U.S. patent application number 17/363714 was filed with the patent office on 2022-01-20 for contextualized personalized insomnia therapy regimen, system, and method.
The applicant listed for this patent is KONINKLIJKE PHILIPS N.V.. Invention is credited to Xia CHEN, Benjamin Irwin SHELLY, Dirk Ernest VON HOLLEN.
Application Number | 20220020461 17/363714 |
Document ID | / |
Family ID | |
Filed Date | 2022-01-20 |
United States Patent
Application |
20220020461 |
Kind Code |
A1 |
SHELLY; Benjamin Irwin ; et
al. |
January 20, 2022 |
CONTEXTUALIZED PERSONALIZED INSOMNIA THERAPY REGIMEN, SYSTEM, AND
METHOD
Abstract
A system and method for providing a recommendation of an
insomnia therapy leverage various metrics including personal health
profile, 24/7 biometrics, behavioral information, and environmental
stressors to predict insomnia severity, to build a personalized
severity and type insomnia therapy map ranked by historic therapy
efficacy, to provide a contextualized personalized therapy
recommendation, and to optimize the insomnia therapy.
Inventors: |
SHELLY; Benjamin Irwin;
(Pittsburgh, PA) ; CHEN; Xia; (Lorton, VA)
; VON HOLLEN; Dirk Ernest; (Clark, NJ) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
KONINKLIJKE PHILIPS N.V. |
Eindhoven |
|
NL |
|
|
Appl. No.: |
17/363714 |
Filed: |
June 30, 2021 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
63054197 |
Jul 20, 2020 |
|
|
|
International
Class: |
G16H 20/00 20060101
G16H020/00; A61B 5/00 20060101 A61B005/00; G16H 50/70 20060101
G16H050/70; G06N 20/00 20060101 G06N020/00 |
Claims
1. A method of providing a recommendation of an insomnia therapy to
a patient, comprising: for each of a plurality of periods of
attempted sleep by the patient: determining a predicted insomnia
severity that is based at least in part upon an insomnia severity
prediction model; outputting a recommendation of an insomnia
therapy from among a plurality of insomnia therapies based at least
in part upon the predicted insomnia severity and an insomnia
therapy map of the patient, the insomnia therapy map including a
corresponding efficacy for each of the plurality of insomnia
therapies; determining an actual insomnia severity that is based at
least in part upon a number of insomnia symptoms in the patient;
determining an efficacy of the insomnia therapy based at least in
part upon the predicted insomnia severity and the actual insomnia
severity; and updating the insomnia therapy map to reflect the
efficacy.
2. The method of claim 1, further comprising: determining an
insomnia type that is based at least in part upon at least one of
an insomnia type trend in the patient and the number of insomnia
symptoms; and outputting the recommendation of the insomnia therapy
further based at least in part upon the insomnia type.
3. The method of claim 2 wherein the insomnia therapy map comprises
a table having a plurality of insomnia severities, a plurality of
insomnia types, the plurality of insomnia therapies, and the
corresponding efficacies, the insomnia therapy map further
comprising, for a given insomnia severity of the plurality of
insomnia severities and for a given insomnia type plurality of
insomnia types, a plural quantity of insomnia therapies and a
plural quantity of corresponding efficacies, and further
comprising: for a given period of attempted sleep: determining that
the actual insomnia severity is the given insomnia severity;
determining that the insomnia type is the given insomnia type; and
outputting as the recommendation the insomnia therapy from among
the plural quantity of insomnia therapies whose corresponding
efficacy is the greatest.
4. The method of claim 3 further comprising, for another period of
attempted sleep subsequent to the given period of attempted sleep,
outputting as the recommendation an insomnia therapy from among the
plural quantity of insomnia therapies whose corresponding efficacy
is other than the greatest.
5. The method of claim 1, further comprising: detecting as a set of
insomnia indication data one or more of: a number of sleep metrics
and/or a sleep debt via a sleep metrics sensing module, a number of
caffeine intake amounts and timings via a related behaviors sensing
module, an exercise intensity and timing via an activity metrics
sensing module, a room temperature and/or a stress level via a
personal and environmental stressor sensing module, an alertness
via an alertness sensing module, and a number of chronic conditions
via a personal profile; in a training phase of the insomnia
severity prediction model, generating the insomnia severity
prediction model by building a machine learning model based at
least in part upon at least a portion of the set of insomnia
indication data; and deploying the insomnia severity prediction
model.
6. The method of claim 2 further comprising, for a given period of
attempted sleep, outputting as the recommendation of the insomnia
therapy a recommendation of an insomnia therapy from among the
plurality of insomnia therapies that includes a pharmacological
therapy from among a plurality of pharmacological therapies.
7. The method of claim 6 further comprising, for another period of
attempted sleep subsequent to the given period of attempted sleep,
outputting as the recommendation of the insomnia therapy a
recommendation of another insomnia therapy from among the plurality
of insomnia therapies other than the pharmacological therapy.
8. The method of claim 6 further comprising, for another period of
attempted sleep subsequent to the given period of attempted sleep,
outputting as the recommendation of the insomnia therapy a
recommendation of another insomnia therapy from among the plurality
of insomnia therapies that includes another pharmacological therapy
from among a plurality of pharmacological therapies other than the
pharmacological therapy.
9. The method of claim 6, further comprising detecting in the
patient a potential tolerance for the pharmacological therapy and,
responsive thereto, outputting as the recommendation of the
insomnia therapy a recommendation of other than the pharmacological
therapy for a predetermined period of time.
10. The method of claim 1, further comprising detecting as the
number of insomnia symptoms at least one of a number of sleep
metrics and a number of next day alertness metrics, the number of
sleep metrics comprising one or more of a Sleep Efficiency (SE), a
Wake After Sleep Onset (WASO), a number of awakenings, a Sleep
Onset Latency (SOL), a deep sleep percentage, and a Total Sleep
Time (TST), and the number of next day alertness metrics comprising
one or more of a PERcentage of eyelid CLOSure over the time
(PERCLOS), a number of naps, and a duration of naps.
11. A system structured and configured to provide a recommendation
of an insomnia therapy to a patient, comprising: a processor
apparatus comprising a processor and a storage; an input apparatus
structured to provide input signals to the processor apparatus and
comprising one or more of a sleep metrics sensing module comprising
a photoplethysmogram (PPG), an alertness sensing module, an
activity metrics sensing module comprising at least one of a step
counter and a Global Positioning System (GPS) sensor, a personal
and environmental stressor sensing module comprising at least one
of a Galvanic Skin Response (GSR) sensor and a room temperature
sensor, a related behaviors sensing module, and a personal profile;
an output apparatus structured to receive output signals from the
processor apparatus and to generate outputs; the storage having
stored therein a number of routines which, when executed on the
processor, cause the system to perform operations comprising: for
each of a plurality of periods of attempted sleep by the patient:
determining a predicted insomnia severity that is based at least in
part upon an insomnia severity prediction model; outputting a
recommendation of an insomnia therapy from among a plurality of
insomnia therapies based at least in part upon the predicted
insomnia severity and an insomnia therapy map of the patient, the
insomnia therapy map including a corresponding efficacy for each of
the plurality of insomnia therapies; determining an actual insomnia
severity that is based at least in part upon a number of insomnia
symptoms in the patient; determining an efficacy of the insomnia
therapy based at least in part upon the predicted insomnia severity
and the actual insomnia severity; and updating the insomnia therapy
map to reflect the efficacy.
12. The system of claim 11 wherein the operations further comprise:
determining an insomnia type that is based at least in part upon at
least one of an insomnia type trend in the patient and the number
of insomnia symptoms; and outputting the recommendation of the
insomnia therapy further based at least in part upon the insomnia
type.
13. The system of claim 12 wherein the insomnia therapy map
comprises a table having a plurality of insomnia severities, a
plurality of insomnia types, the plurality of insomnia therapies,
and the corresponding efficacies, the insomnia therapy map further
comprising, for a given insomnia severity of the plurality of
insomnia severities and for a given insomnia type plurality of
insomnia types, a plural quantity of insomnia therapies and a
plural quantity of corresponding efficacies, and wherein the
operations further comprise: for a given period of attempted sleep:
determining that the actual insomnia severity is the given insomnia
severity; determining that the insomnia type is the given insomnia
type; and outputting as the recommendation the insomnia therapy
from among the plural quantity of insomnia therapies whose
corresponding efficacy is the greatest.
14. The system of claim 13 wherein the operations further comprise,
for another period of attempted sleep subsequent to the given
period of attempted sleep, outputting as the recommendation an
insomnia therapy from among the plural quantity of insomnia
therapies whose corresponding efficacy is other than the
greatest.
15. The system of claim 14 wherein the operations further comprise:
detecting as a set of insomnia indication data one or more of: a
number of sleep metrics and/or a sleep debt via the sleep metrics
sensing module, a number of caffeine intake amounts and timings via
the related behaviors sensing module, an exercise intensity and
timing via the activity metrics sensing module, a room temperature
and/or a stress level via the personal and environmental stressor
sensing module, an alertness via the alertness sensing module, and
a number of chronic conditions via the personal profile; in a
training phase of the insomnia severity prediction model,
generating the insomnia severity prediction model by building a
machine learning model based at least in part upon at least a
portion of the set of insomnia indication data; and deploying the
insomnia severity prediction model.
16. The system of claim 12 wherein the operations further comprise,
for a given period of attempted sleep, outputting as the
recommendation of the insomnia therapy a recommendation of an
insomnia therapy from among the plurality of insomnia therapies
that includes a pharmacological therapy from among a plurality of
pharmacological therapies.
17. The system of claim 16 wherein the operations further comprise,
for another period of attempted sleep subsequent to the given
period of attempted sleep, outputting as the recommendation of the
insomnia therapy a recommendation of another insomnia therapy from
among the plurality of insomnia therapies other than the
pharmacological therapy.
18. The system of claim 16 wherein the operations further comprise,
for another period of attempted sleep subsequent to the given
period of attempted sleep, outputting as the recommendation of the
insomnia therapy a recommendation of another insomnia therapy from
among the plurality of insomnia therapies that includes another
pharmacological therapy from among a plurality of pharmacological
therapies other than the pharmacological therapy.
19. The system of claim 16 wherein the operations further comprise
detecting in the patient a potential tolerance for the
pharmacological therapy and, responsive thereto, outputting as the
recommendation of the insomnia therapy a recommendation of other
than the pharmacological therapy for a predetermined period of
time.
20. The system of claim 11 wherein the operations further comprise
detecting as the number of insomnia symptoms at least one of a
number of sleep metrics and a number of next day alertness metrics,
the number of sleep metrics comprising one or more of a Sleep
Efficiency (SE), a Wake After Sleep Onset (WASO), a number of
awakenings, a Sleep Onset Latency (SOL), a deep sleep percentage,
and a Total Sleep Time (TST), and the number of next day alertness
metrics comprising one or more of a PERcentage of eyelid CLOSure
over the time (PERCLOS), a number of naps, and a duration of naps.
Description
CROSS-REFERENCE TO PRIOR APPLICATION
[0001] 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
[0002] The present invention pertains to a system and method for
providing a recommendation of an insomnia therapy and, in
particular, to an apparatus and method to leverage various metrics
including personal health profile, 24/7 biometrics, behavioral
information, and environmental stressors to predict insomnia
severity, to build a personalized severity and type insomnia
therapy map ranked by historic therapy efficacy, to provide a
contextualized personalized therapy recommendation, and to optimize
the insomnia therapy.
2. Description of the Related Art
[0003] Insomnia interventions include Cognitive Behavioral Therapy
for Insomnia (CBTI) and pharmacologic therapy. CBTI is typically
regarded as the gold standard for insomnia as it is typically
considered curative. However, CBTI often requires in-person therapy
sessions by a trained clinician. Recently, digital CBTI programs
have been developed in order to increase the availability of this
curative therapy.
[0004] However, while CBTI is effective, it typically requires the
user to go through a series of modules, including sleep
consolidation therapy (or sleep restriction therapy), stimulus
control instructions, sleep hygiene education, relaxation
techniques, and cognitive techniques. While effective, CBTI
requires commitment and behavior change in order for a patient to
see successful outcomes, where sleep consolidation therapy, in
particular, requires an extended period of time where the user may
build a significant amount of sleep debt and may thus have
difficulty maintaining daytime alertness. Thus, CBTI, while
effective, often suffers from poor adherence, especially with
digital versions.
[0005] Low adherence to CBTI, especially digital CBTI programs, is
an issue that limits effectiveness of insomnia treatment.
Specifically, it has been difficult to determine which specific
therapy or combination of therapies works for an individual. These
difficulties are a significant cause of prolonged unimproved
insomnia conditions, associated metabolic conditions, and cognitive
deficiencies.
[0006] Thus, pharmacotherapy (either OTC (e.g. sedative
antihistamines) or prescription) remains the most common
intervention for insomnia. However, insomnia sufferers are not
given daily dosing strategies, and pharmacotherapy suffers from a
risk of tolerance and habituation. Improvements in the treatment of
insomnia thus would be desirable.
SUMMARY OF THE INVENTION
[0007] Accordingly, it is an object of the present invention to
provide an improved system and method for providing insomnia
therapy that overcome the shortcomings of conventional systems and
methods for providing and assessing insomnia therapy. This object
is achieved according to one embodiment of the present invention by
providing an apparatus and method that leverage various metrics
including one or more of a personal health profile, 24/7
biometrics, behavioral information, and environmental stressors to
predict insomnia severity, to build a personalized severity and
type insomnia therapy map ranked by historic therapy efficacy, to
provide a contextualized personalized therapy recommendation, and
to optimize the insomnia therapy
[0008] Without knowing what insomnia therapy works for a person and
when to apply it on a daily basis, an insomnia therapy cannot
achieve its expected efficacy. The system and method of the
disclosed and claimed concept advantageously meet these and other
objectives. The overall concept of the disclosed and claimed
concept includes 24/7 personal and environmental
sensing/monitoring, insomnia severity estimation and type trending
from insomnia symptoms, insomnia severity prediction from
behaviors, biometrics, and stressors (personal and/or
environmental), and therapy recommendation from personalized
insomnia severity and type therapy mapping, and therapy efficacy
evaluation.
[0009] The system advantageously includes a predictive model to
estimate insomnia severity through monitoring a user's personal
profile (e.g. Electronic Health Record (EHR) that documents patient
conditions such as chronic conditions, meds, etc.), behaviors,
biometrics, and personal/environmental stressors (e.g. temperature,
stressful events, stress level, activity level and intensity and
timing), sleep metrics (e.g. naps and timing), sleep related
behaviors (e.g. caffeine and alcohol consumption and timing) and a
recommendation module to provide a personalized insomnia therapy
recommendation with the maximum possible efficacy to the user.
[0010] Although the core therapy for insomnia is CBTI, it also may
be required to additionally prescribe a number of medications if
CBTI alone doesn't improve the condition(s). As employed herein,
the expression "a number of" and variations thereof shall refer
broadly to any non-zero quantity, including a quantity of one. For
different types of insomnia (e.g. sleep onset insomnia, sleep
maintenance insomnia, etc.), the prescribed medication(s) could be
different. For instance, suvorexant and doxepin are recommended for
sleep maintenance insomnia, whereas zaleplon, triazolam, and
ramelteon are recommended for sleep onset insomnia. Some of the
medicines are type-agnostic, such as, eszopiclone, zolpidem, and
temazepam. Therefore, the proposed system advantageously considers
both insomnia severity and insomnia type when building the
personalized insomnia therapy map.
[0011] The system also includes an insomnia metrics evaluation
module to estimate an insomnia severity and to also trend over time
an insomnia type based on various sleep metrics (e.g. Sleep Onset
Latency (SOL), Wake After Sleep Onset (WASO), Sleep Efficiency
(SE), number of awakenings and associated durations, Total Sleep
Time (TST)) and alertness metrics (e.g. PERCLOS--PERcentage of
eyelid CLOSure over the time).
[0012] Furthermore, the system includes a therapy efficacy
evaluation module to evaluate the efficacy of various insomnia
therapies based on a comparison between the actual insomnia
severity and the predicted insomnia severity, where the actual
insomnia severity is estimated by the aforementioned insomnia
metrics evaluation module.
[0013] To provide a personalized therapy recommendation, the
improved system builds a personalized insomnia therapy map that
includes insomnia severity and insomnia type versus therapy and is
sorted based on the efficacy of the therapy (i.e. the top of the
list has the maximum efficacy). Additionally, the system
advantageously provides therapy regimen switching or cycling among
available insomnia therapies in order to avoid desensitization to
the interventions and potential side effects. Especially when the
system recommends a less efficacious therapy, such as to avoid
desensitization to a more effective therapy, it may recommend
multiple prioritized interventions during a given period of
attempted sleep, i.e., for a given evening, in order to maintain
efficacy. As the system is continuously used by a user, this
insomnia therapy map will be updated to better reflect the various
insomnia therapies that have been effective for the person, i.e.,
the patient, so that the system and insomnia therapy map
advantageously support the personalized therapy
recommendations.
[0014] Accordingly, aspects of the disclosed and claimed concept
are provided by an improved method of providing a recommendation of
an insomnia therapy to a patient, the general nature of which can
be stated as including, for each of a plurality of periods of
attempted sleep by the patient, determining a predicted insomnia
severity that is based at least in part upon an insomnia severity
prediction model, outputting a recommendation of an insomnia
therapy from among a plurality of insomnia therapies based at least
in part upon the predicted insomnia severity and an insomnia
therapy map of the patient, the insomnia therapy map including a
corresponding efficacy for each of the plurality of insomnia
therapies, determining an actual insomnia severity that is based at
least in part upon a number of insomnia symptoms in the patient,
determining an efficacy of the insomnia therapy based at least in
part upon the predicted insomnia severity and the actual insomnia
severity, and updating the insomnia therapy map to reflect the
efficacy.
[0015] Other aspects of the disclosed and claimed concept are
provided by an improved system structured and configured to provide
a recommendation of an insomnia therapy to a patient, the general
nature of which can be stated as including a processor apparatus
that can be generally stated as including a processor and a
storage, an input apparatus structured to provide input signals to
the processor apparatus and that can be generally stated as
including one or more of a sleep metrics sensing module that can be
generally stated as including a photoplethysmogram (PPG), an
alertness sensing module, an activity metrics sensing module that
can be generally stated as including at least one of a step counter
and a Global Positioning System (GPS) sensor, a personal and
environmental stressor sensing module that can be generally stated
as including at least one of a Galvanic Skin Response (GSR) sensor
and a room temperature sensor, a related behaviors sensing module,
and a personal profile, an output apparatus structured to receive
output signals from the processor apparatus and to generate
outputs, the storage having stored therein a number of routines
which, when executed on the processor, cause the system to perform
operations that can be generally stated as including, for each of a
plurality of periods of attempted sleep by the patient, determining
a predicted insomnia severity that is based at least in part upon
an insomnia severity prediction model, outputting a recommendation
of an insomnia therapy from among a plurality of insomnia therapies
based at least in part upon the predicted insomnia severity and an
insomnia therapy map of the patient, the insomnia therapy map
including a corresponding efficacy for each of the plurality of
insomnia therapies, determining an actual insomnia severity that is
based at least in part upon a number of insomnia symptoms in the
patient, determining an efficacy of the insomnia therapy based at
least in part upon the predicted insomnia severity and the actual
insomnia severity, and updating the insomnia therapy map to reflect
the efficacy.
[0016] These and other objects, features, and characteristics of
the present invention, 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
[0017] FIG. 1 is a depiction of an improved system in accordance
with an aspect of the disclosed and claimed concept;
[0018] FIG. 2 is a depiction of a training phase for building an
insomnia severity prediction model of the system of FIG. 1;
[0019] FIG. 3 is a depiction of a training phase for building an
insomnia therapy map of the system of FIG. 1;
[0020] FIG. 4 is a depiction of the system of FIG. 1 in a
deployment phase;
[0021] FIG. 5 is a further depiction of the system of FIG. 4;
and
[0022] FIG. 6 is a flow chart depicting certain aspects of an
improved method in accordance with the disclosed and claimed
concept.
DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS
[0023] As used herein, the singular form of "a", "an", and "the"
include plural references unless the context clearly dictates
otherwise. As used herein, the statement that two or more parts or
components are "coupled" shall mean that the parts are joined or
operate together either directly or indirectly, i.e., through one
or more intermediate parts or components, so long as a link occurs.
As used herein, "directly coupled" means that two elements are
directly in contact with each other. As used herein, "fixedly
coupled" or "fixed" means that two components are coupled so as to
move as one while maintaining a constant orientation relative to
each other.
[0024] As used herein, the word "unitary" means a component is
created as a single piece or unit. That is, a component that
includes pieces that are created separately and then coupled
together as a unit is not a "unitary" component or body. As
employed herein, the statement that two or more parts or components
"engage" one another shall mean that the parts exert a force
against one another either directly or through one or more
intermediate parts or components. As employed herein, the term
"number" shall mean one or an integer greater than one (i.e., a
plurality).
[0025] 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.
24/7 Personal and Environmental Sensing/Monitoring:
[0026] The disclosed and claimed system 4 and method advantageously
collects personal profile data (e.g. EHR (chronic condition(s),
medication(s)) and monitors various metrics including but not
limited to sleep metrics (e.g. WASO, SOL, SE, TST, number of
awakenings, sleep stages), activity metrics (e.g. step count,
duration, distance, intensity, timing), alertness metrics (e.g.
PERCLOS, nap frequency, nap duration), stressors (e.g. Heart Rate
(HR), blood pressure, skin conductance, environment temperature),
behaviors (e.g. sleep hygiene, caffeine intake frequency and
timing), etc. The proposed system monitors these metrics through
multi-modality sensors such as under mattress sensors, wearable
sensors, etc. In some embodiment, the disclosed and claimed concept
includes subjective responses by a patient to a digital survey
(e.g. medication side effects).
Insomnia Severity Estimation and Type Trending from Insomnia
Symptoms:
[0027] In the disclosed and claimed concept, a patient's insomnia
severity is defined by a set of predetermined levels. In the
disclosed exemplary embodiment, the predetermined levels are four
in quantity (e.g. none, mild, moderate, and severe) based on
validated Insomnia Severity Index (ISI). Instead of the
determination of an ISI depending on a user's subjective responses
to a number of survey questions, the disclosed and claimed concept
advantageously uses multiple sensors, such as may include one or
more of a photoplethysmogram (PPG), a step counter, a Global
Positioning System (GPS) sensor, a HR sensor, a Galvanic Skin
Response (GSR) sensor, a room temperature sensor) to obtain a
number of objective insomnia-related physiological measures, such
as, SOL, WASO, SE, TST, activity timing, duration, and intensity,
and alertness, and further develops a formula to integrate all the
various metrics into an insomnia severity score (e.g. maximum is
100) and map to a predefined insomnia severity level. The formula
can be any type of polynomial or other formula that can combine the
various metrics and weight them according to various criteria, etc.
In some embodiments, this mapping can be shown as in the following
Table 1:
TABLE-US-00001 TABLE 1 Mapping between insomnia severity score and
insomnia severity level Insomnia Severity Score (0-100) Insomnia
Level (4 levels) 0-24 none 25-49 mild 50-74 moderate 75-100
severe
[0028] This method can be used for evaluating the actual insomnia
severity level while an insomnia therapy (or no therapy) is applied
to an individual patient. In addition, this module advantageously
trends an insomnia type over a predefined moving time window (e.g.
weekly) to inform the therapy recommendation.
Insomnia Severity Prediction from Behaviors, Biometrics, and
Stressors (Personal/Environmental):
[0029] To build an insomnia severity prediction model 8 of the
system 4, the present invention captures the indications/data that
are relevant insomnia severity. These indications/data include one
or more of sleep metrics (last night), sleep debt, stress level,
caffeine intake amount and timing, late and hard exercises, hot or
cold room temperature, etc. and are collected through a sleep
metrics sensing module 74, a related behaviors sensing module 90,
an activity metrics sensing module 78, a personal stressor sensing
module 83, an environmental stressor sensing module 84, and a
personal profile 92 (e.g. chronic conditions and other conditions).
In addition, the system 4 collects insomnia metrics such as sleep
metrics (tonight) via a sleep metrics sensing module 72 and
alertness metrics (tomorrow) via an alertness sensing module 76 to
evaluate the insomnia severity via an insomnia metrics evaluation
module 40 that can be said to include the sleep metrics sensing
module 72 and the alertness sensing module 76. Based on the
collected data sets (insomnia severity, relevant metrics/data), the
disclosed and claimed concept advantageously builds a machine
learning model in a training phase as illustrated in FIG. 2. In a
deployment phase as shown in FIG. 4, this model is used as an
insomnia severity prediction model 8 to predict an actual insomnia
severity level (e.g. tonight) based on one or more of the relevant
behaviors, biometrics, and personal/environmental stressors (e.g.
past 24 hours), and projected bedtime, by way of example.
Personalized Severity & Type--Therapy Mapping:
[0030] To enable the system 4 to output a personalized insomnia
therapy recommendation, the disclosed and claimed concept
advantageously creates a personalized insomnia therapy map that
tracks insomnia severity and insomnia type based on the history of
therapy efficacy in the individual patient.
[0031] The disclosed and claimed concept advantageously begins with
a default insomnia therapy map that is not yet personalized but
that is instead based initially upon population data such as can be
derived from clinical guidelines, clinical study results, review
articles, etc. As an individual patient uses an insomnia therapy,
which is defined herein as being either a single insomnia therapy
or multiple therapies combined, the proposed system tracks the
specific therapy the actual insomnia severity, and the insomnia
type and also evaluates the resultant therapy efficacy so that a
personalized insomnia severity and type therapy map can be built
based on history of the personalized therapy efficacy.
[0032] As CBTI is the core therapy for insomnia and it contains
multiple aspects such as, sleep hygiene education, sleep
restriction therapy, etc., CBTI therapy contains many possible
methods. In addition, CBTI alone might not be enough, and
additional pharmacological therapy might be required for an
individual. However, some medications are specific to certain type
of insomnia. The disclosed and claimed concept thus advantageously
also trends the insomnia type of an individual patient over the
predefined period of time to inform the proper choice of the
medication, if needed. Hence, the disclosed and claimed concept
advantageously also includes the insomnia type along with the
insomnia severity in the insomnia therapy map.
[0033] Furthermore, the disclosed and claimed concept
advantageously saves up to a predefined quantity of therapies (up
to three, by way of example) for each combination of insomnia
severity level and insomnia type so that a plurality of
personalized alternative and optional insomnia therapies can be
recommended as well. To support the recommendation, the exemplary
insomnia therapy map illustrated in Table 2 below is organized as a
ranked list for each severity level based on the statistics of
efficacy history of an individual.
TABLE-US-00002 TABLE 2 Personalized Insomnia Severity and Insomnia
Type Therapy Map Insomnia Insomnia type Therapy IDs Severity
(Onset--O/ (ID with max Past Efficacies Level Maintenance--M)
efficacy-bolded) (Max-bolded) moderate O [3, 17, 25] [80, 68, 74]
moderate O & M [4, 11, 39] [55, 77, 69] moderate M [9, 33, 2]
[67, 69, 70] severe M [7, 19, 41] [75, 66, 70] severe O & M
[31, 8, 53] [65, 68, 60] severe O [6, 22, 40] [60, 50, 58] mild O
& M [45, 12, 18] [82, 90, 87] mild M [23, 37, 5] [80, 78, 84]
mild O [10, 26,35] [77, 63, 71]
[0034] In the disclosed and claimed concept, each therapy ID in
Table 2 can be one or more specific therapy methods. For instance,
Therapy ID 1 represents CBTI 1 (e.g. "choose a relaxing activity
for half an hour before bedtime") as illustrated in Table 3 below.
By way of further example, Therapy ID 7 represents a combination of
CBTI 1 and Med N (e.g. eszopiclone). In some embodiments, as an
individual patient continuously uses the proposed system, this
table becomes enhanced and personalized.
TABLE-US-00003 TABLE 3 Relationship of Therapy Identification and
Associated Therapy Choices Therapy Med N ID CBTI 1 . . . CBTI K Med
1 . . . (e.g. 15) 1 X 2 X 3 X 4 X X 5 X X X 6 X X 7 X X . . . X M
(e.g. 35) X X
Therapy Efficacy Evaluation:
[0035] To build a personalized insomnia severity and insomnia type
therapy ranked map informed by therapy efficacy, the disclosed and
claimed concept advantageously creates a therapy efficacy
evaluation module or method to evaluate therapy efficacy. The
disclosed and claimed concept advantageously evaluates the therapy
efficacy through the following processes.
[0036] Sleep quality score: The disclosed and claimed concept
advantageously determines a sleep quality score by using various
sleep metrics (e.g., using one or more of SE, WASO, number of
awakenings, SOL, deep sleep percentage, TST, etc.). The disclosed
and claimed concept advantageously monitors the sleep metrics of a
patient during the night while a specific therapy is in use. The
maximum sleep quality score representing the best sleep quality is
defined as 100.
[0037] Alertness score: The disclosed and claimed concept
advantageously determines a next-day alertness score by using
various metrics (e.g. PERCLOS, number of naps, and duration of
naps). The disclosed and claimed concept advantageously monitors
these metrics during the day after applying a therapy and evaluates
the alertness score. The maximum alertness score corresponding to
the maximum alertness is defined as 100.
[0038] Reduction score of insomnia severity: The disclosed and
claimed concept advantageously compares the predicted insomnia
severity (i.e. before going to the bed) from the insomnia severity
prediction model 8 with the actual insomnia severity informed by
the aforementioned sleep quality score and alertness score via an
insomnia metrics evaluation module 24 (i.e. measured during the
night while a specific therapy is in use) to estimate the reduction
score. In some embodiments, the insomnia metrics evaluation module
combines the results from the sleep quality score and the alertness
score into a composite score (i.e. insomnia severity score) that
corresponds to a predefined severity level. In some embodiments,
the reduction score is determined via a percentage reduction by
using a ratio (e.g. actual insomnia severity score/predicted
insomnia severity score). In some embodiments, the reduction score
is evaluated by the difference between the predicted insomnia
severity score and the actual severity score. The maximum reduction
score is defined as 100 which represents the maximum efficacy.
[0039] The disclosed and claimed concept advantageously evaluates
the therapy efficacy for each therapy used by a patient and saves
the therapy efficacy along with the insomnia severity and the
insomnia type and the specific therapy in the personalized insomnia
therapy map so that the insomnia therapy map reflect the ongoing
therapy efficacy in the patient of the various insomnia therapies
that have been employed. A building phase for building the insomnia
therapy map is illustrated in FIG. 3. This insomnia therapy map
evolves as the patient continues to use the system.
Therapy Recommendation:
[0040] As in shown in FIG. 3, to create an insomnia therapy map 44,
the system 4 advantageously creates a default therapy list (e.g.
single therapy or combined therapy) with a number of insomnia
severities and a number of insomnia types along with a number of
potential therapy efficacies that may be based upon population data
or otherwise. The disclosed and claimed system advantageously uses
this default list to initially provide an insomnia therapy
recommendation. As the patient continues to use the system 4, the
personalized insomnia therapy map 44 that lists insomnia severity
and insomnia type and that is ranked by corresponding therapy
efficacy is built, and the system 4 uses the insomnia therapy map
44 to provides a personalized recommendation to achieve optimized
therapy efficacy and to improve sleep quality of the patient as
illustrated in FIG. 4.
[0041] The system 4 includes a therapy recommendation module 48
that prioritizes therapy swapping in order to avoid
desensitization, habituation, or potential side effects from
chronic usage of a given therapy regimen. In one example,
prescription hypnotics are not recommended for any more than, for
instance, seven days per month. In another example, diphenhydramine
and doxylamine succinate (OTC sedating antihistamines) quickly
build a tolerance effect and are not recommended any more than, for
instance, four days per month. In alternative embodiments, the
tolerance effect for each sleep intervention is tracked
independently and, when a suspected tolerance is detected as having
begun to be built, as detected as a reduced efficacy of the
therapeutic intervention, as tracked and trended by a therapy
efficacy evaluation module 52 of the system, the intervention is
not recommended for a specific "abstinence period" (e.g. two
weeks).
[0042] In some embodiments, "no intervention required" is suggested
for nights when predicted insomnia severity is low. Alternatively,
typical sleep hygiene advice can be given on nights when predicted
insomnia severity is low (e.g. messaging such as, "You've had a
great day today and it'll soon be time to be ready for a great
night. Remember to take time to wind down before bed tonight. A
nice, calming activity before bed helps prepare the mind and body
for rest."). In alternative embodiments, a placebo treatment may be
recommended on nights with low to moderate insomnia severity (e.g.
lavender, etc.).
[0043] The apparatus 4 is depicted in FIGS. 4 and 5. Apparatus 4
can be employed in performing an improved method 100 that is
likewise in accordance with the disclosed and claimed concept and
at least a portion of which is depicted in a schematic fashion in
FIG. 6. Apparatus 4 can be characterized as including a processor
apparatus 56 that can be said to include a processor 60 and a
storage 64 that are connected with one another. Storage 64 is in
the form of a non-transitory storage medium that has stored therein
a number of routines 68 that are likewise in the form of a
non-transitory storage medium and that include instructions which,
when executed on processor 60, cause apparatus 4 to perform certain
operations such as are mentioned elsewhere herein.
[0044] In addition to the other components of system 4 noted
hereinbefore, system 4 includes the sleep metrics sensing module 72
comprising a photoplethysmogram (PPG) 74, the alertness sensing
module 76, the activity metrics sensing module 78 comprising at
least one of a step counter 80 and a Global Positioning System
(GPS) sensor 82, the personal stressor sensing module 83 comprising
a Galvanic Skin Response (GSR) sensor 86, the environmental
stressor sensing module 84 comprising a room temperature sensor 88,
the related behaviors sensing module 90, and the personal profile
92 of the patient. These can all be considered to be a part of an
input apparatus 94 of system 4 that provides input signals to
processor 60. System 4 further includes an output apparatus 96 that
receives output signals from processor 60 and that provides outputs
that are detectable by the patient, such as audible outputs, visual
outputs, and the like without limitation.
[0045] Certain aspects of the improved method 100 noted
hereinbefore are depicted in the flow chart shown generally in FIG.
6. For each of a plurality of periods of attempted sleep by the
patient, the method 100 performs the operations depicted generally
in FIG. 6. For instance, the method 100 includes determining, as at
105, a predicted insomnia severity based upon inputs from the
insomnia severity prediction model 8. The method 100 also includes
outputting, as at 110, a recommendation of an insomnia therapy
based upon the predicted insomnia severity and input from the
insomnia therapy map 44. The method 100 also includes determining,
as at 115, an actual insomnia severity that is based upon a number
of insomnia symptoms in the patient. The various insomnia symptoms
can be obtained via input apparatus 94. The method 100 further
includes determining, as at 120, an efficacy of the insomnia
therapy based upon the predicted insomnia severity and the actual
insomnia severity. The method 100 also includes, as at 125,
updating the insomnia therapy map 44 to reflect the efficacy. Such
operations are repeated, as noted hereinbefore, for each of a
plurality of periods of attempted sleep by the patient. Over time,
therefore, the insomnia therapy map 44 is gradually personalized to
the patient in order to provide improved recommendations of
insomnia therapies, which is desirable for the patient. Other
benefits will be apparent.
[0046] 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.
[0047] 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.
* * * * *