Systems and methods for disease control and management

Abstract

A system for creating and updating one or more models for providing treatment recommendations for health conditions may receive weight measurements from a weight measuring device, execute a basic model based on information regarding the health condition, to generate treatment recommendations, generate reminders prompting the user to obtain weight measurements, estimate an impact of the user data on the weight measurements, generate a modified model, based on the basic model, the received weight measurements, the received user data, and the estimated impact of the user data, the modified model including personalized treatment recommendations specific to the user, and transmit the reminders, the treatment recommendations, and the personalized treatment recommendations to the user device.

Description

TECHNICAL FIELD

The present invention generally relates to the field of disease management. More particularly, and without limitations, the invention relates to systems and methods for disease management by providing treatment recommendations and information based on relevant data collected about a patient.

BACKGROUND

Generally speaking, disease management refers to a wide range of activities that may affect a patient's health status. These activities include programs to improve a patient's compliance with their treatment regimen, and helping the patient adjust their regimen according to evidence-based treatment guidelines. The goal of these programs is to attempt to maintain or improve the patient's health status and quality of life, and to reduce the total costs of health care.

One approach is to identify and provide a variety of appropriate services to patients that are suitable for a certain program. Examples of such services include periodic phone calls to a patient to monitor the status of the patient, personalized goal-oriented feedback on the patient's self care, access to nurse call centers, and educational materials. Some of these programs attempt to modify services based on data obtained from the patient's self reports and administrative claims. These programs attempt to help patients identify regimens, manage their symptoms, self-monitor their conditions, and comply with their treatment. The drawbacks of this type of approach include the enormous resources necessary to provide these human-based services, and the lack of timely, appropriate, and accurate patient data to provide appropriate services. For example, a single case manager can only assist a limited number of patients. As a result, such a case manager may, for example, be able to contact a patient only once a month and may be forced to rely on out-dated data for the patient.

An alternative approach for disease management is to use a system that provides corrective action to a patient based on limited information provided by the patient. For example, a diabetes patient can provide their current glucose value using an electronic patient-operated apparatus, and the system can recommend a corrective action to the patient based on the application of formulas well known in the art. A corrective action can be either administration of an extra insulin dose or consumption of carbohydrates. A drawback of this approach is that it fails to provide customized disease management for each individual patient. Similarly, the formulas that can be applied for any patient part of the general population do not take into account the complete dynamics of a particular's patient's disease and the corrective actions advised to a patient are limited. As a result, a patient is denied the optimal treatment recommendations that can only be targeted for a particular patient. Finally, the success of the system is wholly dependent on a proactive and conscientious patient.

In view of the foregoing, there is a need for an improved solution for disease management. In particular, there is a need for systems and methods for effective disease management that can develop recommendations for a patient based on the particular patient's data.

SUMMARY

The present invention provides methods, computer-readable media, and systems for providing disease management. This is achieved by providing treatment recommendations targeted for a particular patient based on the patient's data.

In one exemplary embodiment, a system is provided including, for example, an input device for receiving patient data; a transmitter for transmitting the received patient data from the input device; and a disease management server. The disease management server may include a receiver for receiving the transmitted patient data, a processor for developing a treatment recommendation, and an output device for outputting the treatment recommendation. The processor may develop treatment recommendations by executing a basic model of the physiological system of the patient to generate a modified model for the patient based on the patient data, performing a statistical analysis of the patient data to detect data excursions of the parameter values, using the modified model to determine factors causing the data excursions, and using the model to develop a treatment recommendation to ameliorate negative effects of the disease. The patient data may include but is not limited to the following parameters: patient carbohydrate intake, patient medication doses, blood glucose level, activity of the patient, and the corresponding time and optional context for the data.

The processor in the disease management server of the exemplary system may generate a plurality of treatment recommendations, including, for example, recommendations for dosing and timing of medication, and for patient dietary behavior. Executing the model comprises applying an algorithm to the patient data in a current state in conjunction with auxiliary patient data including, for example, patient blood lipid level, blood pressure, age, gender, height and weight, and race. The processor may be further configured to develop recommendations for collection of the patient data to improve the model, wherein the collection recommendations comprise recommendations for timing of blood glucose measurement. The processor may be further configured to perform statistical analysis employing a statistical design of experiments methodology and multivariate analyses to identify the factors causing the data excursions.

In another embodiment, the treatment recommendations may be developed at predetermined intervals, which may be determined based on a most-recent patient data collection time. The treatment recommendations may include a recommended time and dose of medication, including recommended combinations of available medications. The treatment recommendations may also include a recommended time and amount of carbohydrate intake.

In another alternate embodiment, the input device may be a patient-interactive interface operated by the patient. The system may include a portable device configured to operate the patient-interactive interface and the transmitter, wherein the transmitter transmits signals over a wireless communication to the disease management server. The system may also include a physician interface operable to receive information about the patient from the disease management server.

In another alternate embodiment, the patient data may be calibrated at a plurality of reading points to provide more information on pharmacokinetic/pharmacodynamic interactions of the patient.

In another alternate embodiment, generating the modified model may include utilizing equations that simulate interaction of primary factors effecting rate of change of the blood glucose of the patient, wherein the primary factors are calculated based on the patient data. The primary factors may include rate of digestion of the patient carbohydrate intake, cellular uptake of blood glucose by the patient, and impact of glucose inventory in liver, skeletal muscle, and fat tissues of the patient. The equation for the cellular uptake is a function of the blood glucose level, level of insulin acting as a catalyst, resistance factors, and digestive-activated hormones, and wherein the level of insulin is calculated based on the patient medication doses, patient pancreatic production, and insulin kinetics.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments and aspects of the present invention. In the drawings:

FIG. 1 illustrates an exemplary system, consistent with an embodiment of the invention.

FIG. 2 is a flowchart of an exemplary method, consistent with an embodiment of the present invention;

FIG. 3 is a flowchart of an exemplary method for collecting patient data, consistent with an embodiment of the present invention;

FIG. 4 depicts an example of a disease managements server developing treatment recommendations, consistent with an embodiment of the present invention;

FIG. 5 is an exemplary diagram showing a generation of a modified model for a patient, consistent with an embodiment of the present invention;

FIG. 6 is an exemplary diagram showing a determination of the insulin of a patient, consistent with an embodiment of the present invention;

DESCRIPTION OF THE EMBODIMENTS

The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. While several exemplary embodiments and features of the invention are described herein, modifications, adaptations and other implementations are possible, without departing from the spirit and scope of the invention. For example, substitutions, additions, or modifications may be made to the components illustrated in the drawings, and the exemplary methods described herein may be modified by substituting, reordering, or adding steps to the disclosed methods. Accordingly, the following detailed description does not limit the invention. Instead, the proper scope of the invention is defined by the appended claims.

FIG. 1 illustrates components of an exemplary system 100, consistent with an embodiment of the present invention. The two main components of the system are an input device 110 and a disease management server 130. A transmitter 120 may be a separate component or part of the input device. Transmitter 120 may include a modem to transmit information collected by input device 110 to disease management server 130. Transmitter 120 may also be used to receive information from disease management server 130 to provide to the user through the input device 110. For example, disease management server 130 may send information regarding what data it needs input device 100 collect from the patient.

Input device 110 and the transmitter 120 may be part of a single computer system. Alternatively, the transmitter may be on an intermediary computer system between the input device 110 and the disease management server 130. The transmitter 120 may serve as the intermediary for communication between the input device 110 and the disease management server. The components 110, 120, 130 may communicate with each over a communication medium 125. The communication medium may be any desired type of communication channel, including (but not limited to) the public switched telephone network (VSTN), cellular channel, other wireless channel, internal computer bus, intranet, internet, etc.

The input device 110 may be used to collect variety of patient data in a variety of ways. The input device 110 may be connected to one or more biometric measurement devices to collect biometric data. The biometric measurement devices may be implanted in the patient, connected to the patient, and/or completely external. A biometric measurement device may be part of or connected to the input device 110, or it may be a stand-alone device. A stand-alone biometric measurement device may communicate wirelessly with the input device 110. Examples of biometric measurement devices include, but are not limited to, scales, external blood pressure monitors, cardiac data sensors, implantable blood glucose sensors for continuous sensing, external blood glucose monitors, etc.

The input device 110 may also receive information from devices for administering medication. For example, the input device 110 may be connected to an insulin-delivery device. The input device 110 may receive information detailing the insulin doses a patient has taken from the insulin-delivery device and the times of dose administration.

The input device 110 may also receive information from other ancillary devices to collect a variety of information about the patient's behavior and status. For example, the input device 110 may be connected to a pedometer worn by the patient or exercise equipment used by the patient to track the physical activity of the patient. The input device 110 may be connected to a GPS system to track the movement and location of the patient. The input device may also be connected to a device that keeps track of a patient's dietary behavior.

The input device 110 may also receive information by having the patient enter particular information. The disease management server 130 may send request for particular information to be entered by the patient using the input device 110. The input device 110 may prompt the user to enter the particular information. The request sent by the disease management server 130 may be in the form of surveys designed to collect particular information. The surveys may be targeted to collect information about a patient's dietary behavior (e.g., carbohydrate intake, portion control), self-monitoring of blood glucose, medication doses, physical activity, psychological status, alcohol intake, smoking activity, and any other information that might effect the patient's well being. The input device 110 may prompt the patient to enter information by displaying the survey and receiving the patient's responses to the questions posed in the survey. The scripts may also be designed to educate the patient or to promote positive behavior/behavior modification by the patient.

The transmitter 120 may send the patient data collected by the input device 110 to the disease management server 130 immediately after the data is entered into the input device 110 by the patient.

As shown in FIG. 1, disease management server 130 may include a receiver 131, a processor 132, and an output device 133. The receiver 131 may receive patient data from the transmitter 120. The processor 132 may execute a program for generating/maintaining a modified model for a patient and developing treatment recommendations for the patient using the model based on the patient data. The output device 133 may output information to either the patient, a third party health care provider, or a remote device based on the treatment recommendations developed by the processor 132.

The processor 132 may generate a modified model for the patient based on the patient data the disease management server 130 receives through the receiver 131. The modified model may be used to estimate impact of a change in the patient's regimen (e.g., medication, food intake, physical activity) on the physiological system of the patient. The processor may generate a modified model for the patient by executing a basic model. A basic model models a physiological system of a patient based on established knowledge of disease dynamics and factors. The patient data is used to generate the modified model for a particular patient. The modified model can provide guidance to improve the patient's regimen and to gain a better understanding of how a particular patient is being affected by a disease dynamic. The use of patient data over an extended period of time allows the modification and improvements of the modified model as more data is collected for a particular patient. The modified model may also be used even when limited/incomplete patient data is received.

After the generation of a modified model, the processor 132 may perform a statistical analysis of patient data to detect data excursions. A data excursion is an event in which a value of a parameter (e.g., blood glucose level) is outside the normal/expected range for the parameter, The processor 132 may use the modified model it generated to determine the factors causing the data excursions and the effects of such data excursions. The modified model may then be used to develop a plurality of treatment recommendations to ameliorate negative effects of the disease. The output device 133 within the disease management server 130 may output information based on the treatment recommendations to the patient, a device relate to the patient, or a third party.

FIG. 2 is a flowchart of an exemplary method 200, consistent with an embodiment of the present invention. Method 200 may be executed on a system illustrated in FIG. 1. According to the method, at step 201, the input device 110 may collect patient data. At step 202, the transmitter 120 may transmit the patient data to the disease management server 130. At step 203, the disease management server 130 may generate a modified model for the patient. At step 204 the disease management server 130 may develop treatment recommendations for the patient using the modified model generated at step 203. At step 205 the disease management server 130 may deploy treatment recommendations developed at step 204, by using the output device 133.

FIG. 3 is a flowchart of another exemplary method 300, consistent with an embodiment of the present invention. Method 300 depicts an example of an input device 110 receiving patient data. Steps 301, 303, 304, 305 of this method may be performed in no particular order. Steps 301, 303, 304, 305 present a limited set of examples of the different patient data that can be collected and how it may be collected by an input device 110.

At step 301, the input device 110 may receive data collected by one or more biometric measurement devices. The input device 110 may receive the data collected by one or more biometric measurement devices every time a measurement occurs by the biometric measurement device, at a certain predetermined interval, or when the input device is prompted to collect the biometric measurement data. Alternatively, as discussed above, at step 301, the biometric measurement data may be entered by the patient into the input device 110.

At step 302, the input device may prompt the user to enter specific information pertaining to factors that can effect the well being of the patient. The patient may be prompted to enter such information by being asked a series of questions. The patient may receive reminders through the input device to enter certain type of information at a certain time. Step 302 may repeat several times to collect different types of data from the patient at steps 301, 303, 304, 305.

At step 303, the input device 110 may receive information about the patient's dietary behavior. This information may be simply entered by the patient on a regular basis using the input device. The patient may use a remote workstation to enter the information and have it transferred to the input device. The information may be entered in response to the prompt(s) at step 302. The information may be received from a device that can track a patient's dietary behavior. An example of such a device is a food/drink caloric intake calculator. The calculator may be implemented, for example, on a cell phone, and a patient may enter information regarding his/her dietary behavior into the cell phone. Alternatively, the calculator may be part of the input device. The information may also be received by the input device 110 from a restaurant where the patient eats. Another example is a camera-based food calculator. The input device 110 may be able to receive pictures of food eaten by the patient. Image recognition techniques may later be used to identify the food consumed by the patient, and determine the carbohydrate intake of the patient for example.

At step 304, the input device 110 may receive information about what medications the patient is taking, at what doses, and at what times. The patient may simply enter the information to be received by the input device independently, or the patient may enter the information in response to a prompt at step 302. The input device 110 may also be connected to other devices, and may receive information regarding the patient's medication intake from the other devices.

At step 305, the input device 110 may receive any other pertinent information from the patient that may assist successful disease management. This information may be received directly from the patient, a health care provider, a monitoring device, a third party, etc. A person can be prompted by the input device 110 to enter the information. Examples of information that may be collected may relate to the patient's exercise, smoking, alcohol intake, etc.

The input device 110 may also receive information from the patient at steps 301, 303, 304, and 305 regarding patients attitude towards modifying behavior that affects the respective data received at each step.

FIG. 4 is a flowchart of another exemplary method 400, consistent with an embodiment of the present invention. Method 400 depicts an example of a disease management server 130 generating treatment recommendations for a patient. At step 401, a receiver 131 of the disease management server 130 receives patient data from a transmitter 120. The patent data is collected by input device 110 (see FIG. 3) and transmitted by transmitter 120 from the input device 110 to the disease management server 130. Steps 402, 403, 404, 405 may be performed by a processor 132 in the disease management server.

At step 402, the disease management server 130 uses the patient data to generate a modified model of the patient's physiological system. The modified model may be used to estimate the impact of a change of a certain factor (data) on the patient (other data). The modified model represents the effects of a change in different data on the particular patient's physiological system, and in turn how the physiological system of the patient effects the data. The modified model may be a previously generated modified model updated based on new patient data. The model is generated by executing a basic model based on the patient data (402). The basic model represents the minimal assumptions and parameters of a person's physiological system and the correlation of certain factors. How the factors interact and correlate is different for different patients. The patient data is used to adjust the basic model and generate a modified model for a particular patient. The more patient data is collected over time, the more accurate the modified model is for the particular patient. In addition, the collection of data from multiple patients may be used to improve the basic model.

At step 403, the disease management server 130 performs a statistical analysis to detect data excursions in the patient data. A data excursion may be indicated when certain data collected at a certain time is outside the normal range that can be expected for that data for the particular patient. For example, a data excursion may be a blood glucose measurement that is outside the normal blood glucose range for the particular patient.

At step 404, the disease management server 130 uses the modified model generated at step 402 to determine the factors causing the data excursions detected at step 403. For example, the disease management server 130 may determine if a change in amount of timing of medication or food intake of the patient caused the data excursion of blood glucose measurement.

At step 405, the disease management server 130 may develop treatment recommendations to ameliorate negative effects of the patient's disease. The disease management server 130 may use the modified model to determine the treatment recommendations which are optimal for the patient. For example, if a data excursion caused a negative effect on the patient, a treatment recommendation may be developed to prevent such a data excursion in the future. Examples of treatment recommendations may include adjusting food or medication intake, adjusting how and what data is collected, advising the patient to modify certain behaviors, providing educational materials to the patient, alerting the patient's health care provider, etc.

At step 406, the output device 133 of disease management server 130 may output the treatment recommendations developed at step 405. The treatment recommendations are transmitted to the appropriate party or device. For example, a treatment recommendation to increase the patient's insulin dose can be transmitted directly to the insulin-delivery device (pump). If, for example, the treatment recommendation is to collect certain additional data about the patient to provide optimal treatment recommendations in the future, a script can be transmitted to the patient through the input device 110 to collect the additional data at certain times.

FIG. 5 is an exemplary diagram showing a generation of a modified model for a patient, consistent with an embodiment of the present invention. The modified model is generated by the basic model. The diagram, in effect, is representing the basic model. The model in this embodiment focuses on the primary factors that impact the daily blood glucose (BC) of a patient: carbohydrate intake, insulin level of the patient, and glucose inventory of the patient. The model inherently includes within these primary factors the complex interactions of the hormonal-signaling network that supports the endocrine processes. First, it is necessary to determine the carbohydrate intake 501, insulin level 503, and glucose inventory 505 of the patient to generate the model. The patient data is used to determine the respective primary factors. The carbohydrate intake is determined based on the amount of carbohydrates ingested by the patient that become the primary source of blood glucose for the patient (501). The insulin level of the patient is determined on a variety of factors including dosing, pancreatic production, and kinetics (505, see FIG. 6 for further detail). The glucose inventory is determined based on the glucose stored in the liver, skeletal muscle, and fat tissues of the patient (506).

After determining the carbohydrate intake of the patient, an impact of the carbohydrate intake (carbs) on concentration of the blood glucose may be modeled (502). This may be modeled based on the following equation for instantaneous blood glucose concentration:

$\frac{d\left[\mathrm{BG}\right]}{\mathrm{dt}}=\beta \frac{d\left[\mathrm{carbs},\mathrm{BG},\mathrm{incretins}\right]}{\mathrm{dt}},$

wherein [BG] may be blood glucose (BG) concentration, [carbs] may be represented as a first order kinetics function of time (t), β may be for example about 5 BG units/carbohydrate unit, and incretins are the digestive-activated hormones of the patient.

The impact of insulin on transfer of blood glucose into patient's cells (504) is accounted for in the modified model. Insulin is accounted for as a catalyst, not as a compound that forms with blood glucose. The instantaneous rate decrease of blood glucose concentration from instantaneous insulin concentration in blood may be modeled based on the following equation:

$-\frac{d\left[\mathrm{BG}\right]}{\mathrm{dt}}=\alpha \left(t\right)\times \left[\mathrm{BG}\right]\left[\mathrm{insulin}\right],$

wherein [insulin] may be the instantaneous insulin concentration in blood, α includes resistance impact of diabetes and is about 0.3 if rate is −50 BG units/insulin unit above BG of 140, and α(t) includes diurnal variations. Alternatively, α(t) may be approximated without any time dependence, using the 24 hour mean.

Finally, it is necessary to account for the impact of the glucose inventory (IG) on the blood glucose (BG) (506), where the glucose inventory absorbs blood glucose on storage and release blood glucose on retrieval (mass action kinetics). This may be modeled based on the following equation:

$\frac{d\left[\mathrm{BG}\right]}{\mathrm{dt}}=-\frac{d\left[\mathrm{IG}\right]}{\mathrm{dt}},$

where

$\frac{d\left[\mathrm{IG}\right]}{\mathrm{dt}}-\gamma \left(\left[\mathrm{IG}\right]+\frac{\left\{-\left[\mathrm{BG}\right]-\left[\mathrm{IG}\right]\right\}}{\left\{1+\exp \left(\omega \left\{\tau -\alpha \left[\mathrm{insulin}\right]\right\}\right)\right\}}\right),$

wherein r is the threshold; if resistant insulin is greater then the threshold, then blood glucose decreases by going into liver and fat as glucose storage (IG) and is not released through the liver. And wherein γ relates concentration of glucose to changes in IG. The IG functionality may be modeled by other similar forms at the conceptual level since the phenomenological description is inclomplete.

The total change in blood glucose over a time interval (508) may be modeled based on the sum of the three factors 502, 504, 506 described above. The complete basic model may be based on the following equation (509):

$\frac{d}{\mathrm{dt}}\mathrm{BG}\left(t\right)=\left[\left[\beta \left(\frac{d}{\mathrm{dt}}\mathrm{carbs}\left(t\right)\right)-\alpha ·\mathrm{BG}\left(t\right)·\mathrm{insulin}\left(t\right)\right]-\frac{d}{dt}\mathrm{IG}\left(t\right)+\mathrm{errors}\right],$

where the storage or release of blood glucose as mediated by resistant insulin may be expressed in the following equation:

$\frac{d}{\mathrm{dt}}\mathrm{IG}\left(t\right)=-\gamma \left[\mathrm{IG}\left(t\right)+\frac{\left(-\mathrm{BG}\left(t\right)-\mathrm{IG}\left(t\right)\right)}{[1+\exp \left[W·\left(\tau -B·\mathrm{insulin}\left(t\right)\right]\right]}\right],$

wherein W is the switching rate (i.e., the rate that IG switches from intake mode to output mode of BG). Errors may account for any additional or unknown factors besides the primary factors (507). Statistical methods may be used to estimate model parameters and their expected variations for a patient.

The model can then be used to determine factors causing the data excursions 404. The relative contributions of the primary factors may vary over the 24 hour day, especially adjacent to meals and fasting events. For example, the fasting segments of the BG profile between meals would see little impact from the carbohydrates (502), and, if in addition, insulin levels are near their norm's as defined by its storage threshold, then insulin (504) becomes the dominant effect. Hence, this allows an estimation of the a parameter and the insulin profile of the patient based on the model. The dosing profile is known (503), and comparison with the estimated profile provides information on pancreatic activity. Under these conditions, one can also test if a changes among different fasting events. The testing can be accomplished through a treatment recommendation. The model provide a guide for timely regimen optimization for the particular patient. The optimization is based on a minimal-assumption model (MAM) that fits the major features in the data patterns of the patient. The MAM for BG data patterns may be expressed, for example, as follows: BG =MAM(t, injections, orals, digestion, diurnals, activity, liver processes, immune reaction, beta islets) +error.

Given α, one can estimate inventory parameters from the segments of the model capturing fasting events at non-normal levels of insulin. With these two sources established, one can now estimate the impact of carbohydrates during meals, since carbohydrates kinetics are known. Similarly, the MAM may be used to determine the effect on the patient's BG of changing other factors (ex. medications). A key feature of MAM is that it can model answers to “what if” questions for each individual patient given any scenario of lifestyle and treatment regimen/conditions over any interval of time both retrospectively and prospectively.

FIG. 6 is a diagram showing a determination of the insulin of a patient (503), consistent with an embodiment of the present invention. The insulin of a patient may be calculated 604 based on the insulin from the medication received by the patient 601, the insulin produced by the patient's pancreatic beta cells 602, and mass action kinetics of insulin 603. The effect of mass action kinetics on insulin may be accounted for, based on the following formula: insulin(t)=D (dbeta [0.3(t−0.5), 2.1, 7]+E), wherein D is the units of insulin dose received by the patient, and wherein E is the approximate equilibrium level of 24 hour SA insulin. Optionally, one may use kinetics models to create the insulin dosing profiles. The insulin profile may take into account the difference between long-acting and short-acting kinetics that vary based on the source of the insulin.

The foregoing description has been presented for purposes of illustration. It is not exhaustive and does not limit the invention to the precise forms or embodiments disclosed. Modifications and adaptations of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the disclosed embodiments of the invention. For example, the described implementations include software, but systems and methods consistent with the present invention may be implemented as a combination of hardware and software or in hardware alone. Examples of hardware include computing or processing systems, including personal computers, servers, laptops, mainframes, micro-processors and the like. Additionally, although aspects of the invention are described for being stored in memory, one skilled in the art will appreciate that these aspects can also be stored on other types of computer-readable media, such as secondary storage devices, for example, hard disks, floppy disks, or CD-ROM, the Internet or other propagation medium, or other forms of RAM or ROM.

Computer programs based on the written description and methods of this invention are within the skill of an experienced developer. The various programs or program modules can be created using any of the techniques known to one skilled in the art or can be designed in connection with existing software. For example, program sections or program modules can be designed in or by means of Java, C++, HTML, XML, or HTML with included Java applets. One or more of such software sections or modules can be integrated into a computer system or existing e-mail or browser software.

Moreover, while illustrative embodiments of the invention have been described herein, the scope of the invention includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of aspects across various embodiments), adaptations and/or alterations as would be appreciated by those in the art based on the present disclosure. The limitations in the claims are to be interpreted broadly based on the language employed in the claims and not limited to examples described in the present specification or during the prosecution of the application, which examples are to be construed as non-exclusive. Further, the steps of the disclosed methods may be modified in any manner, including by reordering steps and/or inserting or deleting steps, without departing from the principles of the invention. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims and their full scope of equivalents.

Claims

1-25. (canceled)

26. A system for creating and updating one or more models for providing treatment recommendations for health conditions, comprising: a weight measuring device configured to obtain weight measurements and to wirelessly transmit the obtained weight measurements; anda disease management server in wireless communication with the weight measuring device, the disease management server including: a receiver for receiving the weight measurements transmitted from the weight measuring device, and configured to receive user data from a user device; andone or more processors configured to:execute a basic model based on information regarding the health condition, to generate treatment recommendations;generate reminders to be transmitted to at least one of the user device and the weight measuring device, the reminders prompting the user to use the weight measuring device to obtain weight measurements;estimate, based on the received weight measurements, an impact of the user data on the weight measurements;generate a modified model, based on the basic model, the received weight measurements, the received user data, and the estimated impact of the user data, the modified model including personalized treatment recommendations specific to the user; andan output device, including a transmitter, configured to transmit the reminders, the treatment recommendations, and the personalized treatment recommendations to the user device.

27. The system according to claim 26, wherein the receiver receives the weight measurements every time the weight measuring device transmits a weight measurement to the disease management server.

28. The system according to claim 26, wherein the receiver receives the weight measurements at predetermined intervals.

29. The system according to claim 26, wherein the user data includes a food and drink caloric intake and exercise data of the user.

30. The system according to claim 26, wherein the personalized treatment recommendations include one or more of advice to modify behavior and educational materials.

31. A computer-implemented method for creating and updating one or more models for providing treatment recommendations for health conditions, the method comprising: receiving, using a receiver of a disease management server, weight measurements from a weight measuring device wirelessly connected to the disease management server, and user data of the user, from a user device;executing, using one or more processors of the disease management server, a basic model based on information regarding the health condition, to generate treatment recommendations;generating, using the one or more processors, reminders to be transmitted to at least one of the user device and the weight measuring device, the reminders prompting the user to use the weight measuring device to obtain weight measurements;estimating, using the one or more processors, based on the received weight measurements, and the received user data, an impact of the user data on the weight measurements;generating, using the one or more processors, a modified model, based on the basic model, the received weight measurements, the received user data, and the estimated impact of the user data, the modified model including personalized treatment recommendations specific to the user; andoutputting, using a transmitter, the reminders, the treatment recommendations, and the personalized treatment recommendations to the user device.

32. The method according to claim 31, wherein the weight measurements are received every time the weight measuring device transmits a weight measurement to the disease management server.

33. The method according to claim 31, wherein the weight measurements are received at predetermined intervals.

34. The method according to claim 31 wherein the user data includes a food and drink caloric intake and exercise data of the user.

35. A system for creating and updating one or more models for providing treatment recommendations for health conditions, comprising: a glucose measuring device configured to obtain glucose measurements from a user, and to wirelessly transmit the obtained glucose measurements; anda blood pressure measuring device configured to obtain blood pressure measurements from the user, and to wirelessly transmit the obtained blood pressure measurements;a weight measuring device configured to obtain weight measurements from the user, and to wirelessly transmit the obtained weight measurements; anda disease management server in wireless communication with the glucose measuring device, the blood pressure measuring device, and the weight measuring device, the disease management server comprising: a receiver for receiving the glucose measurements, the blood pressure measurements, the weight measurements, and user data, from a user device; andone or more processors configured to: execute one or more models of a physiological system generic to any user to generate treatment recommendations for the user, including one or more of adjusting a timing of obtaining the glucose measurements or adjusting a timing of obtaining the blood pressure measurements, and to generate reminders to be transmitted to at least one of the glucose measuring device, the blood pressure measuring device, or the user device, the reminders prompting the user to use at least one of the glucose measuring device to obtain glucose measurements, the blood pressure measuring device to obtain blood pressure measurements, or the weight measuring device to obtain weight measurements;generate one or more modified models specific to a physiological system of the user based on the received glucose measurements, the received blood pressure measurements, the received weight measurements, or the received user data, wherein generating the one or more modified models comprises updating the one or more models based on the received glucose measurements, the received blood pressure measurements, the received weight measurements, or the received user data, the one or more modified models including personalized treatment recommendations specific to the user, the personalized treatment recommendations including at least one or more of adjusting a timing of obtaining glucose measurements, adjusting a timing of obtaining blood pressure measurements, or adjusting a timing of obtaining the weight measurements;execute the one or more modified models to generate personalized treatment recommendations, based on the one or more modified models, the personalized treatment recommendations including one or more of adjusting a timing of obtaining the glucose measurements, adjusting a timing of obtaining the blood pressure measurements, or adjusting a timing of obtaining the weight measurements;execute a statistical analysis of at least the received glucose measurements, the received blood pressure measurements, or the received weight measurements, to determine if at least one of the received glucose measurements, the received blood pressure measurements, or the received weight measurements includes at least one data excursion, including at least one measurement value that is outside a predetermined range of glucose values, a predetermined range of blood pressure values, or a predetermined range of weight values, respectively;generate one or more updated modified models, based on the one or more modified models, upon determining, in the statistical analysis, that at least one of the received glucose measurements, the received blood pressure measurements, or the received weight measurements includes at least one data excursion, wherein generating the one or more updated modified models comprises updating the one or more modified models based on the received glucose measurements, the received blood pressure measurements, the received weight measurements, or the statistical analysis;execute the one or more updated modified models, to generate updated personalized treatment recommendations, including one or more of adjusting a timing of obtaining the glucose measurements, adjusting a timing of obtaining the blood pressure measurements, or adjusting a timing of obtaining the weight measurements; andoutput the treatment recommendations, the reminders, the personalized treatment recommendations, and the updated personalized treatment recommendations to the user device.

36. The system according to claim 35, wherein the receiver receives a glucose measurement from the glucose measurement device every time a glucose measurement is obtained, a blood pressure measurement from the blood pressure measuring device every time a measurement is obtained, and a weight measurement from the weight measuring device every time a weight measurement is obtained.

37. The system according to claim 35, wherein the receiver receives each of the obtained glucose measurements, blood pressure measurements, and weight measurements at predetermined intervals.

38. The system according to claim 35, wherein the user data includes a food and drink caloric intake and exercise data of the user.

39. The system according to claim 38, wherein at least one of the personalized treatment recommendations and the updated personalized treatment recommendations further includes exercise recommendations for the user.

40. The system according to claim 38, wherein at least one of the personalized treatment recommendations and the updated personalized treatment recommendations further includes one or more of advice to modify behavior or educational materials.

41. The system according to claim 35, wherein the one or more processors are further configured to output an alert to a provider associated with the user.

42. The system according to claim 41, wherein the one or more processors output an alert to the provider associated with the user when a measurement value of at least one of the received glucose measurements, the received blood pressure measurements, and the received weight measurements is outside a range of normal measurement values.

43. The system according to claim 35, wherein the glucose measuring device transmits the glucose measurements, the blood pressure measuring device transmits the blood pressure measurements, the weight measuring device transmits the weight measurements, and the disease management server transmits the treatment recommendations, the personalized treatment recommendations, and the updated personalized treatment recommendations, via one of a cellular channel or a wireless network.

44. The system according to claim 35, wherein the glucose measuring device is a continuous glucose monitor.

45. The system according to claim 35, wherein at least one of the personalized treatment recommendations and the updated personalized treatment recommendations includes adjusting a medication intake.