WO2009114755A2

WO2009114755A2 - Methods for diagnosing or treating sleep apnea

Info

Publication number: WO2009114755A2
Application number: PCT/US2009/037063
Authority: WO
Inventors: Michael R. Treacy
Original assignee: Med One Medical
Priority date: 2008-03-14
Filing date: 2009-03-13
Publication date: 2009-09-17
Also published as: WO2009114755A3

Abstract

Methods of diagnosis and treatment of sleep apnea are disclosed, in which optimal continuous positive airway pressures (CPAP) are determined and utilized without the need for in-laboratory titration studies or the use of automatic CPAP machines. These methods comprise acquiring relevant measurements at the home of a subject and employing predictive models to provide the optimal pressure for treatment.

Description

METHODS FOR DIAGNOSING OR TREATING SLEEP APNEA

RELATED APPLICATIONS

The present application is entitled to the benefit of U.S. Provisional Patent Application No. 61/069,604, filed March 14, 2008, which is incorporated herein by reference in its entirety.

BACKGROUND

Sleep disorders are a common problem, and they have been increasingly recognized as negatively impacting the health, well-being, and productivity of sufferers. In particular, sleep apneas — characterized by disturbances in the initiation and maintenance of breathing during sleep — are quite common, particularly among adults. These disorders may be due to assorted neurological pathologies (central sleep apneas) or mainly due to collapse of the airway during sleep (obstructive sleep apnea). Sleep apnea has been associated with heart attacks, heart failure, stroke, hypertension, accelerated development of coronary artery disease, abnormal heart rhythms, convulsions, memory problems, slowed thinking, irritability, mood swings, and depression. For many sufferers, this disorder can be treated in a number of ways, including changes in lifestyle. However, in some people, the disorder may require the use of devices that assist breathing during sleep, such as continuous positive airway pressure (CPAP) machines. The diagnosis and treatment of sleep apnea has often required a sufferer to undergo one or more overnight evaluations in a sleep laboratory. This approach can involve considerable cost and inconvenience to the sufferer. In addition, the success of the procedure can be hampered by the discomfort of sleeping in a foreign environment. As such, this area of health services can greatly benefit from approaches that lower costs and facilitate diagnosis and treatment. DETAILED DESCRIPTION

Before particular embodiments of the present disclosure are disclosed and described, it is to be understood that this disclosure is not limited to the particular process and materials disclosed herein as such may vary to some degree. It is also to be understood that the terminology used herein is used for the purpose of describing particular embodiments only and is not intended to be limiting, as the scope of the present disclosure will be defined only by the appended claims and equivalents thereof.

In describing and claiming the present disclosure, the following terminology will be used.

The singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. The modifier "effective," or "therapeutically effective" when used herein in reference to a treatment refers to a level or frequency of that treatment or some parameter of treatment that is sufficient to bring about the intended effect in the subject. For example, an effective airway pressure for treatment of obstructive sleep apnea would be a pressure that keeps the subject's airway open during sleep so as to facilitate substantially normal respiration. It is understood that various biological or physiological factors may affect the ability of a treatment to achieve its intended result. Therefore, "effective," or "therapeutically effective" may be dependent in some instances on such biological or physiological factors. Further, while the achievement of therapeutic effects may be measured by a physician or other personnel qualified in the art who are using evaluations known in the art, it is recognized that individual variation and response to treatments may make the achievement of therapeutic effects a subjective decision. The determination of a therapeutically effective treatment is well within the ordinary skill in the art of medicine. The terms "sufferer," "person," "patient," or "subject" may be used interchangeably herein to refer to an individual who may be suffering from sleep apnea and is therefore a subject of interest with regard to diagnosis or treatment of sleep apneas.

The term "night" or "overnight" shall refer to the portion of the earth's rotational period during which a person has his or her main sleep period. For a majority of persons, this time is that commonly understood as "night," i.e. the period roughly bounded by sunset and sunrise. However, for purposes of the present disclosure, "night" in regard to a person can be a different part of the rotational period if that is when that person has his main sleep period. One example would be a shift worker who works during the dark hours and sleeps during daytime hours.

The term "home" as used herein refers to a building or location that constitutes the living quarters for a person, such that the person spends at least his or her sleep period in that building or location. This designation serves mainly to indicate where a person may pass the sleep period on any given day. As such it will be understood while that a home is commonly understood as a stationary, permanent structure that serves as a long-term dwelling for the person, other places and arrangements may be considered a home if the person sleeps there. For example, moving structures such as vans, trailers, trailer homes, or recreational vehicles may provide sleeping quarters and therefore serve as a home in accordance with this disclosure. Also, stationary buildings that provide sleeping quarters but are not a person's permanent dwelling can also be considered homes in accordance with this disclosure. This being said, a sleep laboratory or other medical facility that is not a normal place of sleep is not considered to be a home. The term "predictive model" as used herein refers to a model or algorithm by which one may arrive at a working principle based on one or more observed data values. Particularly, predictive models in the context of the present disclosure refer to a numerical model or algorithm by which one may arrive at a value that is relevant for therapy (e.g. an optimal continuous positive airway pressure) based on available data. For example a predictive model for selecting an optimal continuous positive airway pressure can be an algorithm based on demographic, anthropometric, and/or polysomnographic data. Predictive models in accordance with embodiments of the present invention may include purely statistical algorithms. Alternatively, predictive models in accordance with embodiments of the present invention may include adaptive computational models such as artificial neural networks. The term "measurement" as used herein refers to any data obtained by direct observation of a subject as well as observation aided by a device. For example, metric measurements such as length, weight, circumference, etc. are included. However, observations such as age, gender, behavior, occurrence of physiological phenomena, device-aided observations (e.g. electroencephalograms) and values derived from observations (e.g. body mass index) are also considered measurements for purposes of the following discussion.

Concentrations, amounts, and other numerical data may be expressed or presented herein in a range format. It is to be understood that such a range format is used merely for convenience and brevity and thus should be interpreted flexibly to include not only the numerical values explicitly recited as the limits of the range, but also to include all the individual numerical values or sub-ranges encompassed within that range as if each numerical value and sub-range is explicitly recited. As an illustration, a numerical range of "about 0.01 to 2.0 mm" should be interpreted to include not only the explicitly recited values of about 0.01 mm to about 2.0 mm, but also include individual values and sub-ranges within the indicated range. Thus, included in this numerical range are individual values such as 0.5, 0.7, and 1.5, and sub-ranges such as from 0.5 to 1.7, 0.7 to 1.5, and from 1.0 to 1.5, etc. This same principle applies to ranges reciting only one numerical value. Furthermore, such an interpretation should apply regardless of the breadth of the range or the characteristics being described.

Traditionally, diagnosis and treatment of obstructive sleep apnea under the current state of the art typically involves the following general approach. A person suspected of suffering from sleep apnea is referred to a sleep clinic or laboratory. The person is then subjected to one or more overnight observations or studies. For example, the person may first spend a night in the sleep laboratory, during which the person's sleep is observed by laboratory personnel. In this process, termed polysomnography, direct visual observations are typically made by personnel and measurements are taken through various instruments connected to the person. The measurements and observations used include electroencephalograms (EEGs), electrooculograms (EOGs), electromyograms (EMGs), electrocardiograms (ECGs), as well as airflow measurements using oral- nasal thermistors, and measures of respiratory effort. These measurements and observations are used in diagnosing the person's condition. One approach to polysomnography is to divide the sleep period into time epochs and quantify for each sleep stage the occurrence of certain events such as apneas (total suspension of breathing), hypopneas (abnormally shallow breathing), decreases in arterial oxyhemoglobin saturation, and arousals (abrupt shifts in EEG frequency that indicate a disruption of sleep). These observations may then be used to generate various diagnostic indexes, such as apnea-hypopnea index (AHI) which is based on the number of apneas/hypopneas per hour of sleep. A determination may then be made as to whether the person suffers from a sleep apnea disorder, and what treatment is appropriate.

A positive diagnosis of sleep apnea may indicate that a breathing assistance device is needed. Such devices reduce or abolish apneas by splinting the airway of a person open during sleep, preventing airway collapse that would obstruct breathing. A typical fixed-pressure CPAP machine blows air, usually through a mask worn on the face, into the airway of a subject at a preset pressure. The full benefits of such a machine are realized when pressure is sufficient to substantially abolish apneas and hypopneas in the subject. However, as the pressure used increases, the CPAP machine becomes increasingly uncomfortable to wear and actually disrupts sleep. For this reason, an improper pressure setting often leads to lowered compliance by CPAP users, or even to a total cessation of use. Therefore, it can be seen that there is an optimal pressure for operation of a CPAP machine for each person, i.e. a pressure that insures therapeutic effect without compromising compliance. In particular, the term "optimal pressure" as used herein refers to the minimum (or near minimal) pressure output that maintains an open airway such that apneas and hypopneas are substantially prevented. Preferably, this prevention is maintained through all the stages of sleep and in any body position typical of sleep in humans.

Therefore, before a CPAP machine can be prescribed to the person for use, it is desirable to find the optimal pressure so that the CPAP machine will be most effective. Under a typical approach, this requires another overnight session in the sleep laboratory, during which a CPAP titration is performed. In this procedure, the person is fitted with a CPAP machine before retiring, at which time the machine is set at a fairly low pressure, e.g. about 4 cm H₂O. While the person sleeps, lab personnel once again conduct an attended sleep study (polysomnography) in which EEG, respiratory effort, limb movements are observed and respiratory airflow is measured via the CPAP mask. Over the course of the attended sleep period, the CPAP machine pressure is titrated to determine the optimal pressure. The optimal pressure is determined as the pressure at which apneas and hypopneas are abolished or reduced to a target level. The person then is usually instructed to sleep thereafter wearing a CPAP machine set to the optimal pressure indicated by titration.

The traditional approach can be quite time-consuming and inconvenient, as it requires the person to spend multiple nights away from home. Furthermore, many people find it difficult to sleep well in unfamiliar environments, and this discomfort is usually exacerbated by the need to be connected to monitoring equipment while trying to sleep. In addition, in-laboratory studies can be expensive and therefore may not be available to persons of limited means or those lacking health insurance coverage. It is here that the systems and methods of the present disclosure can be highly beneficial. In order to ameliorate these negative aspects of this process, the home sleep study can be used. Under this approach, a person concerned about possible sleep apnea can provide sleep health service providers with information that would traditionally be gathered through in-laboratory polysomnography. Rather than requiring the person to visit a sleep laboratory for polysomnography, recording equipment can be brought or mailed to the person's home for overnight recording while the person sleeps in his or her own bed. This information can then be collected and analyzed by sleep health personnel and a diagnosis can be made. However, if the person is diagnosed with sleep apnea that requires use of a CPAP machine, in the past, he or she still needed to go to a sleep laboratory for a CPAP titration study so that the proper operating pressure could be determined. Therefore, even with the use of a home sleep study, considerable costs and inconvenience may be incurred in getting treatment due to the need for an in-laboratory titration.

Another available solution has been provided by the development of automatic CPAP machines. These machines sense airway obstruction and respond by automatically increasing output pressure. As such, automatic CPAP machines can be programmed to perform a titration as an alternative to having it done in a sleep laboratory. However, automatic CPAP machines typically cost a great deal more than fixed pressure machines, making this approach unavailable to many people as well. Additionally, automatic CPAP devices by may cause central apneas while trying to eliminate obstructive events. In these situations, fixed CPAP devices may yield a better therapeutic effect.

Because of these shortcomings, it has been recognized that a need exists for more convenient and inexpensive methods of providing diagnosis and treatment for sleep apnea. In a general embodiment of the present disclosure, a method of determining a continuous positive airway pressure (CPAP) suitable for treatment of sleep apnea is provided. The method comprises the steps of acquiring one or more physiological measurements from a person while the person sleeps, and entering the measurements into a predictive model that then provides an optimal pressure based on the measurements. According to this method, the optimal pressure can be determined without performing a CPAP titration study either in a sleep laboratory or using an automatic CPAP device at home.

The measurements entered into the predictive model can be any direct biometric measurements and observations having relevance to sleep and respiration as well as scores or indices derived from such measurements and observations. As discussed above, AHI is one index that can be informative with regard to determining a therapeutic approach. As such, AHI can be used in a predictive model in accordance with embodiments of the present invention. Other non-limiting examples of suitable measurements and observations include height, weight, age, gender, neck circumference, body mass index, Mallampati airway score, snoring incidence and related sounds, oxyhemoglobin saturation, pulse oximetry waveforms, EEGs, EMGs, EOGs, ECGs, airway vibration, upper airway resistance, natural respiratory airflow (without aid of a CPAP machine), natural respiratory effort (without aid of a CPAP machine), and sleep stage patterns. All of these may be used, or any combination of them, depending on the predictive model used and the inputs it requires. In a particular embodiment, the predictive model is a neural network model. Another embodiment of the present disclosure provides a method of providing an effective continuous positive airway pressure for treatment of sleep apnea, comprising conducting a sleep study on an person by using a recording apparatus configured to acquire one or more measurements as described above from the person while the person sleeps. The measurements are retrieved from the apparatus and entered into a predictive model that provides an optimal pressure based on the measurements. In a particular embodiment, the predictive model is an artificial neural network. A CPAP machine is then configured to produce the optimal pressure when in functional connection with an airway of the person; and then used to treat the person. According to this method, the optimal pressure is determined without performing a CPAP titration study.

In another general embodiment, the present disclosure sets forth a method for providing sleep apnea treatment services to a person in need of such services, comprising providing a recording apparatus to a home of a person, wherein said recording apparatus is configured to acquire one or more measurements from the person, and conducting a sleep study on the person at the home by using the recorder to acquire the measurements while the person sleeps. The measurements are retrieved from the apparatus and entered into a computer on which a computer-readable neural network model code is embodied, wherein said neural network model provides an optimal pressure based on the measurements. A CPAP machine is provided to the person, wherein the CPAP machine is configured to produce the optimal pressure when in functional connection with an airway of the person. According to this method the optimal pressure is determined without performing a CPAP titration study. Furthermore, the CPAP machine used is not an automatic CPAP machine.

In each of the above embodiments, the CPAP machine used does not have to be an automatic CPAP machine, as the pressure is provided without the need for titration, but rather, is calculated based on other measurements such as described above. In a more particular aspect, the sleep study in each embodiment can be conducted at the home of the person. In another aspect, the step of acquiring the sleep study is conducted substantially by the person himself or herself {with the optional set up help from a trained practitioner). In another specific embodiment, in each embodiment, the neural network model can comprise a general regression neural network. In yet another aspect of each embodiment, one or more verification studies may be conducted at the person's home after the CPAP machine has been provided and is in use. These verification studies are not required, but can be carried out if desired. Additionally, though not required, measurements related to the CPAP itself may optionally be carried out.

These methods provide cost-effective and convenient approaches to the aforementioned problems, as they reduce or even eliminate the need for in-lab overnight studies. One element of the approach provided by this disclosure is the use of neural network models. In recent times, neural network models have been created which can closely approximate the behavior of actual networks of neurons or neural centers found in the human nervous system. While neural models may be represented on paper by relevant mathematic equations, such models are often embodied in program code so that they may be executed on a computer. One such application of this technology is for modeling sleep-related neurophysiology, and artificial neural networks have been recently developed that show a high degree of accuracy in predicting optimal pressure based on certain physical measurements placed in the input layer. One example of such a network is described in El SoIh, et al., Sleep Medicine 8:471-77 (2007) which is hereby incorporated by reference in its entirety.

In one specific embodiment, a method of determining a CPAP suitable for treating sleep apnea comprises first acquiring one or more relevant physiological measurements from a person. Measurements can be acquired while the person sleeps. In particular embodiments, some measurements (e.g. physical dimensions and metrics other than sleeping events) can be obtained while the person is awake. Still other measurements can be obtained after the sleep observation period by deriving them from observations made during sleep. Then the measurements can be entered into a neural network model. In more specific embodiments, the model used comprises a general regression neural network. The model is then used to predict the optimal pressure based on those measurements. By using the neural model to predict optimum pressure, the need for a CPAP titration study is avoided. Combining this approach with the use of a home sleep study provides even further benefits by totally eliminating the need for an in-laboratory overnight study in diagnosing and treating sleep apnea.

Accordingly, another embodiment of the present disclosure provides a sleep apnea treatment method in which optimal pressure can be determined without the need to perform a CPAP titration study or to resort to the use of automatic CPAP machines. The first step in this approach is to conduct a sleep study on a person who may be suffering from sleep apnea in order to acquire measurements to serve as inputs to a neural network model. The sleep study can involve the use of a recording apparatus configured to acquire the needed measurements. In a more particular embodiment, the measurements can include any combination of those discussed above. In one aspect, certain data may not require actual measurements to be made on that particular occasion, and may instead be provided by the person through completion of a questionnaire. As such, the recording apparatus may in fact be an assemblage of individual devices, each configured for acquiring a needed measurement. This sleep study may be a home sleep study so as to eliminate the need for in-laboratory polysomnography. As such, in another particular embodiment the measurements are taken in the home of the person. In yet another embodiment, the person conducts the sleep study herself. In one aspect, the person is responsible for completion of substantially all of the study, including set up of recording equipment. In an alternative aspect, sleep laboratory personnel can set up the recording apparatus, including attaching any electrodes or other leads. In still another aspect, sleep laboratory personnel insures proper attachment of leads, while the actual connection of the recording apparatus to the leads is accomplished by the subject before going to sleep.

After sleep is completed and the measurements made, the measurements are retrieved from the apparatus in the storage form provided by the apparatus or its individual components, e.g. magnetic tape, paper printout or chart, or electronic data stored on a hard drive or flash memory. The measurements are then entered into the neural network model, which provides an optimal pressure based on the measurements. This optimal pressure is used as the pressure setting for a fixed pressure CPAP machine which is then used to treat the person. As a result, the person is provided with CPAP treatment at the optimal pressure without the time or expense of a CPAP titration study or the expense of an automatic CPAP machine. After the CPAP machine has been provided to the patient, it may be desirable to gain further information about the progress of treatment. Accordingly, in a particular aspect, one or more verification studies may be conducted at the person's home, in each of which measurements are taken from the person while the person is sleeping and wearing the CPAP machine. These verification studies are not required, but can be carried out if desired. Additionally, though not required, measurements related to the CPAP itself may optionally be carried out.

The convenience and cost effectiveness of the approach of the present disclosure make it a useful alternative to traditional sleep laboratory based diagnosis and treatment. As such, providers of sleep-related medical services may better serve certain markets and populations with this approach. Accordingly, the methods of the present disclosure can form the basis of a method of providing sleep apnea treatment services in which in-laboratory studies are not needed. As such, a provider who is selected by a person in need of diagnosis and possibly treatment can supply such a person with recording apparatus as described above at the person's home. A home sleep study is conducted on the person there, where the study comprises using the apparatus to acquire measurements while the person sleeps. As discussed above, some measurement data may be provided by questionnaire. The apparatus may be operated by personnel of the provider, by the person to be treated, or both in combination. The provider then retrieves the measurement data from the apparatus (and the questionnaire if applicable) and enters them into a neural network model. In a particular aspect, the model may be embodied in software running on a computer. The model is used to predict an optimal pressure, which is used to set a CPAP machine for use by the person. In a particular aspect, one or more verification studies are conducted at the person's home, in each of which measurements are taken from the person while the person is sleeping and wearing the CPAP machine. These verification studies are not required, but can be carried out if desired. Additionally, though not required, measurements related to the CPAP itself may optionally be carried out.

While the forgoing exemplary embodiments are illustrative of the principles of the present disclosure in one or more particular applications, it will be apparent to those of ordinary skill in the art that numerous modifications in form, usage and details of implementation can be made without the exercise of inventive faculty, and without departing from the principles and concepts of the disclosure. Accordingly, it is not intended that the disclosure be limited, except as by the claims set forth below.

Claims

CLAIMSWhat Is Claimed Is:

1. A method of setting an effective continuous positive airway pressure

(CPAP) for treatment of sleep apnea, comprising:

(a) conducting a sleep study on an person, wherein the sleep study comprises using a recording apparatus configured to acquire one or more measurements from the person while the person sleeps; (b) retrieving the measurements from the recording apparatus;

(c) entering the measurements into a predictive model, wherein said predictive model provides an optimal pressure based on the measurements; and

(d) configuring a CPAP machine to produce the optimal pressure when in communication with an airway passage of the person, wherein the optimal pressure is determined without conducting a CPAP titration study on the person, and wherein the CPAP machine used is not an automatic CPAP machine.

2. The method of claim 1 , wherein the predictive model comprises a neural network model.

3. The method of claim 2, wherein the neural network model comprises a general regression neural network.

4. The method of claim 1 , wherein the predictive model comprises a statistical algorithm.

5. The method of claim 1 , further comprising the step of using the CPAP machine to treat the person.

6. The method of claim 5, comprising a further step of conducting a verification study at the home, wherein said study comprises using the recording apparatus to acquire one or more measurements from the person while using the CPAP machine.

7. The method of claim 1 , wherein the sleep study is conducted at a home of the person.

8. The method of claim 1 , wherein the sleep study is conducted substantially by the person.

9. The method of claim 1 , wherein the measurements are selected from the group consisting of height, weight, age, gender, neck circumference, body mass index, Mallampati airway score, snoring incidence, snoring sounds, oxyhemoglobin saturation, pulse oximetry waveform, electroencephalogram, electromyogram, electrooculogram, electrocardiogram, airway vibration, upper airway resistance, natural respiratory airflow, natural respiratory effort, sleep stage patterns, and combinations or derivations thereof.

10. A method of determining a continuous positive airway pressure (CPAP) suitable for treatment of sleep apnea, comprising: (a) acquiring measurements from a person, wherein the measurements are at least in part acquired using a recording apparatus configured to acquire measurements while the person sleeps, and wherein the measurements are acquired without the aid of a CPAP machine; and

(b) entering the measurements into a predictive model, wherein said predictive model provides an optimal pressure based on the measurements, wherein the optimal pressure is determined without performing a CPAP titration study.

11. The method of claim 10, wherein the predictive model comprises a neural network model.

12. The method of claim 11 , wherein the neural network model comprises a general regression neural network.

13. The method of claim 10, wherein the predictive model comprises a statistical algorithm.

14. The method of claim 10, wherein the measurements are acquired at a home of the person.

15. The method of claim 10, wherein the acquiring step is substantially performed by the person.

16. The method of claim 10, wherein the measurements are selected from the group consisting of height, weight, age, gender, neck circumference, body mass index, Mallampati airway score, snoring incidence, snoring sounds, oxyhemoglobin saturation, pulse oximetry waveform, electroencephalogram, electromyogram, electrooculogram, electrocardiogram, airway vibration, upper airway resistance, natural respiratory airflow, natural respiratory effort, sleep stage patterns, and combinations or derivations thereof.

17. A method for providing sleep apnea treatment services to a person in need of such services, comprising:

(a) providing a recording apparatus to a home of a person, wherein said recording apparatus is configured to acquire one or more measurements from the person;

(b) conducting a sleep study on the person at the home, wherein the sleep study comprises using the recorder to acquire the measurements while the person sleeps;

(c) retrieving the measurements from the recorder; (d) entering the measurements into a computer on which a predictive model code is embodied, wherein said predictive model provides an optimal pressure based on the measurements; and (e) providing a CPAP machine to the person in their home, wherein the CPAP machine is configured to produce the optimal pressure when in communication with an airway of the person, wherein the optimal pressure is determined without conducting a CPAP titration study on the person and wherein the CPAP machine used is not an automatic CPAP machine.

18. The method of claim 17, wherein the predictive model comprises a neural network model.

19. The method of claim 17, wherein the neural network model comprises a general regression neural network.

20. The method of claim 17, wherein the predictive model comprises a statistical algorithm.

21. The method of claim 17, wherein the sleep study further comprises the person completing a questionnaire to provide one or more measurements.

22. The method of claim 17, wherein the sleep study is conducted substantially by the person.

23. The method of claim 17, wherein the measurements are selected from the group consisting of height, weight, age, gender, neck circumference, body mass index, Mallampati airway score, snoring incidence, snoring sounds, oxyhemoglobin saturation, pulse oximetry waveform, electroencephalogram, electromyogram, electrooculogram, electrocardiogram, airway vibration, upper airway resistance, natural respiratory airflow, natural respiratory effort, sleep stage patterns, and combinations or derivations thereof.

24. The method of claim 17, wherein all of the steps are performed at the home.

25. The method of claim 17, comprising a further step of conducting a verification study at the home, wherein said study comprises using the recording apparatus to acquire one or more measurements from the person while using the CPAP machine.