METHOD AND SYSTEM TO OPTIMIZE THERAPY EFFICACY

Abstract

A method of optimizing treatment of a condition includes monitoring one or more characteristics of a patient associated with a condition of the patient, predicting a severity of the condition of the patient, recommending a selected therapy to the patient based on a therapy-severity map, evaluating an actual severity of the condition of the patient, evaluating an efficacy of the selected therapy, and updating the therapy-severity map based on the evaluated efficacy of the therapy.

Description

CROSS-REFERENCE TO PRIOR APPLICATIONS

This application claims the benefit of U.S. Provisional Application No. 63/054,197, filed on 20 Jul. 2020. This application is hereby incorporated by reference herein.

BACKGROUND OF THE INVENTION

1. Field of the Invention

The disclosed concept generally relates to therapy and, more particularly, to optimizing therapy efficacy.

2. Description of the Related Art

Restless Legs Syndrome (RLS) has been estimated to impact between 3.9 to 14.3% of the adult population. Diagnosis of RLS requires the patient to express an urge to move the legs, typically associated with accompanying unpleasant sensations that begin to worsen as the patient remains still for an extended period of time. Typically the urge to move the legs is worse during the evening and night than during the day (most often at sleep onset) and is temporarily relieved by movement. RLS symptoms typically need to occur at least 2×/week and have significant side effects (e.g. daytime sleepiness, mood issues, etc.) in order to be considered for clinical treatment. The prevalence of RLS is significantly higher in women than in men and is a common disorder during pregnancy, especially toward the third trimester.

RLS can be treated with iron supplementation, dopamine agonists, alpha-2-delta calcium channel ligands, as well as nonpharmacologic interventions, like ensuring good sleep hygiene, avoiding caffeine, and getting regular low-intensity exercise. Also, avoiding exacerbating factors, like sleep deprivation or antidepressants.

As RLS symptoms typically vary on a night-to-night basis, different therapies are effective for different patients (and potentially at different times), and because popular pharmacotherapy (i.e. dopamine agonists) has a risk of augmentation with extended usage, many RLS sufferers could benefit from a system that offers daily therapy recommendations based upon predicted severity and efficacy of an intervention.

There remains room for improvement in treatment for RLS or other conditions.

SUMMARY OF THE INVENTION

Accordingly, it is an object of the disclosed concept to provide a system and method optimize treatment of conditions such as RLS or other conditions.

As one aspect of the disclosed concept, a method of optimizing treatment of a condition comprises: monitoring one or more characteristics of a patient associated with a condition of the patient; predicting a severity of the condition of the patient; recommending a selected therapy to the patient based on a therapy-severity map; evaluating an actual severity of the condition of the patient; evaluating an efficacy of the selected therapy; and updating the therapy-severity map based on the evaluated efficacy of the selected therapy.

As one aspect of the disclosed concept, a system for optimizing treatment of a condition comprises: one or more sensing modules structured to monitor one or more characteristics of a patient associated with a condition of the patient; a severity prediction engine structured to predict a severity of the condition of the patient; a therapy recommendation module structured to recommend a selected therapy to the patient based on a therapy-severity map; an actual severity evaluation module structured to evaluate an actual severity of the condition of the patient; a therapy efficacy evaluation module structured to evaluate an efficacy of the selected therapy; and a personalized therapy-severity map update module structured to update the personalized therapy-severity map based on the evaluated efficacy of the selected therapy.

As one aspect of the disclosed concept, a non-transitory computer readable medium storing one or more programs, including instructions, which when executed by a computer, causes the computer to perform a method of optimizing treatment of a condition. The method comprises: monitoring one or more characteristics of a patient associated with a condition of the patient; predicting a severity of the condition of the patient; recommending a selected therapy to the patient based on a therapy-severity map; evaluating an actual severity of the condition of the patient; evaluating an efficacy of the selected therapy; and updating the therapy-severity map based on the evaluated efficacy of the selected therapy.

These and other objects, features, and characteristics of the disclosed concept, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate corresponding parts in the various figures. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a flowchart of a method of optimizing therapy in accordance with an example embodiment of the disclosed concept;

FIG. 2 is schematic diagram of a system for optimizing therapy in a build phase in accordance with an example embodiment of the disclosed concept;

FIG. 3 is a schematic diagram of a system for optimizing therapy in a deployment phase in accordance with an example embodiment of the disclosed concept;

FIG. 4 is a flowchart of a method for building a severity prediction engine in accordance with an example embodiment of the disclosed concept; and

FIG. 5 is a schematic diagram of a system for building a severity prediction engine in accordance with an example embodiment of the disclosed concept.

DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS

As required, detailed embodiments of the disclosed concept are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention, which may be embodied in various forms. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the disclosed concept in virtually any appropriately detailed structure.

As used herein, the singular form of “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.

Directional phrases used herein, such as, for example and without limitation, top, bottom, left, right, upper, lower, front, back, and derivatives thereof, relate to the orientation of the elements shown in the drawings and are not limiting upon the claims unless expressly recited therein.

In accordance with an embodiment of the disclosed concept, optimized and personalized therapy recommendations are provided. For example, a personalized therapy-severity map is generated recommending therapies corresponding to the severity of the patient's condition. The patient is also monitored over time and the efficacy of therapy is evaluated. The personalized therapy-severity map may then be updated to reflect the efficacy of various therapies. In this manner, the most effective therapy corresponding to the severity of the patient's condition may be recommended. In an example embodiment, the severity of the patient's condition can also be predicted and a therapy corresponding to the predicted severity can be recommended. While the disclosed concept with be described with respect to RLS, it will be appreciated that the disclosed concept is also applicable to other conditions.

FIG. 1 is a flowchart of a method of optimizing therapy in accordance with an example embodiment of the disclosed concept. The method begins at 100 where a number of behavior and/or biometrics are monitored. The monitored behavior and/or biometrics may include RLS objective metrics such as, without limitation, leg movement frequency, intensity, and duration. The monitored behaviors and/or biometrics may include sleep metrics such as, without limitation, sleep efficiency, wake after sleep onset, sleep onset latency, total sleep time, a number of awakenings, and sleep stages. The monitored behaviors and/or biometrics may include alertness metrics such as, without limitation, nap frequency, nap duration, movement, movement intensity, and behaviors. The monitored behaviors and/or biometrics may include behaviors such as, without limitation, sleep hygiene, caffeine intake frequency and timing, and medication intake. The monitored behaviors and/or biometrics may be monitored with one or more sensors such as, without limitation, under mattress and/or wearable sensors. The monitored behaviors and/or biometrics may also be monitored by patient provided subjective responses. The patient response may be gathered through any suitable means such as, without limitation, a digital survey, a chat bot, or any other suitable means for gathering subjective responses.

At 102, the severity of the patient's condition is predicted. The prediction may be made for any for a specified period after the prediction. In an example embodiment, a prediction is made for the severity for the upcoming night period. However, it will be appreciated that a prediction may be made for a different time period without departing from the scope of the disclosed concept. In an embodiment, the severity is predicted based on one or more of the monitored behaviors and/or biometrics. In an embodiment, the severity is predicted based on monitored behaviors, sleep metrics, and alertness metrics.

The severity of the patient's condition may be predicted using a severity prediction engine. The severity prediction engine may be, for example and without limitation, a machine learning model built based on the monitored behaviors and/or biometrics. Building the severity prediction engine in an embodiment of the disclosed concept will be described in more detail with respect to FIGS. 4 and 5.

The predicted severity of the patient's condition may be categorized in predetermined levels. In an embodiment, the predetermined levels include mild, moderate, severe, and very severe. In an embodiment, the predetermined levels of mild, moderate, severe, and very severe are based on the International RLS Rating Scale.

At 104 a therapy is recommended to the patient. As part of recommending a therapy, a therapy-severity map is generated. The therapy-severity map corresponds a set of therapies to the severity of the patient's condition. Additionally, the therapy-severity map provides an efficacy of the therapy. An example therapy-severity map is provided below in Table 1.

	TABLE 1
	RLS Severity		Past
	Level	Therapy ID	Efficacy
	very severe	7	78
	very severe	9	65
	moderate	4	80
	moderate	11	70
	moderate	2	50
	severe	1	75
	severe	8	68
	severe	6	60
	mild	3	90
	mild	5	84
	mild	10	77

As shown in the example therapy-severity map, each severity level includes a number of corresponding therapies (e.g., very severe has corresponding therapy IDs 7 and 9). Each therapy also has a corresponding efficacy. The therapy recommended to the patient will be the therapy corresponding to the predicted severity with the highest efficacy. In an embodiment, multiple therapies may be recommended to the patient. For example, the most effective therapy may be recommended to the patient, but also other therapies corresponding to the predicted therapy may be presented as options in the case that the patient may not want to use the most effective therapy.

In an embodiment, the therapies may be a single therapy or a combination of therapies. That is, a particular therapy ID may correspond to a single therapy or a combination of therapies. It will also be appreciated that the therapy recommendation may be that no therapy is required, which may be the case when the predicted severity is low. When the method is applied to treatment of RLS, the recommended therapy for lower levels of severity may be the use of RLS therapy devices and the recommended therapy for higher levels of severity may include medications. For example, a therapy ID may correspond to a therapy of using a particular RLS therapy device, and may also include a particular time and/or duration of usage. Similarly, a therapy ID may correspond to a therapy of taking a particular medication, and may also include a particular dose and time. For example, one therapy ID may correspond to a 0.25 mg/d dose of Pramipexole at 8:00 PM and another therapy ID may correspond to a 0.5 mg/d does of Pramipexole at 7:00 PM. It will also be appreciated that therapy ID may correspond to a combination of therapies, such as both medication and usage of an RLS therapy device. While some examples have been provided of therapies for treatment of RLS, it will be appreciated that the method may also be employed for treatment of other conditions.

The initial therapy-severity map may be a default map based on population data such as, without limitation, clinical study results and review articles. As will be described in more detail herein, as the patient is monitored and utilizes therapies, the therapy-severity map will be updated based on the efficacy of the therapies for the patient, making the therapy-severity map personalized to the patient over time.

At 106 the actual severity of the patient's condition is evaluated. In an embodiment, the actual severity of the patient's condition is evaluated based on monitored biometrics during a specified monitoring period. For example, objective RLS physiological measures such as, without limitation, movement intensity, duration, and frequency may be monitored using one or more sensors. The physiological measures may be monitored while the recommended therapy is applied to the patient. For example, the physiological measures may be monitored at night when the therapy is applied to the patient. From the monitored physiological measures, the actual severity of the patient’ condition may be evaluated. In an example embodiment, the actual severity level may have the same predetermined levels as the predicted severity level described above (e.g., mild, moderate, severe, or very severe).

At 108, the efficacy of the therapy is evaluated. The efficacy of the therapy may be based on a number of factors such as, without limitation, a reduction score of severity, a sleep quality score, and an alertness score. The reduction score may include a comparison of the predicted severity (e.g., predicted before night) and the actual severity (e.g., measured during the night while a therapy is in use). The reduction score may be based on a ratio of the actual to predicted severity or a difference between the predicted and actual severity. In an example embodiment, the reduction score may be within a range of 0 to 100, with a score of 100 being the most effective.

The sleep quality score may be based on a number of sleep metrics such as, without limitation, sleep efficiency, wake after sleep onset, number of awakenings, sleep onset latency, deep sleep percentage, and total sleep time. The sleep metrics may be monitored while the therapy is in use. In an example embodiment, the sleep quality score may be within a range of 0 to 100, with a score of 100 being the most effective.

The alertness score may be based on a number of metrics such as, without limitation, number of naps, duration of naps, movements, movement intensity, and behaviors. The metrics for the alertness score may be monitored during the day. In an example embodiment, the alertness score may be within a range of 0 to 100, with a score of 100 being the most effective.

While a reduction score, sleep quality score, and alertness score are provided as examples of factors that can be used to evaluate the efficacy of a therapy, it will be appreciated that different factors may be employed. The various factors may be weighted differently to determine the therapy efficacy. For example, in an embodiment, the reduction score and sleep quality score are weighted higher than the alertness score. However, it will be appreciated that different weightings may be used without departing from the disclosed concept.

After the efficacy of a therapy used by the patient is evaluated, the therapy-severity map is updated at 110. For example, the default therapy-severity map may be updated as the efficacy of a therapy for the particular patient is evaluated. The default therapy efficacy can then be replaced with the evaluated efficacy of the therapy. For example, the efficacy of a therapy for a particular patient may be different than how effective the therapy is expected to be based on population data. In this manner, over time, the therapy-severity map for the patient becomes personalized based on how effective different therapies are for that patient in particular.

At 112, the severity prediction engine is updated. For example, in an embodiment, the monitored behavior and/or biometrics can be used over time to update the severity prediction engine to improve its ability to predict the severity of the patient's condition.

In some embodiments, one or more steps of the method may be omitted or modified. For example, the method may have a build phase where therapies are recommended by a therapy provider. As the patient uses therapies, the efficacies of the therapies may be evaluated through monitoring of the patient and the therapy-severity map for the patient evolves from a default therapy-severity map to a personalized therapy-severity map. Over time, as the patient has tried different therapies, the method may move to a deployment phase where the personalized therapy-severity map is used to recommend a therapy.

The method may be implement by one or more computing devices, memories, and sensors. For example, monitoring the behaviors and/or biometrics of the patient may be implemented with sensors such as under mattress and/or wearable sensors as well as any suitable computing device for inputting subjective patient responses. The method may be implemented on a localized or distributed system. For example, one or more parts of the method may be implemented on a user device, such as a mobile phone, tablet, or computer, as well, parts of the method may be implemented on a remote device such as a server. For example, the personalized therapy-severity map may be stored on the user device or on a server. Some examples of systems for implementing parts of the method will be described in more detail herein.

FIG. 2 is schematic diagram of a system 200 for optimizing therapy in a build phase in accordance with an example embodiment of the disclosed concept. The system 200 includes an alertness sensing module 202, a sleep metrics sensing module 204, a predicted RLS severity module 206, an RLS metrics monitoring module 208, a selected therapy module 210, a therapy efficacy evaluation module 212, an actual RLS severity evaluation module 214, and a build personalized therapy-severity map module 216.

The alertness sensing module 202 may sense metrics associated with alertness such as nap frequency, nap duration, movement, movement intensity, and behaviors. The alertness sensing module 202 may include or receive outputs from one or more sensors such as under mattress and/or wearable sensors. The sleep metrics sensing module 204 may sense metrics associated with sleep quality such as sleep efficiency, wake after sleep onset, sleep onset latency, total sleep time, number of awakenings, and sleep stages. The sleep metrics sensing module may include or receive outputs from one or more sensors such as under mattress and/or wearable sensors. The RLS metrics monitoring module 208 may sense objective metrics associated with RLS such as leg movement frequency, intensity, and duration. The RLS metrics monitoring module 208 may include or receive output from one or more sensors such as under mattress and/or wearable sensors. Together, the alertness sensing module 202, sleep metrics sensing module 204, and RLS metrics monitoring module 208 may be used to monitor biometrics of a patient.

The predicted RLS severity module 206 may include a severity prediction engine. The predicted RLS severity module 206 may predict the severity of the patient's RLS. The predicted RLS severity module 206 may use the monitored biometrics of one or more of the alertness sensing module 202, the sleep metrics sensing module 204, and the RLS metrics monitoring module 208 to predict the severity of the patient's RLS.

The selected therapy module 210 may identify the selected therapy for the patient. For example, the selected therapy module 210 may receive information on the selected therapy. The actual RLS severity module 214 is structured to estimate the actual severity of the patient's RLS. The actual severity may be estimated based on the objective RLS metrics monitored by the RLS metrics monitoring module 208. The therapy efficacy evaluation module 212 is structured to evaluate the efficacy of the therapy. The efficacy may be evaluated as described above with respect to FIG. 1. The build personalized therapy-severity map module 216 is structured to build a personalized severity-therapy map for the patient based on the selected therapy, the actual RLS severity, and the evaluated efficacy of the therapy. As described above, the severity-therapy map corresponds therapies with levels of severity and includes an evaluation of the efficacy of the therapy.

The system 200 may be implemented as one or more computing devices and sensors. The system 200 may be a localized or distributed system. The system 200 is an example of a build phase, where a selected therapy is provided and its efficacy is evaluated. As the system 200 is used, the therapy-severity map becomes more personalized. The system 200 may then transition to or be replaced by a different system in a deployment phase. An example of a system in a deployment phase will be described in more detail in connection with FIG. 3.

FIG. 3 is a schematic diagram of a system 300 for optimizing therapy in a deployment phase in accordance with an example embodiment of the disclosed concept. The system 300 includes many of the same modules as the system 200. However, the system 300 of FIG. 3 is an example of use in a deployment phase, where the therapy-severity map has been personalized to a desired degree. Additionally, the system 300 may provide recommendations for therapy rather than just receiving a selected therapy.

The system 300 include an RLS metrics monitoring module 302, an alertness sensing module 304, a sleep metrics sensing module 306, a related behaviors monitoring module 308, and an activity metrics sensing module 310. The RLS metrics monitoring module 302, the alertness sensing module 304, and the sleep metrics sensing module 306 may operate similar to the RLS metrics monitoring module 208, alertness sensing module 202, and sleep metrics monitoring module 206 described with respect to FIG. 2. The related behaviors monitoring module 308 may sense behaviors of a patient such as sleep hygiene, caffeine intake frequency and timing, and medication intake. The related behaviors monitoring module 308 may receive and/or interact with a patient to receive subjective responses from the patient. For example, the related behaviors monitoring module 308 may provide questions to the patient and receive responses. The activity metrics sensing module 310 may sense activity levels of the patient. The activity metrics sensing module 310 may sense activity levels via one or more sensors or via subjective responses from the patient.

The system 300 further includes an actual RLS severity module 312, an RLS severity prediction engine 314, and a predicted RLS severity module 316. The actual RLS severity module 312 operates similar to the actual RLS severity module 214 of FIG. 2. The RLS severity prediction engine 314 is structured to predict a level of the patient's RLS severity. The RLS severity prediction engine 314 may be a machine learning module trained to predict the patient's RLS severity based on outputs of the sleep metrics sensing module 306, the related behaviors monitoring module 308, and the activity metrics sensing module 310. An example of building the RLS severity prediction engine 314 will be described in more detail with respect to FIGS. 4 and 5. The RLS severity prediction engine 314 is structured to output the patient's predicted RLS severity to the predicted RLS severity module 316. The predicted RLS severity module 316 is structured to store and output the predicted RLS severity.

The system 300 further includes a personalized therapy-severity map database 318. The personalized therapy-severity map database 318 may initially be a default therapy-severity map based on population data, or may be built using a system such as the system 200 of FIG. 2. In the system 300 of FIG. 3, the personalized therapy-severity map 318 is continuously updated as the patient uses therapies.

The system 300 also includes a therapy efficacy evaluation module 320, a therapy recommendation module 322, a selected therapy module 324, and an enhance personalized therapy-severity map module 326. The therapy efficacy evaluation module 320 operates similar to the therapy efficacy evaluation module 212 of FIG. 2. The therapy recommendation module 322 provides recommendations to the patient for therapies based on the patient's personalized therapy-severity map stored in the personalized therapy-severity map database 318. The recommended therapies will be stored in the selected therapy module 324. The enhance personalized therapy-severity map module 326 is structured to update the patient's personalized therapy-severity map based on the therapy used, the actual severity of the patient's RLS, and the evaluation of the efficacy of the therapy. The updated personalized therapy-severity map is then stored in the personalized therapy-severity map database 318. The system 300 is thus able to continuously update the patient's personalized therapy-severity map as the patient uses therapies. In this manner, more effective therapies corresponding to the patient's severity may be recommended to the patient.

The system 300 may be implemented as one or more computing devices and sensors. The system 300 may be a localized or distributed system. The system 300 is an example of a deployment phase. The systems 200,300 of FIGS. 2 and 3 may be implemented on the same devices. For example the devices may have a build mode where they are configured to operate as the system 200 of FIG. 2 and may switch to a deployment mode where they are configured to operate as the system 300 of FIG. 3. The change in modes may occur based on one or more factors such as, without limitation, when a predetermined number of therapies have been tried to build the personalized therapy-severity map to a desired level. In an embodiment, the systems 200,300 may be implemented on separate devices.

In addition to updating the personalized therapy-severity map, the system 300 may also update the RLS severity prediction engine 314 as the system is used. One or more of the monitored characteristics of the patient may be used to update the RLS severity prediction engine 314 in order to more accurately predict the patient's RLS severity. Examples of building and updating the RLS severity prediction engine 314 will be described in more detail with respect to FIGS. 4 and 5.

FIG. 4 is a flowchart of a method for building a severity prediction engine in accordance with an example embodiment of the disclosed concept and FIG. 5 is a schematic diagram of a system for building a severity prediction engine in accordance with an example embodiment of the disclosed concept.

The RLS severity prediction engine may be a machine learning module that receives sleep metrics, related behaviors, and activity metrics as inputs, and output a predicted RLS severity for a patient. To build the RLS severity prediction engine, data on the sleep metrics, related behaviors, activity metrics, and actual RLS severity of a patient are gathered. With the data, the machine learning is used to learn to predict the RLS severity of the patient based on the sleep metrics, related behaviors, and activity metrics. It will be appreciated that any suitable machine learning techniques may be employed to build the RLS severity prediction engine.

As shown in FIG. 4, at 400 biometrics such as RLS objective metrics for the patient are monitored, and at 402 the RLS objective metrics are used to evaluate an actual RLS severity of the patient. At 404, 406, and 408 sleep metrics, related behaviors, and activity metrics of the patient are monitored. At 410, the RLS severity prediction engine is built using the actual RLS severity of the patient and the sleep metrics, related behaviors, and activity metrics. Once the RLS severity prediction engine is built, it may be deployed in a system such as the system 300 of FIG. 3.

The method of FIG. 4 may be implemented, for example, in the system 500 of FIG. 5. The system 500 includes an RLS metrics monitoring module 502 for monitoring RLS objective metrics, a related behaviors monitoring module 504 for monitoring related behaviors, a sleep metrics monitoring module 506 for monitoring sleep metrics, and an activity metrics sensing module 508 for monitoring activity metrics. The system also include an RLS severity evaluation module 510 for evaluating the actual severity of the patient's RLS based on the monitored RLS objective metrics. A build RLS severity prediction engine module 512 is structured to build the RLS severity prediction engine based on the actual RLS severity and the sleep metrics, related behaviors, and activity metrics. As described above, the RLS severity prediction engine may be built using machine learning techniques to predict an RLS severity of a patient based on monitored sleep metrics, related behaviors, and activity metrics.

While some examples of monitored characteristics that the RLS severity prediction engine may be built based on have been described herein, it will be appreciated that different characteristics may be used to build the RLS severity prediction engine.

The system 500 may be implemented as one or more computing devices and sensors. The system 500 may be a localized or distributed system. As noted above, the system 500 may be used to build an RLS severity prediction engine that may then be employed in the system 300 of FIG. 3, or with the method of FIG. 1.

While some embodiments have been described above related to optimizing treatment of RLS, it will be appreciated that the disclosed concept is also applicable to treatment of other conditions.

It will also be appreciated that an embodiment of the disclosed concept may be embodied on a non-transitory computer readable medium storing one or more programs, including instructions, which when executed by a computer, causes the computer to perform the method described with respect to FIG. 1.

Although the invention has been described in detail for the purpose of illustration based on what is currently considered to be the most practical and preferred embodiments, it is to be understood that such detail is solely for that purpose and that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover modifications and equivalent arrangements that are within the spirit and scope of the appended claims. For example, it is to be understood that the present invention contemplates that, to the extent possible, one or more features of any embodiment can be combined with one or more features of any other embodiment.

In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word “comprising” or “including” does not exclude the presence of elements or steps other than those listed in a claim. In a device claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The word “a” or “an” preceding an element does not exclude the presence of a plurality of such elements. In any device claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The mere fact that certain elements are recited in mutually different dependent claims does not indicate that these elements cannot be used in combination.

Claims

1. A method of optimizing treatment of a condition, the method comprising:

monitoring one or more characteristics of a patient associated with a condition of the patient;

predicting a severity of the condition of the patient;

recommending a selected therapy to the patient based on a therapy-severity map;

evaluating an actual severity of the condition of the patient;

evaluating an efficacy of the selected therapy; and

updating the therapy-severity map based on the evaluated efficacy of the selected therapy.

2. The method of claim 1, wherein the therapy-severity map corresponds one or more therapies with one or more levels of severity of the condition and includes efficacies of the one or more therapies, and wherein recommending the selected therapy includes selecting a therapy from the therapy-severity map corresponding to the severity of the condition of the patient with the highest efficacy among the therapies corresponding to the severity of the condition of the patient.

3. The method of claim 2, wherein updating the severity-therapy includes replacing the efficacy associated with the selected therapy with the evaluated efficacy.

4. The method of claim 2, wherein the therapy-severity map is a default map based on population data, and wherein updating the severity-therapy map includes replacing the efficacy associated in the default severity-therapy map with the selected therapy with the evaluated efficacy.

5. The method of claim 1, wherein evaluating the efficacy of the therapy is based on one or more of a comparison of the predicted severity of the condition to the actual severity of the condition, a sleep quality score, and an alertness score.

6. The method of claim 5, wherein evaluating the efficacy of the therapy is based on a comparison of the predicted severity of the condition to the actual severity of the condition, a sleep quality score, and an alertness score, and wherein each of the comparison of the predicted severity of the condition to the actual severity of the condition, the sleep quality score, and the alertness score has an associated weighting.

7. The method of claim 1, wherein monitoring one or more of the characteristics of the patient includes monitoring one or more objective physiological characteristics associated with Restless Legs Syndrome (RLS), and wherein evaluating the actual severity of the condition is based on the one or more objective physiological characteristics.

8. The method of claim 1, wherein monitoring one or more characteristics of the patient includes monitoring one or more of sleep metrics, activity metrics, and behaviors related to RLS, and wherein predicting the severity of the condition is based on one or more of the monitored sleep metrics, activity metrics, and behaviors related to RLS.

9. The method of claim 1, further comprising:

building a severity prediction engine based on the monitored one or more characteristics of the patient, and

wherein predicting the severity of the condition of the patient uses the severity prediction engine.

10. The method of claim 9, further comprising:

updating the severity prediction engine based on the monitored one or more characteristics of the patient.

11. The method of claim 9, wherein the monitoring one or more characteristics of the patient includes monitoring one or more of sleep metrics, activity metrics, and behaviors related to RLS, and wherein the severity prediction engine is a machine learning model that learns to predict the severity of the condition based on one or more of sleep metrics, activity metrics, and behaviors related to RLS.

12. The method of claim 1, wherein the selected therapy includes at least one of usage of a device for treatment of RLS and medication for treatment of RLS.

13. The method of claim 1, wherein the condition is RLS.

14. A system for optimizing treatment of a condition, the system comprising:

one or more sensing modules structured to monitor one or more characteristics of a patient associated with a condition of the patient;

a severity prediction engine structured to predict a severity of the condition of the patient;

a therapy recommendation module structured to recommend a selected therapy to the patient based on a therapy-severity map;

an actual severity evaluation module structured to evaluate an actual severity of the condition of the patient;

a therapy efficacy evaluation module structured to evaluate an efficacy of the selected therapy; and

a personalized therapy-severity map update module structured to update the therapy-severity map based on the evaluated efficacy of the selected therapy.

15. A non-transitory computer readable medium storing one or more programs, including instructions, which when executed by a computer, causes the computer to perform a method of optimizing treatment of a condition, the method comprising:

monitoring one or more characteristics of a patient associated with a condition of the patient;

predicting a severity of the condition of the patient;

recommending a selected therapy to the patient based on a therapy-severity map;

evaluating an actual severity of the condition of the patient;

evaluating an efficacy of the selected therapy; and

updating the therapy-severity map based on the evaluated efficacy of the selected therapy.