Systems and methods for personalizing sleep restriction therapy

Abstract

A system for guiding sleep restriction therapy is based on a subject's sleep data and medication data for multiple nighttime sleep sessions. The sleep data and medication data are processed to derive a target in-bed duration and a target medication dosage. Sleep restriction and medication recommendations are then output based on the target in-bed duration and the target medication dosage. The system implements an improved sleep restriction therapy that not only promotes the normal gradual increase in an acceptable sleep window but also allows for a gradual reduction in sleep medication, which is beneficial to treatment adherence.

Description

[Technical Field]

[0001] The present invention relates to sleep restriction therapy, and more particularly to a system for automating decision-making in sleep restriction therapy. [Background technology]

[0002] Insomnia is defined as the perception or symptoms of insufficient or poor quality sleep due to multiple factors, such as difficulty falling asleep, frequent waking during the night with difficulty returning to sleep, waking up too early in the morning, or unrefreshing sleep. It is generally believed that 10% to 15% of the adult population suffers from chronic insomnia, and an additional 25% to 35% have transient or occasional insomnia, making insomnia one of the most prevalent sleep disorders worldwide. Summary of the Invention [Problem to be solved by the invention]

[0003] Insomnia is typically treated with medication. The article "A behavioral perspective on insomnia treatment", Spielman AJ, Caruso LS, Glovinsky PB, Psychiatr. Clin. North Am. 1987;10:541, describes the so-called 3P model, which concludes that the use of sleeping pills actually has long-term adverse effects and contributes to chronic insomnia.

[0004] The 3P model is based on three factors that determine the severity of sleep disorders: predisposing factors, precipitating factors, and perpetuating factors.

[0005] Predisposition is an individual's innate tendency to "sleep well" or "sleep poorly."

[0006] The level of sleep disturbance (severity of insomnia) in the pre-symptomatic stage is often well below the insomnia threshold, so predisposition itself is not generally the reason why people end up using sleeping pills.

[0007] Aggravating factors are negative life events that make people worry and dwell on them at night. This leads to poor sleep quality during periods of negative emotions. However, these aggravating factors have a reversible effect on sleep quality, meaning that sleep quality improves once the worries are gone. However, for various reasons, many people cannot wait until this happens and turn to sleeping pills.

[0008] Prolonging factors help the sleep disorder continue. Sleeping pills can themselves be prolonging factors.

[0009] Initially, hypnotics may help alleviate the sleep disturbance to some extent, but the quality of sleep decreases. As a result, even if the precipitating factors disappear, the sleep disturbance likely remains above the insomnia threshold. At this point, insomnia becomes a chronic disorder.

[0010] Over the past few decades, non-pharmacological behavioral therapies have been shown to be effective in treating insomnia. These therapies have many advantages over drug therapies, including no tolerance issues or risk of dependence, and fewer side effects. These therapies address correcting the underlying cause rather than treating associated symptoms. Examples of behavioral therapies include stimulus control therapy, sleep restriction therapy, and relaxation training.

[0011] Sleep restriction therapy is often used as part of cognitive behavioral therapy. Sleep restriction therapy is a highly effective behavioral treatment for insomnia that works to increase sleep depth while decreasing variability in sleep timing. The goal is to shorten the amount of time spent in bed to consolidate sleep. However, several weeks of dedicated commitment to changing the subject's sleep schedule is required to observe improvements in sleep. Subjects initially feel more sleepy and experience more sleep disturbances, but the final beneficial effects are long-lasting.

[0012] Sleep restriction therapy generally involves the following steps:

[0013] Step 1: Determine the allowed bed time. This begins by allowing the subject (i.e., sleep therapy patient) to stay in bed for the average time they are currently asleep. This can be calculated by keeping a sleep diary for a period of time, e.g., two weeks. The average total sleep time for this monitoring period is determined and 30 minutes is added to derive the allowed bed time.

[0014] Step 2: Set the wake-up time. The wake-up time is set to the same time every morning, regardless of how much sleep the subject had had the previous night.

[0015] Step 3: Set bedtime. Bedtime is determined by counting back the allowed time in bed set in step 1 from the desired wake-up time. The subject should not be in bed before the bedtime, even if they feel sleepy and able to sleep.

[0016] Step 4: Stick to your sleep schedule as closely as possible for at least two weeks.

[0017] Therefore, sleep restriction therapy involves not allowing the subject to stay in bed longer than the average sleep duration based on sleep diary analysis. Even if sleep is very fragmented on the first night, sleep pressure increases within a few days, resulting in better sleep on subsequent nights. If this is achieved, the allowed time in bed (length of the sleep window) is gradually increased until the target duration of quality sleep is reached. This therapy is often supervised by sleep therapists working in sleep clinics. It can also be implemented in the form of a mobile phone app.

[0018] While sleep restriction therapy has been shown to be effective when adhered to, many people are very concerned about not getting the "standard" eight hours of sleep each night. They fear that the treatment will make their functioning and mood worse. This is one reason subjects often do not adhere to the treatment, which reduces its beneficial effects. As a result, sleep restriction therapy may actually lead subjects to use sleeping medications.

[0019] For example, patients may stop taking sleep medication before starting sleep therapy to obtain accurate baseline sleep data. However, allowing patients to start sleep therapy without stopping their medication can increase referrals willing to engage in treatment. Patients can then stop taking their medication during treatment. Patients may then experience symptoms of rebound insomnia, at which point they receive support and encouragement to continue with sleep therapy.

[0020] Existing sleep restriction therapy methods do not take into account whether the user is taking sleeping pills.

[0021] The paper "Clinical Guideline for the Evaluation and Management of Chronic Insomnia in Adults" by Schulte-Rodin Sharon et al., XP 055784615, describes a variety of different options for treating insomnia and how to switch treatments when one treatment does not seem to be showing improvement.

[0022] The paper "Management of Hypnotic Discontinuation in Chronic Insomnia" by Belanger Lynda et al., XP 055784524, discusses the issues surrounding discontinuing hypnotic medications to treat chronic insomnia. They suggest that hypnotic medications should be discontinued gradually, and that CBT interventions can be used to gradually reduce the use of hypnotic medications.

[0023] US Patent Application Publication No. 2010 / 094103 discloses an automated system for treating insomnia.

[0024] [Means for solving the problem]

[0025] The invention is defined by the claims.

[0026] According to an example embodiment of the present invention, there is provided a processor of a system for sleep restriction therapy, the processor comprising: a first input for receiving sleep data of the subject for a plurality of nighttime sleep sessions, the sleep data indicating at least the times during the sleep sessions when the subject is asleep and the times during the sleep sessions when the subject is awake; and a second input for receiving medication data for the subject for the plurality of nighttime sleep sessions, the medication data indicating medications taken by the subject; the processor processes the sleep data and the medication data to Derive the target bedtime duration; Deriving a target dosage; and Outputting sleep restriction and medication recommendations based on the target in-bed duration and the target medication use. Adapt to this.

[0027] This system implements an improved sleep restriction regimen that not only facilitates the normal gradual increase in the duration of the acceptable sleep window, but also allows for the gradual reduction of sleep medications. This has many advantages. First, the treatment explicitly considers sleep medications, meaning subjects have less reason to conceal their use. Furthermore, allowing patients to begin sleep restriction therapy without stopping their medications can increase the number of referrals willing to try it. Knowing about the presence of this delaying factor can increase the chances of success with sleep restriction therapy.

[0028] Second, the system provides recommendations that can lead to optimal sleep patterns without the use of sleeping pills, which is healthier in the long run. Third, subjects can be explicitly instructed on reducing their use of sleeping pills, thus addressing anxiety about not being able to sleep without sleeping pills. Furthermore, this can be done in stages, so anxiety is reduced and confidence is built over time.

[0029] Thus, the present invention provides an improved sleep restriction therapy method that allows for a gradual increase in the duration of the tolerated sleep window in combination with a gradual reduction in the sleep medication.

[0030] The target dosage may be the dosage of a drug the subject is already taking, or it may be the dosage of a new drug (e.g., to replace a previous, stronger drug the subject is taking). The target dosage may be zero.

[0031] The processor receives sleep data for multiple sleep sessions, where one sleep session is one period of intended sleep, i.e., one night. The subject's actual sleep performance is analyzed over the series of sleep sessions (i.e., nights), and sleep restriction recommendations and medication recommendations are generated from this analysis.

[0032] Sleep data is based on self-report by the subject, for example, by indicating whether the epoch was asleep or awake for a series of epochs during the night, which is a common method for assessing a subject's sleep in a sleep diary.

[0033] The sleep restriction recommendations are used to control a system that provides a time in bed indicator and a time to wake up indicator. Such a system may be a basic notification and / or alarm, or it may be a more sophisticated sleep control system (e.g., controlling lights and / or sounds for time in bed and lights and / or sounds for time to wake up).

[0034] The processor may be part of, for example, a mobile phone or tablet with an appropriate app installed. The processor may be part of the output device that provides the sleep restriction recommendations to the subject or clinician, or it may be a separate device.

[0035] Medication data includes, for example, type of medication, dosage, and timing of medication, and this data is recorded by a daily self-report completed by the subject.

[0036] The processor further has a third input for receiving effect data from a data structure containing data regarding the effect of different doses of different sleep medications on sleep characteristics of the general population. Knowledge of the expected effect of sleep medications, when combined with recommended sleep time windows, makes it possible to provide drug recommendations that achieve a desired gradual change in sleep characteristics over time.

[0037] The processor is further adapted to use the system to derive personalized effect data regarding the effect of different doses of different sleep medications on the sleep characteristics of a particular subject, thus taking into account the particular effect of the medication on that subject by learning from the historical data of that subject.

[0038] Additionally, the system can generate effect data for a particular subject based on data from other comparable subjects when historical data for that subject is not available.

[0039] The plurality of sleep sessions may comprise, for example, 7 to 21 sleep sessions. Thus, sleep patterns may be analyzed for one to three weeks before a sleep restriction recommendation is generated.

[0040] The processor can derive a target bedtime duration based on at least an estimate of the average actual total sleep time for the plurality of sleep sessions. The sleep restriction recommendation is revised over time based on new sleep data received over time. Thus, the allocated bedtime corresponds to the actual amount of sleep the subject generally achieves. This is the basis of the sleep restriction therapy approach.

[0041] Bedtime can be set to be no earlier than historically observed actual sleep onset times, so that when the subject goes to bed, they should be ready to sleep.

[0042] The processor is further adapted to modify the sleep restriction recommendations over time based on new sleep and medication data received over time. Thus, the progression of sleep restriction therapy over time may be handled by the system based on continuously collected sleep data.

[0043] Sleep data may include, for example, subject input. Sleep questionnaires / sleep diaries may be used to provide at least initial sleep data. Therefore, self-report of the previous night's sleep performance is used as the primary source of data. This is typically the case with sleep restriction therapy. Possible over-exaggeration of sleep deprivation, which is common in self-reported sleep data, is included in the analysis of the data.

[0044] Sleep data optionally also includes sensor data, which can supplement self-reported data; for example, it is of interest to collect data midway through a sleep session. It may also use shorter time epochs.

[0045] Medication data may include subject input, for example, the subject would ideally only need to input the type and dosage of medication taken into the system when the medication was taken (although the time may also need to be input).

[0046] The medication data includes data from an electronic medication dispensing system, such that this data is collected at least in part automatically.

[0047] The processor may further have an input for receiving sleep preferences of the subject, the processor being adapted to take the sleep preferences into account in deriving the target timing.

[0048] The sleep preference may, for example, be for the latest time the subject can be in bed (eg, due to work commitments), so that the wake-up time is at the latest possible point in time.

[0049] The present invention also provides a system for sleep restriction therapy, the system comprising: a sensor device for collecting sensor data and / or drug data; and said processor as defined above for processing said sensor data and said medication data to generate sleep restriction and medication recommendations. It has.

[0050] Thus, the system includes sensors to supplement the self-reported data.

[0051] The sensor device may comprise a single sensor unit or a system of sensor units. The sensor device may comprise at least one wearable sleep sensor, which may be a headband or a wristband. For example, a headband may enable EEG monitoring, and headband devices for such sleep tracking are well known. PPG and movement monitoring using wristwatch-type devices to provide sleep data are also well known.

[0052] The sensor device may alternatively or additionally include at least one monitoring sensor remote from the subject. This sensor may, for example, monitor movement, but may also provide additional environmental information of interest. For example, the sensor device may report when a light is turned on or off, or may provide temperature monitoring (to detect body presence). These may provide additional data to validate or enhance self-reported data or data from a wearable sensor.

[0053] The sensor device may alternatively or additionally include a medication delivery system, which can provide medication data automatically.

[0054] The present invention provides a computer-implemented method for generating sleep restriction recommendations and drug recommendations for sleep restriction therapy, the method comprising: receiving sleep data from a subject for a plurality of nighttime sleep sessions, the sleep data indicating at least time epochs during the sleep sessions when the subject is asleep and time epochs during the sleep sessions when the subject is awake; receiving medication data for the subject for the plurality of nighttime sleep sessions, the medication data indicating medications taken by the subject; deriving a target bedtime duration; deriving a target dosage; and outputting sleep restriction and medication recommendations based on the target in-bed duration and the target medication dosage. It has.

[0055] This method takes into account both a subject's sleep patterns and medication history to configure sleep restriction therapy.

[0056] The method comprises: receiving data from a data structure containing effect data regarding the effect of different doses of different sleep medications on sleep characteristics of the general population; and taking the impact data into account when deriving the target bed duration and the target dosage. It can have:

[0057] This allows the effects of drugs to be taken into account.

[0058] The method may further comprise using the system to derive individualized effect data regarding the effect of different doses of different sleep medications on sleep characteristics of a particular subject.

[0059] The invention also provides a computer program having a computer program code adapted to perform the method defined above, when said computer program is run on a computer.

[0060] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter. [Brief explanation of the drawings]

[0061] For a better understanding of the present invention, and to show more clearly how the same may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings in which: [Figure 1] FIG. 1 shows a system for sleep restriction therapy. [Figure 2] FIG. 2 illustrates a method implemented by the processor of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0062] The present invention will now be described with reference to the drawings.

[0063] While the detailed description and specific examples indicate exemplary embodiments of the devices, systems, and methods, it should be understood that they are for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the devices, systems, and methods of the present invention will become better understood from the following description, appended claims, and accompanying drawings. It should be understood that the drawings are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used to denote the same or similar parts throughout the drawings.

[0064] The present invention provides a system for guiding sleep restriction therapy based on a subject's sleep and medication data for multiple nighttime sleep sessions. The sleep and medication data are processed to derive a target in-bed duration and a target medication dosage. Sleep restriction and medication recommendations are then output based on the target in-bed duration and the target medication dosage. The system implements an improved sleep restriction therapy method that not only promotes the normal gradual increase in the acceptable sleep window, but also allows for a gradual reduction in sleep medication, which is beneficial to treatment compliance.

[0065] 1 shows a system for sleep restriction therapy, including a processor 10 and a user interface device 20. The user interface device is a device for providing instructions to a subject, such as an alarm clock that can set both a bedtime and a wake-up time. The user interface device may simply comprise a mobile phone or tablet with appropriate software installed, in which case the processor 10 may be the processor of that device. Alternatively, the processor may be part of a separate device that communicates with the user interface device 20.

[0066] The processor collects the subject's sleep data for multiple nighttime sleep sessions. sleep The processor has an input 12 for receiving sleep data indicating at least the times, e.g., epochs, during a sleep session that the subject is asleep, and the times, e.g., epochs, during the sleep session that the subject is awake. The processor includes a memory (database) for storing the data for later analysis.

[0067] This sleep data may be based on a self-reported sleep report, such as a sleep diary, that indicates whether the subject was asleep or awake for a series of epochs throughout the night. Such a sleep diary may be based on a digital sleep / wake diary that the subject keeps to self-report their sleep / wake timing. Reporting to this diary may be accomplished using a user interface with the digital diary, such as a dedicated app on a smartphone or tablet, or an existing app associated with the user interface device 20.

[0068] This diary is kept for the sleep period, for example, one or two weeks before the intervention.

[0069] Optionally, sensor data DATA sensorA sensor device 14 is provided for collecting sleep data. A processor further processes the sensor data. The sensor device may be used, for example, to supplement the self-reported data. The sensor device 14 includes at least one wearable sleep sensor, which may be a headband or a wristband. Headbands, for example, allow for EEG monitoring, and headband devices for tracking such sleep are well known. PPG and movement monitoring using wristwatch-type devices to provide data indicative of sleep information are also well known. Less obtrusive sensors, such as cameras, pillow-based sensors, or mattress-based sensors, may also be used.

[0070] The system includes drug data DATA medication 18, which allows the system to know the amount, time and type of sleeping medication the subject is taking.

[0071] Medication data can be obtained from an online questionnaire completed by the subject using the user interface device 20, which details current and past use of sleep medications. Each morning, the subject is asked to update the type and dosage of sleep medication taken within the past 24 hours, as well as the exact time.

[0072] The system may additionally or alternatively be linked to an electronic sleeping pill dispenser 19 so that the amount of sleeping pills taken each day is automatically entered into the system.

[0073] Another option is for the subject using the system to use the camera function of the user interface device 20 to scan the label or barcode on the drug package and send image data DATA to the processor. image Therefore, again, the drug information is automatically entered into the system. The timing may be inferred from the time the image is uploaded to the system, and / or the subject may manually enter the timing and optionally the dosage (if there is an alternative dosage option).

[0074] The processor 10 processes the sleep data and medication data to derive a target bedtime. Optionally, the processor 10 can derive target timings for the target bedtime, i.e., bedtime and wake-up time. The target bedtime and bedtime together define a sleep window. The timings are selected, for example, to achieve a majority of sleep during the bedtime. Alternatively, the subject may select a bedtime or wake-up time.

[0075] Sleep restriction and medication recommendations 22 are then generated based on the target in-bed duration and target timing, and the determined medication dosages, which are provided to the user interface device 20.

[0076] The processor 10 collects sleep data DATA for multiple sleep sessions. sleep A sleep session is one period of intended sleep, i.e., time in bed per night. The subject's actual sleep performance is analyzed over a series of sleep sessions (i.e., nights), and a sleep restriction recommendation is generated from this analysis.

[0077] Explain various examples of how data is processed.

[0078] FIG. 2 shows the most basic example, in which five steps are performed by the system every day or every few days, for example every other day.

[0079] At step 30, sleep data and sensor data are provided to the system. From this, the system derives sleep duration for the past few nights from data generated by the sleep data input or input from sensor device 14. For example, the subject may be shown to sleep only 5 hours per night, compared to 9 hours in bed per night.

[0080] In step 32, the system receives the drug data DATA medicationDetermine the strength of the sleeping medication taken over the past few days. For example, a subject may be shown to take 30 mg of Temazepam every night before bed.

[0081] In step 34, the system suggests a sleep window for the next night based on the average sleep time and medication data from the previous few nights, which defines the length (duration) and start time of the sleep session.

[0082] In step 36, the system suggests dosages for the next night, again based on average sleep duration and medication data from the last few nights.

[0083] For the subject, the length of the advised sleep window is set to, for example, 5 hours. Thus, even if the subject does not sleep the full 5 hours, the subject is advised to go to bed at 1 a.m. and wake up at 6 a.m. The goal is that since the subject did not sleep enough (the subject did not sleep anyway), the subject will become sleepy, so that after a while the subject will sleep at least with fewer interruptions.

[0084] If after a few days the quality of sleep in the sleep window (averaged over several nights) increases, the system will suggest increasing the length of the sleep window.

[0085] For example, after a while, the subject can sleep through most of the 5-hour sleep window.Then, the system will advise the subject to extend the sleep window to 5 hours and 15 minutes, for example, starting at 12:45 AM and waking up at 6 AM.If the 5-hour and 15-minute sleep window also works well, the length of the sleep window will be increased again and again until an acceptable sleep window length is reached.The time increment can be 15 minutes as in this example, but can also be other time increments.

[0086] Instead of (or in addition to) increasing the length of the sleep window, the system of the present invention can also suggest reducing the dosage of sleeping medication for the next few nights. For example, if the subject has successfully adapted to a 5.5 hour sleep window length for the past few days, it may be decided not to increase the sleep window length again, but instead to reduce the dosage of sleeping medication taken each night.

[0087] At this time, the subject is advised to take a reduced amount of sleeping pills, for example, 66% of the current dosage (20 mg temazepam), for the next few days. It is expected that the subject will sleep less again, but in this case, the subject will become sleepy during the day and will sleep better over time even with a lower dosage of sleeping pills. If this occurs, it is decided to increase the length of the sleep window again or further reduce the dosage of sleeping pills until an acceptable sleep window length without the use of sleeping pills is finally reached.

[0088] Duration adaptation is a standard development in sleep restriction therapy. The present invention aims to incorporate drug dosage levels into the sleep recommendations provided to the subject, gradually tapering the sleep medication while simultaneously increasing the sleep window to a desired steady-state level.

[0089] There are various ways in which drug data can be considered. One approach is to utilize a data structure, e.g., a lookup table, that encodes the effects / impact of sleep medications for each dose of each common class of sleep medication.

[0090] 1 shows a data structure 24 containing data relating to the effects of different doses of different hypnotic drugs on sleep characteristics. This data is provided to a third input 26 of the processor 10.

[0091] These effects are known from data on the general (insomnia) population. Thus, the system has a data structure containing data on the effects of different doses of different sleep medications on sleep characteristics. Of course, the system can access a remote database that stores this information.

[0092] The processor can then calculate the average effect / impact based on the type and dosage taken over the last few nights.

[0093] To alter drug dependency, the current effect of the drug being taken is determined. A percentage of that effect / impact is then taken, for example, to reduce the beneficial effect to 80% of its previous value. The type and dosage of drug required for this reduced beneficial effect is then found from the data structure, and this new type and dosage is provided as new guidance for the next night. Thus, both the type of drug and the dosage of drug are adjusted so that the system gradually weans the subject off the drug, while simultaneously (alternately or together) increasing bedtime as treatment progresses.

[0094] Calculations using such a data structure are particularly useful when different types of drugs, such as temazepam and alcohol, are used by a subject, either alternately over multiple nights or in combination on one night. Thus, the data structure may also include information regarding the effects / impact of various doses of the drug combination.

[0095] Based on the sleep data and medication data, the system can also derive the effect / impact of sleep medication on a particular individual subject. For example, the system can detect that a 20 mg dose of temazepam results in an average of 4 hours of sleep, while a 30 mg dose results in an average of 4.5 hours of sleep. This allows the system to create a personalized version of the data structure, thus personalizing the sleep therapy advice given.

[0096] Similarly, the system can determine from the sleep data which part of the night the sleep window is most effective for this subject. For example, the system can detect that the total sleep duration is longer, i.e., sleep fragmentation is less, when the subject goes to bed relatively late (e.g., at 1:15 AM instead of 1:00 AM), than when the subject goes to bed relatively early (e.g., at 12:45 AM). The system can then recommend that the bedtime should be shifted to 1:15 AM while keeping the sleep window constant. Thus, the timing of the sleep window can be adjusted according to historical sleep data.

[0097] The start time of the sleep window can then also be used as an additional input parameter for the personalized data structure, allowing for modeling of any interactions between the type of sleeping pill, the sleeping pill dosage, and the start time of the sleep window.

[0098] The processor may also take into account the subject's sleep preferences. For example, if the sleep therapy has the same probability of success, the subject may prefer to go to bed early and wake up early. Sleep preferences may relate, for example, to the latest time the subject can be in bed (e.g., due to work commitments) or the earliest time the subject can be in bed (e.g., due to evening appointments).

[0099] In addition to the benefits of treatment (i.e., sleep-improving effects), both sleep restriction and hypnotic medications are associated with adverse effects in the morning (and sometimes in the afternoon). Adverse effects are identified, for example, by decreased cognitive performance, decreased alertness, and sleepiness. Thus, the system also functions as a monitoring system for tracking daytime functioning and a system for issuing warnings to individuals undergoing treatment. Known effects of sleep restriction and hypnotic medications (by type and dosage) can be warned in advance, and individual responses to adverse effects can be tracked and the warning system based thereon.

[0100] The warning may consist, for example, of stating the time it takes for a certain sleeping pill to be metabolized and no longer cause any cognitive impairment.

[0101] The number of sleep sessions used at the beginning of therapy does not have to be two weeks. More typically, it can be between 7 and 21 sleep sessions. Thus, sleep patterns are analyzed for one to three weeks before a sleep restriction therapy recommendation is generated. Once treatment is administered, adaptations are made daily, every other day, or every few days. These adaptations may be made for longer periods, such as weekly, if it takes time to reliably establish that sleep using the current sleep duration and bedtime has improved sufficiently to proceed to the next step. The adaptation time may be personalized, for example, based on expected improvement from historical data of comparable subjects.

[0102] Sleep restriction therapy begins with a fixed target bedtime duration, e.g., 5 hours as described above. However, the target bedtime duration may instead be based on an estimate of the actual total sleep time averaged over multiple sleep sessions. Thus, the starting point can be based on the actual amount of sleep the subject generally achieves. This is the basic operation of the sleep restriction therapy approach.

[0103] Bedtime is set to be no earlier than historically observed actual sleep onset times, so that when subjects go to bed, they should be ready to sleep.

[0104] The sleep restriction recommendations evolve over time, and thus the processor can modify the sleep restriction recommendations over time based on new sleep data received over time. Thus, the progression of a sleep restriction therapy over time may be handled by the system based on continuously collected sleep data.

[0105] The sensor devices described above can include wearable sensors, so that a processor can be used to extend the functionality of a headband, for example, to monitor sleep. Alternatively or additionally, the sensor device may include at least one unobtrusive monitoring sensor. This sensor can, for example, monitor movement but also provide additional environmental information of interest. For example, the sensor device may report when lights are turned on or off, or provide temperature monitoring (to detect body presence). These can provide additional data to validate or enhance self-reported data or data from the wearable sensor.

[0106] Processing of the data can be handled in a variety of ways, either locally or remotely to the subject. For example, the data may be stored in a remote database.

[0107] The system may automatically generate a summary report, for example, to provide a specialist with a quick overview of the data. The clinician / physician can evaluate the data in a graphical interface and use this to discuss a new bedtime schedule with the subject. This allows for simple adaptation of the treatment to maximize individual compliance. The recommendations are then provided to the subject (i.e., patient) directly or to a sleep therapist and / or other clinician. This allows the therapist / clinician to check whether they are giving unrealistic advice, and if so, the therapist may be provided with a module to modify / adapt that advice.

[0108] As described above, the system utilizes a processor to process data. This processor may be implemented in a variety of ways using software and / or hardware to perform the various functions required. The processor typically uses one or more microprocessors that are programmed using software (e.g., microcode) to perform the required functions. The processor may also be implemented as a combination of dedicated hardware to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.

[0109] Examples of circuitry that may be used in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs).

[0110] In various implementations, the processor may be associated with one or more storage media, e.g., volatile and non-volatile computer memory such as RAM, PROM, EPROM, and EEPROM. The storage media may be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform the required functions. The various storage media may be mounted within the processor or controller, or may be transportable such that one or more programs stored on the storage media can be read by the processor.

[0111] Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and an absence of a plurality of elements does not exclude the presence of a plurality of elements.

[0112] The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0113] The computer program may be stored / distributed on a suitable medium, for example an optical storage medium or a solid-state medium provided together with or as part of other hardware, but may also be distributed in other forms, for example via the Internet or other wired or wireless telecommunications systems.

[0114] It is noted that when the term "adapted to" is used in the claims or the specification, the term "adapted to" is meant to be equivalent to the term "configured to."

[0115] Any reference signs between parentheses shall not be construed as limiting the scope.

Claims

1. 1. A processor of a system for sleep restriction therapy, a first input for receiving sleep data of the subject for a plurality of nighttime sleep sessions, the sleep data indicating at least times during the sleep sessions when the subject is asleep and times during the sleep sessions when the subject is awake; and a second input for receiving medication data for the subject for the plurality of nighttime sleep sessions, the medication data indicating medications taken by the subject; the processor processes the sleep data and the medication data to Derive the target bedtime duration; Deriving a target dosage; and outputting sleep restriction recommendations and medication recommendations for the next night based on the target in-bed duration and the target medication dosage to implement a gradual increase in the target in-bed duration and a gradual decrease in the medication taken by the subject; Adaptable to the processor.

2. The processor of claim 1 , wherein the medication data comprises medication type, dosage, and timing of medication.

3. 10. The processor of claim 1, further comprising a third input for receiving effect data from a data structure containing data on the effect of different doses of different sleep medications on sleep characteristics of the general population.

4. 4. The processor of claim 3, further adapted to use the system to derive personalized effect data regarding the effect of different doses of different sleep medications on sleep characteristics of a particular subject.

5. 5. The processor of claim 1, wherein the plurality of night-time sleep sessions comprises between 7 and 21 sleep sessions.

6. 6. The processor of claim 1, adapted to derive the target in-bed duration based on at least an estimate of average actual total sleep time for the plurality of sleep sessions.

7. The sleep restriction recommendation is further adapted to modify over time based on new sleep and medication data received over time.

7. A processor according to any one of claims 1 to 6.

8. The sleep data is Subject input data, and Sensor Data 8. The processor of claim 1, further comprising:

9. The drug data includes: Subject input data, and Data from an electronic drug dispensing system 9. The processor of claim 1, further comprising:

10. a sensor device for collecting sensor data and / or drug data; and A processor according to any one of claims 1 to 9 for processing the sensor data and medication data and generating the sleep restriction recommendation and medication recommendation. A system for sleep restriction therapy comprising:

11. The sensor device includes: at least one wearable sleep sensor, and / or Drug Delivery Systems The system of claim 10, comprising:

12. 1. A computer-implemented method for generating sleep restriction recommendations and medication recommendations for sleep restriction therapy, the method comprising: receiving sleep data from a subject for a plurality of nighttime sleep sessions, the sleep data indicating at least times during the sleep sessions when the subject is asleep and times during the sleep sessions when the subject is awake; receiving medication data for the subject for the plurality of nighttime sleep sessions, the medication data indicating medications taken by the subject; deriving a target bedtime duration; deriving a target dosage; and outputting a sleep restriction recommendation and a medication recommendation for the next night based on the target in-bed duration and the target medication dosage to implement a gradual increase in the target in-bed duration and a gradual decrease in the medication taken by the subject. A method comprising:

13. receiving data from a data structure containing impact data regarding the impact of different doses of different sleep medications on sleep characteristics of the general population and considering the impact data when deriving the target in-bed duration and target dosage; 13. The method of claim 12, comprising:

14. Using a system for sleep restriction therapy, deriving personalized effect data regarding the effects of different doses of different sleep medications on sleep characteristics of a particular subject. The method of claim 13 further comprising:

15. A computer program which, when executed on a computer, causes the computer to carry out the method of any one of claims 12 to 14.

Images