System and method for displaying an image-based representation of measurement data

Abstract

A method for operating a medical monitoring system includes providing stored program instructions for a software application. The software application is configured to be stored in the non-temporary memory of a computing device. When executed by the computing device's processor, the software application is configured to (i) acquire measurement data, (ii) store non-medical image data in non-temporary memory, (iii) modify the image data based on the measurement data to generate modified image data, and (iv) render the modified image data as a modified image on the computing device's display screen. Modifying the image data includes changing the features of the non-medical image to represent the measurement data.

Description

Technical Field

[0001] [Cross - Reference to Related Applications] This application claims the priority of International Patent Application No. PCT / US2023 / 066236, filed with the United States Patent and Trademark Office on April 26, 2023, the disclosure of which is hereby incorporated by reference in its entirety.

[0002] [Technical Field] This disclosure relates to a medical monitoring system and method for displaying an image representing measurement data on an electronic device. The system and method can be applied to monitor information on blood glucose concentration, blood pressure, cholesterol level, and / or coagulation. The system and method enhance the privacy of the user.

Background Art

[0003] In many fields of medical treatment and healthcare, monitoring of specific body functions is required. For diabetic patients, regularly checking blood glucose concentration is typically part of their daily life. Preferably, the blood glucose concentration is measured at least several times a day so that the person can determine when to initiate responsive drug therapy (such as insulin or insulin analogs) when a specific limit is exceeded. Often, portable medical testing devices are used so as not to overly disrupt the person's daily life. A number of portable medical testing devices for monitoring various body functions are commercially available. These medical testing devices provide blood glucose concentration data, for example, in a rapid and reliable manner.

[0004] In many cases, people with diabetes check their blood glucose levels in public places, such as before a business lunch at a restaurant or at the company of people who may or may not know that the person is managing a medical condition. For example, someone using a continuous glucose monitor can open a smartphone or smartwatch application, or "app," to see a medical image (such as a graph or chart) of plotted blood glucose data. Charts are an effective way to communicate concentration data to the person. However, in many cases, charts and the associated graphical interface of the app are easily visible to others as medical information. As a result, by checking blood glucose levels in public, the person may unintentionally or unknowingly share personal medical information with those close to them. Furthermore, for some people, the medical record and the clinical interface of the app unnecessarily remind them that they are managing a serious medical condition.

[0005] Based on the aforementioned shortcomings of currently available medical testing devices, there is a need to improve the management and display of health measurement data to enhance user privacy and improve the user experience. [Overview of the project]

[0006] According to an exemplary embodiment, a method for operating a medical monitoring system includes providing stored program instructions for a software application. The software application is configured to be stored in the non-temporary memory of a computing device. When executed by the processor of the computing device, the software application is configured to (i) acquire measurement data, (ii) store image data of a non-medical image in non-temporary memory, (iii) modify the image data based on the measurement data to generate modified image data, and (iv) render the modified image data as a modified image on the display screen of the computing device. Modifying the image data includes changing the features of the non-medical image to represent the measurement data.

[0007] According to one aspect of this method, the feature is a horizon, and the measurement data includes measured values ​​and corresponding time values. Modifying the feature includes changing the horizon to represent the measured values ​​in a time series, depending on the time values.

[0008] According to another aspect of the present method, the measurement includes a previous measurement and a subsequent measurement, and modifying the feature further includes (i) changing the horizon so that the display of the portion of the image located above the horizon is reduced in response to the subsequent measurement being greater than the previous measurement, and (ii) changing the horizon so that the display of the portion of the image located above the horizon is increased in response to the subsequent measurement being smaller than the previous measurement.

[0009] In another aspect of this method, the non-medical image shows a mountain range, and the horizon includes at least one peak of the mountain range and / or at least one valley of the mountain range. Modifying the features of the non-medical image further includes resizing and / or rearranging at least one peak and / or at least one valley to represent the measurement.

[0010] According to a further embodiment of the method, the non-medical image is a selected non-medical image from a plurality of non-medical images, and the software application is further configured to (i) store the image data of the plurality of non-medical images in non-temporary memory, each non-medical image having a corresponding feature, (ii) determine a feature mathematical function for each feature of the plurality of non-medical images, the feature mathematical function defines a feature curve determined by the corresponding feature, (iii) determine a data mathematical function corresponding to a data curve determined by the measured values ​​of the measurement data, and (iv) use a processor to compare the values ​​of the data mathematical function with the values ​​of the image mathematical function to identify the selected non-medical image as a plurality of non-medical images having a feature curve that best fits the data curve.

[0011] In one embodiment of the method, the non-medical image is a selected non-medical image from a plurality of non-medical images, and the software application is further configured to receive user-derived input data for the input device of the computing device. The input data identifies the selected non-medical image.

[0012] Another aspect of the method involves receiving input data from a user for an input device of a computing device, the input data corresponding to a selected theme from among several themes stored in non-temporary memory as theme data. A non-medical image is a selected non-medical image from among several non-medical images. Each non-medical image is assigned a theme from among several themes, and the theme of the selected non-medical image matches the theme of the selected image.

[0013] In a further embodiment of the method, the software application is configured to acquire overlay data corresponding to time, weather information, and / or critical condition information, and to render the overlay data as time graphics, weather graphics, and / or critical condition graphics overlaid on a modified image as shown on a display screen.

[0014] In yet another aspect of the method, the software application is further configured to generate corrected image data using a machine learning model that operates (i) on the processor of a remote server communicating with the computing device, and / or (ii) on the processor of the computing device.

[0015] According to another aspect of the method, the measurement data includes a measured value and a corresponding time value. In this aspect, correcting the image data further includes segmenting a non-medical image into a plurality of segments, each segment containing a portion of the features; generating a plurality of corrected segments by modifying a portion of the features of each segment so as to represent at least one measured value; and arranging the corrected segments in chronological order based on the corresponding time values ​​to form a corrected image.

[0016] In another aspect of the method, the software application is further configured to (i) acquire additional measurement data, (ii) generate an updated corrected segment having some of the features corresponding to the measurements of the additional measurement data, (iii) append the updated corrected segment to the corrected image, and (iv) remove the image data corresponding to the oldest corrected segment from the corrected image.

[0017] A further aspect of the method includes rendering the measurement data on a display screen.

[0018] According to another exemplary embodiment, a medical monitoring system includes a measuring device, a remote server, and a computing device. The measuring device includes a sensor configured to generate measurement data. The remote server is configured to (i) receive measurement data, (ii) store image data of a non-medical image in non-temporary memory, and (iii) modify the image data based on the measurement data and generate the modified image data using the remote server's processor. The computing device communicates with the remote server and is configured to receive the modified image data. The computing device includes a processor configured to render the modified image data as a modified image on the computing device's display screen. Modifying the image data includes altering the features of a non-medical image to represent the measurement data.

[0019] In one embodiment of the medical monitoring system, the measuring device is a wearable continuous blood glucose monitor, and the sensor is configured to detect glucose in the interstitial fluid. The measurement data represents the blood glucose concentration over time.

[0020] In another aspect of the medical monitoring system, the computing device is one of the following: a smartphone, a smartwatch, a laptop computer, or a desktop computer.

[0021] In another exemplary embodiment, a method for operating a medical monitoring system includes receiving measurement data using a remote server, and using the remote server to generate synthetic image data of a synthetic non-medical image based on the measurement data. The synthetic non-medical image includes features representing the measurement data. The method further includes transmitting the synthetic image data to a computing device for rendering as a synthetic non-medical image on the display screen of the computing device. The synthetic non-medical image is generated by a machine learning model running on the remote server. At least one trend in the measurement data is represented by features in the synthetic non-medical image.

[0022] Depending on the method, the characteristic feature is the horizon representing the measurement data.

[0023] In another embodiment, the method includes (i) receiving additional measurement data on a remote server; (ii) generating updated composite image data of the updated composite non-medical image portion, having updated features representing the additional measurement data; and (iii) processing the updated composite image data and the composite image data on a processor of a remote server or computing device so that the updated composite non-medical image portion is added to the composite non-medical image.

[0024] Further aspects of the method include using a processor on a computing device or a remote server to detect that measurement data includes at least one measurement outside a predetermined range, and using a processor on the computing device to generate overlay data corresponding to a critical condition graphic based on the at least one measurement for rendering as a synthetic non-medical overlay on a display screen.

[0025] Further embodiments of the method include generating measurement data using a wearable continuous glucose monitor and transmitting the measurement data from the wearable continuous glucose monitor to a remote server using a computing device. The measurement data represents blood glucose concentration over time.

[0026] According to further exemplary embodiments of the present disclosure, a method for operating a medical monitoring system includes acquiring measurement data and storing image data of non-medical images in a non-temporary memory device. The method further includes modifying the image data based on the measurement data to generate modified image data and rendering the modified image data as a modified image on a display screen of a computing device using the processor of the computing device. Modifying the image data includes altering the features of the non-medical image to represent the measurement data.

[0027] According to yet another exemplary embodiment of the present disclosure, a method for operating a medical monitoring system includes acquiring measurement data on a remote server and generating image data of a synthetic non-medical image on the remote server based on the measurement data. The synthetic non-medical image includes features representing the measurement data. The method further includes transmitting the image data to a computing device and rendering the image data as a synthetic non-medical image on a display screen of the computing device. The synthetic non-medical image is generated by a machine learning model running on the remote server. At least one trend in the measurement data is indicated by features in the synthetic non-medical image.

[0028] According to a further exemplary embodiment of the present disclosure, a method of operating a medical monitoring system includes receiving measurement data, storing image data of a non-medical image in a non-temporary memory device, modifying the image data based on the measurement data to generate modified image data, and transmitting the modified image data as a modified image for rendering on a display screen of a computing device using a processor of the computing device. Modifying the image data includes changing features of the non-medical image to represent the measurement data.

[0029] In yet another exemplary embodiment of the present disclosure, a method of operating a medical monitoring system includes providing stored program instructions for a software application. The software application is configured to be stored in a non-temporary memory of a computing device. When executed by a processor of the computing device, the software application is configured to receive measurement data at a remote server and generate composite image data of a composite non-medical image based on the measurement data at the remote server. The composite non-medical image includes features representing the measurement data. The software application is further configured to transmit the composite image data to the computing device for rendering as the composite non-medical image on a display screen of the computing device. The composite non-medical image is generated by a machine learning model operating on the remote server. At least one trend in the measurement data is indicated by features of the composite non-medical image.

Brief Description of the Drawings

[0030] The above features, advantages, and others should become more readily apparent to those skilled in the art by reference to the following detailed description and the accompanying drawings.

[0031] [Figure 1]This specification discloses a computing device (referred to as a smartphone) for a medical monitoring system, which has a display screen that shows a modified image representing a person's measurement data, such as blood glucose concentration. [Figure 2] Figure 1 is a block diagram of a medical monitoring system including a computing device, the medical monitoring system further including measuring devices and a remote server. [Figure 3] Figure 2 is a flowchart illustrating an exemplary method for operating the medical monitoring system. [Figure 4] It depicts an uncorrected, non-medical image suitable for correction to represent measurement data from a measuring device. [Figure 5] Figure 4 depicts a modified image based on a non-medical image, and the modified image includes features representing measurement data from the measurement device. [Figure 6] Figure 2 is a flowchart illustrating another exemplary method for operating the medical monitoring system. [Figure 7] These are synthetic non-medical images generated by a machine learning model according to the method described in the flowchart in Figure 6. [Modes for carrying out the invention]

[0032] Herein, for the purpose of facilitating an understanding of the principles of this disclosure, embodiments shown in the drawings will be referenced and described in the subsequent details. It will be understood that no limitation on the scope of this disclosure is intended therein. It will be further understood that this disclosure includes any changes and modifications to the exemplary embodiments and includes further applications of the principles of this disclosure as would ordinarily conceivable to those skilled in the art to whom this disclosure relates.

[0033] Aspects of this disclosure are disclosed in the accompanying description. Alternative embodiments of this disclosure and their equivalents can be devised without departing from the spirit or scope of this disclosure. Any discussion in this specification relating to “one embodiment,” “an embodiment,” “an exemplary embodiment,” etc., should be noted to indicate that the described embodiment may include certain features, structures, or characteristics, and that such certain features, structures, or characteristics may not necessarily be included in all embodiments. Furthermore, references above do not necessarily include references to the same embodiment. Finally, whether expressly stated or not, a person skilled in the art will readily understand that each of the certain features, structures, or characteristics of a given embodiment may be used in relation to, or in combination with, those of any other embodiment described herein.

[0034] For the purposes of this disclosure, the phrase "A and / or B" means (A), (B), or (A and B). For the purposes of this disclosure, the phrase "A, B, and / or C" means (A), (B), (C), (A and B), (A and C), (B and C), or (A, B and C).

[0035] Terms such as “comprising,” “including,” and “having” as used in relation to embodiments of this disclosure are synonymous.

[0036] As shown in Figure 1, the exemplary computing device 108 includes a display screen 172 showing a graphical user interface ("GUI") 188. The GUI 188 includes an image of a mountain region, the time, and certain other data overlaid on it. To an uninformed person, the GUI 188 is the wallpaper, home screen, or background scene of the computing device 108, which is presented as a smartphone. Thus, when viewed by a third party, the user of the computing device 108 appears to be checking the time or checking notifications. However, to the user, the GUI 188 communicates blood glucose concentration data 158 (Figure 2) in a non-medical, motivational, and disguised form. Specifically, the user's blood glucose concentration data or other measurement data 158 is encoded in a modified image 184 and corresponds to the illustrated horizon 232. As a result, the user can view their measurement data 158 in public without others knowing that they are managing a medical condition. Furthermore, the user is provided with measurement data 158 in a non-medical setting, which improves the user experience by being less likely to directly remind the user of their medical condition. The following describes various aspects of a medical monitoring system 100, including a computing device 108, which includes methods 300, 600 for encoding measurement data 158 into images.

[0037] Referring to Figure 2, the medical monitoring system 100 includes a measuring device 104, a computing device 108, and a remote server 112. In one embodiment, the measuring device 104 is a wearable continuous glucose monitor ("CGM") used to generate measurement data 158 corresponding to a person's blood glucose concentration. The measuring device 104 includes a sensor 116, a memory device 120, and a transceiver 124, each operably connected to a processor 128.

[0038] The sensor 116 is attached to the skin 132 of a person 136 by adhesive and includes a probe 140 positioned directly beneath the skin 132. The probe 140 is in contact with the interstitial fluid 144 of the person 136. In one embodiment, the probe 140 is an enzyme-based amperometric biosensor configured to measure the glucose concentration in the interstitial fluid 144. In other embodiments, the sensor 116 measures the glucose concentration according to other suitable structural configurations and methodologies. The measuring device 104 can operate with or without a corresponding insulin pump (not shown).

[0039] The processor 128 of the measuring device 104 is configured to execute instructions that cause the measuring device 104 to operate in order to enable the features, functions, characteristics, etc., described herein. The processor 128 generally comprises one or more processors that can operate in parallel with each other or in coordination. As used herein, the term “processor” will be recognized by those skilled in the art to include any hardware system, hardware mechanism, or hardware component that processes data, signals, or other information. Accordingly, the processor 128 may include a central processing unit, a graphics processing unit, a plurality of processing units, a system having dedicated circuits, programmable logic, or other processing systems for achieving a function.

[0040] As shown in Figure 2, the memory device 120 is configured to store data and program instructions that, when executed by the processor 128, enable the measuring device 104 to perform the various operations described herein. The memory device 120 may be any type of electronic device capable of storing information accessible by the processor 128, such as a memory card, read-only memory ("ROM"), random access memory ("RAM"), hard drive, solid-state drive, disk, flash memory, or any of various other computer-readable media that function as data storage devices, as will be recognized by those skilled in the art. The memory device 120 is also referred to herein as a non-temporary computer-readable medium, a non-temporary memory device, and non-temporary memory. The memory device 120 stores measurement data 158 generated by the processor 128 and measured by the sensor 116. Exemplary measurement data 158 is shown in Figure 2 and is identified by the letters A–J for reference. The letters A–J are not part of the measurement data 158.

[0041] In one embodiment, the transceiver 124 of the measuring device 104 is configured for wired and / or wireless exchange of data with the computing device 108. The transceiver 124 includes one or more modems, processors, memory, oscillators, antennas, or other hardware conventionally included in a communication module to enable electronic communication with various other devices. For example, the transceiver 124 can exchange electronic data using wireless local area networks ("Wi-Fi"), personal area networks, Bluetooth®, near-field communication ("NFC"), ultra-wideband ("UWB"), cellular networks, and / or any other wireless network protocols. Thus, the transceiver 124 is compatible with any desired wireless communication standard or protocol, including, but not limited to, IEEE 802.11, IEEE 802.15.1 ("Bluetooth®"), Global System for Mobile ("GSM"), and Code Division Multiple Access ("CDMA"). In one embodiment, the transceiver 124 operably connects the measuring device 104 to the Internet 148 for data exchange with any other device connected to the Internet 148. In another embodiment, the transceiver 124 sends and receives data directly from the computing device 108 without being connected to the Internet 148. The transceiver 124 is also referred to herein as a network adapter, a network device, and / or a network communication module.

[0042] Continuing to refer to Figure 2, the computing device 108 of the medical monitoring system 100 includes a memory device 160, a transceiver 164, an input device 168, and a display screen 172, each operably connected to a processor 176. The computing device 108 is described and illustrated herein as a smartphone. It will be understood that the illustrated embodiments of the computing device 108 are merely illustrative embodiments and represent only one of various ways, configurations, or combinations of servers, personal computers, desktop computers, laptop computers, smartwatches, mobile phones, tablet computers, or any other computing devices operating in the manner described herein.

[0043] The processor 176 is configured to execute instructions that cause the computing device 108 to operate in order to enable the features, functions, characteristics, etc., described herein. The processor 176 generally comprises one or more processors that can operate in parallel or in cooperation with one another. The processor 176 may include a central processing unit, a graphics processing unit, a plurality of processing units, a dedicated circuit for achieving a function, programmable logic, or other processing system. The processor 176 is configured to execute applications (i.e., “apps”) stored in the memory device 160 as app data 180.

[0044] As shown in Figure 2, the memory device 160 is configured to store data and program instructions that, when executed by the processor 176, enable the computing device 108 to perform various operations and methods described herein. The memory device 160 may be any type of electronic device capable of storing information accessible by the processor 176, such as a memory card, ROM, RAM, hard drive, solid-state drive, disk, flash memory, or any of various other computer-readable media that function as data storage devices, as will be recognized by those skilled in the art. The memory device 160 is also referred to herein as a non-temporary computer-readable medium, a non-temporary memory device, and non-temporary memory. The memory device 160 is configured to store image data 198 of a non-medical image 224 used by the computing device 108 and / or the remote server 112 to generate a modified image 184. Furthermore, in at least some embodiments, the memory device 160 stores theme data 202 corresponding to the theme of the non-medical image 224 of the image data 198, prompt data 210 to be provided to the machine learning model 216, and overlay data 206 corresponding to the time, smartphone information, and critical condition information.

[0045] In one embodiment, the transceiver 164 is configured for wired and / or wireless exchange of data with the measuring device 104, the remote server 112, and the Internet 148. The transceiver 164 includes one or more modems, processors, memory, oscillators, antennas, or other hardware conventionally included in a communication module to enable electronic communication with various other devices. For example, the transceiver 164 can exchange data using Wi-Fi, personal area networks, Bluetooth®, NFC, UWB, cellular networks, and / or any other wireless network protocols. Therefore, the transceiver 164 is compatible with any desired wireless communication standard or protocol, including but not limited to IEEE 802.11, Bluetooth®, GSM, and CDMA. The transceiver 164 operably connects the computing device 108 to the Internet 148 for data exchange with any other device connected to the Internet 148. The transceiver 164 also transmits and receives data directly or indirectly with the measuring device 104. The transceiver 164 is also referred to herein as a network adapter and / or network device.

[0046] The display screen 172 of the computing device 108 is configured to render and display text, images, and other user-perceptible output and visually understandable data, including the modified image 184 of Figure 1 which encodes the measurement data 158. The display screen 172 may include any of the various known types of displays, such as a liquid crystal display ("LCD") or an organic light-emitting diode ("OLED") screen, configured to display the GUI 188 and / or the modified image 184, as described herein.

[0047] Referring again to Figure 1, the input device 168 of the computing device 108 is a touchscreen applied to a display screen 172 configured to respond to touches of a finger or stylus by generating user input data 192 (Figure 2). The input device 168 may also include at least one button, switch, keyboard, and / or keypad configured to generate input data 192 when touched or moved by the user. Additionally or alternatively, the input device 168 may include a microphone configured to generate input data 192 in response to sound, such as the voice of the user of the computing device 108. In yet another embodiment, the input device 168 may be any device configured to generate input data 192, as will be recognized by those skilled in the art.

[0048] As shown in Figure 2, the remote server 112 of the medical monitoring system 100 includes a transceiver 200 and a memory device 204 operably connected to a processor 208.

[0049] The processor 208 is configured to execute instructions for operating the remote server 112 and to enable the features, functions, characteristics, etc. described herein. The processor 208 generally comprises one or more processors that can operate in parallel with each other or in cooperation with each other. The processor 208 may include a central processing unit, a graphics processing unit, a plurality of processing units, dedicated circuits for achieving functions, programmable logic, or other processing systems.

[0050] In one embodiment, the transceiver 200 is configured for wired and / or wireless exchange of data with a computing device 108 and the Internet 148. The transceiver 200 includes one or more modems, processors, memory, oscillators, antennas, or other hardware conventionally included in a communication module to enable electronic communication with various other devices. For example, the transceiver 200 can exchange data using Wi-Fi, personal area networks, Bluetooth®, NFC, UWB, cellular networks, and / or any other wireless network protocol. Thus, the transceiver 200 is compatible with any desired wireless communication standard or protocol, including but not limited to IEEE 802.11, Bluetooth®, GSM, and CDMA. The transceiver 200 is also referred to herein as a network adapter and / or network device.

[0051] The memory device 204 is configured to store data and program instructions that, when executed by the processor 208, enable the remote server 112 to perform the various operations and methods described herein. The memory device 204 may be any type of electronic device capable of storing information accessible by the processor 208, such as a memory card, ROM, RAM, hard drive, solid-state drive, disk, flash memory, or any of various other computer-readable media that function as data storage devices, as will be recognized by those skilled in the art. The memory device 204 is also referred to herein as a non-temporary computer-readable medium, a non-temporary memory device, and non-temporary memory. The remote server 112 is configured to store modified image data 212 corresponding to the modified image 184, and, in some embodiments, synthetic image data 214 generated by the machine learning model 216.

[0052] As shown in Figure 2, the machine learning model 216 of the remote server 112 is a text-image model configured to receive natural language descriptions and numerical inputs (i.e., prompts, prompt data 210). The machine learning model 216 can be characterized as an artificial neural network ("ANN") or a simulated neural network ("SNN"). In one embodiment, the machine learning model 216 generates a new image that accurately represents the prompt and encodes or represents the measurement data 158. The new image is stored in memory 112 as synthetic image data 214 of a synthetic non-medical image 280. In another embodiment, the machine learning model 212 modifies an existing non-medical image 224 stored as image data 198 based on the measurement data 158 to arrive at the modified image data 212.

[0053] The machine learning model 216 is trained on training data containing millions of images and millions of corresponding text-based descriptions. Exemplary machine learning models 216 suitable for generating modified image data 212 and / or synthetic image data 214 include DALL-E and DALL-E 2, developed by OpenAI, Stable Diffusion, and Midjourney. DALL-E and DALL-E 2 are trained generative pre-trained transformer 3 ("GPT-3") language models that use deep learning to convert text to images. In some embodiments, the machine learning model 216 is referred to as an artificial intelligence ("AI") art generator or AI image generator.

[0054] Referring to Figure 3, the flowchart depicts a first exemplary method 300 for operating the medical monitoring system 100. In one embodiment, method 300 is provided as stored program instructions for a software application. For example, the software application is stored in the memory 160 of the remote server 112, the computing device 108, and / or memory 204. When executed by at least one of the corresponding processors 128, 176, the software application is configured to perform method 300 as shown in Figure 3. The software application is also called an “app”.

[0055] In Method 300, with further reference to Figure 4, the medical monitoring system 100 starts with a non-medical image 224 stored as image data 198, and then runs an application (stored as application data 180) on the computing device 108 that modifies or corrects the non-medical image 224 so that its features 228 represent measurement data 158 generated by the measurement device 104. The various aspects of the first Method 300 are described below.

[0056] In block 304 of method 300, measurement data 158 is generated by the measuring device 104 and acquired from the measuring device 104 by the computing device 108. As shown in Figure 2, exemplary measurement data 158 includes multiple measurements and the corresponding time values ​​on which the measurements were recorded. First, the measurement data 158 is stored in the memory device 120 of the measuring device 104. However, for example, in response to a request from the computing device 108, the measuring device 104 uses transceivers 124, 164 to either directly transmit the measurement data 158 to the computing device 108 or transmit it indirectly to the computing device 108 via the internet 148. The computing device 108 stores the acquired measurement data 158 in the memory device 160.

[0057] In some embodiments, the time and measured values ​​of the measurement data 158 are converted, transformed, and / or calibrated to at least one suitable, appropriate, or desired unit among the measuring device 104, the computing device 108, and the remote server 112. The measurement data 158 may be converted, transformed, and / or calibrated based on the country or location of use and the health function being measured, among other factors. In some embodiments, the original, unconverted, or uncalibrated measurement data 158 remains stored in the memory 120 of the measuring device 104 as an index of time and / or raw current units.

[0058] The measuring device 104 periodically generates measurement data 158 according to a predetermined time interval, for example, every 5 minutes. The measurement data 158 shown in Figure 2 is simplified and includes measured values ​​and time values ​​at 30-minute intervals (another predetermined period). In one embodiment, the computing device 108 periodically acquires the measurement data 158 from the measuring device 104 whenever new measured values ​​are stored in the memory device 120. Alternatively, the computing device 108 waits until a predetermined period has elapsed or until a predetermined number of measured values ​​and time values ​​have been stored in the memory device 120 before acquiring the measurement data 158.

[0059] Next, in block 308, method 300 includes sending the measurement data 104 and image data 198 to the remote server 112 for processing by the processor 208 so that the remote server 112 acquires the measurement data 104 and image data 198. In this example, the remote server 112 performs correction of the non-medical image 224. In other embodiments, the remote server 112 is not required, and the correction of the non-medical image 224 is performed by the processor 176 of the computing device 108. Furthermore, in other embodiments, the measurement data 158 is sent to the remote server 112 via the internet without first being sent to the computing device 108.

[0060] As shown in Figure 4, the exemplary non-medical image 224 depicts a landscape with a mountain range. The dashed vertical line 234 overlaid on the non-medical image 224 is not part of the image 224 but is included to aid in illustrating the image modification process by method 300. As used herein, a non-medical image 224 is an image that is not, does not concern, is not used, or is not related to the medical or healthcare field. A non-medical image 224 is not a chart or graph of medical data or measurement data 158. As used herein, a medical image is an image that concerns, is used, or is related to the medical or healthcare field. A graph or chart of measurement data 158 is a medical image.

[0061] The exemplary non-medical image 224 in Figure 4 shows a horizon 232 between the sky 238 and the ground 240. The horizon 232 is a feature 228 of the non-medical image 224 that is modified, corrected, adjusted, redrawn, and / or otherwise manipulated to represent measurement data 158. The horizon 232 is the line where the sky 238 and the ground 240 intersect, and “ground” is the ground or a body of water. The upper-side image portion of the non-medical image 224 is located above the horizon 232 on the opposite side of the ground and may include clouds and / or any other elements typically located in the sky. The ground-side image portion of the non-medical image 224 is located on the opposite side of the sky 238 and the upper-side portion and includes the ground. The exemplary horizon 232 includes some mountain peaks 242 and some valleys 244 of the mountain range. In Figure 4, the non-medical image 224 does not represent measurement data 158. Instead, for example, a non-medical image 224 is a digital representation of a photograph of an actual mountain range, or an artist's depiction of a mountain range created without connection to measurement data 158. Other suitable subjects for non-medical images 224 include, but are not limited to, dunes, waves, and city skylines. Most non-medical images 224 depicting a horizon 232 are suitable non-medical images 224 for use in the medical surveillance system 100. Furthermore, any other non-medical image having abstract techniques or prominent stripes, lines, ridges, or grooves (each being a feature 228) is a suitable non-medical image 224 for use in the medical surveillance system 100.

[0062] In block 312 of this method, the processor 208 of the remote server 112 modifies the image data 198 of the non-medical image 224 based on the measurement data 158 to generate modified image data 212 corresponding to the modified image 184. The modified image data 212 is initially stored in the memory device 204 of the remote server 112. As used herein, modifying the image data 198 includes changing the image data 198 to change the appearance of the non-medical image 224 rendered on the display screen 172. The modification to the non-medical image 224 results in a modified image 184 having features 228 representing the measurement data 158. In some embodiments, method 300 includes extending or adding to the previously generated non-medical image 224 so that method 300 maintains a consistent image that enables smooth animation.

[0063] An exemplary modified image 184 is shown in Figure 5. In modified image 184, the processor 208 modifies the image data 198 so that the feature 228 is modified to represent the measurement data 158. Specifically, as an example of modifying the feature 228, the processor 208 modifies the appearance of the horizon 232 so that the contours of the mountain peaks 242, valleys 244, and mountain ranges correspond to the measurements of the measurement data 158 over time, based on the time values ​​of the measurement data 158. Thus, modifying the feature 228 includes increasing the height of the valleys 244 or mountain peaks 242, decreasing the height of the valleys 244 or mountain peaks 242, and flattening or removing the valleys 244 or mountain peaks 242 so that the horizon 232 represents the measurements of the measurement data 158. In this example, the horizontal direction of the modified image 184 corresponds to time, with older measurements shown on the left side of the image 184 and newer measurements shown on the right side of the image 184. The vertical dimension of the corrected image 184 corresponds to the size of the measured values. Feature 228 being closer to the top of image 184 (less sky 238, smaller upper-view image portion, more ground 240) indicates a relatively high size, while feature 228 being closer to the bottom of image 184 (more sky 238, larger upper-view image portion, less ground 240) indicates a relatively low size.

[0064] In one embodiment, the modified image 184, as shown on the display screen 172, does not include a scale that allows the user to determine the magnitude of the measured values ​​of the measurement data 158. This is because the modified image 184 is a non-medical image, not a chart or graph of medical data. Instead, the features 228 of the modified image 184 communicate to the user the trend or change in the measurement data 158, rather than directly displaying the measured values ​​of the measurement data 158. For example, as shown in Figure 5, the features 228 are nearly flat from measurement point A to measurement point C, which coincides with the corresponding measured values ​​that are progressing flatly. Thus, the user can determine that blood glucose was relatively stable during this period. From measurement points C to I, the features 228 show a slope, which coincides with the measured values ​​of the measurement data 158 that are going upward. Thus, the user can determine that blood glucose was rising during this period. From measurement points I to J, the features 228 show a decrease, which coincides with the measured values ​​of the measurement data 158 that are going downward. Thus, the user can determine that blood glucose was decreasing during this period. The modified image 184 requires only a glance from the user and provides insight into the user's measurement data 158 without displaying any measurement or time values.

[0065] According to one method for modifying feature 228, the processor 208 segments the non-medical image 224 into multiple segments 248 (Figure 4), as identified by the dashed line 234. Each segment 248 contains a portion of feature 228 that is modified to represent the measurement data 158. Next, as shown in Figure 5, the processor 208 generates a modified segment 250 in which a portion of feature 228 in that segment 250 is moved or modified to correspond to at least one of the measurements of the measurement data 158.

[0066] For example, the modified image 184 in Figure 5 includes a modified feature 228 based on measurement data 158 labeled A-J in Figure 2, with additional measurements and time values ​​between the labeled measurement data 158. As indicated by the time values, the "A" data 158 is a previous measurement generated before the "B" data 158, and a subsequent measurement generated after the "A" data 158. In this example, the subsequent measurement ("B" data, 80 mg / dl) is smaller than the previous measurement ("A" data, 85 mg / dl). As a result, the processor 208 modified the image data 198 of the "B" data modified segment 254 to modify the feature 228 to increase the display of the sky 238 (i.e., increase the display of the upper part of the image above the horizon 232 and decrease the display of the lower part of the image below the horizon 232) so that the display of the horizon 232 in the "B" data modified segment 258 is lower compared to the display of the horizon 232 in the "A" data modified segment 254. In this example, this can be thought of as modifying image data 198 to lower the horizon 232.

[0067] In another example, the "F" data 158 is a previous measurement generated before the subsequent measurement, the "G" data 158. In this example, the subsequent measurement ("G" data 130 mg / dl) is greater than the previous measurement ("F" data 125 mg / dl). As a result, the processor 208 modifies the image data 198 of the "G" data correction segment 262 to modify the feature 228 to reduce the display of sky 238 (i.e., reducing the display of the upper part of the image above the horizon 232 and increasing the display of the lower part of the image above the horizon 232) so that the horizon 232 in the "G" data correction segment 262 is higher compared to the display of the horizon 232 in the "F" data correction segment 264. This can also be thought of as modifying the image data 198 to raise the horizon 232 in this example. The processor 208 performs this analysis for each measurement of the measurement data 158 to generate the corrected image data 212 of the corrected image 184. The corrected segments 250 are arranged in a time series based on the corresponding time values ​​of the measurement data 158.

[0068] As a result of modifying feature 228 in the manner described above, the peaks 242 and valleys 244 of the mountain range are resized and / or rearranged to represent the measurements of the measurement data 158. In this way, the mountain range can be represented in significantly different configurations depending on the measurement data 158. For example, if the measurement data 158 contains almost the same measurements, feature 228 is modified to have a nearly flat horizon 232 with little or no distinction between the peaks 242 and valleys 244. If the measurements of the measurement data 158 increase or decrease at a nearly constant rate, feature 228 is modified to have a slope, again with little or no distinction between the peaks 242 and valleys 244. However, if the measurement data 158 contains measurements that increase and decrease over time, the peaks 242 and valleys 244 of the horizon 232 are rearranged and / or resized, resulting in the mountain range appearing as an entirely new mountain range.

[0069] Next, in block 316, method 300 includes transmitting the corrected image data 212 to a computing device 108 using transceivers 164, 200 over the internet 148. This process is also referred to as downloading the corrected image data 212 using the computing device 108. The computing device 108 is configured to store the corrected image data 212 in a memory device 160.

[0070] In block 320 of method 300, the computing device 108 displays the corrected image 184 on the display screen 172. Displaying the corrected image 184 includes rendering the corrected image data 212 as the corrected image 184 on the display screen 172 using the processor 176.

[0071] As shown in the flowchart of Figure 3, the method 300 returns to block 304 after displaying the corrected image 184, so that the computing device 108 can obtain additional measurement data 158 from the measuring device 104 that were not previously encoded in the corrected image 184. In one embodiment, after receiving the additional measurement data 158, the computing device 108 sends the additional measurement data 158 to the remote server 112 for processing by the processor 208. The processor 208 selects a predetermined number of segments 248 and then modifies the features 228 shown in the segments 248 to generate updated corrected segments 266 which are stored in the memory device 204 as updated corrected image data 212. Each updated corrected segment 266 contains features 228 corresponding to the measurements of the additional measurement data 158. When generating the updated corrected segment 266, the processor 208 also blends the updated corrected segment 266 with the previously generated corrected image 184, so that the features 228 flow continuously, seamlessly, and / or smoothly match all of the updated corrected segment 266.

[0072] For example, referring to Figure 5, the display screen 172 of a particular computing device 108 is configured to display only the portion of the modified image 184 related to the measurement data 158 "A" to "H". Additional measurement data 158 corresponds to measurement data 158 "I" and "J". The processor 208 generates an updated modified segment 266 and adds the updated modified segment 266 to the modified image 184. The updated modified segment 266 is added to the right side of the modified image 184 because the updated modified segment 266 corresponds to the most recent measurement data 158. Furthermore, the modified image data 212 of the oldest segment 268 is not shown as part of the modified image 184. In this way, the modified image 184 is a dynamic wallpaper or home screen that scrolls from right to left to display a representation of the most recent measurement data 158 generated by the measurement device 104 over a predetermined period of time. An exemplary predetermined period of time is from 30 minutes to 24 hours. In at least one embodiment, the image progresses smoothly horizontally in real time (i.e., real-time computing), pixel by pixel or minute by minute, in order to render a seamless animation of feature 228.

[0073] In one embodiment, image data 198 includes data corresponding to a plurality of non-medical images 224. For example, a computing device 108 renders one or more of the non-medical images 224 on a display screen 172, and the user interacts with an input device 168 to generate input data 192 that identifies selected non-medical images 224 to be modified based on measurement data 158. The user can select a non-medical image 224 by touching the touchscreen 168, by pressing a button 168, and / or by speaking into the microphone 168. In some embodiments, the non-medical images 224 are internally tested, recommended, and supplied to maintain alignment with the company / product brand strategy and to ensure general aesthetics and / or psychological motivation.

[0074] In another embodiment, each of the multiple non-medical images 224 is assigned a corresponding theme from a set of themes. The themes are stored as theme data 204 in the memory device 160 of the computing unit 108. The computing device 108 is configured to receive input data 192 from the user corresponding to a selected theme from the set of themes. The selected theme is also stored as theme data 204 in the memory device 160. Then, one or more non-medical images 224 that have been assigned a theme matching the selected theme are displayed on the display screen 172. The user can narrow down the selection of non-medical images 224 and then select a non-medical image 224 that corresponds to or matches the selected theme. Exemplary themes include snow-covered mountains, grassy mountains, gentle hills in summer, gentle hills in autumn, sand dunes, waves, nighttime city skyline, and daytime city skyline.

[0075] In a further embodiment, non-medical images 224 are selected based on a best-fit curve method. According to this method, for each non-medical image 224 of the image data 198, the processor 176 determines a feature mathematical function corresponding to the feature curve defined by the features 228. The processor 176 then analyzes the measurements of the measurement data 158 to determine a data mathematical function corresponding to the data curve defined by the measurements. Next, the values ​​of the data mathematical function are compared with the values ​​of the image mathematical function to identify the feature curve that best fits the data curve. The non-medical image 224 corresponding to the best-fit feature curve is selected as the selected non-medical image 224. This method typically results in a selected non-medical image 224 with fewer changes to the features 228 required to modify the image data 184 to represent the measurement data 158, thereby saving processing power.

[0076] In some embodiments, non-medical images 224 are ranked according to their use by collecting corresponding data from a computing device 108. When selecting non-medical images 224, the highest-ranking non-medical images 224 may be presented to the user first. Additionally or alternatively, when selecting non-medical images 244, images 224 may be filtered based on the user's age, gender, type of diabetes, type of treatment, and interests to assist the user in determining the selected non-medical images 224.

[0077] As shown in Figure 1, in block 320 of method 300, in some embodiments, the processor 176 of the computing device 108 acquires overlay data 206 and renders a graphic 272 corresponding to the overlay data 206 on the modified image 184, as shown on the display screen 172. Exemplary overlay data 206 includes the time, weather information, and the state of the computing device 108, including signal strength and battery charge status. The overlay data 206 is rendered as a time graphic, a weather information graphic, and / or a state graphic, as shown in Figure 1. The overlay data 206 can be acquired, for example, by downloading it from the internet 148.

[0078] Continuing to refer to Figure 1, the overlay data 206 also results in the display of a critical condition graphic 274 corresponding to critical condition information. For example, in some embodiments, the processor 176 of the computing device 108 compares the measured values ​​of the measurement data 158 to a range of predetermined conditional values ​​to determine whether the measurement data 158 indicates a potential health problem (i.e., an exemplary critical condition) for the user. For example, an embodiment of a medical monitoring system 100 configured to monitor glucose concentration may compare the measured glucose concentration of the measurement data 158 to a predetermined range of conditional values, including a predetermined minimum safe glucose concentration value and a predetermined maximum safe glucose concentration value. If at least one of the measured values ​​of the measurement data 158 is less than a predetermined minimum value or greater than a predetermined maximum value (i.e., outside the predetermined range), the processor 176 is configured to render a predetermined critical condition graphic 274 on the display screen 172 to notify the user of a potential health problem.

[0079] A predetermined critical condition graphic 274 is configurable and / or selectable by the user so that the user understands the meaning of the graphic 274 and why it is being displayed. In one example, the predetermined critical condition graphic 274 is a color frame overlay (not shown) displayed around a non-medical image 224 and / or around the display screen 172. The color of the color frame overlay indicates the severity, severity, and / or urgency of the measured health function. For example, if the measured health function is below a predetermined value, the color frame overlay is a first color, such as yellow. If the measured health function is above a predetermined value, the color frame overlay is a second color, such as red, which is different from the first color. In another example shown in Figure 1, the critical condition graphic 274 is a dog icon and is a non-medical graphic to maintain the user's privacy in situations where others can see the display screen 172. Therefore, even in the case of a potential health problem or other critical condition, as identified by the computing device 108, the entire GUI 188 is non-medical, and an uninformed observer has no indication that the user is interpreting the modified image 184 to gain insight into the state of the measured health function. The critical condition graphic 274 is included in Figure 1 for illustrative purposes only, and the measurements of the measurement data 158 shown in Figure 2 will not allow the computing device 108 to determine a potential health problem or another critical condition in most people.

[0080] Furthermore, upon viewing the graphic 274 of the critical state, when a privacy point is reached, or at any other time, the user can easily navigate to or open the corresponding app stored as app data 180 and directly view the measured and time values ​​of the measurement data 158, thereby enabling them to make appropriate health decisions. Thus, the processor 176 is configured to render the measurement data 158 on the display screen 172 in addition to, or instead of, the modified image 184. Method 300 does not prevent the user from directly accessing the measurement data 158; instead, Method 300 is a non-medical means of communicating trends in the measurement data 158 to the user. Exemplary health decisions include eating or snacking, delaying eating or snacking, administering insulin, delaying insulin administration, starting an exercise routine, ending an exercise routine, and contacting emergency services.

[0081] In some embodiments, the overlay data 206 may also include a highlight graphic (not shown) overlaid on the modified image 184 to emphasize and / or highlight the feature 228. The highlight graphic tends to reduce user confusion and misunderstanding when interpreting the modified image 184. In one embodiment, the highlight graphic is shown in a color that follows the feature 228 and is easily distinguishable from the scene or subject of the modified image 184. For example, the highlight graphic may be configured to follow the horizon 232 of an exemplary modified image 184 of a mountain range.

[0082] As shown in Figure 2, the measurement data 158 is a measurement determined by the sensor 116. In some embodiments, the measurement data 158 further includes predicted measurements corresponding to future time values. The predicted measurements are not generated by the sensor 116. Instead, the predicted measurements of the measurement data 158 are generated by at least one of the processors 128, 176, and 208 using an algorithm. In one embodiment, the algorithm determines the predicted measurements based on the sensor-generated measurement data 158, known user characteristics, and factors specific to the monitored health function. In one embodiment, the predicted measurements are included in the modified image 184 but are visually distinguishable from the measurement data 158 generated by the sensor 116. That is, the predicted measurements are represented by features 228 in the modified image 184 but are shown differently from the portions of features 228 based on the sensor-generated measurements. For example, portions of the modified image 184 and features 228 based on predicted measurements are shown on the display screen 172 in a weakened or duller color scheme compared to portions of the modified image 184 and features 228 generated based on sensor-generated measurements. Additionally or alternatively, a dividing line or boundary (not shown) can be displayed between the two portions of the corrected image 184 to further visually distinguish the portion of the corrected image 184 based on predicted measurements from the portion of the corrected image 184 based on sensor-generated measurements.

[0083] In the example described above, Method 300 in Figure 3 was illustrated by the remote server 112 (i) receiving measurement data 158 and image data 198, and (ii) processing the image data 198 to generate corrected image data 212 corresponding to the corrected image 184. In another embodiment of Method 300, a computing device 108 is configured to generate corrected image data 212 without using the remote server 112. In particular, the processor 176 of the computing device 108 is configured to perform Method 300 and generate corrected image data 212 without sending any data to the remote server 112.

[0084] Furthermore, in other embodiments, the machine learning model 216 is used to generate a modified image 184 instead of the modified approach for the segmented approach feature 228 described above. In such embodiments, the image data 198 of the non-medical image 224, measurement data 158, and prompt data 210 are sent to the remote server 112. The prompt data 210 corresponds to a prompt instructing the machine learning model 216 to modify the feature 228 of the non-medical image 224 to represent the measurement data 158. The machine learning model 216 then outputs modified image data 212 corresponding to a modified image 184 in which the feature 228 represents the measurement data 158. In further embodiments, the machine learning model 216 operates and is stored in the memory device 160 of the computing device 108 instead of the remote server 112.

[0085] As shown in Figure 6, the flowchart depicts a second exemplary method 600 for operating the medical monitoring system 100. In one embodiment, method 600 is provided as stored program instructions for a software application. For example, the software application is stored in the memory 160 of the remote server 112, the computing device 108, and / or memory 204. When executed by at least one of the corresponding processors 128, 176, the software application is configured to perform method 600 as shown in Figure 6. The software application is also called an “app”.

[0086] Method 600 does not start with a non-medical image 224, as described in Method 300. Instead, Method 600 uses a machine learning model 216 to generate a synthetic non-medical image 280 (Figure 7). The synthetic non-medical image 280 represents the measurement data 158 and includes a feature 228 that shows at least one trend of the measurement data 158. The following describes each aspect of the second Method 600.

[0087] In block 604, method 600 includes acquiring and / or receiving measurement data 158 generated by the measuring device 104. The measurement data 158 is first stored in the memory device 120 of the measuring device 104. However, for example, in response to a request from the computing device 108, the measuring device 104 uses transceivers 124, 164 to transmit the measurement data 158 directly to the computing device 108 or indirectly to the computing device 108 via the internet 148. The computing device 108 stores the acquired measurement data 158 in its memory device 160.

[0088] Next, in block 608, the measurement data 158 and prompt data 210 are sent to the remote server 112, which then acquires and / or receives the measurement data 158 and prompt data 210. Typically, the measurement data 158 and prompt data 210 are sent to the remote server 112 via the internet 148. The measurement data 158 includes the measured value and the corresponding time value, although in this example, these are not the same values ​​as those shown in Figure 2. Image data, such as image data 198, is not sent to the remote server 112.

[0089] The prompt data 210 is provided to the machine learning model 216 and includes prompts (i.e., text-based instructions or guidance) for the machine learning model 216 to generate a synthetic non-medical image 280. Exemplary prompts are “sand dunes,” “mountain range,” and “sea waves.” Thus, the prompts are the subject or theme of the synthetic non-medical image 280, and the measurement data 158 is used by the machine learning model 216 to form the features 228 of the synthetic non-medical image 280.

[0090] In block 612 of method 600, referring to Figure 7, the machine learning model 216 generates synthetic image data 214 corresponding to the synthetic non-medical image 280. The synthetic non-medical image 280 is a unique computer-generated image produced based on learned correlations with text captions for an image library. The synthetic non-medical image 280 includes features 228 representing the measurement data 158. The synthetic image data 214 is first stored in the memory device 204 of the remote server 112.

[0091] As shown in Figure 7, the exemplary synthetic non-medical image 280 is generated at the “dune” prompt and includes a horizon 232 as a feature 228 corresponding to the measurement data 158. Feature 228 does not correspond to the exemplary measurement data 158 in Figure 2, but instead corresponds to a different measurement data 158. The synthetic non-medical image 280 is not an existing image segmented, adjusted, or otherwise modified by the processor 208. Instead, the synthetic non-medical image 280 is a new image that corresponds to the subject of the prompt and has a feature 228 representing the measurement data 158.

[0092] Feature 228 of the synthesized non-medical image 280 shows the trend of the measurement data 158. For example, feature 228 shows a downward trend from point A to point B, indicating a decrease in blood glucose concentration. Another downward trend is shown from point C to point D. From point B to point C, feature 228 shows an upward trend, indicating an increase in blood glucose concentration. Another increasing trend is shown from point D to point E.

[0093] In block 616 of method 600, the composite image data 214 is transmitted from the remote server 112 to the computing device 108 and stored in the memory device 160. Transceivers 164, 200 and the internet 148 are used to transmit the composite image data 214. This process is also referred to as downloading the composite image data 214 using the computing device 108.

[0094] Next, in block 620, the processor 176 of the computing device 108 renders the composite image data 214 as a composite non-medical image 280 on the display screen 172. The corresponding overlay data 206 can be rendered and displayed as overlay graphics as described in relation to Figure 1.

[0095] For example, the processor 176 can render a critical condition graphic 274 overlaid on a synthetic non-medical image 280. To determine when the critical condition graphic 274 should be rendered, the processor 176 of the computing device 108 compares the measured values ​​of the measurement data 158 to a range of predetermined conditional values ​​to determine whether the measurement data 158 indicates a potential health problem for the user. For example, an embodiment of a medical monitoring system 100 configured to monitor glucose concentration can compare the measured glucose concentration of the measurement data 158 to a range of values ​​that includes a predetermined minimum safe glucose concentration value and a predetermined maximum safe glucose concentration value. If at least one of the measured values ​​of the measurement data 158 is not within the predetermined range, the processor 176 is configured to render a predetermined critical condition graphic 274 on the synthetic non-medical image 214 of the display screen 172 to notify the user of a potential health problem. The predetermined critical condition graphic 274 is configurable and / or selectable by the user so that the user can understand the meaning of the graphic 274 and why the graphic 274 is being shown.

[0096] As shown in the flowchart of Figure 6, the method 600 returns to block 604 after displaying the synthetic non-medical image 280, so that the computing device 108 can acquire and / or receive additional measurement data 158 from the measurement device 104 that has not been previously provided to the machine learning model 216. In one embodiment, after receiving the additional measurement data 158, the computing device 108 sends the additional measurement data 158 to the remote server 112 for processing by the processor 208 and the machine learning model 216. The additional measurement data 156 is used to generate updated synthetic image data 214 of an updated synthetic non-medical image portion (not shown) that is appended to or otherwise combined with the already displayed synthetic non-medical image 280. The updated synthetic non-medical image portion includes updated features 228 representing the additional measurement data 158. When generating the updated synthetic non-medical image portion, the processor 208 configures the machine learning model 216 to blend and / or combine the updated synthetic non-medical image portion with the previously generated synthetic non-medical image 280 so that the features 228 flow continuously, seamlessly, and / or coincidentally through the image 280 and the updated synthetic non-medical image portion.

[0097] In one embodiment, Method 600 includes extending and / or identifying a portion of the horizon 232 of a composite image 280 corresponding to measurement data 158. For example, in block 612 of Method 600, a machine learning model 216 generates a composite non-medical image data 214 based on prompt data 210, but it does not necessarily correspond to measurement data 158. This is because, in at least some embodiments, the machine learning model 216 may not generate a suitable version of the composite image 280 that adequately corresponds to the measurement data 158 of the first image generation request. The composite image associated with the composite non-medical image data 214 is, for example, a theme image, showing a dune or a mountain. The horizon 232 of the theme image does not correspond to the measurement value of the measurement data 158, or does not adequately correspond to the measurement value of the measurement data 158.

[0098] Next, Method 600 includes iterating through a machine learning model 216 on the synthesized non-medical image data 214 and / or prompt data 210 until at least a portion of the horizon 232 of the theme image corresponds to or sufficiently corresponds to the measurement data 158. In one example, the machine learning model 216 iterates through the synthesized image data 214 based on the prompt data 210 to generate multiple versions of the theme image. The synthesized image data 214 of each theme image is processed by a processor 208 to determine whether any portion of the horizon 232 of the theme image corresponds to the measurement data 158. If there is no portion of the horizon 232 that corresponds to the measurement data 158, the theme image is discarded or iterated through the machine learning model 216 again. However, if the processor 208 determines that the theme image contains at least a portion of the horizon 232 that corresponds to the measurements of the measurement data 158, the iteration stops. The iteration is useful, for example, to avoid unnatural or unrealistic "steps" in the horizon 232 of the synthesized image 280 based on the measurements of the measurement data 158.

[0099] In response to the identification of the portion of the horizon 232 corresponding to the measurement data 158, that portion of the theme image composite data 214 is extracted as composite image data 214 and rendered on the display screen 172. For example, the machine learning model 214 may generate a theme image that includes a left portion and a right portion. Only the right portion of the theme image contains the feature 228 corresponding to the measurement data 158. In this case, the processor 208 discards the composite image data 214 of the left portion of the theme image and retains the composite image data 214 of the right portion of the theme image as a composite image 280 that is displayed / rendered on the display screen 172 in a representation of the measurement data 154.

[0100] The iterative process described above is repeated based on the next measurement value of the measurement data 158 generated by the measurement device 104. That is, when additional measurement data 158 is generated, the machine learning model 216 is used to iteratively generate image portions that "extend" the horizon 232 of the composite image 280 in a smooth and natural manner. The new iteratively generated image portions are then added to the previously generated composite image 280 to show the user a representation of the next measurement value on the display screen 172. The iterative process helps to avoid unnatural or unrealistic "steps" in the horizon 232 of the combined composite image 280.

[0101] As described above, the measuring device 104 is a continuous glucose monitor (CGM). However, in other embodiments, the measuring device 104 is provided as a spot glucose measuring device that generates measurement data 158 in response to analyzing the user's blood deposited on a disposable test strip (not shown), instead of monitoring interstitial fluid 144. Methods 300 and 600 operate similarly using a CGM and a spot glucose measuring device, also called a glucose meter or glucometer.

[0102] Furthermore, methods 300, 600 can be applied to other types of measurement data 158, including blood pressure data, cholesterol level data, coagulation data, heart rate, basal body temperature, and other types of health functions. In these other embodiments, the measuring device 104 includes one or more of the following: a blood pressure sensor for generating blood pressure measurement data, a cholesterol level sensor for generating cholesterol level measurement data, a blood coagulation sensor for generating coagulation measurement data, a heart rate sensor for generating heart rate data (i.e., pulse data), and a thermometer for generating basal body temperature data. After generating measurement data 158 from one or more of the sensors, methods 300, 600 proceed in the same manner to generate modified images 184 and / or composite images 280 associated with the corresponding measured health functions.

[0103] Medical monitoring systems 100 and methods 300, 600 are improvements in medical monitoring, disease management, and user privacy technology. As mentioned above, certain conditions, such as diabetes, require a person to monitor their blood glucose levels regularly and periodically. As a result, at some point, most people will be in a public place where they need to monitor their blood glucose levels. While CGMs prevent these people from having to prick their fingers, displaying measurement data 158 in medical images on a smartphone could lead to the disclosure of personal medical information that the user does not want to share. Medical monitoring systems 100 and methods 300, 600 enable users to monitor trends in blood glucose levels and even determine when potential health problems may arise without disclosing personal medical data in an obvious way. This is because the measurements of the measurement data 158 are "hidden" or encoded in non-medical modified images 184 and synthetic non-medical images 280. An inexperienced person, even by directly looking at images 184, 280, would not suspect that the person is managing a medical condition. As a result, when in public, a person does not need to make excuses or hide their display screen 172 when checking their blood glucose levels. The generation, rendering, and display of images 184, 280 represent an improvement in medical monitoring, patient management, and user privacy technologies.

[0104] While this disclosure has been illustrated and described in detail in the drawings and the foregoing description, these should be considered illustrative and not limited to text. Only preferred embodiments are presented, and it is understood that all changes, modifications, and further uses within the scope of the spirit of this disclosure are to be protected.

Claims

1. A method for operating a medical monitoring system, To provide stored program instructions for a software application, wherein the software application is configured to be stored in the non-temporary memory of a computing device, and when executed by the processor of the computing device, the software application is provided. Obtain measurement data, The non-temporary memory is used to store image data of non-medical images. Based on the measurement data, the image data is modified to generate corrected image data. The modified image data is rendered as a modified image on the display screen of the computing device. To be set up, to provide, including A method for modifying the image data, comprising altering the features of the non-medical image to represent the measurement data.

2. The aforementioned feature is the horizon, The measurement data includes the measured value and the corresponding time value, The method according to claim 1, wherein modifying the aforementioned features includes changing the horizon so that the measured values ​​are represented in a time series according to the time value.

3. The aforementioned measurement includes previous and subsequent measurements. Changing the aforementioned features means In response to the fact that the subsequent measurement is larger than the previous measurement, the horizon is changed so that the display of the portion of the image located above the horizon becomes smaller, and The method according to claim 2, further comprising changing the horizon to increase the display of the portion of the image located above the horizon in accordance with the fact that the subsequent measurement is smaller than the previous measurement.

4. The aforementioned non-medical image shows a mountain range. The horizon includes at least one peak of the mountain range and / or at least one valley of the mountain range, The method according to claim 2, further comprising modifying the features of the non-medical image by resizing and / or rearranging the at least one peak and / or the at least one valley to represent the measured value.

5. The aforementioned non-medical image is a selected non-medical image from among multiple non-medical images, and the software application is The image data of the plurality of non-medical images is stored in the non-temporary memory, and each non-medical image has a corresponding feature, A feature mathematical function is determined for each feature of the plurality of non-medical images, and the feature mathematical function determines a feature curve defined by the corresponding feature. Determine the data mathematical function corresponding to the data curve defined by the measured values ​​of the aforementioned measurement data. The method according to claim 1, further configured to identify the selected non-medical image as the non-medical image among the plurality of non-medical images having a feature curve that best fits the data curve, by comparing the value of the data mathematical function with the value of the image mathematical function.

6. The aforementioned non-medical image is a selected non-medical image from among multiple non-medical images, and the software application is The method according to claim 1, further configured to receive user-derived input data from an input device of the computing device, wherein the input data identifies the selected non-medical image.

7. The aforementioned software application is The computing device is further configured to receive user-derived input data from its input device, wherein the input data corresponds to a selected theme from among a plurality of themes stored in the non-temporary memory as theme data. The aforementioned non-medical image is a selected non-medical image from among multiple non-medical images. Each non-medical image is assigned a theme from among the multiple themes mentioned above. The method according to claim 1, wherein the theme of the selected non-medical image matches the selected image theme.

8. The aforementioned software application is Obtain overlay data corresponding to the time, weather information, and / or critical condition information. The method according to claim 1, further configured to render the overlay data as a time graphic, weather information graphic, and / or critical condition graphic overlaid on the modified image as shown on the display screen.

9. The aforementioned software application is The method according to claim 1, further configured to generate the modified image data using a machine learning model that operates on the processor of a remote server communicating with the computing device and / or on the processor of the computing device.

10. The measurement data includes the measured value and the corresponding time value, Modifying the aforementioned image data is The non-medical image is segmented into multiple segments, wherein each segment includes a part of the aforementioned features. Generating multiple modified segments by modifying some of the features of each segment so as to represent at least one measurement, and The method according to claim 1, further comprising arranging the corrected segments in a time series based on the corresponding time values ​​in order to form the corrected image.

11. The aforementioned software application is Obtain additional measurement data, An updated modified segment is generated having some of the features corresponding to the measured values ​​of the additional measurement data. The updated corrected segment is added to the corrected image. The method according to claim 10, further configured to delete image data corresponding to the oldest modified segment from the modified image.

12. The aforementioned software application is The method according to claim 1, further configured to render the measurement data on the display screen.

13. A medical monitoring system, A measuring device including a sensor configured to generate measurement data, A remote server configured to (i) receive the measurement data, (ii) store non-medical image data in non-temporary memory, (iii) modify the image data based on the measurement data, and generate modified image data using the remote server's processor, and A computing device configured to communicate with the remote server and receive the modified image data, comprising a processor configured to render the modified image data as a modified image on the display screen of the computing device, A medical monitoring system in which modifying the image data includes changing the features of the non-medical image to represent the measurement data.

14. The aforementioned measuring device is a body-worn continuous blood glucose monitor, The sensor is configured to detect glucose in interstitial fluid. The aforementioned measurement data represents blood glucose concentration over time, as described in claim 13, for the medical monitoring system.

15. The medical monitoring system according to claim 13, wherein the computing device is one of a smartphone, a smartwatch, a laptop computer, and a desktop computer.

16. A method for operating a medical monitoring system, Receiving measurement data using a remote server, Using the remote server, generate composite image data of a composite non-medical image based on the measurement data, wherein the composite non-medical image includes features that represent the measurement data, and This includes transmitting the synthesized image data to the computing device for rendering it as the synthesized non-medical image on the display screen of the computing device, The aforementioned synthetic non-medical images are generated by a machine learning model running on the remote server. A method wherein at least one trend in the measurement data is indicated by the features of the synthesized non-medical image.

17. The method according to claim 16, wherein the aforementioned feature is a horizon representing the measurement data.

18. The remote server receives additional measurement data. To generate updated composite image data of the updated composite non-medical image portion, wherein the updated composite image data has updated features representing the additional measurement data, and The method according to claim 16, further comprising processing the updated composite image data and the composite image data on the processor of the remote server or the computing device so that the updated composite non-medical image portion is added to the composite non-medical image.

19. Using the computing device or the processor of the remote server, detect that the measurement data includes at least one measurement value outside a predetermined range, and The method according to claim 16, further comprising using the processor of the computing device to generate overlay data corresponding to the critical state graphic based on the at least one measurement for rendering as a critical state graphic overlaid on the synthetic non-medical display screen.

20. To generate the measurement data using a body-worn continuous blood glucose monitor, and The further includes using the computing device to transmit the measurement data from the wearable continuous blood glucose monitor to the remote server, The method according to claim 16, wherein the measurement data represents the blood glucose concentration over time.

Images