DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This action is in reply to the current action filed on October 8th, 2021.
Claims 1-24, 26-28, and 31-34 are currently pending and have been examined.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on April 19th, 2022 was filed after the mailing date of the first action on the merits. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Objections
Claim 27 is objected to for reciting “the interface system is as a reference of known dimension”. Examiner recommends rewording this limitation to “the interface system is a reference of known dimension”.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-24, 26-28, and 31-34 are rejected under 35 USC § 101 as being directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Step 1 Analysis:
Independent Claims 1 and 34 are within the four statutory categories. Claims 1 and 34 are drawn to a method and system, respectively. Dependent Claims 2-24, 26-28 and 31-33 are further directed to a method and therefore also fall into one of the four statutory categories.
Step 2A Analysis – Prong One:
Claim 1, which is indicative of the inventive concept, recites the following:
A method of managing sleep therapy, comprising: inputting characterization data associated with each of a plurality of patients into a database system stored in a memory system;
inputting outcome data associated with each of the plurality of patients resulting from use of one of a plurality of interface systems worn during sleep therapy;
training at least one machine learning procedure of an algorithm stored in the memory system and executable via a processor system using a training set of the characterization data associated with each of a plurality of patients and the outcome data associated with each of the plurality of patients resulting from use of one of the plurality of interface systems to create at least one machine learning model,
determining a management option for sleep therapy for a person via execution of the algorithm based at least in part upon an optimization of at least one outcome parameter for the person predicted by the at least one machine learning model based at least in part upon characterization data of the person input into the database system,
wherein the management option comprises at least one of selection of an interface system from the plurality of interface systems for future use, fitting of a selected interface system for future use, and a change in use of a currently used interface system;
and communicating information regarding the management option to the person.
The limitations as shown in underline above, given the broadest reasonable interpretation, cover the abstract idea of certain methods of organizing human activity because they recite managing personal behavior or relationships or interactions between people (i.e. social activities, teaching, and following rules or instructions, and/or mental process that a neurologist should follow when testing a patient for nervous system malfunctions- in this case, using a set of data associated with patients to determine a management option for sleep therapy for a patient and communicating that information to the patient), e.g. see MPEP 2106.04(a)(2). Any limitations not identified above as part of the abstract idea are deemed “additional elements” and will be discussed in further detail below.
Dependent Claims 2-3, 5-8, 11-12, 14-15, 18-24, 26, 28, 31, and 33 include other limitations directed to the abstract idea. For example, Claim 2 recites the person is one of the plurality of patients, Claim 3 recites the management option for sleepy therapy determined via the predicted optimization of the outcome parameter based on characterization data and outcome data of the person, Claim 5 recites an outcome parameter is a function of outcome metrics including a number of apneas and usage time over a predetermined period of time, Claim 6 recites the outcome metrics comprise a level of drowsiness, Claim 7 recites the outcome data is determined from data from a PAP device, questionnaire, or observed patient behavior, Claim 8 recites patients are monitored over time, Claim 11 recites the management option comprising a change in a sleep therapy option and determining if a recommendation is to be communicated to the patient based on a threshold, Claim 12 recites the management option includes a recommendation for an appointment with a physician, change in lifestyle change in sleep behavior, education, or providing positive feedback, Claim 14 recites upon a triggering event, determining an updated management option for sleep therapy based in part on at least one outcome parameter, Claim 15 recites what the triggering event comprises, Claim 18 recites communicating a questionnaire to the person, Claim 19 recites situation sensitivity is determined from data from the person, Claim 20 recites data from the person is used to determine that the person is likely to have recently participated in a predetermined activity and the questionnaire includes at least one question of the level of drowsiness of the person, Claim 21 recites situation sensitivity is determined from data of motion, time or location data, Claim 22 recites the predetermined activity is driving, Claim 23 recites the characterization data of each patient comprises anatomical, sleep behavior, demographic, health, or sleep therapy data, Claim 24 recites obtaining a video or image of the person wearing a interface system, Claim 26 recites determining if the patient is using the system correctly, Claim 28 recites the anatomical data comprises at least one anatomical characteristic of the person’s head, Claim 31 recites the image is a two-dimensional image analyzed via an image characterization, Claim 33 recites determining a fitting for headgear. These limitations only server to further narrow the abstract idea, and a claim may not preempt abstract ideas, even if the judicial exception is narrow, e.g., see MPEP 2106.04. Additionally, any limitations in the dependent claims not addressed above are deemed additional elements to the abstract idea and will be further addressed below. Hence dependent Claims 2-3, 5-8, 11-12, 14-15, 18-24, 26, 28, 31, and 33 are nonetheless directed towards fundamentally the same abstract idea as independent Claims 1 and 34.
Step 2A Analysis – Prong Two:
Claims 1 and 34 are not integrated into practical application because the additional elements (i.e. the non-underlined limitations above – in this case, the database system, memory system, interface systems, machine learning model, algorithm, and processor system of Claims 1 and 34) are recited at a high level of generality (i.e. as a generic processor performing generic computer functions) such that they amount to no more than mere instructions to apply an exception using generic computer parts. For example, Applicant’s specification explains that the processor may be associated with various other circuits that support operation of the processor, such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM) [0056]. Characterization data associated with each of a plurality of patients is stored in one or more databases of a database system which is stored in a memory system. Patient clinical outcome data from the sleep therapy associated with each of a plurality of patients is also stored in the one or more databases of the database system. Models from one or more machine learning algorithms, previously trained using patient characterization data metrics and patient outcome data metrics (which are determined, from previous sleep therapy treatment for the plurality or population of patients) in the database system hereof are used in determining/optimizing one or more predicted outcome parameters [0073]. In the case of a patient having an interface system (for example, a patient already in PAP therapy), a video or a photograph of the patient wearing their currently supplied interface system (for example, a mask system as illustrated in Figure 2) may be obtained and the interface system or a portion thereof may be used as a known dimensional reference. In that regard, the interface system data (type, brand and/or size) may be determined using, for example, computer vision software as known in the computer arts [0070]. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into practical application because they do not impose any meaningful limits on practicing the idea. Therefore, Claims 1 and 34 are directed to an abstract idea without practical application.
Dependent Claims 3-4, 8-10, 13-20, 24, 26-28, and 32-33 also recite additional elements. Claim 3 recites the previously recited additional element of the database system and specifies the characterization data of the person is input into the database system, Claim 4 narrows the previously recited algorithm and machine learning model and specifies the algorithm comprises a plurality of machine learning procedures or a plurality of machine learning models, Claim 8 recites the previously recited database system and specifies new characterization or new outcome data is input into the database system, Claim 9 recites the previously recited machine learning model and algorithm and specifies updating training of the algorithm based on the new data to create an updated machine learning model, Claim 10 narrows the previously recited machine learning model by specifying testing each of the machine learning model against a test dataset and determining which of the updated models has a better confidence interval, Claim 13 narrows the previously recited element of the interface system by specifying the management option comprises a selection of an interface system, Claim 14 recites the previously recited additional elements of the algorithm and machine learning model by specifying upon occurrence of a triggering event, determining an updated management option for sleep therapy through the algorithm based on an optimization of an outcome parameter by the machine learning model, Claim 15 recites the previously recited machine learning model and a new interface system by specifying the triggering event comprises initiation of use of at least one updated machine learning model, use of a new interface system by at least a portion of the patients, Claim 16 recites new additional limitations of a software application, device, and remote system, specifying the method comprises a software application on a patient device to facilitate communication of information between the patient and a remote system including the database system and the algorithm, Claim 17 recites a new additional element of a mobile personal communication device and specifies the device of Claim 16 is a mobile personal communication device, Claim 18 recites the previously recited elements of the software application and the database system and specifies the software application communicates a questionnaire to the person that is situation sensitive and inputting outcome data determined from a response of the person in the database system, Claim 19 recites the previously recited element of the device and specifies the situation sensitivity is determined from data from the device of the person and the timing of the questionnaire is based on data from the device, Claim 20 recites the previously recited device and specifies the device of the person is used to determine that the person has participated in an activity, Claim 24 recites the previously recited additional elements of the interface system and algorithm and specifies obtaining a video/image of the person who is wearing the interface system and the algorithm determines if the person is wearing the interface system correctly, Claim 26 recites the previously recited algorithm and interface system and specifies the algorithm comprises a computer vision procedure to determine if the interface system is used incorrectly/non-optimally, Claim 27 recites the previously recited additional element of the interface system and specifies a portion of the interface system is a reference of known dimension, Claim 28 recites a new additional element of a sleep therapy interface and specifies the determination of an anatomical characteristic based on a video/image and a known dimensional reference selected from an iris of the patient or a portion of a sleep therapy interface worn by the patient, Claim 32 recites the interface system and specifies the management option comprises the selection of an interface system and the fitting of a selected interface system, Claim 33 recites the interface system and specifies the management option comprises determining a fitting for headgear of the interface system. However, these additional elements are recited only at a high level of generality such that they amount to no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Step 2B Analysis:
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements of the database system, memory system, interface systems, machine learning model, algorithm, and the processor system of Claims 1 and 34 amount to no more than mere instruction to apply the exception using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”). MPEP 2106.05(I)(A) indicates that merely stating “apply it” or equivalent to the abstract idea cannot provide an inventive concept (“significantly more”). Accordingly, even in combination, these additional elements do not provide significantly more. As such, Claims 1 and 34 are not patent eligible.
Dependent Claims 2, 5-7, 11-12, 21-23, and 31 solely narrow the abstract idea and do not recite any additional elements. Claim 2 recites the person is one of the plurality of patients. Claim 5 recites an outcome parameter is a function of outcome metrics including a number of apneas and usage time over a predetermined period of time. Claim 6 recites the outcome metrics comprise a level of drowsiness. Claim 7 recites the outcome data is determined from data from a PAP device, questionnaire, or observed patient behavior. Claim 11 recites the management option comprising a change in a sleep therapy option and determining if a recommendation is to be communicated to the patient based on a threshold. Claim 12 recites the management option includes a recommendation for an appointment with a physician, change in lifestyle change in sleep behavior, education, or providing positive feedback, Claim 21 recites situation sensitivity is determined from data of motion, time or location data. Claim 22 recites the predetermined activity is driving. Claim 23 recites the characterization data of each patient comprises anatomical, sleep behavior, demographic, health, or sleep therapy data. Claim 31 recites the image is a two-dimensional image analyzed via an image characterization.
Dependent Claims 3-4, 8-10, 13-14 18-20, 24, 26-27, and 32-33 recite previously cited additional elements, which are not eligible for the reasons stated above, and further narrow the abstract idea. Claim 3 recites the previously recited additional element of the database system and specifies the characterization data of the person is input into the database system, Claim 4 narrows the previously recited algorithm and machine learning model and specifies the algorithm comprises a plurality of machine learning procedures or a plurality of machine learning models, Claim 8 recites the previously recited database system and specifies new characterization or new outcome data is input into the database system, Claim 9 recites the previously recited machine learning model and algorithm and specifies updating training of the algorithm based on the new data to create an updated machine learning model, Claim 10 narrows the previously recited machine learning model by specifying testing each of the machine learning model against a test dataset and determining which of the updated models has a better confidence interval, Claim 13 narrows the previously recited element of the interface system by specifying the management option comprises a selection of an interface system, Claim 14 recites the previously recited additional elements of the algorithm and machine learning model by specifying upon occurrence of a triggering event, determining an updated management option for sleep therapy through the algorithm based on an optimization of an outcome parameter by the machine learning model, Claim 18 recites the previously recited elements of the software application and the database system and specifies the software application communicates a questionnaire to the person that is situation sensitive and inputting outcome data determined from a response of the person in the database system, Claim 19 recites the previously recited element of the device and specifies the situation sensitivity is determined from data from the device of the person and the timing of the questionnaire is based on data from the device, Claim 20 recites the previously recited device and specifies the device of the person is used to determine that the person has participated in an activity, Claim 24 recites the previously recited additional elements of the interface system and algorithm and specifies obtaining a video/image of the person who is wearing the interface system and the algorithm determines if the person is wearing the interface system correctly, Claim 26 recites the previously recited algorithm and interface system and specifies the algorithm comprises a computer vision procedure to determine if the interface system is used incorrectly/non-optimally, Claim 27 recites the previously recited additional element of the interface system and specifies a portion of the interface system is a reference of known dimension, Claim 32 recites the interface system and specifies the management option comprises the selection of an interface system and the fitting of a selected interface system, Claim 33 recites the interface system and specifies the management option comprises determining a fitting for headgear of the interface system.
Dependent Claims 15-17 and 28 recite new additional elements with new limitations. Claim 15 recites the previously recited machine learning model and a new interface system and specifies the triggering event comprises initiation of use of at least one updated machine learning model, use of a new interface system by at least a portion of the patients, Claim 16 recites new additional limitations of a software application, device, and remote system, specifying the method comprises a software application on a patient device to facilitate communication of information between the patient and a remote system including the database system and the algorithm, Claim 17 recites a new additional element of a mobile personal communication device and specifies the device of Claim 16 is a mobile personal communication device, Claim 28 recites a new additional element of a sleep therapy interface and specifies the determination of an anatomical characteristic based on a video/image and a known dimensional reference selected from an iris of the patient or a portion of a sleep therapy interface worn by the patient.
Thus, taken alone, the additional elements do not amount to significantly more than the abstract idea above. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually, and there is no indication that the combination of elements improves the functioning of a computer or improves any other technology, and their collective functions merely provide a conventional computer implementation.
Therefore, whether taken individually or as an ordered combination, Claims 1-24, 26-28, and 31-34 are nonetheless rejected under 35 U.S.C. 101 as being directed to abstract ideas without significantly more.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-9, 13-17, 23, and 34 are rejected under 35 USC 103 as being unpatentable over Apte et al. (US 20180286520 A1) in view of Richard et al. (US 20150306330 A1).
Regarding Claim 1, Apte discloses:
A method of managing sleep therapy, comprising: (Apte discloses as shown in FIGS. 1A-1B, embodiments of a method 100 for characterizing one or more sleep-related conditions can include:… and/or determining one or more therapies [0016].)
inputting characterization data associated with each of a plurality of patients into a database system stored in a memory system; (Apte discloses data from populations of subjects (e.g., associated with one or more sleep-related conditions; positively or negatively correlated with one or more sleep-related conditions; etc.) can be used to characterize subsequent users [0021].)
inputting outcome data associated with each of the plurality of patients resulting from use of one of a plurality of interface systems worn during sleep therapy; (Apte discloses supplementary data can include any one or more of: survey-derived data... site-specific data…Processing survey-derived data can include facilitating collection of survey-derived data, such as including providing one or more surveys to one or more users, subjects, and/or other suitable entities. Additionally or alternatively, processing supplementary data can include processing sensor data (e.g., sensors of sleep-related devices, wearable computing devices, mobile devices; biometric sensors associated with the user, such as biometric sensors of a user smart phone; etc.). Sensor data can include any one or more of: physical activity- and/or physical action-related data (e.g., …mobility sensor data from one or more devices such as a mobile device and/or wearable electronic device, etc.), sensor data describing environmental factors…, biometric sensor data (e.g., heart rate sensor data; fingerprint sensor data; optical sensor data such as facial images and/or video; data recorded through sensors of a mobile device; data recorded through a wearable or other peripheral device; etc.), and/or any other suitable data associated with sensors [0060-62]. The Examiner interprets the wearable device as the interface system work during therapy.)
training at least one machine learning procedure of an algorithm stored in the memory system and executable via a processor system (Apte discloses the method can include Block S120, which can function to process data for supplementing microorganism datasets, …such as for facilitating training, validating, generating, determining, applying and/or otherwise processing sleep-related characterization models, etc.) [0059]. The characterization process can be generated and trained according to a random forest predictor (RFP) algorithm that combines bagging (e.g., bootstrap aggregation) and selection of random sets of features from a training dataset to construct a set of decision trees, T, associated with the random sets of features [0076].)
using a training set of the characterization data associated with each of a plurality of patients and the outcome data associated with each of the plurality of patients resulting from use of one of the plurality of interface systems to create at least one machine learning model, (Apte discloses embodiments can function to generate models (e.g., sleep-related characterization models such as for phenotypic prediction; therapy models such as for therapy determination; machine learning models such as for feature processing, etc.), such as models that can be used to characterize and/or diagnose users …and/or that can be used to select and/or provide therapies for subjects in relation to one or more sleep-related conditions [0020]. The method 100 can additionally or alternatively include Block S120, which can include processing… supplementary data (e.g., one or more supplementary datasets, etc.) associated with… one or more sleep-related conditions, one or more users, and/or other suitable entities. Block S120 can function to process data…and/or can function to supplement any suitable portion of the method 100 and/or system 200 (e.g., processing supplementary data for facilitating one or more characterization processes, such as in Block S130; such as for facilitating training, validating, generating, determining, applying and/or otherwise processing sleep-related characterization models, etc.) [0059].)
determining a management option for sleep therapy for a person via execution of the algorithm based at least in part upon an optimization of at least one outcome parameter for the person predicted by the at least one machine learning model based at least in part upon characterization data of the person input into the database system, (Apte discloses the therapy model is preferably based upon data from a large population of subjects… Such data can be used to train and validate the therapy provision model, in identifying therapeutic measures that provide desired outcomes for subjects based upon different sleep-related characterizations. In variations, support vector machines, as a supervised machine learning algorithm, can be used to generate the therapy provision model. However, any other suitable machine learning algorithm described above can facilitate generation of the therapy provision model [0095]. In examples, machine learning approaches…, parameter optimization approaches (e.g., Bayesian Parameter Optimization),… and/or other suitable analytical techniques (e.g., described herein) can be applied in determining site-related …characterizations…, therapies, and/or any other suitable outputs [0080].)
and communicating information regarding the management option to the person. (Apte discloses the therapy facilitation system 230 can include any one or more of: a communications system (e.g., to communicate therapy recommendations, selections, discouragements, and/or other suitable therapy-related information to a computing device (e.g., user device and/or care provider device; mobile device; smart phone; desktop computer; at a website, web application, and/or mobile application accessed by the computing device; etc.); [0043].)
Apte does not disclose the selection of an interface system which is met by Richard:
wherein the management option comprises at least one of selection of an interface system from the plurality of interface systems for future use, fitting of a selected interface system for future use, and a change in use of a currently used interface system; (Richard teaches the present invention provides an easy to use website or app (or application) that can assist the provider or physician and subject in making current or future mask selections that best match their facial profiles [0023]. Under an embodiment of the present system, a subject can easily take a photo of their face and then run that image through the mask database allowing them to see masks that can better fit their current needs, thus eliminating leaks and improving compliance with their therapy [0026]. By using these measurements, one or masks that actually fit the subject, based on the calculated measurements and the known sizes/tolerances of the masks, can be selected for the subject. Accordingly, mask(s) with the measurements that best fit the measurements of the subject taken from the photo are the mask(s) the system can select [0036].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the selection and fitting of an interface system for future use as taught by Richard. This modification would create a system and methods for ensuring CPAP users are wearing the proper device thus creating effective sleep therapy (see Richard, ¶ 0003).
Regarding Claim 34, this claim recites limitations that are substantially similar to those recited in Claim 1 above; thus, the same rejection applies. Apte further discloses:
A system of managing sleep therapy, comprising: a memory system; a processor system in operative connection with the memory system; (Apte discloses embodiments of the method 100 and/or system 200 can function to characterize (e.g., assess, evaluate, diagnose, describe, etc.) one or more sleep-related conditions [0018]. The system 200…can be embodied…as a machine configured to receive a computer-readable medium storing computer-readable instructions. The instructions are preferably executed by computer-executable components preferably integrated with the system. The computer-readable medium can be stored on any suitable computer-readable media such as RAMs, ROMs, flash memory, EEPROMs, optical devices (CD or DVD), hard drives, floppy drives, or any suitable device. The computer-executable component is preferably a general or application specific processor, but any suitable dedicated hardware or hardware/firmware combination device can alternatively or additionally execute the instructions [0124].)
Regarding Claim 2, Apte and Richard teach the limitations as seen in the rejection of Claim 1 above. Apte further discloses:
wherein the person is one of the plurality of patients or is a new patient additional to the plurality of patients. (Apte discloses specific examples of the technology can amount to an inventive distribution of functionality across a network including a sample handling system, a sleep-related characterization system, and a plurality of users, where the sample handling system can handle substantially concurrent processing of biological samples…from the plurality of users, which can be leveraged by the sleep-related characterization system in generating personalized characterizations and/or therapies (e.g., customized to the user's microbiome such as in relation to the user's dietary behavior, probiotics-associated behavior, medical history, demographic characteristics, other behaviors, preferences, etc.) for sleep-related conditions [0032]. )
Regarding Claim 3, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
wherein characterization data of the person and any available output data is input into the database system (Apte discloses Block S130 and/or other portions of the method 100 can include applying computer-implemented rules… to process population-level data, but can additionally…include applying computer-implemented rules to process…condition-specific basis (e.g., subgroups exhibiting a specific sleep-related condition, a combination of sleep-related conditions, triggers for the sleep-related conditions, associated symptoms, etc.), a sample type-specific basis (e.g., applying different computer-implemented rules to process microbiome data derived from different collection sites; etc.), a user basis … and/or any other suitable basis. As such, Block S130 can include assigning users from the population of users to one or more subgroups; and applying different computer-implemented rules for determining features…for the different subgroups [0077].)
and the management option for sleep therapy determined via the predicted optimization of the at least one outcome parameter based at least in part upon characterization data and the outcome data of the person input into the database system. (Apte discloses the therapy model is …based upon data from a large population of subjects, which can include the population of subjects from which the…datasets are derived in Block S110, where…functional features or states of health…are well characterized. Such data can be used to train and validate the therapy provision model, in identifying therapeutic measures that provide desired outcomes for subjects based upon different sleep-related characterizations…a supervised machine learning algorithm, can be used to generate the therapy provision model. Upon identification of a subset of subjects of the population of subjects who are characterized to be in good health (e.g., using features of the characterization process), therapies that modulate microbiome compositions and/or functional features toward those of subjects in good health can be generated in Block S140. Block S140 can thus include identification of one or more baseline microbiome compositions and/or functional features (e.g., one baseline microbiome for each of a set of demographic characteristics), and potential therapy formulations and therapy regimens…The therapy model can, however, be generated and/or refined in any other suitable manner [0095-96]. The Examiner interprets the refinement of the model based on outcome and characterization data as optimizing the model.)
Regarding Claim 4, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
wherein the algorithm comprises a plurality of machine learning procedures or a plurality of machine learning models (Apte discloses embodiments can function to generate models (e.g., sleep-related characterization models such as for phenotypic prediction; therapy models such as for therapy determination; machine learning models such as for feature processing, etc.), such as models that can be used to characterize and/or diagnose users …and/or that can be used to select and/or provide therapies for subjects in relation to one or more sleep-related conditions [0020].)
Regarding Claim 5, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
wherein the at least one outcome parameter is a function of outcome metrics comprising a number of apneas over a predetermined period of time (Apte discloses the method 100 and/or system 200 can preferably determine and/or promote… characterizations and/or therapies for one or more sleep-related conditions, and/or any suitable portions of the method 100 and/or system 200 can be performed in relation to sleep-related conditions. Sleep-related conditions can include any one or more of: …sleep-related breathing disorders (e.g., sleep apnea, obstructive sleep apnea, snoring, central sleep apnea, child sleep apnea, infant sleep apnea, …etc.), …and/or any other suitable conditions associated with sleep [0022]. Data…can be associated with any suitable temporal indicators…including one or more: temporal indicators indicating when the data was collected…, determined, transmitted, received, and/or otherwise processed; temporal indicators providing context to content described by the data … [0025].)
and a usage time over the predetermined period of time. (Apte discloses the method 100 can… include one or more of: … determining, with one or more characterization processes, a sleep-related characterization for the user for one or more sleep-related conditions, based on a user microorganism dataset … associated with a biological sample of the user S160; facilitating therapeutic intervention for the one or more sleep-related conditions for the user … S170; monitoring effectiveness of one or more therapies and/or monitoring other suitable components … for the user…, over time (e.g., such as to assess user microbiome characteristics such as user microbiome composition features and/or functional features associated with the therapy, for the user over time, etc.) S180; [0017].)
Regarding Claim 7, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
wherein at least a portion of the outcome data is determined from at least one of data measured from a PAP device, questionnaire data or observed patient behavior. (Apte discloses data from populations of subjects (e.g., associated with one or more sleep-related conditions; positively or negatively correlated with one or more sleep-related conditions; etc.) can be used to characterize subsequent users, such as … to facilitate therapeutic intervention (e.g., promoting one or more therapies;…such as in relation to one of more sleep-related conditions [0021]. One or more sleep-related conditions can be characterized by and/or diagnosed by medical interview, medical history, survey, sensor data, medical exams, data activities including and/or requiring monitoring individuals as they sleep, other supplementary data, and/or through any suitable techniques [0023].)
Regarding Claim 8, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
wherein each of the plurality of patients is monitored over time and new data comprising at least one of new characterization data or new outcome data for each of the plurality of patients is input into the database system over time. (Apte discloses monitoring effectiveness of one or more therapies and/or monitoring other suitable components (e.g., microbiome characteristics, etc.) for the user (e.g., based upon processing a series of biological samples from the user), over time [0017]. Variations of the method 100 can further facilitate selection, monitoring … and/or adjusting of therapies provided to a user, such as through collection and analysis (e.g., with sleep-related characterization models) of additional samples from a subject over time [0021].)
Regarding Claim 9, Apte and Richard teach the limitations as seen in the rejection of Claim 8 above. Apte further discloses:
updating training of the algorithm based upon the new data for each of the plurality of patients to create at least one updated machine learning model. (Apte discloses updating (e.g., of characterization models and/or therapy models based on processed biological samples over time; etc.),…[0040]. Block S130 can include processing (e.g., generating, training, updating, executing, storing, etc.) one or more sleep-related characterization models (e.g., sleep-related condition models, therapy models, etc.) for one or more sleep-related conditions [0078].)
Regarding Claim 11, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
the management option comprises a change in a sleep therapy option, (Apte discloses other suitable data (e.g., supplementary data describing user behavior associated with one or more sleep-related conditions; supplementary data describing a sleep-related condition such as observed symptoms; etc.) can be used in determining a post-therapy characterization…, updated therapies (e.g., determining an updated therapy based on effectiveness and/or adherence to the promoted therapy, etc.) [0118]. The Examiner interprets updated therapies as a change in therapy.)
and the method further comprises determining if a recommendation to make the change in the sleep therapy option is to be communicated to the patient based upon a predetermined threshold in a change in the predicted optimization of the at least one output parameter. (Apte discloses the method can…include Block S180, which can include: monitoring effectiveness of one or more therapies. Monitoring of a user during the course of a therapy promoted by the therapy model…can thus be used to generate a therapy-effectiveness model for each characterization provided by the characterization process of Block S130, and each recommended therapy measure provided in Blocks S140 and S170. The method can include…promoting an updated therapy to the user for the sleep-related condition based on the post-therapy sleep-related characterization …and/or the user adherence to the therapy (e.g., modifying the therapy based on positive or negative results for the user microbiome in relation to the sleep-related condition; etc.). Additionally or alternatively, other suitable data… be used in determining a post-therapy characterization (e.g., degree of change from pre-to post-therapy in relation to the sleep-related condition; etc.), updated therapies (e.g., determining an updated therapy based on effectiveness and/or adherence to the promoted therapy, etc.) [0116-118].)
Regarding Claim 12, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
the management option further includes at least one of a recommendation for an appointment with a physician, a recommendation for a change in lifestyle, a recommendation for a change in sleep behavior, providing education on sleep therapy, or providing positive feedback. (Apte discloses the therapy facilitation system 230 of the system 200 can function to facilitate therapeutic intervention …for one or more sleep-related conditions…the therapy facilitation system 230 can update and/or otherwise modify an application and/or other software of a device …to promote a therapy (e.g., promoting, at a to-do list application, lifestyle changes for improving a user state associated with one or more sleep-related conditions, etc.). However, the therapy facilitation system 230 can be configured in any other manner [0044]. Therapies (e.g., sleep-related therapies, etc.) can include any one or more of: consumables…device-related therapies…surgical operations…behavior modification therapies (e.g., physical activity recommendations such as increased exercise; dietary recommendations such as reducing sugar intake, increased vegetable intake, increased fish intake, decreased caffeine consumption, decreased alcohol consumption,…; weight-related recommendations; sleep habit recommendations; device recommendations…[0091].)
Regarding Claim 13, Apte and Richard teach the limitations as seen in the rejection of Claim 1 above. Apte does not disclose the following limitation met by Richard:
wherein the management option comprises a selection of an interface system from the plurality of interface systems for future use. (Richard teaches when the vector points and measurements are calculated, the measurements are compared to the known measurements for each of the masks in the database. By using these measurements, one or masks that actually fit the subject, based on the calculated measurements and the known sizes/tolerances of the masks, can be selected for the subject. Accordingly, mask(s) with the measurements that best fit the measurements of the subject taken from the photo are the mask(s) the system can select [0035-36].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the selection of an interface system from a plurality of options as taught by Richard. This modification would create a system and methods for ensuring CPAP users are wearing the proper device thus creating effective sleep therapy (see Richard, ¶ 0003).
Regarding Claim 14, Apte and Richard teach the limitations as seen in the rejection of Claim 1 above. Apte does not disclose the following limitation met by Richard:
upon occurrence of a triggering event, determining an updated management option for sleep therapy for at least one of the plurality of patients via execution of the algorithm based at least in part upon an optimization of the at least one outcome parameter for the at least one of the plurality of patients predicted by at least one machine learning model determined for use at the time of the triggering event and based at least in part upon the characterization data associated with the at least one of the plurality of patients and the outcome data associated with the at least one of the plurality of patients. (Apte discloses sleep-related conditions can include one or more of: diseases, symptoms, causes (e.g., triggers, etc.), disorders, associated risk…, associated severity [0023]. The method can additionally or alternatively include Block S180, which can include: monitoring effectiveness of one or more therapies. Monitoring of a user during the course of a therapy promoted by the therapy model …can be used to generate a therapy-effectiveness model for each characterization each characterization provided by the characterization process of Block S130, and each recommended therapy measure provided in Blocks S140 and S170. The method can include…promoting an updated therapy to the user for the sleep-related condition based on the post-therapy sleep-related characterization …and/or the user adherence to the therapy (e.g., modifying the therapy based on positive or negative results for the user microbiome in relation to the sleep-related condition; etc.)…other suitable data …can be used in determining a post-therapy characterization (e.g., degree of change from pre- to post-therapy in relation to the sleep-related condition; etc.), updated therapies (e.g., determining an updated therapy based on effectiveness and/or adherence to the promoted therapy, etc.) [0116-118].)
Regarding Claim 15, Apte and Richard teach the limitations as seen in the rejection of Claim 14 above. Apte further discloses:
wherein the triggering event comprises a passage of a predefined period of time, a request for the at least one of the plurality of patients, receipt of new characterization data associated with the at least one of the plurality of patients or new outcome data associated with the at least one of the plurality of patients, (Apte discloses sleep-related conditions can include one or more of: diseases, symptoms, causes (e.g., triggers, etc.), [0023]. Block S160, which can include determining…, a sleep-related characterization for the user,…in an example, Block S160 can include generating a sleep-related characterization for the user based on…a sleep-related condition model. Sleep-related characterizations can include one or more of: diagnoses…; risk,… comparisons…; therapy determinations; other suitable outputs associated with characterization processes [0105]. The method 100 can include receiving a post-therapy biological sample from the user; collecting a supplementary dataset from the user,…generating a post-therapy sleep-related characterization of the first user in relation to the sleep-related condition based on the sleep-related characterization model…; and promoting an updated therapy to the user for the sleep-related condition based on the post-therapy sleep-related characterization …and/or the user adherence to the therapy. Additionally or alternatively, other suitable data… can be used in determining a post-therapy characterization…, updated therapies (e.g., determining an updated therapy based on effectiveness and/or adherence to the promoted therapy, etc.) [0118]. The Examiner interprets these triggering events as a receipt of new characterization data.)
initiation of use of at least one updated machine learning model, (Apte discloses sleep-related characterization models, other models, other components of the system 200, and/or suitable portions of the method 100…can employ analytical techniques including… updating (e.g., of characterization models and/or therapy models based on processed biological samples over time; etc.) [0040].)
Apte does not disclose the use of a new interface system which is met by Richard:
use of a new interface system by at least a portion of the plurality of patients. (Richard teaches a system for selecting a mask comprising: a database storing information related to one or more masks;…determine one or more measurements of the at least the portion of the face of the subject based on the image; access information for at least one mask from the database based on the one or more measurements; generate a representation of the information on the display; and receive a selection of one of the at least one masks [0006]. The database can consist of 50-75 (or more or less) of the most popular masks used on the market and be updated regularly, such as every 3-4 months [0039].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the selection of a new interface system as taught by Richard. This modification would create a system and methods for ensuring CPAP users are wearing the proper device thus creating effective sleep therapy (see Richard, ¶ 0003).
Regarding Claim 16, Apte and Richard teach the limitations as seen in the rejection of Claim 1 above. Apte further discloses:
providing a software application on a device of the person which is executable on the device of the person to communicate information between the patient and a remote system including the database system and the algorithm. (Apte discloses the therapy facilitation system 230 can include any one or more of: a communications system (e.g., to communicate therapy recommendations, selections, discouragements, and/or other suitable therapy-related information to a computing device (e.g., user device …; mobile device; smart phone; desktop computer; at a website, web application, and/or mobile application accessed by the computing device; etc.); to enable telemedicine between a care provider and a subject in relation to a sleep-related condition; etc.) [0043].)
Regarding Claim 17, Apte and Richard teach the limitations as seen in the rejection of Claim 16 above. Apte further discloses:
wherein the device is a mobile personal communication device. (Apte discloses the therapy facilitation system 230 can include … mobile device; smart phone;… to enable telemedicine between a care provider and a subject in relation to a sleep-related condition; etc.) [0043].)
Regarding Claim 23, Apte and Richard teach the limitations as seen in the rejection of Claim 2 above. Apte further discloses:
wherein the characterization data of each of the plurality of patients comprises one or more of anatomical data, sleep behavior data, demographic data, health data, or sleep therapy data. (Apte discloses data from populations of subjects (e.g., associated with one or more sleep-related conditions; positively or negatively correlated with one or more sleep-related conditions; etc.) can be used to characterize subsequent users, such as for indicating …areas of improvement, and/or to facilitate therapeutic intervention … such as in relation to one or more sleep-related conditions [0021]. Sleep-related conditions can include one or more of: diseases, symptoms, causes (e.g., triggers, etc.), …. associated severity, behaviors,…sleep habits such as sleep time, wake time, naps, length, quality, sleep phases, consistence, variance and/or other sleep behaviors;…demographic-related characteristics (e.g., age, weight, race, gender, etc.), [0023].)
Claims 6 and 18-22 are rejected under 35 U.S.C. 103 as being unpatentable over Apte et al. (US 20180286520 A1) and Richard et al. (US 20150306330 A1) in view of Gan et al. (US 20160311440 A1).
Regarding Claim 6, Apte and Richard teach the limitations as seen in the rejection of Claim 5 above. Apte and Richard do not teach the following limitation met by Gan:
wherein the outcome metrics further comprise a level of drowsiness after a defined activity. (Gan teaches drowsy driver module 118 causes activation of heart rate monitor 138 to confirm drowsy driver condition 216. Heart rate monitor 138 can be used to confirm drowsy driver condition 216 because a person's heart rate may be indicative of drowsiness…[0045]. Drowsy driver module 118 receives motion data 212 from motion sensor 136, and compares motion data 212 to a movement threshold to determine whether motion data 212 corresponds to an abnormal movement 214 that is indicative of a drowsy driver condition 216. The movement threshold, for example, may correspond to a normal amount of motion that may be generated during the normal course of driving vehicle 108. Thus, if motion data 212 includes motion that is greater than the movement threshold, drowsy driver module 118 determines that an abnormal movement 214 has occurred that is indicative of the drowsy driver condition 216 [0040].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the metrics including a level of drowsiness as taught by Gan. This modification would create a system and methods which can determine when a person is drowsy or impaired in an accurate manner (see Gan, ¶ 0010).
Regarding Claim 18, Apte and Richard teach the limitations as seen in the rejection of Claim 16 above. Apte further discloses:
communicating a questionnaire to the person via the software application… (Apte discloses supplementary data can include any one or more of: survey-derived data (e.g., data from responses to one or more surveys surveying for one or more sleep-related conditions, for any suitable types of data described herein; etc.); site-specific specific data…sleep-related condition data [0060]. Surveys can be provided in-person (e.g., in coordination with sample kit provision and/or reception of samples; etc.), electronically (e.g., during account setup; at an application executing at an electronic device of a subject, at a web application and/or website accessible through an internet connection; etc.), and/or in any other suitable manner [0061].)
and inputting outcome data determined from a response of the person in the database system. (Apte discloses as shown in FIGS. 8A-8C, different sleep-related characterization models and/or other suitable models…can be generated for different sleep-related conditions,…features associated with biometric sensor data and/or survey response data vs. models independent of supplementary data, etc.), and/or other suitable criteria [0079].)
Apte and Richard do not teach the following limitation met by Gan:
via the software application that is situation sensitive (Gan teaches drowsy driver module 118 is configured to initiate a drowsy driver mode on wearable wireless device 104, such as a smart watch or smart bracelet, in response to detecting that the user is driving vehicle 108…configured to monitor the user while the user is driving, and initiate one or more alerts responsive to detecting that the user is drowsy or otherwise impaired [0027]. Drowsy driver module 118 can determine whether the user is a driver, or an operator, of vehicle 108 or a passenger in vehicle 108. This determination can be based on an assumption that the driver is likely the owner of vehicle 108, and has configured wireless device 102 to automatically connect to vehicle kit device 106 [0033]. The Examiner interprets the drowsy driver module detecting that the user is driving as being a situation sensitive software. )
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the software application being situation sensitive as taught by Gan. This modification would create a system and methods which can determine the situation a person is in and when they are drowsy or impaired in an accurate manner (see Gan, ¶ 0010).
Regarding Claim 19, Apte, Richard, and Gan teach the limitations as seen in the rejection of Claim 18 above. Apte and Richard do not teach the following limitations met by Gan:
situation sensitivity is determined from data from the device or at least one other device of the person used by the person and the timing of communicating the questionnaire to the person is based upon data from the device or the at least one other device. (Gan teaches drowsy driver module is configured to provide alert 224 by requesting voice-feedback from the user. For example, drowsy driver module 118 can ask the user if the user is “ok”. Based on the response from the user, or lack thereof, drowsy driver module 118 can automatically contact the emergency operator. For example, if the user does not respond to the request for voice-feedback, this may be a sign that the user is unconscious and needs help. Similarly, if the user indicates that they are “ok”, then the drowsy driver module 118 can follow up with other questions to ensure that the user does not need help [0057].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the situation sensitivity being determined from device data and a questionnaire being sent based on data from the device as taught by Gan. This modification would create a system and methods which can determine the situation a person is in and when they are drowsy or impaired in order to ensure they are okay (see Gan, ¶ 0010).
Regarding Claim 20, Apte, Richard, and Gan teach the limitations as seen in the rejection of Claim 19 above. Apte further discloses:
…questionnaire includes at least one question inquiring of a level…of the person. (Apte discloses processing supplementary data can include processing survey-derived data, where the survey-derived data can provide physiological data, demographic data, behavior data, environmental factor data…different levels of mobility… [0061]. Survey-derived data from the user, pertaining to experiences of the user while on the therapy (e.g., experienced side effects, personal assessment of improvement, behavioral modifications, symptom improvement, etc.) [0118].)
Apte and Richard do not teach the following limitations met by Gan:
data from the device of the person or the at least one other device used by the person is used to determine that the person is likely to have recently participated in a predetermined activity (Gan teaches the drowsy driver module can be implemented at the wearable wireless device and/or at an additional wireless device that is wirelessly connected to the wearable wireless device…a user may wear a wearable wireless device on her wrist (e.g., a smart watch) that is wireless connected to a wireless device (e.g., a smart phone) in her purse [0007]. Module 118 is configured to detect that a user is driving vehicle 108 based on a connection status of wireless device 102 with vehicle kit device 106 of vehicle 108 [0032]. The Examiner interprets the predetermined activity as driving.)
and the questionnaire includes at least one question inquiring… drowsiness of the person. (Gan teaches drowsy driver module is configured to provide alert 224 by requesting voice-feedback from the user. For example, drowsy driver module 118 can ask the user if the user is “ok”. Based on the response from the user, or lack thereof, drowsy driver module 118 can automatically contact the emergency operator. For example, if the user does not respond to the request for voice-feedback, this may be a sign that the user is unconscious and needs help. Similarly, if the user indicates that they are “ok”, then the drowsy driver module 118 can follow up with other questions to ensure that the user does not need help [0057].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the data from the device being used to determine if the person has participated in a predetermined activity and sending a questionnaire as taught by Gan. This modification would create a system and methods which can determine the situation a person is in and when they are drowsy or impaired in order to ensure they are okay (see Gan, ¶ 0010).
Regarding Claim 21, Apte, Richard, and Gan teach the limitations as seen in the rejection of Claim 20 above. Apte and Richard do not teach the following limitations met by Gan:
situation sensitivity is determined from data comprising one or more of motion data, time data and location data. (Gan teaches motion sensor 136 is configured to sense movement and generate motion data based on the movement…As described in more detail below, the motion data and the heart rate data may be communicated to drowsy driver module 118 to enable the drowsy driver module to detect that the user is drowsy or otherwise impaired [0021]. Drowsy driver module 118 may also be configured to provide a current location of the user, so that an emergency team may be dispatched to the user's current location [0056].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the situation sensitivity including motion and location data as taught by Gan. This modification would create a system and methods which can determine the situation a person is in to provide the necessary help (see Gan, ¶ 0054).
Regarding Claim 22, Apte, Richard, and Gan teach the limitations as seen in the rejection of Claim 20 above. Apte and Richard do not teach the following limitations met by Gan:
wherein the predetermined activity is driving. (Gan teaches drowsy driver module 118 is configured to initiate a drowsy driver mode on wearable wireless device 104, such as a smart watch or smart bracelet, in response to detecting that the user is driving vehicle 108. Generally, the drowsy driver mode is configured to monitor the user while the user is driving, and initiate one or more alerts responsive to detecting that the user is drowsy or otherwise impaired [0027].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the predetermined activity being driving as taught by Gan. This modification would create a system and methods which can monitor drowsiness of a driver (see Gan, ¶ 0010).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Apte et al. (US 20180286520 A1) and Richard et al. (US 20150306330 A1) in view of Wang et al. (US 20200065712 A1).
Regarding Claim 10, Apte and Richard teach the limitations as seen in the rejection of Claim 8 above. Apte further discloses:
testing each of the at least one updated machine learning model and the at least one machine learning model against a test data set …(Apte discloses monitoring of a user during the course of a therapy promoted by the therapy model (e.g., by receiving and analyzing biological samples from the user throughout therapy, by receiving survey-derived data from the user throughout therapy) can thus be used to generate a therapy-effectiveness model for each characterization provided by the characterization process of Block S130, and each recommended therapy measure provided in Blocks S140 and S170 [0117]. The …computer-implementable rules can enable… improvements in data storage and retrieval (e.g., storing and/or retrieving sleep-related characterization models; storing specific models such as in association with different users and/or sets of users, with different sleep-related conditions;…and/or other suitable improvements to technological areas [0031].)
and using the one of the at least one updated machine learning model and the at least one machine learning model with the better confidence interval to determine the management option. (Apte discloses Block S130 can include processing (e.g., generating, training, updating, executing, storing, etc.) one or more sleep-related characterization models (e.g., sleep-related condition models, therapy models, etc.) for one or more sleep-related conditions (e.g., for outputting characterizations for users describing user microbiome characteristics in relation to sleep-related conditions; therapy models for outputting therapy determinations for one or more sleep-related conditions; etc.) [0078].)
Apte does not disclose determining which of the machine learning models has a better confidence interval which is met by Wang:
to determine which of the at least one updated machine learning model and the at least one machine learning model has a better confidence interval; (Wang teaches an approach to automated machine learning that generally involved training and testing a set of candidate machine-learning configurations (herein also “candidate set”) over a sampled…dataset to iteratively identify an optimal or near-optimal configuration… upon training and testing a selected configuration over a sampled dataset, associated training and test accuracies… are used to estimate a confidence interval…of the real performance of the configuration if trained and tested on the full dataset [0004]. A final selection step may identify, among the remaining configurations within the set at termination time, the one having the highest performance (e.g., highest lower confidence bound) [0016].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the selection of the machine learning model tested against training data and with the best confidence interval as taught by Wang. This modification would create a system and methods capable of selecting optimal machine learning models to and better automate the data processing step (see Wang, ¶ 0002-3).
Claims 24, 26-28, and 31-33 are rejected under 35 U.S.C. 103 as being unpatentable over Apte et al. (US 20180286520 A1) and Richard et al. (US 20150306330 A1) in view of Yajima et al. (US 20180246334 A1).
Regarding Claim 24, Apte and Richard teach the limitations as seen in the rejection of Claim 1 above. Apte and Richard do not teach the following limitations met by Yajima:
obtaining a video or an image of the person wearing a currently used interface system (Yajima teaches FIG. 7 shows a state in which the image display section 20 is worn in a proper position of the head of the user. In FIG. 7, the captured image data 300 of the inner cameras 68 at the time when the image display section 20 is worn in the proper position of the head of the user is shown. When receiving pressing operation of the button 11, the worn-state determining section 151 causes the inner cameras 68 to execute imaging [0149-150].)
and the algorithm is further configured to determine if the patient is using the interface system incorrectly or non-optimally and to recommend changes or adjustments in use of the interface system or to change the interface system. (Yajima teaches the worn-state determining section 151 detects an image of the eyes of the user from the captured image data 300 of the inner cameras 68 and specifies a range of the captured image data 300 in which the image of the eyes is captured [0150]. The Examiner interprets determining if the device is worn correctly as determining if the patient is using the interface system incorrectly/non-optimally. When determining that the worn state of the image display section 20 is the state of (2), the control section 150 adjusts the transmittance of the external light in the right electronic shade 227 and the left electronic shade 247 and further causes the image display section 20 to display, in the display region PN, a message indicating that the worn state is not correct [0185]. The right electronic shade 227 and the left electronic shade 247 adjust the transmittance of the external light transmitted through the image display section 20. The control section 150 determines the worn state of the image display section 20 on the head of the user and guides the adjustment of the worn state of the image display section 20 on the basis of a result of the determination [0193].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the obtaining an image/video of the user wearing the device and determining if it is used properly as taught by Yajima. This modification would create a system and methods which can determine if the interface device is properly worn so that the system functions correctly (see Yajima, ¶ 0002-3).
Regarding Claim 26, Apte, Richard, and Yajima teach the limitations as seen in the rejection of Claim 24 above. Apte further discloses:
wherein the algorithm comprises… (Apte discloses the method can include Block S120, which can function to process data for supplementing microorganism datasets, …such as for facilitating training, validating, generating, determining, applying and/or otherwise processing sleep-related characterization models, etc.) [0059]. The characterization process can be generated and trained according to a random forest predictor (RFP) algorithm that combines bagging (e.g., bootstrap aggregation) and selection of random sets of features from a training dataset to construct a set of decision trees, T, associated with the random sets of features [0076].)
Apte and Richard do not teach the following limitations met by Yajima:
…a computer vision procedure to assist in at least one of identifying the interface system or in determining if the patient is using the interface system incorrectly or non-optimally. (Yajima teaches FIG. 7 shows a state in which the image display section 20 is worn in a proper position of the head of the user. In FIG. 7, the captured image data 300 of the inner cameras 68 at the time when the image display section 20 is worn in the proper position of the head of the user is shown… In FIG. 7, the captured image data 300 at the time when the image display section 20 is worn in the proper position of the head of the user and a normal range 310 on the captured image data 300 based on the normal range information 125 are shown [0149-150]. The Examiner interprets determining if the device is worn correctly as determining if the patient is using the interface system incorrectly/non-optimally.)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate determining if the person wearing the device is using it properly as taught by Yajima. This modification would create a system and methods which can determine if the interface device is properly worn so that the system functions correctly (see Yajima, ¶ 0002-3).
Regarding Claim 27, Apte and Yajima teach the limitations as seen in the rejection of Claim 24 above. Apte does not disclose the following limitations met by Yajima:
using at least a portion of the interface system is as a reference of known dimension. (Yajima teaches when detecting the line of sight directions of the right eye RE and the left eye LE from the captured images of the inner cameras 68, the control section 150 can calculate an angle of convergence of the right eye RE and the left eye LE. In FIG. 4, the angle of convergence is indicated by a sign PA. The angle of convergence PA corresponds to the distance to the object OB gazed by the user. That is, when the user three-dimensionally visually recognizes an image or an object, the angle of convergence of the right eye RE and the left eye LE is decided according to the distance to the visually recognized target [0086].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the interface system having a reference of known dimension as taught by Yajima. This modification would create a system and methods which can determine if the interface device is properly worn so that the system functions correctly (see Yajima, ¶ 0002-3).
Regarding Claim 28, Apte and Richard teach the limitations as seen in the rejection of Claim 23 above. Apte does not disclose the following limitations met by Yajima:
wherein the anatomical data comprises at least one anatomical characteristic of the person's head and the method further comprises: determining the at least one anatomical characteristic based at least in part on the at least one image or video and a known dimensional reference in the at least one image of video selected from an iris of the patient or at least a portion of a sleep therapy interface worn by the patient in the at least one image or video. (Yajima teaches when the image of the eyes of the user can be detected from the captured image data 300 of the inner cameras 68, the worn-state determining section 151 determines that the deviation of the worn state of the image display section 20 is within the preset range [0154].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate determining an anatomical characteristic based on the image/video of the device as taught by Yajima. This modification would create a system and methods which can determine if the interface device is properly worn so that the system functions correctly (see Yajima, ¶ 0002-3).
Regarding Claim 31, Apte and Yajima teach the limitations as seen in the rejection of Claim 28 above. Apte does not disclose the following limitations met by Yajima:
wherein the at least one image is a two-dimensional image and the two-dimensional image is analyzed via an image characterization. (Yajima teaches as shown in FIG. 3, inner cameras 68 are disposed on the user side of the image display section 20…The inner cameras 68 are a pair of cameras that respectively images the right eye RE and the left eye LE of the user…The control section 150 may detect an image of the eyes of the user from the captured image data 300 of the inner cameras 68 and determine a worn state on the head of the image display section 20 on the basis of the positions of the eyes in the captured image data 300 [0085].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the image being two-dimensional and analyzes with image characterization as taught by Yajima. This modification would create a system and methods which can determine if the interface device is properly worn so that the system functions correctly (see Yajima, ¶ 0002-2).
Regarding Claim 32, Apte discloses the limitations as seen in the rejection of Claim 1 above. Apte does not disclose the following limitations met by Yajima:
wherein the management option comprises at least one of selection of an interface system from the plurality of interface systems and fitting of a selected interface system. (Yajima teaches when signals indicating that contact is detected are input from all of the piezoelectric sensors 217 and 239 provided in the right holding section 21 and the left holding section 23 and the left and right nose pad sections, the worn-state determining section 151 determines that the worn state of the image display section 20 is correct. When a value of pressure indicated by the signals input from the piezoelectric sensors 217 and 239 provided in the right holding section 21 and the left holding section 23 and the left and right nose pad section is in a normal range, the worn-state determining section 151 may determine that the worn state of the image display section 20 is correct. The normal range of the value of the pressure is a value of pressure measured by the piezoelectric sensors 217 and 239 when the calibration is performed [0156].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate the fitting of the interface device as taught by Yajima. This modification would create a system and methods which can determine if the interface device is properly worn so that the system functions correctly (see Yajima, ¶ 0002-3).
Regarding Claim 33, Apte and Yajima teach the limitations as seen in the rejection of Claim 32 above. Apte does not disclose the following limitations met by Yajima:
wherein the management option comprises determining a fitting for headgear of the interface system so that the fitting of the headgear of the interface system is adjusted to the determined fit before delivery. (Yajima teaches when calibration is performed in advance and the image display section 20 is properly worn on the head of the user, the worn-state determining section 151 registers, as a normal position, the position of the image of the eyes of the user detected from the captured image data 300 of the inner cameras 68. More specifically, the worn-state determining section 151 causes the image display section 20 to display the image and causes the user to adjust the worn position of the image display section 20 [0148]. When determining the worn state of the image display section 20, the worn-state determining section 151 guides adjustment of the worn state of the image display section 20 on the basis of a result of the determination [0157].)
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the claimed invention to have modified the systems and methods for inputting characterization data and interface data for training a machine learning algorithm to determine a management option for sleep therapy and communicating that recommendation to the user as disclosed by Apte to incorporate determining if the headgear is properly fitting as taught by Yajima. This modification would create a system and methods which can determine if the interface device is properly worn so that the system functions correctly (see Yajima, ¶ 0002-3).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to OLIVIA R GEDRA whose telephone number is (571)270-0944. The examiner can normally be reached Monday - Friday 8:00am-5:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Peter H Choi can be reached at (469)295-9171. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/OLIVIA R. GEDRA/Examiner, Art Unit 3681
/PETER H CHOI/Supervisory Patent Examiner, Art Unit 3681
Prosecution Insights