Methods and systems for predicting changes in physiological parameters of a patient

Abstract

The present disclosure relates to methods and systems for predicting changes in a target physiological parameter of a target patient expected to result from a medication to be administered to the target patient. The methods and systems may comprise deriving one or more parameter-estimation functions based on historical data, wherein each parameter-estimation function models how a separate parameter of a prediction function varies in accordance with one or more starting physiological parameters. The methods and systems may further comprise receiving user input indicative of a value for one or more starting physiological parameters for the target patient, calculating a value for each parameter of the prediction function by applying the derived parameter-estimation functions to the one or more indicated values, and predicting changes in the target physiological parameter using the prediction function and the calculated parameter values. The predicted changes may then be displayed on a user-interface.

Description

METHODS AND SYSTEMS FOR PREDICTING CHANGES IN PHYSIOLOGICAL PARAMETERS OF A PATIENT FIELD OF THE INVENTION

[0001] The present disclosure relates to methods and systems for predicting changes in one or more physiological parameters of a patient. More specifically, the present disclosure relates to methods and systems for predicting changes in one or more target physiological parameters of a patient expected to result from a course of medication to be administered to the patient. BACKGROUND OF THE INVENTION

[0002] Patients are generally administered medications in order to effect changes in one or more target physiological parameters of the patient. This is especially the case for patients suffering from chronic conditions that require long-term treatment. As a result, when a patient is administered a medication or a course of medication, patients and their caregivers (e.g. healthcare providers or HCPs) generally expect to see some measurable change in the one or more target physiological parameters of the patient. The changes in the physiological parameter(s) of the patient may be considered an outcome or a result of the administered medication or course of medication. However, the outcomes resulting from a medication or course of medication may differ from patient to patient. SUMMARY OF THE INVENTION

[0003] In one aspect, the present disclosure is directed at a method for predicting changes in a target physiological parameter of a target patient expected to result from a medication to be administered to the target patient. The method may comprise: accessing, at one or more computing devices, historical data indicative of changes observed over an observation period in the target physiological parameter of a plurality of patients resulting from administration of the medication; deriving, at the one or more computing devices, one or more parameter- estimation functions based on the historical data, wherein each parameter-estimation function models how a separate parameter of a prediction function for predicting changes in the target physiological parameter over time varies in accordance with one or more starting physiological parameters observed in the plurality of patients; receiving, at the one or morecomputing devices, user input indicative of a value for each of the one or more starting physiological parameters for the target patient; calculating, by the one or more computing devices, a value for each parameter of the prediction function by applying the one or more derived parameter-estimation functions to the one or more values indicated by the received user input; predicting, by the one or more computing devices, changes in the target physiological parameter of the target patient at a plurality of future time points using the prediction function and the calculated parameter values; and displaying, on a user interface of at least one of the computing devices, the predicted changes in the target physiological parameter of the target patient to assist at least one of the target patient and a medical professional in determining whether the medication should be administered to the target patient.

[0004] In some embodiments, the medication is an anti-obesity medication and the target physiological parameter is the patient’s body weight.

[0005] In some embodiments, the medication is an anti-diabetes medication and the target physiological parameter is the patient’s A1C level.

[0006] In some embodiment, the one or more starting physiological parameters comprise at least one of age, A1C level, height, weight, resting heart rate, and biological sex.

[0007] In some embodiments, the prediction function is a probability distribution function.

[0008] In some embodiments, predicting changes in the target physiological parameter of the target patient comprises predicting, for each time point of the plurality of future time points, an expected change in the target physiological parameter and a prediction interval for the expected change.

[0009] In some embodiments, at least one of the parameter-estimation functions models how a parameter indicative of a measure of statistical variance varies in accordance with the one or more starting physiological parameters.

[0010] In some embodiments, the plurality of patients in the historical data were administered different dose levels of the medication, such that the historical data is indicative of how changes in the target physiological parameter varies with dose level. In such embodiments, at least one of the derived parameter-estimation functions may model how one of the parameters of the prediction function varies in accordance with dose level; the userinput received at the one or more computing devices may be further indicative of a target dose level for the medication to be administered to the target patient; the value for at least one parameter of the prediction function may be calculated, by the one or more computing devices, based at least in part on the target dose level; and the predicted changes in the target physiological parameter of the target patient displayed on the user interface may be calculated based at least in part on the target dose level to assist at least one of the target patient and the medical professional in determining whether the target dose level of the medication should be administered to the target patient.

[0011] In some embodiments, the method may further comprise receiving, at the one or more computing devices, further user input indicative of actual changes to the target physiological parameter observed in the target patient in response to a course of the medication previously administered to the target patient, wherein the calculated parameter values of the prediction function are calculated based at least in part on the further user input.

[0012] In some embodiments, the parameter-estimation functions are derived by the one or more computing devices and saved into a memory accessible by the one or more computing devices before the user input is received.

[0013] In some embodiments, the accessing and deriving steps are implemented at a first computing device, and the receiving, calculating, predicting, and displaying steps are implemented at a second computing device.

[0014] In some embodiments, the one or more parameter-estimation functions are derived from the historical data using linear regression.

[0015] In another aspect, the present disclosure is directed at a system for predicting changes in a target physiological parameter of a target patient expected to result from a medication to be administered to the target patient, the system comprising: a user interface; one or more memory systems storing computer-executable instructions; and one or more processors communicably coupled with the one or more memory systems and the user interface, and configured to execute the instructions to: access historical data indicative of changes observed over an observation period in the target physiological parameter of a plurality of patients resulting from administration of the medication; derive one or more parameter- estimation functions based on the historical data, wherein each parameter-estimation function models how a separate parameter of a prediction function for predicting changes in the targetphysiological parameter over time varies in accordance with one or more starting physiological parameters observed in the plurality of patients; receive user input indicative of a value for each of the one or more starting physiological parameters for the target patient; calculate a value for each parameter of the prediction function by applying the one or more derived parameter-estimation functions to the one or more values indicated by the received user input; predict changes in the target physiological parameter of the target patient at a plurality of future time points using the prediction function and the calculated parameter values; and display, on the user interface, the predicted changes in the target physiological parameter of the target patient to assist at least one of the target patient and a medical professional in determining whether the medication should be administered to the target patient.

[0016] In yet another aspect, the present disclosure is directed at non-transitory computer- readable media storing computer-executable instructions for predicting changes in a target physiological parameter of a target patient expected to result from a medication to be administered to the target patient that, when executed by one or more processors, are operable to cause the processors to: access, by the one or more processors, historical data indicative of changes observed over an observation period in the target physiological parameter of a plurality of patients resulting from administration of the medication; derive, at the one or more processors, one or more parameter-estimation functions based on the historical data, wherein each parameter-estimation function models how a separate parameter of a prediction function for predicting changes in the target physiological parameter over time varies in accordance with one or more starting physiological parameters observed in the plurality of patients; receive, at the one or more processors, user input indicative of a value for each of the one or more starting physiological parameters for the target patient; calculate, by the one or more processors, a value for each parameter of the prediction function by applying the one or more derived parameter-estimation functions to the one or more values indicated by the received user input; predict, by the one or more processors, changes in the target physiological parameter of the target patient at a plurality of future time points using the prediction function and the calculated parameter values; and display, on a user interface communicably coupled with at least one of the one or more processors, the predicted changes in the target physiological parameter of the target patient to assist at least one of the target patient and a medical professional in determining whether the medication should be administered to the target patient.BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Additional embodiments of the disclosure, as well as features and advantages thereof, will become more apparent by reference to the description herein taken in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale. Moreover, in the figures, like-referenced numerals designate corresponding parts throughout the different views.

[0018] FIG.1 is a conceptual block diagram depicting an exemplary computing device for implementing the presently disclosed methods.

[0019] FIG.2 is a conceptual block diagram depicting an alternate exemplary computing system for implementing the currently disclosed methods.

[0020] FIGS.3A and 3B is a flowchart depicting exemplary logic for predicting changes in a target physiological parameter of a patient expected to result from a course of medication administered or to be administered to the patient.

[0021] FIG.4 is an exemplary screen of a web interface on a mobile device for receiving user input from a user.

[0022] FIG.5A and 5B are exemplary screens of the web interface for presenting predicted changes in the body weight of a patient expected to result from a course of medication.

[0023] FIG.6 is another exemplary screen of the web interface for presenting predicted changes in an A1C level of the patient expected to result from the course of medication.

[0024] FIG.7 is another exemplary screen of the web interface configured for display on a laptop, desktop, and / or tablet, and for presenting predicted changes in the body weight of the patient expected to result from the medication.

[0025] FIG.8 is another exemplary screen of the web interface configured for display on the laptop or desktop, and for presenting predicted changes in the A1C level of the patient expected to result from the medication. DETAILED DESCRIPTION OF THE INVENTION

[0026] For the purposes of promoting an understanding of the principles of the present disclosure, reference will now be made to the embodiments illustrated in the drawings, andspecific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended.

[0027] The present disclosure relates to methods and systems for predicting changes in physiological parameters of a patient expected to result from a course of medication administered or to be administered to the patient. When patients take medication, they generally expect to see some measurable change in one or more physiological parameters of the patient. This is especially the case for patients taking medications over a relatively long period of time in order to treat a chronic condition. For instance, patients taking blood pressure medication in order to lower their blood pressure often expect to see reductions in their blood pressure. Patients taking anti-obesity medications often expect to see reductions in their body weight. And patients taking medication to treat diabetes often expect to see improvements in their Hemoglobin A1C (HbA1C or A1C) score over time. The changes in one or more target physiological parameter(s) that may be observed in a particular patient as a result of taking a medication may therefore be considered an outcome of the medication.

[0028] However, outcomes that result from taking medications may differ widely from patient to patient. Some patients may experience dramatic changes or improvements on their physiological changes, while other patients may experience only modest changes. The amount of time required for patients to see changes in their target physiological parameters may also differ: some patients may experience dramatic changes relatively quickly, while other patients may only see the same changes after taking the medication for a longer time. In order to decide whether or not to start or continue taking a medication, an individual patient and his / her caregivers (e.g., healthcare providers or HCPs) often desire to predict, with as much accuracy as possible, the outcomes that this individual patient may expect to see from this medication. In other words, the individual patient and his / her caregivers may desire to personalize predictions of outcomes to take into account starting physiological parameters of the specific individual patient, so as to improve the accuracy of such predictions.

[0029] Such outcomes may be an important factor to help the patient and his / her caregivers decide whether or not to take the medication. When such outcomes are predicted for multiple types of medications, these predicted outcomes may help a patient and his / her caregivers to compare and contrast the likely effects of different medications, and ultimately help the patient and his / her caregivers decide which medication to take. Such predicted outcomes may also be useful to help the patient and his / her caregivers form realistic expectations regardinghow much a medication may or may not improve the patient’s condition. Furthermore, accurate predicted outcomes may help a patient and his / her caregiver to determine whether there are certain unforeseen medical complications or causes that need to be taken into account. For instance, if a patient’s actual outcomes after taking the medication for some time do not match the patient’s initial predicted outcomes, this may prompt the patient and his / her caregivers to investigate further into the root causes for the patient’s condition or disease, and adjust the patient’s treatment plan as needed.

[0030] The inventors have appreciated that the outcomes that a patient may expect from a course of medication can often be predicted with greater accuracy if certain starting physiological parameters of the patient are taken into account. As used herein, starting physiological parameters of a patient comprise physiological parameters that are measured before the patient begins taking a target course of medication, wherein the effects of the target course of medication are being predicted. This is because outcomes that a patient may expect in the future from a course of medication often varies predictably with the patient’s starting physiological condition. The inventors have further appreciated that the way in which outcomes vary predictably with the patient’s starting physiological condition may be determined, or at least estimated, from analysis of historical data indicative of outcomes observed in a plurality of patients that had received the medication. Preferably, the plurality of patients in the historical data would exhibit a diverse array of physiological conditions, and present with different starting physiological parameters before being administered the medication. By applying standard regression techniques to this historical data, the way in which outcomes may be expected to vary with different starting physiological conditions of a patient can be estimated.

[0031] For example, a certain medication may be prescribed to help a patient lose weight. The amount of weight that a specific patient may expect to lose as a result of a target course of medication may vary based on the patient’s starting physiological parameters, such as the patient’s height, weight, resting heart rate, and the patient’s A1C level measured before beginning the target course of medication. Furthermore, the way in which the patient’s expected weight loss varies with the aforementioned starting physiological parameters may be estimated by analyzing historical data indicative of outcomes in a population of users that exhibited different starting height, weight, resting heart rates, and A1C levels. By taking these current physiological parameters into account, and by analyzing the historical data, theamount of weight that a specific patient may expect to lose as a result of taking this medication may be estimated with greater accuracy.

[0032] The term "logic," "control logic", “application,” or “computer-executable instructions” as used herein may include software and / or firmware executing on one or more programmable processors, application-specific integrated circuits (ASICs), field- programmable gate arrays (FPGAs), digital signal processors (DSPs), hardwired logic, or combinations thereof. Therefore, in accordance with the embodiments, various logic may be implemented in any appropriate fashion and would remain in accordance with the embodiments herein disclosed.

[0033] FIG.1 is a conceptual block diagram depicting an exemplary computing device 101 for implementing the presently disclosed methods. Computing device 101 illustratively includes a mobile device, such as a smartphone. Alternatively, any suitable computing device may be used, including but not limited to a laptop, desktop, tablet, or server computer, for example.

[0034] The computing device 101 includes at least one processor 102 that executes software and / or firmware stored in memory 104 of device 101. The software / firmware code contains instructions that, when executed by processor 102, causes computing device 101 to perform the functions described herein. The at least one processor 102 may be configured to execute control logic 106, which may be stored in memory 104 and may be operative to predict changes in one or more target physiological parameters of a patient, as discussed in detail herein. Memory 104 may be any suitable computer readable medium that is accessible by processor 102. Memory 104 may be a single storage device or multiple storage devices, may be located internally or externally to processor 102, and may include both volatile and non- volatile media. Exemplary memory 104 includes random-access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), flash memory, a magnetic storage device, optical disk storage, or any other suitable medium which is configured to store data and which is accessible by processor 102.

[0035] Computing device 101 includes a user interface 108 in communication with processor 102 and operative to provide user input data to the system and to receive and display data, information, and prompts generated by the system. User interface 108 includes at least one input device for receiving user input and providing the user input to the system. In theillustrated embodiment, user interface 108 is a graphical user interface (GUI) including a touchscreen display operative to display data and receive user inputs. The touchscreen display allows the user to interact with presented information, menus, buttons, and other data to receive information from the system and to provide user input into the system. Alternatively, a keyboard, keypad, microphone, mouse pointer, or other suitable user input device may be provided.

[0036] FIG.2 is a conceptual block diagram depicting an alternative exemplary computing system 200 for implementing the presently disclosed methods. System 200 may comprise a computing device 201. Similar to computing device 101, device 201 may also comprise a memory 204 (analogous to memory 104), a processor 202 (analogous to processor 102), and user interface 208 (analogous to user interface 108). In addition, computing device 201 may comprise a communications interface 212 configured to establish a communication link 230 with a corresponding communications interface 214 of another computing device 250. Computing device 250 may, but need not be, be remote from computing device 101, e.g., in another room, another building, another city, another country, or another continent. For example, computing device 250 may illustratively be a remote server, or one or more cloud servers configured to provide a virtual computing device or to provide virtual computing services. Communications link 230 may be a direct communications link established through a direct wired or wireless connection between computing device 101 and 250 (e.g., a Bluetooth, NFC, or WiFi connection). Alternatively, or in addition, all or part of communications link 230 may include one or more intermediate devices, and / or traverse a data network (not shown), such as a Local Area Network (LAN), cellular network, or the Internet. Similar to computing device 201 and 101, computing device 250 may comprise a processor 252 and a memory 254 (or, in the case of a cloud computing service, a virtual processor and a virtual memory). In the embodiments depicted in FIG.2, the control logic 206 (analogous to control logic 106) operative to predict changes in one or more target physiological parameters of a subject may be stored in memory 254 and be configured to be executed by processor 252. In the embodiments depicted in FIG.2, user input may be received via user interface 208 of computing device 201 and conveyed to computing device 250 via communications link 230. Computing device 250, in turn, may implement the logic discussed herein for predicting one or more target physiological parameters of the patient. Computing device 250 may store or further process the output (e.g., the target physiological parameters), and provide the output back to computing device 201, or forward the output toanother device (not shown). If the output is provided back to computing device 201, device 201 may display the output, or information derived from the output, to a user via user interface 208.

[0037] In one exemplary embodiment, the communications link 230 between computing device 201 and 250 may be a web link established over the World Wide Web. Computing device 201 may be configured to present a web page or web interface via a browser or similar interface to its user. User input from the user received via user interface 208 may be passed through said web page or web interface and transmitted to computing device 250 over said web link. In this embodiment, computing device 250 may be a remote server (or one or more cloud servers implementing a virtual server) configured to receive the user input, predict one or more physiological parameters of a patient, and provide the predicted parameters back to computing device 201 via web link 250. Computing device 201 may then present the predicted parameters, or information derived from the predicted parameters, to its user via the web page or web interface.

[0038] FIGS.3A and 3B present a flowchart depicting exemplary logic 300 for predicting changes in a target physiological parameter of a patient expected to result from a course of medication administered or to be administered to the patient. As discussed herein, logic 300 may be executed at processors 102, 202, and / or 252. Logic 300 may be executed at a single one of these processors operating independently, or in concert between two or more processors. When logic 300 is implemented in concert between two or more processors, the processors may cooperate such that different processors among the two or more processors perform different steps, or such that multiple processors may cooperate to perform one or more steps.

[0039] In some embodiments, the target physiological parameter may be a body weight of the patient. Alternatively or in addition, the target physiological parameter may be a Hemoglobin A1C (HbA1C or A1C) level of the patient. Alternatively or in addition, the target physiological parameter may be any measurable physiological parameter of the patient, such as (but not limited to) blood pressure, heart rate, muscle-to-fat ratio, Body Mass Index (BMI), a level of one or more biomarkers in the patient’s blood, tissue, or other bodily media, or a level of severity of one or more observed symptoms in a patient. The medication may be any pharmaceutical medication that is expected to effect a change in the one or more target physiological parameter. For example, the medication may be any of a class of medicationsthat, if administered to the patient, either once or repeatedly over a period of time, are expected to change the patient’s A1C level or the patient’s weight. Such medications may include an SGLT2, a GLP-1 agonist, a GIP / GLP1 agonist, a GIP / GLP1 / Glucagon agonist, a sulfonyluria, an insulin, an insulin-analog, and / or other medication approved by a regulatory agency for use in treating diabetes and / or chronic weight management. Such medications may include, for example, but not limited to, tirzepatide, semaglutide, retatrutide, metformin, insulin glargine, insulin lyspro, and the like. In an embodiment, such medication is tirzepatide.

[0040] Logic 300 may begin at step 302, in which one or more computing devices accesses historical data indicative of changes observed over an observation period in the target physiological parameter of a plurality of patients resulting from administration of the medication. The observation period should preferably be long enough such that changes in the target physiological parameter resulting from the medication may be observed, such as a number of weeks, months, or years. The historical data may comprise data derived from clinical trials in which the effect of the medication on the target physiological parameter was studied and observed in a large population of patients. The historical data may also comprise other types of data that quantitatively measures or indicates the effect of the medication on the target physiological parameter in a population of subjects that had been previously administered the medication. Such alternative types of data may comprise or be derived from real world data and / or observational studies, electronic health records from one or more health systems, insurance claims data from one or more health care payers, and the like.

[0041] As explained herein, the plurality of patients studied in the historical data should preferably exhibit a diverse array of starting physiological conditions, such that the historical data may be used to estimate how outcomes vary with different starting physiological conditions. The starting physiological conditions included in the historical data may comprise any physiological parameter that may be measured in a patient. Illustrative examples of suitable starting physiological parameters include a patient’s height, weight, resting heart or pulse rate, and starting A1C level. Further examples of suitable starting physiological parameters include a patient’s biological sex, age, race or ethnicity, blood pressure, Body Mass Index (BMI), the presence or level of one or more genetic markers in a patient, and / or the presence or level of one or more biomarkers present in a patient’s blood, tissue, or some other bodily media. Suitable physiological parameters may also include elements of apatient’s medical history, such as an indication of one or more diseases or conditions present in the patient, an indication of one or more medications that the patient is currently taking or has taken, an indication of one or more treatments or therapies that the patient is currently undertaking or has undertaken, and / or an indication of the patient’s family medical history (e.g., diseases or conditions present in the patient’s immediate or extended family).

[0042] In some embodiments, the historical data may also comprise outcomes recorded from patients that were administered different dose levels of the medication, such that the historical data may be used to estimate how outcomes vary with different dose levels. For example, the historical data may comprise outcomes recorded from patients that were each administered one out of a set of pre-determined dose levels (e.g., three, four, or five pre-determined dose levels). In some embodiments, the historical data may comprise outcomes recorded from patients that were administered widely varying dose levels.

[0043] At step 304, the one or more computing devices derive one or more parameter- estimation functions based on the historical data. Each parameter-estimation function may be associated with, and may be used to model, a separate parameter of a prediction function.

[0044] A prediction function may be a computer-implemented model or engine, a set of computer-implemented logic, or sequence of computer-implemented steps for predicting changes in the target physiological parameter of a target patient expected to result over time from administration of the target medication (or from administration of a course of the target medication). For example, the prediction function may take as input a time t and output an expected change in the target physiological parameter of a target patient. The prediction function may comprise one or more configurable parameters that may be changed. Such configurable parameters may be adjusted in order to take into account the starting physiological parameters of the target patient. Each of the aforementioned parameter- estimation functions may be used to model how each parameter of the prediction function varies in accordance with one or more starting physiological parameters of the target patient. The parameter-estimation functions may be derived by applying any of a number of standard regression techniques on the historical data. For example, a simple linear regression or multiple linear regression may be used to predict an assumed linear relationship between an independent variable (e.g., the parameter of the prediction function being modeled) and one or more dependent variables (e.g., one or more starting physiological conditions, dose levels, and / or prediction time).

[0045] One example of a prediction function is provided in the following Equation 1: Equation

[0046] Where: • t is a future time point, e.g., in units of days, weeks, or months; • d is a pre-specified parameter that can represent the length of time for which patients’ physiological parameters were tracked after and / or during administration of a course of the medication in the historical data (e.g., if the historical data comprises clinical trial data which observes how trial subjects’ target physiological parameters changed over 12 months after taking, or starting to take, the medication, d would be a parameter that represents 12 months); • Yijis a random variable representing the change from baseline of the target physiological parameter (wherein the baseline may be established from the current level of the target physiological parameter); • θijis a mathematical (numerical) parameter representing the expected change from baseline of the target physiological parameter for dose level i and subject j (i.e., a subject having the same or similar starting physiological parameters as the patient) at time d; • kiis a mathematical (numerical) parameter representing an expected decay rate associated with dose level i; and • εijis a random variable representing the random error from predicting changes in the target physiological parameter. The random variable may be assumed to follow a probability distribution (such as a normal distribution) having expectation zero and a standard deviation σ. The standard deviation σ may vary based on the dose level i and the subject j.

[0047] This exemplary prediction function is an exponential decay function that accepts an input time t and outputs an expected change in the target physiological parameter frombaseline. To be specific, this prediction function comprises two exponential decay functions:1 − exp { ^^^^ ^^^^ ^^^^} and 1 − exp{ ^^^^ ^^^^ ^^^^}. In this exemplary prediction function, there are threeconfigurable parameters: a first parameter associated with a first parameter-estimationfunction, a second parameter kiassociated with a second parameter-estimation function, and a third parameter εijassociated with a third parameter-estimation function. Each parameter is explained in further detail below.

[0048] θijmay be estimated based on a first parameter-estimation function. In the example given in Equation 1, θijvaries based on the subject j and the dose level i. Therefore, the parameter-estimation function for θijmay accept as input values for any or all of a set of starting physiological parameters for the target patient, as well as a target dose level to be administered to the target patient. The first parameter-estimation function may then process these inputs according to a mathematical formula or equation to output a numerical estimate for θij. This first parameter-estimation function may be derived based on the aforementioned historical data. For example, the first parameter-estimation function may be determined by applying any standard regression technique (e.g., a linear regression) to the aforementioned historical data in order to estimate how θijvaries with (i) starting physiological parameters observed in the plurality of patients studied in the historical data and (ii) the dose levels administered to the plurality of patients. Although θij in this exemplary embodiment varies based on the subject j and the dose level i, it should be understood that in other embodiments, θijmay be estimated based on different parameters. For example, θijmay additionally be estimated based on the duration d of the observation period in the historical data. θijmay be estimated based on fewer input parameters, more input parameters, or different input parameters. In some embodiments, θijmay even be set at a single invariate value that applies to all subjects and all dose levels, e.g., θijdoes not vary based on any input parameters at all.

[0049] Similarly, kimay be estimated based on a second parameter-estimation function. In the example given in Equation 1, kivaries based on the dose level i. Therefore, the parameter- estimation function for kimay accept as input a target dose level to be administered to the target patient. The parameter-estimation function may then process the dose level according to a mathematical formula or equation to output a numerical estimate for ki.Again, the parameter-estimation function for kimay be determined by applying any standard regression tecnique to the aforementioned historical data in order to esitmate how kivaries with dose level. Although kiin this exemplary embodiment varies based on the dose level i only, it should be understood that in other embodiments, kimay be estimated based on different parameters, including any or all of the parameters used to estimate θij. Should it be desired to estimate kibased on additional or different parameters, the estimation function for kimayagain be determined by applying the aforementioned standard regression techniques to determine how kivaried with the aforementioned additional / different parameters in the historical data.

[0050] εijdiffers from θijand kiin that εijis a random variable and not an estimated numerical value. εijmay be modeled by a probability distribution function, such as (but not limited to) a normal Gaussian distribution. In this embodiment, it is assumed that εijhas an expectation of zero. The probability distribution for εijmay include a measure of variability, such as a standard deviation σ. In the example given in Equation 1, the standard deviation σ varies based on the subject j and the dose level i. Therefore, similar to θijand ki, the standard deviation σ may be estimated using a third parameter-estimation function that accepts as input values for any or all of a set of starting physiological parameters for the target patient, as well as a target dose level to be administered to the target patient. This third parameter-estimation function may again be derived by applying any standard regression technique to the aforementioned historical data in order to estimate how σ varies with starting physiological parameters and dose level. Although σ in this example varies based on the subject j and the dose level i, it should be understood that in other embodiments, σ may be estimated based on fewer input parameters, more input parameters, or different input parameters. For example, σ may also be estimated, either additionally or in the alternative, based on the forecast time t. In some embodiments, σ may be set at a single invariate value that applies regardless of the curent physiological parameters of the patient, the dose levels, and / or the forecast time t, e.g., σ does not vary based on any input parameters at all. While this discussion is focused on the standard deviation σ of the probability distribution function for modeling εij, it should be understood that any measure of statistical variability for the random variablemay be used, including but not limited to a statistical variance (e.g., σ2), an interquartile range, and / or a range.

[0051] At step 306, the one or more computing devices receives user input indicative of a value for each of one or more starting physiological parameters for the target patient. For example, if the set of starting physiological parameters includes a target patient’s starting weight, A1C level, resting pulse rate, and height, the one or more processors may receive user input indicative of values for each of these starting physiological parameters (e.g., starting weight = 279 lbs., starting A1C level = 8.2, starting pulse rate = 88 beats per minute, starting height = 5 ft., 7 in.). Optionally, at step 306, the one or more computing devices may also receive user input indicative of a target dose level expected to be administered to the target patient.Additionally or alternatively, the processor may also receive user input indicative of a duration of a forecast period for which the user desires to predict changes in the patient’s target physiological parameter.

[0052] At step 308, the one or more computing devices calculate a value for each parameter of the prediction function by applying the one or more derived parameter-estimation functions to the one or more values indicated by the received user input. For example, the parameter θijmay be estimated by applying the first parameter-estimation function derived at step 304 to some or all of the starting physiological parameters and / or the dose level received at step 306. Similarly, the parameter kimay be estimated by applying the second parameter-estimation function derived at step 304 to the dose level received at step 306. The paramter σ may be estimated by applying the third parameter-estimation function derived at step 304 to some or all of the starting physiological parameters and / or the dose level received at step 306.

[0053] When the parameters θij, ki, and σ have all been estimated using their respective parameter-estimation functions, the prediction function provided in equation 1 may now be used to estimate (at step 310) the expectation of change Yijin the target physiological parameter of the patient at a plurality of time points t during the forecast period. The plurality of future time points may extend into a forecast period in the future, wherein the forecast period is long enough such that changes in the target physiological parameters are expected to result from administration of the medication or the course of medication. For example, the forecast period may extend 1 month, 3 months, 6 months, 9 months, and / or 12 months into the future. The plurality of future time points may comprise two time points, three time points, or any number of time points within the forecast period.

[0054] In the exemplary prediction function given in equation 1, Yijis a random variable since it is determined in part based on a random variableHence, equation 1 may be used to determine not only an expected change in the target physiological parameter, but also the probabilities associated with higher-than-expected and lower-than-expected values of Yij. For example, given a certain time t within the forecast period, equation 1 may be used to determine a 90% prediction interval for Yij, e.g., a range of values for Yijthat the patient’s target physiological parameter is expected to fall within with 90% probability. Such a prediction interval could then be used to derive and present a range of expected values fortime t. Of course, different prediction intervals (e.g., an 85% interval, or 95% interval) may also be used.

[0055] At step 312, the processor may display the predicted changes in the target physiological parameter of the patient. This may comprise displaying the expected value for Yijas determined by Equation 1. Alternatively or in addition, the processor may display probabilities associated with higher-than-expected and / or lower-than-expected values of Yij.In some embodiments, the processor may also display a prediction interval for the expected change. The processor may display the predicted changes on a user display communicatively coupled to the processor. Such a display may be integrated into or physically coupled with the same device embodying the processor (e.g., processor 102 on computing device 101 may display the results on user interface 108), or such a display may be remote from the processor implementing logic 300 (e.g., processor 252 on computing device 250 may communicate the predicted changes Yijto computing device 201 via communication link 230, thereby allowing computing device 201 to display the predicted changes on user interface 208). The displayed predicted changes may be used to assist at least one of the target patient and a medical professional (e.g., a healthcare professional directly or indirectly responsible for caring for the target patient or advising the target patient) in determining whether the medication should be administered to the target patient.

[0056] While FIGS.3A and 3B and the prior discussion presents one exemplary embodiment of logic 300, it should be appreciated that any of the steps in logic 300 may be adjusted, extended, re-arranged, deleted, and / or modified in various ways. For example, although θijand kiare presented in the prior discussion as mathematical (numerical) parameters that may be estimated using their respective parameter-estimation functions, θijand kimay also be random variables similar to εij, each of which may be modeled by an associated probability distribtion functions. Also similar to εij, the probability distribution function for θijand / or kimay have parameters that may be estimated using estimation functions derived from applying standard regression techniques to the aforementioned historical data. For instance, the type of distribution (e.g., normal (Gaussian), binomial, poisson, etc.), the expectation of the distribution, and / or a statistical measure of the variability of the distribution (e.g., variance, standard deviation, inter-quartile range, or range) for modeling θijand / or kimay all be estimated based on some or all of the patient’s current physiological parameters, the dose level, and / or the forecast period by applying regression techniques to the historical data.

[0057] In some embodiments, a user may use logic 300 to predict changes in the target physiological parameter of the patient after the patient has already been taking the medicationfor a prior period of time. In such embodiments, the patient may already have observed certain actual changes in the target physiological parameter as a result of taking the medication for the prior observation period. In such embodiments, logic 300 may be extended and / or modified to take into account the actual changes observed by the patient in order to improve the accuracy of the predicted changes in the target physiological parameter expected to result from continued administration of the medication. For example, a patient may have been taking a medication for weight loss for a prior observation period of three months. During those three months, the patient may have observed certain actual changes in his / her body weight (e.g., a reduction in weight of 10 lbs.) as a result of taking the medication. The logic 300 may be extended and / or modified to take the patient’s actual observed change in body weight over the prior 3 month observation period into account while predicting further expected changes in the patient’s body weight, should the patient continue to take the medication. In this way, the logic 300 may improve the accuracy of its predictions by customizing its logic to the specific patient under consideration.

[0058] Logic 300 may be extended and / or modified in this way by adding an optional step (not shown) between steps 302 and 304, in which the processor receives a number of observed changes in the target physiological parameter of the patient during the prior observation period. Let d’ denote the duration of the prior observation period, L denote the number of observed changes received, and Zt’represent the actual observed change in the target physiological parameter at time t’, wherein t’ is a time point within the prior observation period. Then, a parameter ŝjspecific to the patient j may be generated according to Equation 2:

[0059] Equation

[0060] The parameter ŝjmay then be added to a modified version of the prediction function provided in Equation 1, now represented by Equation 3 below:

[0061] Equation

[0062] Equation 3 is identical to Equation 1 except that the parameter ŝjhas been added. In this way, the parameter ŝjrepresents an adjustment specific to patient j that has been estimated based on the changes in the target physiological parameter that the patient actually observed during the prior observation period.

[0063] Logic 300 represents a technical improvement over prior known systems in several ways. First, because logic 300 uses a prediction function (e.g., the exponential decay function provided in Equations 1 or 3) that takes as input a time t and outputs an expected change in the target physiological parameter at said input time t, the prediction function may be used to estimate an expected change in the target physiological parameter at multiple times t. Therefore, unlike prior known systems, logic 300 is not constrained to providing estimated changes at only one or two pre-determined points of time in the future (e.g., only estimating changes 3 months or 6 months in the future), but can estimate predicted changes at any user- specified time t.

[0064] Second, logic 300 is structured in such a way that certain computational or memory- intensive steps may be performed ahead of time, potentially by a first computing device with access to greater computational and / or memory resources. These first resource-intensive steps result in output (e.g., the parameter-estimation functions derived by step 304) that may be saved in memory and / or communicated to computing devices with access to relatively fewer computational and / or memory resources. When a user provides starting physiological parameters for a specific target patient and requests a personalized prediction for the target patient, that saved output may then be used to calculate the expected change in the target patient’s target physiological parameter with only a relatively modest expenditure of time and / or computing or memory resources.

[0065] Specifically, the historical data accessed at steps 302 and 304 (in FIG.3A) may be large in size and require larger computational and / or memory resources to handle. Similarly, the derivation of the parameter-estimation functions at step 304 may be a resource intensive task, since it requires running one or more regressions over a large dataset. If steps 302 and 304 are repeated every time a user desired to calculate an expected change in the target physiological parameter of a target patient, it would be difficult to implement logic 300 at a computing device with access to only modest computational and / or memory resources. It may also be difficult to implement logic 300 quickly, i.e., logic 300 may require a long runtime.

[0066] However, logic 300 has been structured in such a way that steps 302 and 304 may be implemented ahead of time (e.g., before a user requests an estimate for a specific target patient) at a first computing device (e.g., processor 252 at computing device 250) with access to comparatively large computational and memory resources. Once implemented, the outputof step 304 (e.g., the derived parameter-estimation functions) may be saved in memory and / or communicated to other devices, such as computing device 201 with comparatively fewer computational and / or memory resources. This saved output incorporating the derived parameter-estimation functions may be embedded into a relatively compact code module or data structure that does not require much memory to save (or much bandwidth to transfer) and may then be leveraged at runtime, e.g., when a user actually requests a prediction for a specific target patient. This improves responsiveness from the user’s point of view, since less time is required to generate the prediction once requested. Furthermore, since steps 306 to 312 require only relatively modest computational resources, they may be implemented on computing devices with comparatively fewer computational and / or memory resources (such as computing device 201).

[0067] Third, logic 300 improves the security of the historical data accessed at step 302. The historical data accessed at step 302 are typically not only large in size but may also be commercially or strategically valuable. For instance, clinical trials may require years of effort and expenditure of large sums of money and resources to run, which makes the resulting data extremely valuable. The historical data may also be subject to certain privacy restrictions to protect sensitive information pertaining to the plurality of patients studied, such that leakage of the historical data to unauthorized users may lead to liability for the owner and / or manager of the historical data. For these and other reasons, owners and / or managers of the historical data may often desire to restrict access to the historical data so as to mitigate the possibility of the data being leaked or exploited by others. To improve the security of the historical data, steps 302 and 304 (which are the only steps which require direct access to the historical data) may be implemented ahead of time on a relatively secure computing device (e.g., a device operating under heightened cybersecurity measures). The output of step 304 (e.g., the derived parameter-estimation functions) may then be exposed or transferred to other parties or less secure computing devices to implement steps 306 through 312, since the parameter- estimation functions cannot be easily reverse-engineered to derive the source historical data. To further improve the security of the historical data, the derived parameter-estimation functions may be embedded into a code module or data structure in an opaque way that is not easily discoverable through reverse engineering. For instance, the derived parameter- estimation functions may be incorporated into compiled machine code, and only the compiled machine code may be made available to other parties or less secure computing devices, such that the other parties or devices have no way of recovering the source code that sets out thederived parameter-estimation functions in a human-readable format. In this way, less secure computing devices or other parties may benefit from the historical data without requiring the owner and / or manager of the historical data to expose the source data.

[0068] FIG.4 presents an exemplary screen 400 of a web browser or web-enabled application interface (hereinafter referred to as a “web interface”) on a mobile device for receiving user input from a user. In this example, the web interface is configured to predict changes in either the patient’s body weight or A1C level expected to result from a course of a GIP / GLP-1 agonist administered to the patient. The user may be the patient, or someone entering data on behalf of the patient, such as a caregiver, family member, or health care provider (HCP). Screenshot 400 includes separate fields that may be populated by the user. In this example, those fields include a field 402 for receiving user input indicative of the patient’s starting weight, a field 404 for receiving user input indicative of the patient’s starting A1C level, a field 406 for receiving user input indicative of the patient’s starting resting heart rate, and a field 408 for receiving user input indicative of the patient’s starting height. Further fields, different fields, or different measurement units may also be used in web interface 400. In this example, the user has provided input indicating that the patient has a current weight of 279 lbs., a current A1C level of 8.2, a current resting pulse rate of 88, and a current height of 5 feet, 7 inches. Once the user has finished providing user input, the user may touch or actuate button 410 (“See the Projected Path”) to progress to the next step of logic 300. For example, upon pressing button 410, the user input may be transmitted by computing device 201 via web link 230 to computing device 250 for processing.

[0069] Upon pressing button 410, the web interface may transition to the exemplary screen 500 presented in FIG.5A. Screenshot 500 includes a toggle button 502 to allow the user to select the target physiological parameter, e.g., whether to view predicted changes for the patient’s A1C level or the patient’s weight – in the depicted example, the user has selected to view predicted changes in the patient’s weight. Screen 500 further includes a dropdown menu 504 allowing the user to select a dose level, e.g., between 5, 15, or 15 mg – in the depicted example, dropdown menu 504 is set to the dose level of 15 mg. The user’s selection in dropdown menu 504 informs the dose level i in the previously-discussed equations. Screen 500 also includes a selection bar 520 allowing a user to select an appropriate forecast period, e.g., to select between forecasting 1 month, 3 months, 6 months, 9 months, or 12 months into the future – in the depicted example, the user has selected a forecast period of 6 months.

[0070] Screen 500 further includes a results panel 506. Panel 506 includes a graph 514. In graph 514, the horizontal axis represents time while the vertical axis represents a magnitude or level of the target physiological parameter. Graph 514 comprises three curves 516a, b, c showing predictions for the level of the target physiological parameter at a plurality of time points over the forecast period. Curve 516a shows the average expected level, curve 516b shows a maximum expected level, and curve 516c shows the minimum expected level over time. Each of curve 516a, b, c, may be derived from Equation 1 (or Equation 3) as discussed above. In this embodiment, the maximum and minimum expected levels are derived from the 90% prediction intervals from Equation 1 (or Equation 3), as previously discussed.

[0071] Graph 514 further comprises a selected time indicator 518. Time indicator 518 may comprise any visual feature that indicates to the user what is the current time selected. In some embodiments, it may appear as an icon, symbol, or text indicating the current time selected. In the specific embodiment depicted in FIG.5A, selected time indicator 518 appears as a vertical bar overlaid on top of curves 516a, b, and c. Selected time indicator 518 may be selected and moved left or right by the user interacting with the web interface to select a different time point within the forecast period. In the example shown in FIG.5A, the selected time indicator 518 is currently positioned over the date June 24, 2023. Results panel 506 further displays an expected level 508 for the target physiological parameter at the selected time, as well as a maximum expected level 510 and a minimum expected level 512. In this case, since the user has selected toggle button 502 to select “Weight”, expected level 508 shows an expected weight (in this case: 207 lbs.), a maximum expected weight (209 lbs.), and a minimum expected weight (205 lbs.) for the patient at the selected future time of June 24, 2023.

[0072] FIG.5B shows screen 500 after the user has changed the forecast period to 9 months in the selection bar 520, and also moved the selected time indicator 518 to the right to select another date: August 11, 2023. Since the selected time has changed, expected level 508 now shows 202 lbs., while the maximum and minimum expected levels now show 206 lbs. and 198 lbs., respectively.

[0073] Selection of the side effect profile link 524 takes the user to a screen that informs the user about potential side effects of the medication that the user is taking. Selection of the details link 522 takes the user to a screen that provides additional details regarding how the web interface calculates expected changes to the user’s body weight and / or A1C level.

[0074] FIG.6 shows screen 500 after the user has changed toggle button 502 to select A1C level instead of weight. As a result, expected level 508 now shows a projected A1C level of 5.7% on the selected date of June 24, 2023, while the maximum and minimum expected levels now show 5.9% and 5.5%, respectively.

[0075] FIG.7 shows an exemplary screen 700 for a web interface that is configured for display on a monitor coupled to a laptop or desktop (as opposed to on a mobile device such as a smartphone). Similar to screen 500, screen 700 includes a toggle button 702 (analogous to toggle button 502), a dropdown menu 704 for selecting a dose level (analogous to dropdown menu 504), and a selection bar 720 for selecting a forecast period (analogous to selection bar 520). Screen 700 further includes a results panel 706 (analogous to results panel 506) that includes a graph 714 (analogous to graph 514). Graph 714 further includes a first curve 714a showing an average expected level for the target physiological parameter during the forecast period, a second curve 714b showing a maximum expected level, and a third curve 714c showing a minimum expected level. Overlaid on top of the three curves is a selected time indicator 718 (analogous to selected time indicator 518). Results panel 706 further includes a numerical readout 708 of an expected level of the target physiological parameter at the selected time (analogous to expected level 508), as well as a numerical readout 710 and 712 for the maximum and minimum expected levels, respectively (analogous to readouts 510 and 512). Finally, screen 700 further includes a side effect profile link 724 and a details link 722, analogous to links 524 and 522 in FIG.5.

[0076] FIG.7 shows an exemplary screen if the user selected “weight” in the toggle button 702, such that the results panel 706 displayed predicted levels for the patient’s weight. FIG.8 shows another exemplary screen from the same web interface if the user had selected “A1C” in the toggle button 702, such that the results panel 706 displayed predicted levels for the patient’s A1C level.

[0077] Various aspects of the present disclosure may be used alone, in combination, or in a variety of arrangements not specifically discussed in the embodiments described in the foregoing and is therefore not limited in its application to the details and arrangement of components set forth in the foregoing description or illustrated in the drawings. For example, aspects described in one embodiment may be combined in any manner with aspects described in other embodiments. Thus, while the present teachings have been described in conjunction with various embodiments and examples, it is not intended that the present teachings belimited to such embodiments or examples. On the contrary, the present teachings encompass various alternatives, modifications, and equivalents, as will be appreciated by those of skill in the art. Accordingly, the foregoing description and drawings are by way of example only.

Claims

CLAIMS We claim:

1. A method for predicting changes in a target physiological parameter of a target patient expected to result from a medication to be administered to the target patient, the method comprising: accessing, at one or more computing devices, historical data indicative of changes observed over an observation period in the target physiological parameter of a plurality of patients resulting from administration of the medication; deriving, at the one or more computing devices, one or more parameter-estimation functions based on the historical data, wherein each parameter-estimation function models how a separate parameter of a prediction function for predicting changes in the target physiological parameter over time varies in accordance with one or more starting physiological parameters observed in the plurality of patients; receiving, at the one or more computing devices, user input indicative of a value for each of the one or more starting physiological parameters for the target patient; calculating, by the one or more computing devices, a value for each parameter of the prediction function by applying the one or more derived parameter-estimation functions to the one or more values indicated by the received user input; predicting, by the one or more computing devices, changes in the target physiological parameter of the target patient at a plurality of future time points using the prediction function and the calculated parameter values; and displaying, on a user interface of at least one of the computing devices, the predicted changes in the target physiological parameter of the target patient to assist at least one of the target patient and a medical professional in determining whether the medication should be administered to the target patient.

2. The method of claim 1, wherein the medication is an anti-obesity medication and the target physiological parameter is body weight.

3. The method of claim 1, wherein the medication is an anti-diabetes medication and the target physiological parameter is A1C level.

4. The method of any one of claims 1-3, wherein the one or more starting physiological parameters comprise at least one of age, A1C level, height, weight, resting heart rate, and biological sex.

5. The method of any one of claims 1-4, wherein the prediction function is a probability distribution function.

6. The method of claim 5, wherein predicting changes in the target physiological parameter of the target patient comprises predicting, for each time point of the plurality of future time points, an expected change in the target physiological parameter and a prediction interval for the expected change.

7. The method of any one of claims 5-6, wherein at least one of the parameter-estimation functions models how a parameter indicative of a measure of statistical variance varies in accordance with the one or more starting physiological parameters.

8. The method of any one of claims 1-7, wherein: the plurality of patients in the historical data were administered different dose levels of the medication, such that the historical data is indicative of how changes in the target physiological parameter varies with dose level; at least one of the derived parameter-estimation functions models how one of the parameters of the prediction function varies in accordance with dose level; the user input received at the one or more computing devices is further indicative of a target dose level for the medication to be administered to the target patient; the value for at least one parameter of the prediction function is calculated, by the one or more computing devices, based at least in part on the target dose level; and the predicted changes in the target physiological parameter of the target patient displayed on the user interface are calculated based at least in part on the target dose level to assist at least one of the target patient and the medical professional in determining whether the target dose level of the medication should be administered to the target patient.

9. The method of any one of claims 1-8, further comprising receiving, at the one or more computing devices, further user input indicative of actual changes to the targetphysiological parameter observed in the target patient in response to a course of the medication previously administered to the target patient, wherein the calculated parameter values of the prediction function are calculated based at least in part on the further user input.

10. The method of any one of claims 1-9, wherein the parameter-estimation functions are derived by the one or more computing devices and saved into a memory accessible by the one or more computing devices before the user input is received.

11. The method of any one of claims 1-10, wherein the accessing and deriving steps are implemented at a first computing device, and the receiving, calculating, predicting, and displaying steps are implemented at a second computing device.

12. The method of any one of claims 1-12, wherein the one or more parameter-estimation functions are derived from the historical data using linear regression.

13. A system for predicting changes in a target physiological parameter of a target patient expected to result from a medication to be administered to the target patient, the system comprising: a user interface; one or more memory systems storing computer-executable instructions; and one or more processors communicably coupled with the one or more memory systems and the user interface, and operable to execute the instructions to: access historical data indicative of changes observed over an observation period in the target physiological parameter of a plurality of patients resulting from administration of the medication; derive one or more parameter-estimation functions based on the historical data, wherein each parameter-estimation function models how a separate parameter of a prediction function for predicting changes in the target physiological parameter over time varies in accordance with one or more starting physiological parameters observed in the plurality of patients; receive user input indicative of a value for each of the one or more starting physiological parameters for the target patient;calculate a value for each parameter of the prediction function by applying the one or more derived parameter-estimation functions to the one or more values indicated by the received user input; predict changes in the target physiological parameter of the target patient at a plurality of future time points using the prediction function and the calculated parameter values; and display, on the user interface, the predicted changes in the target physiological parameter of the target patient to assist at least one of the target patient and a medical professional in determining whether the medication should be administered to the target patient.

14. The system of claim 13, wherein the medication is an anti-obesity medication and the target physiological parameter is body weight.

15. The system of claim 13, wherein the medication is an anti-diabetes medication and the target physiological parameter is A1C level.

16. The system of any one of claims 13-15, wherein the one or more starting physiological parameters comprise at least one of age, A1C level, height, weight, resting heart rate, and biological sex.

17. The system of any one of claims 13-16, wherein the prediction function is a probability distribution function.

18. The system of claim 17, wherein predicting changes in the target physiological parameter of the target patient comprises predicting, for each time point of the plurality of future time points, an expected change in the target physiological parameter and a prediction interval for the expected change.

19. The system of claim 17-18, wherein at least one of the parameter-estimation functions models how a parameter indicative of a measure of statistical variance varies in accordance with the one or more starting physiological parameters.

20. The system of any one of claims 13-19, wherein:the plurality of patients in the historical data were administered different dose levels of the medication, such that the historical data is indicative of how changes in the target physiological parameter varies with dose level; at least one of the derived parameter-estimation functions models how one of the parameters of the prediction function varies in accordance with dose level; the received user input is further indicative of a target dose level for the medication to be administered to the target patient; the value for at least one parameter of the prediction function is calculated, by the one or more processors, based at least in part on the target dose level; and the predicted changes in the target physiological parameter of the target patient displayed on the user interface are calculated based at least in part on the target dose level to assist at least one of the target patient and the medical professional in determining whether the target dose level of the medication should be administered to the target patient.

21. The system of any one of claims 13-20, wherein the one or more processors are further operable to execute the instructions to receive further user input indicative of actual changes to the target physiological parameter observed in the target patient in response to a course of the medication previously administered to the target patient, wherein the calculated parameter values of the prediction function are calculated based at least in part on the further user input.

22. The system of any one of claims 13-21, wherein the one or more processors are operable to derive and save the parameter-estimation functions into the one or more memory systems before the user input is received.

23. The system of any one of claims 13-22, wherein the one or more processors comprise a first processor operable to implement the accessing and deriving steps and a second processor operable to implement the receiving, calculating, predicting, and displaying steps.

24. The system of any one of claims 13-23, wherein the one or more parameter-estimation functions are derived from the historical data using linear regression.

25. Non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, are operable to cause the one or more processors to implement the method of any one of claims 1-12.

Images