Patent Grant
10679750
The subject matter disclosed herein relates to computing systems, specifically, computer systems for generating predictive medical feedback.
Mobile computing devices may include applications to track a user's diet and related activities. Some applications allow a user to share information such as meal plans or nutritional information with other users. Some users carry mobile computing devices frequently which may enable them to conveniently input data regarding what they have eaten.
In one embodiment, a system is disclosed that includes one or more processors, and one or more memories storing code that is executable by the one or more processors to: access a data log corresponding to a diet of a user over a predetermined period; determine a diet context for the user based at least in part on the data log; analyze the data log to determine a variance in the diet context; determine a potential medical issue in response to the variance; and generate predictive feedback for the user in response to the potential medical issue.
In one embodiment, a method is disclosed that includes accessing, by processor, a data log corresponding to a diet of a user over a predetermined period; determining, by processor, a diet context for the user based at least in part on the data log; analyzing, by processor, the data log to determine a variance in the diet context; determining, by processor, a potential medical issue in response to the variance; and generating, by processor, predictive feedback for the user in response to the potential medical issue.
In one embodiment, a non-transitory computer-readable storage medium having instructions stored thereon is disclosed, that in response to execution, cause a system including one or more processors to: access a data log corresponding to a diet of a user over a predetermined period; determine a diet context for the user based at least in part on the data log; analyze the data log to determine a variance from the diet context; determine a potential medical issue in response to the variance; and generate predictive feedback for the user in response to the potential medical issue.
In order that the advantages of the embodiments of the invention will be readily understood, a more particular description of the embodiments briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings. Understanding that these drawings depict only some embodiments, and are not therefore to be considered to be limiting of scope, the embodiments will be described and explained with additional specificity and detail through the use of the accompanying drawings, in which:
Reference throughout this specification to “one embodiment,” “an embodiment,” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in one embodiment,” “in an embodiment,” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment, but mean “one or more but not all embodiments” unless expressly predetermined otherwise. The terms “including,” “comprising,” “having,” and variations thereof mean “including but not limited to” unless expressly predetermined otherwise. An enumerated listing of items does not imply that any or all of the items are mutually exclusive and/or mutually inclusive, unless expressly predetermined otherwise. The terms “a,” “an,” and “the” also refer to “one or more” unless expressly predetermined otherwise.
Furthermore, the described features, advantages, and characteristics of the embodiments may be combined in any suitable manner. One skilled in the relevant art will recognize that the embodiments may be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in particular embodiments that may not be present in all embodiments.
The present invention may be a system, a method, and/or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.
The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk drive (“HDD”), a solid-state disk drive (“SDD”), a random access memory (“RAM”), a read-only memory (“ROM”), an erasable programmable read-only memory (“EPROM” or Flash memory), a static random access memory (“SRAM”), a portable compact disc read-only memory (“CD-ROM”), a digital versatile disk (“DVD”), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.
Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts predetermined in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act predetermined in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts predetermined in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the predetermined logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the predetermined functions or acts or carry out combinations of special purpose hardware and computer instructions. Blocks or elements, labelled using singular descriptions may include multiple of the blocks of objects in some embodiments. Similarly, blocks, elements, and/or objects labelled using plural form descriptions do not necessarily include a plurality of blocks, elements, and/or objects in some embodiments. Descriptions of Figures may refer to elements described in previous Figures, like numbers referring to like elements.
As used herein, the smart phone 110a, 110b may refer to a mobile phone that transmits and/or receives textual data. The wearable computing device 110c may be a smart watch, a fitness tracker, or any computing device that is attachable to, or wearable by, a user, and that is capable of accessing and/or displaying data regarding a user's diet. The mobile computing device 110d may be a laptop, a notebook, or tablet devices that do not have a physical keyboard. In some embodiments, the system 100 includes a data storage 125, e.g. cloud storage that is accessible via any other device on a network 135.
In some embodiments, the system 100 may include computing devices 110 having one or more applications that enable a user to capture and/or record data related to the user's diet. The data may form a portion of a user's diet context 105. The term diet, as used herein, may refer primarily to the items a person consumes and may include other information such as the type, quantity, and nutritional components of the items consumed. The term diet context 105, as used herein, may refer to data related to a person's diet that can be used to characterize the situation of a person, place, or object that is considered relevant to the interaction between a user and applications for computing devices that relate to the user's diet. In addition to data about the user's diet, the diet context 105 may include data about the user and the applications themselves. For example, the location or name of the user, demographic data about the user, account data about a user, the status of an application, or a relationship between two applications, and so forth. Examples of the types of data that may be included in a diet context 105 are depicted below with respect to
In an embodiment, the system 100 may include computing devices 110 that may include and/or communicate with a diet medical analyzer 115 for determining potential medical issues 280. The operation of the diet medical analyzer 115 for determining potential medical issues is described below in more detail with respect to
In one embodiment, each of the computing devices 110, e.g. 110a, 110b, 110c, 110d, and 110e, is depicted as including both at least a portion of a user's diet context 105 and at least a portion of diet medical analyzer 115. It will be understood that the system 100 may be fully operative in configurations in which one or more of the computing devices 110 does not include a portion of diet medical analyzer 115. For example, in some embodiments, computing device 110 may use a browser application to connect via network 135 with a diet medical analyzer 115 hosted on another computing device 110 such as server 110e.
In some embodiments, the system 100 further includes a meal planner 120. The meal planner 120 may also be included in a mobile computing device 110, e.g. 110a, 110b, 110c, 110d. In other embodiments at least a portion of meal planner 120 may be a meal planner 120 that is cloud-based, e.g. hosted on one or more servers 110f. One example of a meal planner 120 that is cloud-based is called Chef Watson® by IBM®. Chef Watson® uses cognitive computing to analyze textual sources of recipes and other meal related data to automatically generate meal plans based on user input. The computing devices 110 may include application programming interfaces (APIs) that communicate with the meal planner 120.
In one embodiment, illustrated in
In some embodiments, the computing device 110 includes a display 205 that displays texts and other graphical data. In some embodiments, display 205 includes one or more I/O interfaces 230 in the form of a touchscreen that allows a user to input text, e.g. with a finger or fingers or with a stylus. In some embodiments, the I/O interfaces 230 may connect to an external device 235 such as a storage device, an input device, or any other external device.
The computing device 110 may include other I/O interfaces 230. For example, computing device 110 may include an I/O interface such as a global positioning system (GPS) or any other location sensor that enables computing device 110 to determine its current location. In other embodiments, computing device 110 include a near field communication (NFC) as one of the I/O interfaces 230, that enables computing device 110 to communicate with another electronic device in close proximity. Other types of I/O interfaces 230 that enable the computing device 110 to communicate with external devices 235 may include Bluetooth® transceivers, wired microphone and headphone jacks, digital data transfer interfaces, and so forth. The system 200 may further include network adapter 215. The network adapter 215 may enable the computing device 110 to communicate with other computing devices 110, e.g. via network 135 which may be a wireless network in some embodiments.
The system 200 of
The diet medical analyzer 115 further includes a data collector 265 which collects medical issue data from a variety of sources, for example, medical journals, news articles, websites, magazine articles, and so forth, to determine one or more potential medical issues 280 in response to the variance from the user's diet context 105. The diet medical analyzer 115 may include a parser 270 that parses the data collected by the data collector 265 to find words in the description of medical issues that relate to diet. The diet medical analyzer 115 may include an issue finder 275 that finds potential medical issues 280, for example, by comparing diet-related elements of the collected medical issue data with data from the diet context 105 of the user.
The diet medical analyzer 115 further includes a predictive feedback generator 285 that generates predictive feedback for the user in response to the potential medical issue 280. For example, in some cases, the text pertaining to the potential medical issues 280 may also include text relating to a diagnostic test 380 that may be able to detect a potential medical issue 280 prior to a user or physician being aware of the potential medical issue 280.
In some embodiments, the diet medical analyzer 115 may be included in code 225 stored on a memory 220 to be executed by a single processor in a single computing device 110. In some embodiments, computing device 110 is a mobile computing device such as smart phone 110a, 110b, wearable computing device 110c, or mobile laptop/notebook computer 110d. In other embodiments, a first portion of code 225 may be executed by a first processor 210 in a first computing device 110, e.g. smart phone 110a, and a second portion of code 225 may be executed on a second processor 210 in a second computing device 110, e.g. server 110e.
In some embodiments, the system 200 may operate primarily on a mobile computing device, e.g. 110a, 110b, 110c, and 110d. In other embodiments, the system 200 operates primarily on a computing device such as server 110e. The server 110e accesses the diet context 105 on the server 110e itself. For example, a user of a mobile device, e.g. 110a, 110b, 110c, and 110d may log into a website with a browser, or may open an “app” i.e. application, to enter diet context 105 including data log 245. In some embodiments, code 225 may include a graphical user interface 240 for user interaction with the system 200, e.g. for inputting and/or interacting with user data (e.g. data log 245, user profile 250, and/or displaying results (e.g. potential medical issues 280). In some embodiments code 225 includes a profile manager 255 for creating, modifying, deleting, and otherwise managing a user profile 250. In other embodiments, the diet context 105 including data log 245 and user profile 250 may be stored in memory 220 on a mobile computing device, e.g. 110a, 110b, 110c, and 110d. For example, the data log 245 may be included in a meal planning application, a calorie tracking application, a fitness application, or the like.
In still other embodiments, a first processor 210 within a mobile computing device e.g. 110a, 110b, 110c, and 110d captures at least a portion of the data log 245. A second processor 210, for example on a server 110e executes at least a portion of the code to determine the potential medical issue 280 in response to the variance. In some embodiments, a computing device 110, such as server 110e has significantly greater data collection and analysis resources than typical mobile computing devices 110a-110d. Powerful servers are often used in cognitive computing systems. As used herein, cognitive computing systems may refer generally to computing systems for interacting with humans naturally including analyzing unstructured and complex data, to generate hypotheses, reasoned arguments, and recommendations. IBM Watson® is one example of a powerful cognitive computing device that acts as a server to various applications that require data collection and analysis of large quantities of unstructured data, including textual data. Thus, in some preferred embodiments, diet medical analyzer 115 may be executed on a server 110e that has significant data gathering and processing resources.
As depicted in
Referring in more detail to
In some embodiments, the data log 245 includes a wellness indicator 310. In other embodiments, the system 200 may operate effectively without the need for wellness indicator 310. As used herein, wellness generally may refer to a user's subjective perceptions or feelings that may be related to his or her diet. In some embodiments, the wellness indicator 310 may include data objects such as the time assessed 312, meaning the time at which the user assessed his or her wellness. The wellness indicator with 310 may also include an appetite 314 data object where the user records, for example, feeling full, or hungry. The wellness indicator may also include a mood indicator 316 or a stress level 318 or any other wellness indicator 319. In other embodiments, the wellness indicator 310 may be an objective measurement such as blood pressure, body temperature, redness, and so forth.
These wellness indicators may not be recognized as symptoms by a user, or by a physician. However, they may be useful in providing additional context for the dietary records related to items consumed 300. Similarly, the location of consumption 306 of the items consumed 300 may be recorded generally automatically, for example by recording a GPS location at the time the data log 245 was updated with items consumed 300. In some embodiments, the location of consumption 306 may be a relevant part of the diet context 105 if the variance is determined in the data log 245.
For example, a user may have eaten at a particular location of consumption 306 without perceiving any impact on his or her diet context 105, e.g. his or her eating patterns. Later in response to the determined variance in the user's diet context 105, the issue finder 275 may access the data object named location of consumption 306 and find data sources indicating that items, like the items consumed 300 at a particular location of consumption 306 may present potential medical issues 280. Additional examples are provided below.
In some embodiments, the diet context 105 also includes a user profile 250. User profile 250 may include user demographics 320 such as age 322, domicile 323, gender 325, race 326, culture 327, relatives 328, and/or other demographics 329. The user demographics 320 may be readily available from data already stored digitally, for example in a user account, or accessible by a data collector 265 that collects demographic data for a particular user from online sources, such as the user's social media accounts or genealogical databases for which the user has granted the system 200 access.
In some embodiments, the diet context 105 includes a user profile 250 that includes eating preferences 330 for a user. Eating preferences 330 for a user may include, for example a preferred cuisine 332, such as Chinese food, Italian food, or Cajun food. Eating preferences 330 may also include preferences regarding eating schedule 334. For example, a user may prefer to skip breakfast or a user may prefer to eat meals that take less than 20 minutes to prepare. In some embodiments, the eating preferences 330 may include other preferences 336. Thus, the diet context 105 which may include a data log 245 and a user profile 250 is a source of relevant data that may be used to analyze a particular user's diet and variances in a user's diet context 105.
Referring again to
Some variance in diet context 105 may be imperceptible to a user acting without the system 200, or the user may be unaware of the degree of variance. The variance analyzer 260 may include a predetermined threshold to determine whether a meaningful variance exists. In some embodiments, predetermined threshold may be predetermined by the user. In other embodiments the system may import a predetermined threshold from a user or from published data. In some embodiments, the predetermined threshold may be a composite threshold formed by a mathematical expression of a plurality of variables.
The variance analyzer 260 determines the variance in the diet context 105, e.g. a decrease in the quantity 302 of dairy items or spicy items consumed 300. Although a user may be unaware of any potential medical issues associated with the variance in diet from his or her typical diet context 105, the variance may in fact be useful in determining potential medical issues 280. Some examples of potential medical issues 280 are illustrated in
In some embodiments, the variance analyzer 260 determines different types of variances in the diet context 105 of a particular user. In some embodiments, the term variance may refer to a statistical variance expression such as Z=(X−Average)/(Standard Deviation) where Z is the standardized normal variate and X is the diet variable (e.g. quantity 302 in a predetermined period). If Z=0, then the measurement X (of calories, grams of protein, carbohydrates, etc.) is equal to the average. If Z=+1, then the measurement X is one standard deviation above the average. If Z=+2, then the measurement X is two standard deviations above the average. If Z=−1, then the measurement X is one standard deviation below the average. If Z=−2, then the measurement X is two standard deviations below the average, and so forth. If X represents something critical, such as carbohydrate intake by a user with diabetes, then a Z value of +1 or −1 could trigger social media alerts to the user and friends. If the value of Z of +2 or −2 could trigger alarms to medical personnel.
In some embodiments, the thresholds Zmax and Zmin need not be equal in value, as they were (for simplicity) in the above paragraph. The thresholds may vary for different portions of one's diet. For example, the variance analyzer may use a Z thresholds of +0.5 or −0.5 instead of +1 and −1 (for Zmax and Zmin) when tighter tolerances are needed on critical items. Thus Z (as defined above) is a very simple way of representing a normalized variance.
For example, the quantity 302 of items consumed 300 may be X and a running average is subtracted from X, which is then divided by the Standard Deviation (assuming a Gaussian Distribution on the variance). When Z exceeds a threshold (either too high or too low), that could trigger step 535. For example, if a user's intake of carbohydrates in a portion of the data log 245 is significantly higher or lower than a reference level (e.g. a prior level or a level of another person or group of persons) the method 500 may generate 550 predictive feedback regarding potential medical issues 280.
Variance may also be used in the broader sense to refer to a change or a difference. The variance from the diet context 105 may be a variance in the user's diet between a first portion of the predetermined period and a second portion of the predetermined period. In other words, a change in diet over time. In other embodiments, a variance may be between the user's diet and a third party's diet. For example, if a user's profile includes information about a third-party's diet (e.g., relative 328, a family member, or someone living in the same household) that includes items consumed 300 in the same location of consumption 306 as the user and the type of items consumed 300 by the user varies from the type of items consumed by the third party.
Determining this variance may be useful in determining potential medical issues 280 because the sources of the potential medical issues 280 may refer to items consumed 300 without referring to variance in diet, or may refer to deficiencies or excesses in a type of food item or nutrient. In some embodiments, the third-party may be a user of the system, e.g. the systems 100, 200. In other embodiments, the user may enter data relating to the third-party's diet into the systems 100, 200 for comparison against the user's own diet. Likewise, other diet context 105 data objects for the third-party may be entered into the systems 100, 200, either by the third-party or by the user.
A third type of variance from a diet context 105 of a user may include a variance between the user's diet and published diet standards for a demographic group to which the user belongs. For example, a user may have a particular age 322, and a particular body size 324. The body size 324 may include, for example, weight, height, and/or other measurements such as waistline size. The variance analyzer 260 may compare the data log 245 of the user with published dietary standards or ranges for people of a particular demographic group, e.g. a particular age range, a particular weight range, particular height range, and so forth. Thus, the variance analyzer 260 may determine a variance in the diet context of a user over time, a variance between a user's diet and a third party's diet, and/or a variance between the user's diet and published diet ranges for a demographic group to which the user belongs.
In some embodiments, the issue finder 275 searches for text in the description 350 data objects of the potential medical issues 280 that relate to variances in diet. For example, the phrases “loss of appetite”, “craving”, “lack of” or “due to an excess” of a particular nutrient, within text related to a potential medical issue may indicate that the issue is related to a variance in a user's diet context.
In some embodiments, the issue finder 275 searches for text in the potential medical issues 280 that relate to an issue type 360. The issue type 360 may include eating disorders 362, food intolerances 364, food allergies 366, diseases 367, mental illnesses 368, and/or other issue types 369, e.g. seasonal affective disorder, depression, job-related stress, post-traumatic stress disorder, etc. The issue type 360 may be useful to compare with the wellness indicators 310 and the diet context 105. The issue type 360 may further be useful in finding diagnostic tests 380 which the system 200 may include in generating predictive feedback for the user. Thus, the user may be made aware of diagnostic tests 380 that may predictively detect or confirm a particular potential medical issue 280 before the user is aware and/or before it becomes a more serious issue.
In some embodiments, the issue finder 275 searches for text in the potential medical issues that relate to a contributory factor 370. Diet-related factors 372 may be contributory factors 370 of primary interest. Other contributory factors such as demographic factors 374 may be useful to determine the relevance of a particular potential medical issue 282 a change in the diet context 105 of a particular user.
In some embodiments, a data object such as a location 376 may be a contributory factor to a potential medical issue 280 that is diet-related. The issue finder 275 may find that a particular type of cuisine eaten in a particular area is associated with potential medical issues 280. For example, there may be a custom in some location 376 of preparing food in a way that may contribute to potential medical issues such as by under cooking meats.
Additionally, the issue finder 275 may search for data objects such as public health factors 377. For example, particular menu items from particular restaurants at a particular location may have resulted in illnesses due to pathogens and/or toxins which are not immediately detectable by the consumer of those menu items, but after some period of time some consumers begin to experience medical issues. In some embodiments, the issue finder 275 searches for other factors 378 that may correspond to a variance in diet (e.g. physical activity, metabolism, hormones, temperature, palatability, boredom social influences, and so forth).
In some embodiments, the data collector 265 gathers vast amount of data from hundreds of news sources of which the user may be unaware. By determining a variance in an eating pattern of a user (e.g., a diet context item such as location of consumption 306 which is unusual for the particular user), the predictive feedback generator 285 of the diet medical analyzer 115 may generate predictive feedback that alerts the user to a potential medical issue related to the location of consumption 306. The location of consumption 306 may be a location where the items consumed 300 were consumed.
Accordingly, the embodiments of the system 200 may improve the function of the computing devices 110 that implement code 225 by enabling them to detect and determine potential medical issues related to the variance in diet context of which a user may be completely unaware. Moreover, the system 200 does not necessarily rely on the results of a diagnostic medical test whereby a user who is ill seeks to retrospectively examine potential causes of the illness. Rather, the system 200 determines potential medical issues 280 based on variances in the diet context 105.
The method 400 includes determining 410 a diet context 105 for the user, based at least in part on the data log 245. The method 400 includes analyzing 415 the data log 245 to determine a variance from the diet context 105. In some embodiments, the analyzing 415 may be implemented by a diet medical analyzer 115 that includes a variance analyzer 260 as described above. The method 400 further includes determining 420 a potential medical issue 280 in response to the variance. In some embodiments, the determining 420 a potential medical issue 280 may be accomplished by a diet medical analyzer 115 that includes a data collector 265 that collects data about potential medical issues 280 and parses the data using parser 270.
The diet medical analyzer 115 may further include an issue finder 275 that analyzes the parsed data collected and compares textual data objects within the collected data with data objects in the diet context 105 of the user. The method 400 further includes 425 generating predictive feedback for the user in response to the potential medical issue 280. In some embodiments, the predictive feedback for the user may include one or more diagnostic tests 380 for further determining whether the potential medical issue 280 is relevant to the user.
As described above, one or more parts of method 400 may be implemented on a first processor of a system such as the system 200, while other parts of method 400 may be implemented in a separate part of the system 200 on a second processor. For example, in some embodiments, assessing the data log 245 and determining a diet context 105, may be done on a mobile computing device 110, such as smart phone 110a. The analyzing the data log 245 to determine a variance and determining the potential medical issue 280 in response the variance and generating predictive feedback for the user may be done by a second processor on a server 110e.
In some embodiments, the data log 245 further includes a wellness indicator 310 provided by the user for the predetermined period. The method 500 includes determining 525 a diet context 105 for the user. The time period included in the data log 245 may be as short as a matter of days or maybe as long as many years depending on the period predetermined by the user or by a third-party that implements the method 500.
The method 500 further includes analyzing the data log 245 to determine a variance in the diet context 105 of the user. The variance may be a variance in the user's own diet over time, a variance between the user's diet and a third-party's diet, or a variance between a user's diet and published diet standards for demographic group to which the user belongs. In some embodiments, the method 500 checks 535 whether the variance is greater than a predetermined threshold. If not, then the method 500 ends. If yes, then the method 500 further determines 540 potential medical issues 280 related to the variance in the diet context 105 of the user. In some embodiments, the method 500 further generates 545 a relevance score. The relevance score may be used by method 500 to sort the potential medical issues 280 so that the more relevant potential medical issues 280 are presented first, or otherwise highlighted to the user.
The method 500 may further include generating 550 predictive feedback for the user in response to potential medical issues 280 determined in response to the variance in the user's diet context 105. In some embodiments, the predictive feedback may include one or more diagnostic tests 380 to further assess whether the user is likely to develop the potential medical issue 280. In some embodiments, the generating predictive feedback 550 may further includes generating predictive feedback message about potential medical issues 280 caused by the variation for communicating to persons whom the user has authorized to receive such messages. In some embodiments the predictive feedback may be tweeted, snapped, or otherwise broadcast on social media for immediate attention, to the user, and/or authorized doctors, nurses, friends, etc. This may allow an EpiPen® to be used in time to save someone's life.
In some embodiments, the method 500 checks 555 to see whether a meal plan for counteracting the variance is desired. For example, if the variance analyzer determines that a user's diet has significantly increased in consumption of carbohydrates, the method 500 may generate a diet modification for counteracting the variance, for example by planning meals that moderate consumption of items with a high-glycemic index or high glycemic load and that increase protein consumption to reduce inter-meal hunger. In addition to determining potential medical issues 280 and generating a diet modification for counteracting the variance, the method 500 may access 565 one or more eating preferences of the user.
For example, the user's preferred type of cuisine 332, the user's preferred schedule for eating and/or preparing meals, the number of persons for which the meal is to be planned, and so forth. Thus, the meal planner 120 may prepare a meal that addresses both the desired diet modification and the user's eating preferences. For example, a user may prefer to eat fruits and desire a diet modification that decreases glycemic load. Accordingly, the meal planner 120 may plan meals that includes more low glycemic load fruits such as strawberries, apricots, and/or grapefruit and that include fewer high glycemic load fruits such as bananas and grapes.
The method 500 may then transfer 570 diet data including, the data log 245, the eating preferences, and/or diet modification, to a meal planner 120 that automatically generates a meal plan taking into account the diet data. In any of the embodiments of the systems 100, 200, and/or methods 400, 500, the data that is transferred may be de-identified i.e. anonymized, before transferring so that a user's privacy is safeguarded.
The method 500 may then communicate 575 the automatically generated meal plan to the user. In some embodiments, the method 500 may query 580 whether the user wants to re-assess for potential medical issues after implementing the diet modification for a predetermined period of time. If yes, the method 500 repeats at least some of the steps, e.g. 520, 525, 530, 535, 540, 545, 550, 555, 560, 565, 570, 575, and/or 580 of the method 500. If not, the method 500 ends.
In some embodiments, the method 400 depicted in
In some embodiments, the method 400 and/or the method 500 are implemented by a non-transitory computer readable storage medium having instructions stored, that when executed cars the system to access the data log 245 corresponding to a diet of a user over predetermined period of time. The instructions may further cause the system to determine a diet context 105 for the user based at least in part on the data log 245. Instructions may further cause the one or more processors 210 to analyze the data log 245 to determine a variance from the diet context 105.
The instructions may further cause the one or more processors 210 to determine a potential medical issue 280 in response to the variance. Instructions may further cause the one or more processors 210 to generate predictive feedback for the user in response the potential medical issue 280. It will be noted that instructions may cause the system comprising one or more processors 210 to access the data log 245 determine the diet context, analyze the data log 245 to determine a variance, determine the potential medical issue 280 in response to the variance, and generate predictive feedback, and may be in accordance the methods and systems described above.
As previously described, the diet context 105 may include data objects such as shown in
Thus, the systems 100, 200 improves the function of a computing device 110 by enabling it to detect potential medical issues based on variances in the user's diet context in ways that the user may be unable to perceive or analyze without the assistance of the system. The systems 100, 200 may further generate predictive feedback that may enable the user to obtain a diagnostic test which may otherwise be overlooked in the absence of a cognitive analysis of the user's diet. In some embodiments, the systems 100, 200 may generate and communicate to the user, a meal plan for counteracting potential medical issues 280 related to variance in the user's diet context 105.
The embodiments may be practiced in other specific forms. The described embodiments are to be considered in all respects only as illustrative and not restrictive. The scope of the invention is, therefore, indicated by the appended claims rather than by the foregoing description. All changes which come within the meaning and range of equivalency of the claims are to be embraced within their scope.
| Number | Name | Date | Kind |
|---|---|---|---|
| 7970633 | Bulat | Jun 2011 | B2 |
| 8015145 | Liu et al. | Sep 2011 | B2 |
| 8690578 | Nusbaum | Apr 2014 | B1 |
| 9011153 | Bennett et al. | Apr 2015 | B2 |
| 9148483 | Molettiere | Sep 2015 | B1 |
| 20040116785 | Bulat | Jun 2004 | A1 |
| 20060293572 | Bulat | Dec 2006 | A1 |
| 20070016451 | Tilson | Jan 2007 | A1 |
| 20100136508 | Zekhtser | Jun 2010 | A1 |
| 20110301505 | Chen Wang et al. | Dec 2011 | A1 |
| 20130307918 | Bulat | Nov 2013 | A1 |
| 20140255882 | Hadad et al. | Sep 2014 | A1 |
| 20140316220 | Sheldon | Oct 2014 | A1 |
| 20140380218 | Johnnie | Dec 2014 | A1 |
| 20150220624 | Bhatt et al. | Aug 2015 | A1 |
| 20150261928 | Refvik | Sep 2015 | A1 |
| 20150278622 | Fan et al. | Oct 2015 | A1 |
| 20150364057 | Catani et al. | Dec 2015 | A1 |
| 20160000323 | Myr | Jan 2016 | A1 |
| 20160071432 | Kurowski et al. | Mar 2016 | A1 |
| 20160225284 | Schoen et al. | Aug 2016 | A1 |
| 20170249445 | Devries | Aug 2017 | A1 |
| Number | Date | Country |
|---|---|---|
| 2014134375 | Sep 2014 | WO |
| 2014178077 | Nov 2014 | WO |
| Number | Date | Country | |
|---|---|---|---|
| 20180046770 A1 | Feb 2018 | US |
