device can determine that there is a device change.

[0061] In some embodiments, if the change time is within a predetermined amount of time of the injection event group, within a time window determined based on the injection event group, etc., it can be determined that the injection event group is associated with the device change. For example, if the user changes the pen or changes the replaceable cartridge during a certain time period, the device can determine that the injection event group is associated with the device change, and this time period starts 5 minutes before the first injection event in the group and ends at the time of the last injection event in the group. As another example, if the user changes the pen or changes the replaceable cartridge during a certain time period, the device can determine that the injection event group is associated with the device change, and this time period starts 5 minutes before the first injection event in the group and ends 5 minutes after the time of the last injection event in the group.

[0062] If the injection event group is not associated with the change, the method proceeds to step 406 to analyze the injection event group based on the first dose detection algorithm shown in steps 406 to 414 to determine the dose administered to the user. If the injection event group is associated with the drug delivery device change, the method proceeds to the method shown below Figure 4B shown, to analyze the injection event group based on the second dose detection algorithm to determine the dose administered to the user.

[0063] At step 406, the device determines whether there are three or more injection events in the injection event group. If there are three or more injection events, the method proceeds to step 408, and the device determines that the dose administered to the patient is equal to the dose associated with the last injection event in the group (which is the injection event that occurs later in time than any other injection event). The device may designate the remaining injection events as fill injection events.

[0064] If there are not three or more injection events, the method proceeds to step 410. Although not shown in the flowchart of Figure 4A , if the injection event includes only one event, the system can be configured to determine that the injection event includes an injection dose. At step 410, if there are two injection events in the injection event group, the device determines whether the dose of the injection event that occurs first in time is greater than the dose of the second injection event that occurs later in time. If the dose of the first injection event is greater than the dose of the second injection event, the method proceeds to step 412, and the dose is determined based on the sum of the doses of the two injection events. If the dose of the first injection event is not greater than the dose of the second injection event, the method proceeds to step 414, and the device determines that the dose administered to the patient is equal to the dose of the second injection event. The device can designate the first injection event as a priming injection event.

[0065] In some embodiments, step 410 can be modified such that the method proceeds to step 412 only if the dose of the first injection event is greater than a predetermined threshold than the dose of the second injection event. If the dose of the first injection event is not greater than the dose of the second injection event by a predetermined threshold, the method can proceed to step 414. The predetermined threshold can be an absolute number of units of insulin (e.g., 7 units), or a required minimum ratio of the first injection dose to the second injection dose can be specified (e.g., the ratio of the first injection dose to the second injection dose must exceed 5:1).

[0066] Figures 5A - 5C are tables 500, 530, and 560 that respectively illustrate examples of dose determination for groups of injection events not associated with drug delivery device changes according to some embodiments. Referring to Figure 5A in table 500, the injection event group includes two injection events 502 and 504. Since there are only two injection events, the device compares the doses of the two injections. Since the dose of injection two 504 (33 units) is greater than the dose of injection one 502 (2 units), the device determines that the injection dose is 33 units, and the first injection event is a priming event that does not count towards the amount injected by the user.

[0067] Referring to Figure 5B in table 530, the injection event group includes three injection events 532, 534, and 536. Since there are three injection events, the device determines that the last injection event 536 is the injection event, and the other two injection events 532 and 534 are priming events.

[0068] Referring to Figure 5CIn Table 560, the injection event group includes two injection events 562 and 564. Since there are only two injection events, the device compares the amounts of the doses of the two injections. Since the dose of the first injection event 562 (12 units) is greater than the dose of the second injection event 564 (2 units), the device determines that each injection event is an injection, and thus the amount injected is equal to the combination of the two doses, i.e., 14 units.

[0069] Figure 4B FIG. 4 is a flowchart showing an exemplary computerized process 450 for determining a dose based on a group of injection events associated with a change in a drug delivery device according to some embodiments. At step 452, the device determines whether a drug delivery device change has occurred between the injection events in the injection event group. If the change occurs before or after all of the injection events in the injection event group, the device proceeds to step 454 and determines that the last injection event (the event that occurs after the other injection events in the group) is an injection dose and the remaining injection events are fill events. For example, as described herein, if the change event occurs within a certain period of time after the injection events in the injection event group (e.g., within five minutes after the last injection event), the injection event group may be associated with the change event. As another example, as described herein, if the change event occurs within five minutes before all of the injection events in the injection event group, the injection event group may be associated with the change event. If all of the injection events in the injection event group occur before or after the change, the method may proceed to step 454 and determine that the last injection event is an injection dose and the remaining injection events are fill events. Otherwise, the method may proceed to step 456, as described below.

[0070] If the change occurs between the injection events, the device proceeds to step 456 and determines two sub-injection groups. The first sub-injection event group includes each injection event in the injection event group that occurred before the change. The second sub-injection event group includes each injection event in the injection event group that occurred after the change. At step 458, the device determines the injection doses based on the last injection event in each sub-injection event group. In particular, for the first sub-injection event group, the device determines that the most recent injection event (the one that occurs after the other injection events in the first sub-injection event group) is an injection dose and the remaining injection events (if any) are fill events. Similarly, for the second sub-injection event group, the device determines that the most recent injection event is an injection dose and the remaining injection events (if any) are fill events. Thus, the device can determine the total injection dose by adding the doses of the last injection events in each sub-injection event group.

[0071] Figures 6A - 6BTables 600, 650 are examples showing dose determination for groups of injection events associated with drug delivery device changes. Refer to Figure 6A Table 600 in

[0072] Table 600 includes five injection events 602 - 610. As shown in the third column of Table 600, the change time (e.g., the time the user changed the cartridge and / or the time the user switched to a new pen) is 4:54:56 PM. Since the change time occurred before all of the injection events 602 and 610 (which occurred between 4:55:14 - 4:55:34 PM), the device determined that the last injection event 610 represents the injection dose, such that the injection dose is 4 units), and the remaining injection events are fill events. Figure 6B Table 650 in

[0073] Table 650 includes two injection events 652 and 654. As shown in the third column, the change time is 7:41:55 PM, which occurred between the time of the first injection event 652 at 7:39:31 PM and the time of the second injection event 654 at 7:42:10 PM. Therefore, the system will determine two different sub - groups of injection events. In this example, each sub - group of injection events includes only one injection event: the first sub - group of injection events includes injection event 652, and the second sub - group of injection events includes injection event 654. The last (and only) injection event in each sub - group of injection events is identified as including the injection dose. Thus, the injection dose for the example shown in Table 650 is six units.In some embodiments, other methods that do not require determining whether an injection event group is associated with a drug delivery device change can be used to determine the dose administered to a patient. Such methods can be used when no drug delivery device change information is available. Such methods can determine the dose administered to a patient by using an injection event group that includes injection events over a particular time period (e.g., injection events that occur within a particular number of minutes, seconds, etc.). The technique can include determining the dose administered to a user by determining whether each of one or more injection events is associated with a dose administered to the user or a priming dose not administered to the user. The determination can include determining whether the injection event group includes a first injection event and a second injection event that occurs after the first injection event. When it is determined that the injection event group includes the first injection event and the second injection event, the determination can be based on the time period between the first injection event and the second injection event (e.g., the ranking of the time period with respect to the time periods of other sequential injection events, and / or whether the time period is greater than a predetermined time period). The determination can also optionally be based on one or more of the following: the dose size of the injection event (e.g., whether the dose size is greater than a unit dose) and the position of the injection event within the injection event group (e.g., whether the injection event is the only remaining injection event in the injection event group, or whether there are more injection events).

[0074] Figure 7 FIG. 4 is a flow diagram showing an exemplary computerized process 700 for determining a dose based on an injection event group that includes one or more injection events that occur within a predetermined time period. At step 702, the device selects an injection event from the injection event group. The injection event group can include one or more injection events. In some embodiments, the injection event group is a set of one or more injection events that occur during a predetermined time period. For example, the injection event group can include all injections that occur within three minutes, five minutes, seven minutes, and / or other time periods after a first injection event in the injection event group. In some embodiments, the device can access data related to multiple injection events of the injection event group substantially simultaneously (e.g., as a batch download of pre-recorded data for some or all of a set of injection events in the injection event group). In some embodiments, the device accesses one or more injection events of the injection event group individually, such as by receiving data indicating each injection event separately in time (e.g., at the time each injection event occurs and / or shortly after each injection event occurs). Thus, step 702 can include selecting an injection event from multiple injection events and / or processing an individual injection event (e.g., when received from a drug delivery device and / or at the time the injection event occurs).

[0075] In step 704, the device determines whether the dose size of the selected injection event is greater than a first predetermined threshold. For example, the predetermined threshold can be 6 units, 7 units, 9 units, 10 units, 11 units, etc. If the dose size is greater than the threshold, the method proceeds to step 706, where the device determines that the selected injection event is associated with an injection dose administered to the user. If the dose size is not greater than the first predetermined threshold, the method proceeds to step 708 and determines whether there is a next injection event that occurs after the selected injection event in the group of injection events. If there are no other injection events, the method proceeds to step 706, where the device determines that the selected injection event is associated with an injection dose administered to the user. After step 706, the method proceeds to step 718 as described below. If, in step 708, the method determines that there is a next injection event, the method proceeds to step 710.

[0076] As described herein, the injection events of the group of injection events can be accessed as a group of injection events (e.g., receiving and / or accessing a batch of pre-recorded data indicating the injection events substantially simultaneously) and / or can be accessed individually (e.g., received individually in time when each injection event occurs or shortly after it occurs). In some embodiments, when the injection events are accessed individually, step 708 can include the device determining whether the device has received the next injection event within the injection event window of the first injection event (e.g., the injection event selected in step 702) (e.g., within a predetermined time period, such as three minutes, five minutes, seven minutes, or some other time period). In some embodiments, when one or more injection events are accessed as a group of events, step 708 can include analyzing the data of the group of events to determine whether there is a next injection event.

[0077] In step 710, the device determines whether the time between the selected injection event and the next injection event is greater than a second predetermined threshold. For example, the device can determine whether the next injection event occurs more than a predetermined number of seconds after the selected injection event (e.g., greater than 59.5 seconds, 60 seconds, 60.5 seconds, 79.5 seconds, 80 seconds, etc.). If the time between the events is not greater than the threshold, the method proceeds to step 712, where the device determines that the selected injection event (i.e., the injection event selected in step 702) is associated with a bolus dose that has not been administered to the user. After step 712, the method proceeds to step 718.

[0078] If the time between injection events is greater than a second predetermined threshold, the method proceeds to step 714, and the device determines whether the dose size of the selected injection event is greater than a third predetermined threshold. For example, the device can determine whether the dose size is greater than 3 units, 3.5 units, 4 units, 4.5 units, 5 units, 5.5 units, etc. If the dose size is not greater than the threshold, the method proceeds to step 712, where the device determines that the selected injection event is associated with a fill dose not given to the user, and then the method proceeds to step 718. If the dose size is greater than the third predetermined threshold, the method proceeds to step 706, and the device determines that the selected injection event is associated with an injection dose given to the user.

[0079] After steps 706 and 712, the method proceeds to step 718, where the device determines whether there are any additional injection events in the injection event group that need to be classified as injection doses or fill doses. If there are no additional events, the method proceeds to step 720, where the device ends the dose detection process. If there are additional injection events, the method returns to step 702, selects the next injection event in the injection event group, and repeats the process as described herein.

[0080] Figures 8A - 8E Tables 800, 820, 840, 860, and 880 are examples of dose determinations for exemplary injection event groups in which injection events occur within a predetermined time period of 5 minutes according to some embodiments. For these examples, the dose size of the first threshold is 10 units, the time between injection events of the second threshold is 79.5 seconds, and the dose size of the third threshold is 4.5 units.

[0081] Reference Figure 8A Referring to Table 800 in

[0082] Reference Figure 8BIn Table 820, the device selects the first injection event 824 and determines that the corresponding dose size of 3 units is not greater than the predetermined threshold of 10 units. Then, the device determines that there are no other injection events in the injection event group after the first injection event 824, and thus determines that the first injection is associated with the injection dose administered to the user. Therefore, the injection dose of the injection event group shown in Table 820 is 3 units.

[0083] Reference Figure 8C In Table 840, the device selects the first injection event 842 and determines that the corresponding dose size of 5 units is not greater than the predetermined threshold of 10 units. Then, the device determines that the second injection event 844 occurs after the first injection event 842, and further determines that the time period of 60 seconds between the first injection event 842 and the second injection event 844 is not greater than the threshold of 79.5 seconds. Therefore, the device determines that the first injection event 842 is associated with a priming dose not administered to the user. Since there is a second injection event 844 that occurs after the first injection event 842, the device then selects that event for analysis. The device determines that the dose size of 3 units is not greater than the threshold of 10 units, and that no other injection events occur within five minutes of the second injection event 844. Therefore, the second injection event 844 is associated with the injection dose administered to the user. Therefore, the injection dose of the injection event group shown in Table 840 is 3 units.

[0084] Reference Figure 8D In Table 860, the device selects the first injection event 862 and determines that the corresponding dose size of 5 units is not greater than the predetermined threshold of 10 units. Then, the device determines that the second injection event 864 occurs after the first injection event 862, and further determines that the time period of 81 seconds between the first injection event 862 and the second injection event 864 is greater than the threshold of 79.5 seconds. Additionally, the device determines that the dose size of the first injection event 862 of 5 units is greater than the predetermined threshold of 4.5 units. Therefore, the device determines that the first injection event 862 is associated with the injection dose administered to the user. Then, the device selects the second injection event 864, and after determining that the corresponding dose size of 3 units is not greater than the threshold of 10 units, determines that there are no other injection events after the second injection event 864. Therefore, the device determines that the second injection event 864 is also associated with the injection dose administered to the user. Therefore, the injection dose of the injection event group shown in Table 860 is 8 units.

[0085] Reference Figure 8EIn Table 880, the device selects the first injection event 882 and determines that the corresponding dose size of 2 units is not greater than the predetermined threshold of 10 units. Then, the device determines that the second injection event 884 occurs after the first injection event 882 and further determines that the time period of 81 seconds between the first injection event 882 and the second injection event 884 is greater than the threshold of 79.5 seconds. Additionally, the device determines that the corresponding dose size of 2 units is less than the threshold of 4.5 units. Thus, the device determines that the first injection event 882 is associated with a bolus dose not administered to the user. Then, the device selects the second injection event 884 and, after determining that the corresponding dose size of 3 units is less than the threshold of 10 units, determines that there is a third injection event 886 that occurs after the second injection event 884. The device determines that the time period of 40 seconds between the second injection event 884 and the third injection event 886 is not greater than the threshold of 79.5 seconds. Thus, the device determines that the second injection event 884 is also associated with a bolus dose not administered to the user. Finally, the device selects the third injection event 886 and, after determining that the corresponding dose size of 3 units is not greater than the threshold of 10 units, determines that no other injection events occur after the third injection event 886. Thus, the third injection event 886 is associated with the injection dose administered to the user. Thus, the injection dose of the injection event group shown in Table 880 is 3 units.

[0086] One advantage of the process 700 for determining the dose is that it does not require the drug delivery device to change information that may not always be available. Another advantage of the process 700 is that any given injection event can be classified as being associated with either the injection dose administered to the user or the bolus dose not administered to the user within five minutes of the occurrence of that given injection event. The process 700 does not require the user to wait until all injection events within the injection event group are known before making a classification decision.

[0087] In some embodiments, the process 700 can be modified by simplifying steps 710 and 714. For example, if the process 700 determines at step 708 that there is a next injection event within a certain time period after the selected injection event (e.g., there is a next injection event within three minutes, five minutes, seven minutes, or some other predetermined time period after the selected injection event), then the process 700 can automatically classify the selected injection event as a bolus dose without going through steps 710 and / or 714. In such an embodiment, the process 700 can classify the selected injection event as an injection dose while waiting for a predetermined time period after the selected injection event has passed. If a next injection event is received before the expiration of this predetermined time period, then the selected injection event can be reclassified from an injection dose to a bolus dose.

[0088] This modified embodiment of the process 700 will result in the same as Figure 8A-C classifies injection events using the same filling as presented in 8E, but will result in a classification different from the classification presented in Figure 8D . Specifically, referring to the table 860 in Figure 8D , in a modified embodiment of process 700, the device selects a first injection event 862 and determines that the corresponding dose size of 5 units is not greater than a predetermined threshold of 10 units. Then, the device determines that a second injection event 864 occurs within five minutes (predetermined time period) after the first injection event 862. Without further querying the time interval between injection events 862 and 864, and without further querying the dose size of injection event 864, the device classifies injection event 862 as a filling dose. Then, the device selects injection event 864 for analysis. After determining that no additional injection events occur within five minutes of injection event 864, the device classifies injection event 864 as an injection dose administered to the user.

[0089] Figure 9 is a flowchart showing another exemplary computerized process 900 for determining a dose based on a group of injection events according to some embodiments. At step 902, the device selects an injection event from the group of injection events and proceeds to step 904. As described herein, the group of injection events can include one or more injection events associated with one or more drug delivery devices. Also as described herein, an injection event can include injection events that occur within a predetermined time period (e.g., a single time period (e.g., a total of five minutes, a total of ten minutes, etc.) and / or a certain time period from each injection (e.g., within five minutes of each injection)).

[0090] At step 904, the device determines whether the selected injection event is the last injection event in the group of injection events. If the selected injection event is the last injection event, the method proceeds to step 906, and the device determines that the selected injection event is an injection dose administered to the user. If the selected injection event is not the last injection event in the group of injection events, the method proceeds to step 908.

[0091] At step 908, the device determines whether the time between the selected injection event and the next injection event in the group is greater than a first predetermined threshold (e.g., greater than 58.5 seconds, 60 seconds, 60.5 seconds, 73.5 seconds, 80 seconds, etc.). When determining that the time between the injection events is not greater than the threshold, the method proceeds to step 910, and it is determined that the selected injection event is a filling dose not administered to the user.

[0092] If the time period is greater than a first predetermined threshold, the method proceeds to step 912, and the device determines whether the time interval ranking associated with the selected injection event is greater than or equal to a second predetermined threshold. The time interval ranking can be, for example, a ranking of the amount of time between each sequential pair of injection events in a group of injection events, as further discussed herein. The second predetermined threshold can be, for example, 2, 3, 4, etc. When it is determined that the time interval ranking is not greater than or equal to the second predetermined threshold, the method proceeds to step 912, in which the device determines that the selected injection event is a fill dose not administered to the user. However, if the time interval ranking is greater than or equal to the second predetermined threshold, the method proceeds to step 914, in which it is determined that the selected injection event is an injection event associated with an injection dose administered to the user.

[0093] After steps 910 and 914, the method returns to step 902, selects the next injection event in the group of injection events, and repeats the process described herein.

[0094] In some embodiments, if no other injection events occur within a predetermined time period after the selected injection event, it can be determined that the selected injection event is the last injection event in the group of injection events (step 904). For example, if no other injection events occur within 4 minutes, 5 minutes, 6 minutes, etc. after the selected injection event, the device can determine that the injection event is the last injection event in the group of injection events. When making this determination, the device can close the group of injection events.

[0095] In some embodiments, the time interval ranking can be determined by evaluating and comparing the time periods between consecutive injection events in the group of injection events. The time periods between consecutive injection events can be sorted, for example, from the shortest time period between consecutive injection events to the longest time period between consecutive injection events, and corresponding rankings are assigned in ascending order. Consider an example with first, second, and third injection events, where the time period between the first and second injection events is 5 seconds, and the time period between the second and third injection events is 3 seconds. Since there are no other injection events in the group of injection events, the time period associated with the third injection event can be set to zero. For this example, the corresponding time interval rankings are 3 for the first injection event (since the 5 - second time interval is the largest of all three time intervals), 2 for the second injection event (since the 3 - second time interval is less than the time interval of the first injection event but greater than the time interval of the third injection event), and 1 for the third injection event (since the 0 - second time interval is the smallest of all three time intervals). This is shown in the example further discussed Figure 10A below.

[0096] Figures 10A - 10CTables 1000, 1030, and 1060 are examples of dose determinations that respectively show exemplary groups of injection events according to some embodiments. For these examples, the time period between injection events of the first threshold is 73.5 seconds, and the time interval ranking of the second threshold is 3.

[0097] Reference Figure 10A Referring to Table 1000 in, the group of injection events includes three injection events 1002 - 1006. The device selects the first injection event 1002 and determines that it is not the last injection event in the group of injection events. The device then compares the 5 - second time period between the first injection event 1002 and the second injection event 1004 with a predetermined time period of 73.5 seconds. When determining that the 5 - second time period is not greater than the predetermined time period, the device determines that the first injection event 1002 is associated with a bolus dose not given to the user and selects the second injection event 1004. The device determines that the second injection event 1004 is not the last injection event, and the 3 - second time period between the second injection event 1004 and the third injection event 1006 is not greater than the 73.5 - second predetermined threshold. Thus, the device determines that the second injection event 1004 is associated with a bolus dose not given to the user. Then the third injection event 1006 is selected and determined to be the final injection event of the group of injection events. Thus, the device determines that the third injection event is the injection dose given to the user. Thus, the injection dose of the group of injection events shown in Table 1000 is 4 units.

[0098] Reference Figure 10BIn Table 1030, the injection event group includes five injection events 1032 - 1038. The first injection event 1032 is selected, and the device determines that it is not the final dose in the injection event group. Therefore, the time period (5 seconds) before the second injection event 1034 is compared with a predetermined threshold of 73.5 seconds. Since the time period of the selected injection event is not greater than the threshold, the device determines that the first injection event 1032 is a priming dose not administered to the user. Then the second injection event 1034 is selected, and the device determines that it is not the final injection event in the injection event group. The time period of 81 seconds between the second injection event 1034 and the third injection event 1036 is determined to be greater than the predetermined threshold of 73.5 seconds. Then, the device determines that the time interval rank 4 associated with the time period between the second and third injection events 1034 - 1036 is greater than or equal to the predetermined threshold 3. The device determines that the second injection event is associated with an injection dose administered to the user. Then, the third injection event 1036 is selected by the device, and the device then determines that it is not the final injection event in the injection event group. Since the time period of 48 seconds between the third injection event 1036 and the fourth injection event 1038 is not greater than the 73.5 - second threshold, the device determines that the third injection event 1036 is a priming dose not administered to the user. Finally, the device determines that the fourth injection event 1038 is associated with an injection dose administered to the user because it is the final injection event in the injection event group. Thus, the injection dose of the injection event group shown in Table 1030 is 5 units.

[0099] Reference Figure 10C In Table 1060, the injection event group includes two injection events 1062 and 1064. The first injection event 1062 is selected by the device and determined not to be the final injection event in the injection event group. The time period (81 seconds) between the first injection event 1062 and the second injection event 1064 is greater than the predetermined threshold of 73.5 seconds, so the device proceeds to evaluate the time interval rank. The time interval rank 1 associated with the time period discussed previously is not greater than or equal to the predetermined threshold 3. Therefore, the device determines that the first injection event 1062 is a priming dose not administered to the user. Then the second injection event 1064 is selected and determined to be the injection dose delivered to the user because it is the final injection event in the injection event group. Thus, the injection dose of the injection event group shown in Table 1060 is 3 units.

[0100] According to some embodiments, the determination of the dose of an injection event can be performed in real time (e.g., when information about one or more doses is received, rather than generating a group of injection events). The device can select the current injection event and compare the dose magnitude with a first predetermined threshold (e.g., a dose magnitude of 8 units, 9 units, 10 units, 11 units, etc.). If the dose magnitude is greater than or equal to the first predetermined threshold, the device can determine that the current injection event is associated with a dose administered to the user. However, if the dose magnitude is not greater than or equal to the first predetermined threshold, the device can compare the dose magnitude with a second predetermined threshold. For example, the second predetermined threshold can be a dose magnitude of 3 units, 4 units, 5 units, etc. In the case where the dose magnitude exceeds the second predetermined threshold, the method can proceed to compare the time period since the last dose with a predetermined time period (e.g., a time of 8 seconds, 9 seconds, 10 seconds, 11 seconds, etc.). When it is determined that the time period since the last dose is greater than the predetermined time period, the device can determine that the current injection event is associated with an injection dose administered to the user. The device can determine that all other injection events (e.g., if the dose magnitude does not exceed the second predetermined threshold and / or if the time period since the last dose is not greater than the predetermined time period) are fill doses not administered to the user.

[0101] Figure 11 FIG. 4 is a diagram of an exemplary system 1100 for implementing the computerized processes described herein. As used herein, the terms "logic", "control logic", "application", "process", "method", "algorithm", and "instructions" can include software and / or firmware executed on one or more programmable processors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), hardwired logic, or combinations thereof. Thus, according to embodiments, the various logics can be implemented in any suitable manner and will remain consistent with the embodiments disclosed herein. System 1100 includes a computing device 1110 in wireless communication with a drug delivery device 1140. Computing device 1110 can also communicate with a server 1160 via a network 1150.

[0102] Computing device 1110 illustratively includes a mobile device, such as a smart phone. Alternatively, any suitable computing device can be used, including but not limited to, for example, a laptop computer, a desktop computer, a tablet computer, or a server computer. Computing device 1110 includes a processor 1112, a memory 1116, a display / user interface (UI) 1118, and a communication device 1119.

[0103] The processor 1112 includes at least one processor that executes software and / or firmware stored in the memory 1116 of the computing device 1110. The software / firmware code contains instructions that, when executed by the processor 1112, cause the processor 1112 to perform the functions described herein. Such instructions illustratively include control logic / application 1114 operable to implement the functions described herein. The memory 1114 is any suitable computer-readable medium accessible by the processor 1112. The memory 1114 can be a single storage device or multiple storage devices, can be located inside or outside the processor 1112, and can include both volatile and non-volatile media. Exemplary memories 1114 include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic storage devices, optical disc storage, or any other suitable medium configured to store data and accessible by the processor 1112.

[0104] The computing device 1110 includes a display / user interface 1118 that communicates with the processor 1112 and is operable to provide user input data to the system and receive and display data, information, and prompts generated by the system. The user interface 1118 includes at least one input device for receiving user input and providing the user input to the system. In the illustrated embodiment, the user interface 1118 is a graphical user interface (GUI) that includes a touchscreen display operable to display data and receive user input. The touchscreen display allows the user to interact with the presented information, menus, buttons, and other data to receive information from the system and provide user input into the system. Alternatively, a keyboard, keypad, microphone, mouse pointer, or other suitable user input device can be provided.

[0105] The computing device 1110 also includes a communication device 1119 that allows the computing device 1110 to establish wired or wireless communication links with other devices. The communication device 1119 can include one or more wireless antennas and / or signal processing circuitry for transmitting and receiving wireless communications, and / or one or more ports for receiving physical lines for transmitting and receiving data. Using the communication device 1119, the computing device 1110 can establish one or more short-range communication links, including a communication link 1103 with the drug delivery device 1140. Such short-range communication links can utilize any known wired or wireless communication technology or protocol, including but not limited to radio frequency communication (e.g., Wi-Fi; Bluetooth, Bluetooth Low Energy (BLE), Near Field Communication (NFC), RFID, etc.), infrared transmission, microwave transmission, and optical wave transmission. Such short-range communication links can be one-way links (e.g., a data stream only from the device 1140 to the computing device 1110) or two-way links (e.g., a two-way data stream). The communication device 1119 can also allow the computing device 1110 to establish a long-range communication link with the server 1160 via the network 1150 and communication links 1104 and 1105. The server 1160 can be located at a location remote from the computing device 1110, e.g., in another building, in another city, or even in another country or continent. The network 1150 can include any cellular or data network suitable for potentially relaying information from the computing device 1110 to the server 1160 and / or from the server 1160 via one or more intermediate nodes or switches. Examples of suitable networks 1150 include cellular networks, Metropolitan Area Networks (MANs), Wide Area Networks (WANs), and the Internet.

[0106] The drug delivery device 1140 illustratively includes any device configured to deliver one or more drug doses to a patient, measure and / or record the time and amount of each dose, and transmit this information to the computing device 1110. In some embodiments, the drug delivery device 1140 may be configured to store and / or deliver one or more drug doses to an individual. As used herein, the term "drug" or "medicine" may refer to insulin, insulin analogs (such as lispro insulin or glargine insulin) and / or insulin derivatives, but may also refer to one or more other therapeutic agents, including but not limited to GLP-1 receptor agonists (such as dulaglutide or liraglutide), glucagon, glucagon analogs, glucagon derivatives, gastric inhibitory polypeptide (GIP), GIP analogs, GIP derivatives, oxyntomodulin analogs, oxyntomodulin derivatives, therapeutic antibodies, and any therapeutic agent capable of being delivered by the above device. The drug used in the device may be formulated with one or more excipients. The device is operated by a patient, caregiver, or healthcare professional to deliver the medicine to an individual. The drug delivery device 1140 may be configured as a reusable device that can be refilled with drug once its drug storage is depleted, or may be configured as a disposable device designed to be discarded and replaced once its drug storage is depleted. The drug delivery device 1140 includes a processing circuit 1142, a dose detection sensor 1144, a communication device 1146, a drug reservoir 1148, and a dose adjustment mechanism 1149. The processing circuit 1142 may include any of the possible types of processing circuits described previously. The dose detection sensor 1144 may include any suitable sensor for detecting and / or recording the time and amount of the delivered dose. The communication device 1146 enables the drug delivery device 1140 to communicate with the computing device 1110 via a communication link 1103. The drug reservoir 1148 may be sized to be sufficient to accommodate enough drug for multiple doses, while the dose adjustment mechanism 1149 allows a user to adjust the amount of the dose for injection by the drug delivery device.

[0107] Server 1160 illustratively includes any computing device configured to receive information about a patient from computing device 1110 via network 1150, process the information, and optionally send a response, notification, or instruction to computing device 1110 in response to the information. Server 1160 includes processing circuitry 1162, memory 1164, and communication device 1166. Processing circuitry 1162 may include any of the possible types of processing circuitry described previously. Processing circuitry 1162 may execute software and / or firmware stored in memory 1164 of server 1160. The software / firmware code contains instructions that, when executed by processing circuitry 1162, perform the functions described herein. Memory 1164 may also be configured to store information about one or more patients, such as biometric information and / or medical information (e.g., medication dosage records, medical history, etc.). Information received from or sent to computing device 1110 may also be stored in memory 1164. Memory 1164 may include any of the possible types of memory described previously. Communication device 1166 enables server 1160 to communicate with computing device 1110 via communication link 1105, network 1150, and communication link 1104.

[0108] In some embodiments, computing device 1110 may operate without being connected to any network 1150 and / or server 1160.

[0109] In other embodiments, system 1100 may be modified by adding components. For example, server 1160 may be configured as a plurality of networked servers 1160 that cooperate to process information. Such a configuration of networked servers may be referred to as a "cloud" of servers that perform the functions described herein. (One or more) servers 1160 may communicate with a plurality of computing devices 1110 via network 1150, and each computing device 1110 may in turn optionally be connected to one or more drug delivery devices 1140.

[0110] In some embodiments, the techniques described herein may be used with reusable drug devices, such as a reusable insulin pen, including a reusable insulin pen that reports cartridge change events. In some embodiments, a reusable drug delivery device may generate data indicative of the time of cartridge change as described herein, which may be used to process injection data based on reservoir change.

[0111] In some embodiments, some or all of the techniques described herein (e.g., processes 200, 400, 450, 700, and / or 900) may be performed by a drug delivery device. For example, the drug delivery device may include processing circuitry configured to determine a set of injection events and / or determine an injection dose (e.g., by differentiating between filling and injection events, including appropriately handling cartridge changes). In some embodiments, the drug delivery device may be configured to transmit the determined information (e.g., the set of injection events and / or the injection dose) to a separate device, such as a smart phone or a module that may be attached to the drug delivery device.

[0112] In some embodiments, some or all of the techniques described herein (e.g., processes 200, 400, 450, 700, and / or 900) may be performed by a device separate from the drug delivery device, such as by an application running on a smart phone or other device (e.g., computing device 1110) communicatively coupled to the drug delivery device, a remote server (e.g., server 1160), etc. The drug delivery device may be configured to transmit injection data and / or processing data (e.g., the set of injection events and / or device change information) to a separate device. In some embodiments, the drug delivery device may be a disposable drug delivery device. Some illustrative examples of such disposable drug delivery are described in further detail in International Publication No. WO 2019 / 040313, having an international filing date of Aug. 14, 2018, and entitled MEDICATION DELIVERY DEVICE WITH SENSING SYSTEM, the contents of which are incorporated herein by reference in their entirety.

[0113] In some embodiments, the drug delivery device may not include a wireless transmission function, a dose detection function, and / or a processing function. In some embodiments, a reusable electronic module may be attached to / detached from the drug delivery device to add one or more such features to the drug delivery device. For example, the reusable electronic module may be configured to sense the amount of the dose associated with each injection event and report the information to a second device that processes injection event data. Some illustrative examples of such reusable electronic modules are described in further detail in International Publication No. WO 2018 / 160425, having an international filing date of Feb. 22, 2018, and entitled DOSE DETECTION AND DRUG IDENTIFICATION FOR A MEDICATION DELIVERY DEVICE, the contents of which are incorporated herein by reference in their entirety. As another example, the reusable electronic module may be configured to report information when the device is attached to / removed from the drug delivery device, and the receiving device may use the information to determine change information.

[0114] In some embodiments, the processes 200, 400, 450, 700, and / or 900 described above may be refined based on user feedback. As described above, the processes 200, 400, 450, 700, and / or 900 may classify each received injection event as being associated with a dose administered to the user or as a fill dose not administered to the user. In some embodiments, the user may manually provide feedback indicating whether the classification applied by the processes 200, 400, 450, 700, and / or 900 to a particular injection event is correct. For example, the user may confirm that a particular injection event was correctly classified as an administered dose versus a fill dose, or the user may modify and / or correct the label imposed by the processes 200, 400, 450, 700, and / or 900. When the user provides feedback confirming or correcting the classification output by the processes 200, 400, 450, 700, and / or 900, the feedback may be used to modify the processes to more accurately classify future injection events. For example, once sufficient user feedback has been collected over a specified period of time (e.g., days, a week, several weeks, or a month), the user feedback may be used to train a machine learning model that adjusts the thresholds or timers in the processes to increase the accuracy of the processes. The user feedback used to train the machine learning model may be obtained from a single user or from a group of users. A non-limiting set of thresholds and / or timers that may be adjusted by such a machine learning model may include (i) the duration of the injection event window in step 206, (ii) the first threshold referenced in step 704, (iii) the duration of the second threshold referenced in step 710, (iv) the magnitude of the third threshold referenced in step 714, (v) the first predetermined threshold referenced in step 908, and / or (vi) the second predetermined threshold referenced in step 912. The adjustment of the machine learning model and / or the thresholds and / or timers may be implemented on the computing device 1110, but may also be implemented on the drug delivery device 1140 and / or the server 1160. By continuously learning from user feedback, such a machine learning model may continuously improve and increase the accuracy of the processes 200, 400, 450, 700, and / or 900.

[0115] Although adjusting the thresholds and / or timers in the process changes certain programmable features in such a process, the data flow in such a process remains substantially the same. However, in some embodiments, in addition to adjusting the thresholds and / or timers in certain process steps, such user feedback can also be used to modify the process 200, 400, 450, 700 and / or 900 by adding, deleting, rearranging and / or editing any of the steps of the process. For example, such user feedback can be used to derive new data features (e.g., in addition to data features such as dose size, time between doses, dose order and / or time interval ranking of the above doses) and incorporate such new data features into a completely new process. Such user feedback can also be used to prompt a switch from one of the above processes 200, 400, 450, 700 and / or 900 to another of the above processes.

[0116] A machine learning model capable of making these more extensive adjustments to a process may require a greater amount of training data, computing resources, and / or memory than a model that simply adjusts thresholds and / or timers. Therefore, some embodiments may employ a two-level model to adjust a process. First, a simpler machine learning model may be used to adjust thresholds and / or timers. This simpler machine learning model may be implemented relatively frequently (e.g., weekly) and on a device (e.g., computing device 1110) with relatively modest computing resources and / or memory. The user feedback group used to train such a model may also be obtained from only a single user, or from a smaller user group. Second, a more complex machine learning model may be used to implement the aforementioned more extensive modifications to processes 200, 400, 450, 700, and / or 900. This more complex machine learning model may be implemented relatively less frequently (e.g., monthly) and / or on a device (e.g., server 1160) using a greater amount of training data (e.g., from a larger user group) and / or on a device (e.g., server 1160) with a greater amount of computing resources and / or memory. Once the second machine learning model outputs a revised process, the revised process may be distributed to one or more computing devices 1110 and / or drug delivery devices 1140 to classify further injection events.

[0117] The various methods or processes outlined herein may be encoded as software that can be executed on one or more processors using any of a variety of operating systems or platforms. In addition, such software may be written using any of a variety of suitable programming languages ​​and / or programming or scripting tools, and may also be compiled into executable machine language code or intermediate code that is executed on a virtual machine or a suitable framework.

[0118] In this regard, various inventive concepts can be implemented as at least one non-transitory computer-readable storage medium encoded with one or more programs (e.g., computer memory, one or more floppy disks, compact disks, optical disks, magnetic tapes, flash memories, circuit configurations in field-programmable gate arrays or other semiconductor devices, etc.), which, when executed on one or more computers or other processors, implement various embodiments of the present invention. One or more non-transitory computer-readable media can be transportable, such that one or more programs stored thereon can be loaded into any computer resource to implement the various aspects of the present invention as described above.

[0119] The terms "program", "software", and / or "application" are used herein in a general sense to refer to any type of computer code or set of computer-executable instructions that can be used to program a computer or other processor to implement the various aspects of the embodiments described above. Additionally, it should be understood that, according to one aspect, one or more computer programs that execute the methods of the present invention when executed do not need to reside on a single computer or processor, but can be distributed in a modular fashion among different computers or processors to implement the various aspects of the present invention.

[0120] Computer-executable instructions can be in many forms, such as program modules, executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Generally, the functions of program modules can be combined or distributed as needed in various embodiments.

[0121] Furthermore, data structures can be stored in a non-transitory computer-readable storage medium in any suitable form. A data structure can have fields that are related by their positions in the data structure. Such a relationship can also be achieved by allocating positions in the non-transitory computer-readable medium that convey the relationship between the fields for the storage of the fields. However, any suitable mechanism can be used to establish the relationship between the information in the fields of a data structure, including by using pointers, tags, or other mechanisms for establishing relationships between data elements.

[0122] Various inventive concepts can be embodied as one or more methods, and examples of the methods have been provided. The actions performed as part of a method can be ordered in any suitable way. Thus, embodiments can be constructed in which the actions are performed in an order different from the order shown, which can include performing some actions simultaneously, even though they are shown as sequential actions in the illustrative embodiments.

[0123] Unless expressly stated to the contrary, as used in this specification and the claims, the indefinite articles "a" and "an" shall be understood to mean "at least one". As used in the specification and the claims, the phrase "at least one" in reference to a list of one or more elements shall be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each of the specifically listed elements in the list of elements, and not excluding any combinations of elements in the list of elements. This allows elements optionally to be present other than those specifically recited within the list of elements to which the phrase "at least one" refers, whether related or unrelated to those specifically recited.

[0124] The phrase "and / or" as used in the specification and the claims shall be understood to mean "either or both" of the elements so conjoined, i.e., elements that are present conjunctively in some cases and disjunctively in other cases. Multiple elements listed with "and / or" shall be construed in the same manner, i.e., "one or more" of the elements so conjoined. Other elements may optionally be present in addition to the elements specifically recited by the "and / or" clause, whether related or unrelated to those specifically recited. Thus, as a non-limiting example, a reference to "A and / or B" when used in conjunction with open-ended language such as "comprising" can, in one embodiment, refer to only A (optionally including elements other than B); in another embodiment, to only B (optionally including elements other than A); in yet another embodiment, to both A and B (optionally including other elements); and so on.

[0125] As used in the specification and the claims, "or" shall be understood to have the same meaning as "and / or" as defined above. For example, when used to separate items in a list, "or" or "and / or" shall be interpreted as inclusive, i.e., including at least one of a plurality of elements or the elements in a list of elements, but also including more than one, and optionally, including additional unlisted items. Only terms expressly stated to the contrary (such as "only one" or "exactly one") or when used in a claim "consisting of" shall refer to including exactly one element of a plurality of elements or the elements in a list of elements. Generally, when an exclusive term such as "any", "one of", "only one of", or "exactly one of" precedes the term "or", the term "or" as used herein shall be interpreted only as indicating exclusive alternative elements (i.e., "one or the other, but not both"). When used in a claim, "consisting essentially of" shall have its ordinary meaning as used in the field of patent law.

[0126] The use of ordinal numbers such as "first", "second", "third", etc. in the claims to modify the claim elements themselves does not mean any priority, order or sequence of one claim element relative to another, or the chronological order of acts of performing a method. These terms are merely used as labels to distinguish one claim element having a particular name from another element having the same name (but using an ordinal term).

[0127] The language and terminology used herein are for descriptive purposes and should not be regarded as limiting. The use of "comprising", "including", "having", "containing", "involving" and their variants means including the items listed thereafter and additional items.

[0128] Having described several embodiments of the present invention in detail, various modifications and improvements should be readily conceivable to those skilled in the art. These modifications and improvements are all within the spirit and scope of the present invention. Therefore, the foregoing description is merely exemplary and not restrictive.

Claims

1. A computer-implemented method for determining a dose injected into a user by one or more drug delivery devices, the method comprising: Accessing data indicative of a group of injection events, the group of injection events including one or more injection events associated with one or more drug delivery devices, wherein each of the one or more injection events occurs within a predetermined time period, and wherein each of the one or more drug delivery devices includes: A dose adjustment mechanism that allows a user to adjust the amount of the dose for an injection by the drug delivery device; A reservoir sized to hold a drug for a plurality of doses; One or more sensors for detecting the amount of the dose dispensed for each injection; and A wireless communication unit that conveys the amount of the dose dispensed and the time at which it is dispensed; Determining the dose administered to the user, including: Determining whether the group of injection events includes a first injection event and a second injection event that occurs after the first injection event; and When determining that the group of injection events includes the first injection event and the second injection event, determining whether the first injection event is associated with a dose administered to the user or a priming dose not administered to the user based on the time period between the first injection event and the second injection event; and Wherein determining whether the first injection event is associated with a dose administered to the user or a priming dose not administered to the user based on the time period between the first injection event and the second injection event includes: Determining whether the time period is less than a second predetermined threshold; When determining that the time period is less than the second predetermined threshold, determining that the first injection event is associated with a priming dose not administered to the user; and When determining that the time period is not less than the second predetermined threshold, determining the dose administered to the user based on the dose magnitude of the first injection event.

2. The method according to claim 1, wherein The predetermined time period is between four minutes and six minutes.

3. The method according to claim 1, wherein Determining the dose administered to the user includes: determining whether the injection event in the group of injection events is associated with a dose administered to the user or a priming dose not administered to the user based on the dose magnitude of the injection event.

4. The method according to claim 3, further comprising: Determining whether the dose magnitude is greater than a first predetermined threshold; When determining that the dose magnitude is greater than the first predetermined threshold, determining that the injection event is associated with a dose administered to the user; And When determining that the dose magnitude is not greater than the first predetermined threshold, determining the dose administered to the user based on whether there is a next injection event that occurs after the injection event in the group of injection events.

5. The method according to claim 4, wherein, The first predetermined threshold is a dose magnitude between nine units and eleven units.

6. The method according to claim 4 further comprises: When determining that the dose magnitude is not greater than the first predetermined threshold: Determining whether there is a next injection event that occurs after the injection event in the group of injection events; When determining that there is no next injection event in the group of injection events, determining that the injection event is associated with a dose administered to the user; And When determining that there is a next injection event in the injection event group, the dose to be administered to the user is determined based on the time period between the injection event and the next injection event in the injection event group.

7. The method according to claim 1, wherein The second predetermined threshold is a time period between 75 seconds and 85 seconds.

8. The method according to claim 1, wherein Determining the dose to be administered to the user based on the dose magnitude of the first injection event includes: Determining whether the dose magnitude is greater than a third predetermined threshold; When determining that the dose magnitude is greater than the third predetermined threshold, determining that the first injection event is associated with the dose administered to the user; and When determining that the dose magnitude is not greater than the third predetermined threshold, determining that the first injection event is associated with a priming dose not administered to the user.

9. The method according to claim 8, wherein The third predetermined threshold is a dose magnitude between four units and five units.

10. A computer program comprising instructions that, when executed by one or more processors on a computing device, are operable to cause the one or more processors to perform the method according to any one of claims 1-9.

11. A system comprising a memory storing instructions and a processor, the processor being configured to execute the instructions to perform the method according to any one of claims 1-9.

Images