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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 3/13/2026 has been entered.
Status of the Claims
Note: Applicant is reminded of the requirements of 37 CFR 1.121 as detailed in MPEP 714(II)(C)(A)-(B): “The current status of all the claims in the application, including any previously canceled or withdrawn claims, must be given…. All claims being currently amended must be presented with markings to indicate the changes that have been made relative to the immediate prior version. The changes in any amended claim must be shown by strike-through (for deleted matter) or underlining (for added matter).” At least claim 10 does not comply with these requirements, because its status is listed as (Currently Amended) with a strikethrough of the words “at least one of (i)” despite those words having already been removed from the immediate prior version of the claims such that no amendments appear to have been made from the immediate prior version, such that this claim’s status should be listed as (Previously Presented). Examiner requests that all future amendments comply with the requirements of 37 CFR 1.121.
The status of the claims as of the response filed 3/13/2026 is as follows: Claim 9 is cancelled, and all previously given rejections for this claim are considered moot. Claims 1, 17, and 20 are currently amended. Claim 10 is as previously presented. Claims 2-8, 11-16, and 18-19 are original. Claims 1-8 and 10-20 are currently pending in the application and have been considered below.
Response to Amendment
Rejection Under 35 USC 101
The claims have been amended but the 35 USC 101 rejections are upheld.
Rejection Under 35 USC 103
The amendments made to the claims introduce limitations that are not fully addressed in the previous office action (e.g. the user data associated with the users including at least counts of disruptions per sleep session), and thus the corresponding 35 USC 103 rejections are withdrawn. However, Examiner will consider the amended claims in light of an updated prior art search and address their patentability with respect to prior art below.
Response to Arguments
Rejection Under 35 USC 101
On pages 7-14 of the response filed 3/13/2026 Applicant argues that the independent claims provide a particular technical solution to a technical problem by using a computer system to collect and analyze data from sensors of a bed system when a user rests on the bed system, thereby allowing for unobtrusive and automatic monitoring of a user’s health while they are sleeping so that a cardiac failure risk probability for a user of the bed system may be determined. Applicant specifically notes “the specified relationship between the ‘bed system’ and the ‘sensors’, which collect user data ‘when a user rests on the bed system’” and thus reflects a particular solution to identified technical problems. Applicant’s arguments are fully considered, but are not persuasive. Applicant has not provided evidence that the technological aspects of a sensor-based bed system are being improved, and instead appears to be arguing that use of a sensor-based bed system to collect and analyze data at all is the technological improvement. Examiner notes that it is well-understood, routine, and conventional in the art to utilize a bed system with one or more sensors to collect user data from a user resting on the bed for computerized sleep and/or cardiac evaluations, as evidenced by at least deSa et al. (US 20210057101 A1) Fig. 1A & [0030]; Pinhas et al. (US 20070118054 A1) Fig. 2, [0016], & [0175]-[0176]; Nagura et al. (Reference U on the PTO-892 mailed 3/7/2025) first full paragraph of second column on Pg 317; and Meriheina (Reference V on the PTO-892 mailed 3/7/2025) Pg 2. Applicant has not described specific technological drawbacks of current bed sensing technology that this invention seeks to solve, described any technical details of the bed system that would show it is a particular machine under the considerations of MPEP 2106.05(b), nor provided an improvement to bed sensing technology itself by merely utilizing a bed with sensors to obtain the data needed for the main abstract analysis / risk determination steps of the invention. Examiner maintains that such additional elements amount to insignificant extra-solution activity in the form of necessary data gathering (see MPEP 2106.05(g)), while the use of the computer system to perform the analysis amounts to mere instructions to “apply” the otherwise-abstract sleep metric calculations/determinations in a digitized/automated environment (see MPEP 2106.05(f)). Accordingly, the 35 USC 101 rejections are maintained for claims 1-8 and 9-20.
Rejection Under 35 USC 103
On pages 14-15 Applicant alleges that none of the cited references describe the newly-introduced limitation directed to “the user data associated with the users including at least counts of disruptions per sleep session.” Applicant’s arguments are fully considered, but are not persuasive. Examiner submits that at least Molony does teach user data associated with users including at least counts of disruptions per sleep session in at least [0114] (describing sleep-related parameters including a fragmentation index determined based on the number of awakenings (i.e. disruptions) during a sleep session), [0176] (noting sleep-related parameters include a number of awakenings (i.e. a count of disruptions per sleep session)), & [0208] (noting determination of an interruption score for a sleep session). Accordingly, the 35 USC 103 rejections are maintained for claims 1-8 and 9-20.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 17-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 17 and 20 each recite "receive, from the at least one sensor, user data collected by the at least one sensor when a user rests on the bed, the user data associated with the users including at least counts of disruptions per sleep session" (emphasis added). There is insufficient antecedent basis for “the user data associated with the users” in each claim because there is no previously introduced instance of multiple users. For purposes of examination, Examiner will interpret this limitation as "receive, from the at least one sensor, user data collected by the at least one sensor when a user rests on the bed, the user data associated with the user including at least counts of disruptions per sleep session." Claims 18-19 are also rejected on this basis because they inherit the indefinite language due to their dependence on claim 17.
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 1-8 and 10-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1
In the instant case, claims 1-8 and 10-16 are directed to a method (i.e. a process) and claims 17-20 are directed to systems (i.e. machines). Thus, each of the claims falls within one of the four statutory categories. Nevertheless, the claims fall within the judicial exception of an abstract idea.
Step 2A – Prong 1
Independent claims 1, 17, and 20 recite steps that, under their broadest reasonable interpretations, cover certain methods of organizing human activity, e.g. managing personal behavior, relationships, or interactions between people. Specifically, claim 20 (as representative) recites:
A system for determining a probability measurement of a risk of cardiac failure for a user of a bed system, the system comprising:
a bed having at least one sensor;
and a computer system in communication with the at least one sensor of the bed, the computer system configured to:
receive, from the at least one sensor, user data collected by the at least one sensor when a user rests on the bed, the user data associated with the users including at least counts of disruptions per sleep session;
determine in-bed-duration data for a sleep session of the user based on analyzing the user data;
determine, by the computer system, sleep-duration data for the sleep session of the user based on analyzing the user data;
determine an in-bed-to-asleep metric for the sleep session of the user based on analysis of the in-bed-duration data and the sleep-duration data;
determine wake after sleep onset data based on analyzing the user data;
provide the in-bed-duration data and the wake after sleep onset data as input to a model that was trained to determine a probability measurement of a risk of cardiac failure for users of beds based at least in part on user data associated with the users;
receive the probability measurement of the risk of cardiac failure for the user of the bed as output from the model; and
perform an action based on the probability measurement.
But for the recitation of high level components like a bed having at least one sensor and a computer system, the italicized functions, when considered as a whole, describe a sleep evaluation and diagnosis operation that could be achieved by a human actor such as a clinician managing their personal behavior and/or interacting with other users such as a patient. For example, a clinician could examine bed sensor readouts to count a number of disruptions per sleep session, calculate in-bed duration and sleep duration for a patient, and then use those metrics to calculate an in-bed-to-asleep ratio or percentage representing the sleep efficiency of the patient. The clinician could also observe the sensor readouts to derive wake after sleep onset data, and use sleep indicators like in-bed-duration and wake after sleep onset as inputs for a trained model (e.g. a decision tree, regression equation, etc.) to determine a risk probability of cardiac failure for the patient. The clinician could finally perform an action based on the risk probability, such as notifying the patient or a colleague of the risk, making a note of the risk in the patient’s records, generating a report, etc. Thus, the steps recited in this claim describe an abstract idea in the form of a certain method of organizing human activity. Claims 1 and 17 recite substantially similar subject matter as claim 1 and are also found to recite an abstract idea under the same analysis.
Dependent claims 2-8, 10-16, and 18-19 inherit the limitations that recite an abstract idea from their dependence on claims 1 and 17, respectively, and thus these claims also recite an abstract idea under the Step 2A – Prong 1 analysis. In addition, claims 2-8 and 10-16 recite additional limitations that further describe the abstract idea identified in the independent claims.
Specifically, claim 2 specifies that the user data includes ballistocardiogram signals, which is a type of data that a clinician would be capable of evaluating to make sleep and cardiac risk determinations.
Claims 3-4 and 6-8 describe types of data used when the model was trained, each of which are types of data that a human actor could use to initialize or fit (i.e. train) a risk model like a decision tree, logistic regression model, etc.
Claim 5 specifies that the model is a logistic regression model, which is a type of simple equation that a clinician would be capable of fitting to data (i.e. training) and executing to make risk determinations.
Claim 10 recites providing wake after sleep onset data to the model which was trained to correlate wake after sleep onset with probability measurements of cardiac failure risk, which a clinician could achieve by identifying wake after sleep onset from a patient’s sensor data (as explained for similar limitations in claim 20 above) and using the model which includes known associations between such sleep data and cardiac failure risk.
Claims 11-13 describe the type of probability risk output from the model as being numerical and/or categorical and possibly used to generate a further numeric score via multiplication. A clinician would be capable of using the model to output numerical and/or categorical risk probabilities, and possibly further multiplying a numerical output to generate a score.
Claims 14-15 specify that the action comprises outputting an alert to either the user or a healthcare provider when the probability exceeds a threshold range, which a clinician could achieve by communicating (e.g. verbally, in writing, etc.) an alert to the patient or a colleague when the risk exceeds a preset amount.
Claim 16 specifies that the cardiac failure is congestive heart failure, which is a type of cardiac failure that a clinician would be capable of determining risk for based on patient data.
However, recitation of an abstract idea is not the end of the analysis. Each of the claims must be analyzed for additional elements that indicate the abstract idea is integrated into a practical application to determine whether the claim is considered to be “directed to” an abstract idea.
Step 2A – Prong 2
The judicial exception is not integrated into a practical application. In particular, independent claims 1, 17, and 20 do not include additional elements that integrate the abstract idea into a practical application. The additional elements of claims 1, 17, and 20 include a computer system to perform the various steps and a bed system with sensors to collect the user data. The computer system merely serves to automate and/or digitize the otherwise-abstract functions of receiving data, determining sleep indicators from the data, providing the sleep indicators to a model, receiving a probability measurement as output from the model, and performing an action based on the probability that could be achieved as a certain method of organizing human activity (as described above), and thus amounts to instructions to “apply” the abstract idea with a computer (see MPEP 2106.05(f)). The use of a bed system with one or more sensors to collect and provide the user data to the computer system amounts to insignificant extra-solution activity because it merely provides a necessary means of data gathering for the main data analysis steps (see MPEP 2106.05(g)). Accordingly, claims 1, 17, and 20 as a whole are each directed to an abstract idea without integration into a practical application.
The judicial exception recited in dependent claims 2-8, 10-16, and 18-19 is also not integrated into a practical application under a similar analysis as above. The functions of claims 3-8, 10-13, and 16 are performed with the same additional elements introduced in the independent claims, without introducing any new additional elements of their own, and accordingly also amount to mere instructions to apply the abstract idea on these same additional elements. Claim 2 specifies that the user data includes ballistocardiogram signals, which indicates that the one or more sensors include a BCG sensor. However, the BCG sensor would still merely be utilized as a means of necessary data gathering as explained for the one or more sensors of the independent claims, and thus also amounts to insignificant extra-solution activity. Claims 14-15 introduce the additional elements of a user’s user device and a healthcare provider’s user device that receive the alert/notification. These high level user devices are merely used as tools with which to digitize the otherwise-abstract function of sharing alerts/notifications between clinical entities such that they amount to instructions to apply the exception using generic computing components. Claim 18 recites that the bed further comprises a controller and that the computer system is the controller, which still merely describes the computing system at a high level of generality (i.e. as a controller) and nominally indicates that the computer system is integrated with the bed, which does not provide integration into a practical application. Claim 19 specifies that the computer system is remote from the bed, which is a nominal description of the relative location of these two elements and does not provide integration into a practical application.
Accordingly, the additional elements of claims 1-8 and 10-20 do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Claims 1-8 and 10-20 are directed to an abstract idea.
Step 2B
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 integration of the abstract idea into a practical application, the additional element of a computing system for performing the receiving, determining, providing, performing, etc. steps of the invention amount to mere instructions to apply the exception using generic computer components. As evidence of the generic nature of the computer system, Examiner notes paras. [0085]-[0103] of Applicant’s specification where the computer system is disclosed in terms of standard, general-purpose components known to those of ordinary skill in the art.
The use of a bed system with one or more sensors to collect and provide the user data to the computer system for analysis amounts to insignificant extra-solution in the form of necessary data gathering, as explained above. Examiner further notes that it is well-understood, routine, and conventional in the art to utilize a bed system with one or more sensors (including BCG sensors as implied in claim 2) to collect user data for sleep and/or cardiac evaluations, as evidenced by at least deSa et al. (US 20210057101 A1) Fig. 1A & [0030]; Pinhas et al. (US 20070118054 A1) Fig. 2, [0016], & [0175]-[0176]; Nagura et al. (Reference U on the PTO-892 mailed 3/7/2025) first full paragraph of second column on Pg 317; and Meriheina (Reference V on the PTO-892 mailed 3/7/2025) Pg 2.
Sending an alert or notification from the computer system to a user device as in claims 14-15 also amounts to mere instructions to apply the exception using generic computer components, because the otherwise-abstract function of sharing data between clinical entities is merely being digitized with high level computer components. As evidence of the generic nature of these components, Examiner notes paras. [0085]-[0103] of Applicant’s specification where the computer system and is disclosed in terms of standard, general-purpose components known to those of ordinary skill in the art, as well as para. [0037] where the user device is disclosed as being “any appropriate type of mobile device of the user 106, including but not limited to a cellphone, smart phone, laptop, tablet, wearable device, or other computing system.” Further, Examiner notes that receiving or transmitting data over a network is recognized as a well-understood, routine, and conventional computer function previously known to the industry, as outlined in MPEP 2106.05(d)(II).
Specifying that the computer system is a controller that is part of the bed as in claim 18 is insignificant extra-solution activity, as explained above. Further, it is well-understood, routine, and conventional to integrate a sleep analysis computer system into a sensor-based bed, as evidenced by at least Kahn et al. (US 11883188 B1) Fig. 1A & Col2 L61 – Col3 L5; Warner et al. (US 20080147442 A1) Fig. 1 & [0019]; and Pinhas Fig. 1 & [0350].
Specifying that the computer system is remote from the bed as in claim 19 is insignificant extra-solution activity, as explained above. Further, it is well-understood, routine, and conventional to utilize a computer system remote from a bed sensor system for sleep analysis, as evidenced by at least Kahn Fig. 1A & Col2 L61 – Col3 L5; Warner Fig. 1 & [0019]; and Pinhas Fig. 1 & [0173]-[0175].
Analyzing these additional elements as an ordered combination adds nothing that is not already present when considering the elements individually; the overall effect of the computer system, bed sensors, and user devices in combination is to digitize and/or automate a sleep evaluation and diagnosis operation that could otherwise be achieved as a certain method of organizing human activity. Thus, when considered as a whole and in combination, claims 1-8 and 10-20 are not patent eligible.
Claim Rejections - 35 USC § 103
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4, 10-11, and 13-20 are rejected under 35 U.S.C. 103 as being unpatentable over Molony et al. (US 20230245780 A1) in view of Pinhas et al. (US 20070118054 A1).
Claim 1
Molony teaches a method for determining a (Molony Fig. 13, [0095], [0206], [0218]-[0220], noting a method of predicting a health outcome such as a risk score of heart attack for a user based on data obtained during a sleep session taking place on a bed), the method comprising:
receiving, by a computer system, user data collected by sensors (Molony [0041]-[0042], noting a processor-based control system that carries out the functions of the invention; see also [0045], [0205]-[0206], noting the control system receives user data collected by sensors during a sleep session (i.e. when a user rests on a bed system as in [0095]));
determining, by the computer system, in-bed-duration data for a sleep session of the user based on analyzing the user data (Molony [0058]-[0059], [0103], noting the system analyzes the sensor data to determine total time in bed (TIB), i.e. in-bed-duration data);
determining, by the computer system, sleep-duration data for the sleep session of the user based on analyzing the user data (Molony [0058]-[0059], [0103], noting the system analyzes the sensor data to determine total sleep time (TST), i.e. sleep-duration data);
determining an in-bed-to-asleep metric for the sleep session of the user based on analysis of the in-bed-duration data and the sleep-duration data (Molony [0113], noting the system determines sleep efficiency (i.e. an in-bed-to-asleep metric) by determining a ratio of total time in bed to total sleep time);
providing, by the computer system, the in-bed-to-asleep metric as input to a model that was trained to determine a receiving, by the computer system, the (Molony [0218]-[0220], noting a determined first parameter (which is a sleep-related parameter per [0208], e.g. sleep efficiency as in [0058]-[0059] & [0113]) is input to a machine learning algorithm trained to output a predicted health outcome such as heart attack risk based on user data. [0219] specifically notes that the model may be trained with any of the first and second parameters as inputs, which [0208] notes include sleep-related parameters like a number of awakenings (i.e. a count of disruptions per sleep session), while [0114] further describes one of the sleep-related parameters being a fragmentation index determined based on the number of awakenings (i.e. disruptions) during a sleep session; taken together, these disclosures show that the model can be trained based on user data associated with counts of disruptions per sleep session of multiple users. See also [0176], noting determination of an interruption score for a sleep session); and
performing, by the computer system, an action based on the (Molony [0222], noting the system generates a custom message for a user (i.e. performs an action) based on the predicted health outcome).
In summary, Molony teaches a method for determining various sleep-related parameters based on sensor data collected during a sleep session and generating a heart failure risk score based on the determined sleep-related parameters. Molony further teaches that many types of sensor arrangements are contemplated (Molony [0056], [0080]-[0081]). However, in Molony the sensors are not explicitly disclosed as being sensors of a bed system, and the predicted risk score is not explicitly disclosed as being a probability measurement. However, Pinhas shows an analogous heart failure monitoring system that employs non-contact sensors installed in a patient’s bed to collect sleep and other user data (Pinhas abstract, [0193], [0350], [0437]-[0441]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the sensors of Molony to include sensors of a bed system on which a patient rests as in Pinhas in order to utilize more unobtrusive, non-contact sensors for data collection (as suggested by Pinhas abstract). Pinhas further teaches that predicting health outcomes based on collected sleep data can include predicting a probability or likelihood of the outcome (Pinhas [0293], [0410]-[0411]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the health outcome risk scores of Molony to specifically include probability measurements as in Pinhas in order to allow the system to output quantitative risk measurements indicating how likely a given outcome is, as well as to facilitate alerting a user if a predicted probability exceeds a threshold likelihood that an outcome is imminent so that preventative action may be taken (as suggested by Pinhas [0293]).
Claim 2
Molony in view of Pinhas teaches the method of claim 1, but the present combination fails to explicitly disclose wherein the user data includes ballistocardiogram (BCG) signals. However, Pinhas further teaches that sensor data collected and analyzed for predict heart failure includes ballistogardiogram signals (Pinhas [0016], [0348], [0437]-[0438]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the user data of the combination to include BCG signals as in Pinhas because Pinhas shows that ballistocardiography is an available and useful means of measuring patient heart and respiratory data for heart failure analysis in a non-contact manner (as suggested by Pinhas [0016] & [0437]).
Claim 3
Molony in view of Pinhas teaches the method of claim 1, and the combination further teaches wherein the model was trained with a training dataset of historic user data associated with the user (Molony [0219], noting the machine learning algorithm is trained with previously-recorded data associated with the user).
Claim 4
Molony in view of Pinhas teaches the method of claim 1, and the combination further teaches wherein the model was trained with a training dataset of historic user data associated with different users of the bed systems (Molony [0219], noting the machine learning algorithm is trained with previously-recorded data associated with other users).
Claim 10
Molony in view of Pinhas teaches the method of claim 1, and the combination further teaches:
providing, by the computer system as input to the model, wake after sleep onset data (Molony [0219], noting a determined first parameter (which is one or more sleep-related parameters per [0208] & [0212], e.g. wake after sleep onset as in [0058]-[0059] & [0112]) is input to the machine learning algorithm),
wherein the model was trained, by the computer system, to correlate wake after sleep onset data with probability measurements of a risk of cardiac failure for the users of the bed systems (Molony [0218]-[0220], noting the machine learning algorithm may be trained via supervised learning, indicating that it is trained to correlate inputs (e.g. wake after sleep onset data as explained above) with outputs (e.g. measurements of a risk of cardiac failure as in [0218] & [0220], and which may include probability when considered in the context of the combination with Pinhas).
Claim 11
Molony in view of Pinhas teaches the method of claim 1, showing prediction of a probability measurement of a risk of cardiac failure. However, the present combination fails to explicitly disclose wherein the probability measurement of the risk of cardiac failure is a numeric value. However, Molony further teaches that other determined scores may be numeric values (Molony [0125], [0185]). It therefore would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to specify that the probability measurement of risk of cardiac failure as in the combination is a numeric value so that it can be quantified within a numeric range so that a user can easily understand the score (as suggested by Molony Figs. 5A-D).
Claim 13
Molony in view of Pinhas teaches the method of claim 1, showing prediction of a probability measurement of a risk of cardiac failure. However, the present combination fails to explicitly disclose wherein the probability measurement of the risk of cardiac failure is a categorical value, the categorical value being at least one of low risk, medium risk, or high risk. However, Molony further teaches that other determined scores may be categorical values indicating low, medium, and high values (Molony [0122], noting health scores are color coded into different categories). It therefore would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to specify that the probability measurement of risk of cardiac failure as in the combination is a categorical value representing at least one of low risk, medium risk, or high risk so that it can be visually categorized within a color range so that a user can easily understand the score (as suggested by Molony [0122] & [0131]).
Claim 14
Molony in view of Pinhas teaches the method of claim 1, and the combination further teaches wherein performing, by the computer system, an action based on the probability measurement comprises outputting an alert at a user device of the user indicating that the user is at risk of cardiac failure (Molony [0084], [0222], noting the system generates a custom message for a user (i.e. outputs an alert) on a user device based on the predicted health outcome). However, the present combination fails to explicitly disclose that the alert is output specifically based on a determination that the probability measurement exceeds a threshold range.
However, Pinhas further teaches that an alert is provided to a patient based on a physiological score exceeding a threshold (Pinhas [0292], noting that if a physiological score F exceeds a reference value (i.e. a threshold range), an alert is output to a patient and/or caregiver). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the message outputting function of the combination such that an alert is output specifically based on the probability measurement exceeding a threshold as in Pinhas in order to only alert users of actually concerning situations and avoid inconsequential or false alerts (as suggested by Pinhas [0294]-[0299]).
Claim 15
Molony in view of Pinhas teaches the method of claim 1, and the combination further teaches wherein performing, by the computer system, an action based on the probability measurement comprises transmitting a notification to a user device (Molony [0084], [0222], noting the system generates a custom message for a user (i.e. outputs an alert) on a user device based on the predicted health outcome). However, the present combination fails to explicitly disclose that the notification is transmitted specifically to a user device of a health care provider and based on a determination that the probability measurement exceeds a threshold range.
However, Pinhas further teaches that an alert is provided to a caregiver based on a physiological score exceeding a threshold (Pinhas [0292], noting that if a physiological score F exceeds a reference value (i.e. a threshold range), an alert is output to a patient and/or caregiver). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the message outputting function of the combination such that a notification is transmitted to a healthcare provider specifically based on the probability measurement exceeding a threshold as in Pinhas in order to alert a user’s caregiver of a worrying situation, but only in the case of actually concerning situations so that inconsequential or false alerts are avoided (as suggested by Pinhas [0292]-[0299]).
Claim 16
Molony in view of Pinhas teaches the method of claim 1, showing determination of a probability measurement of a heart attack (i.e. heart failure) risk. However, the present combination fails to explicitly disclose wherein the cardiac failure is congestive heart failure. However, Pinhas further teaches that its heart failure prediction includes prediction of congestive heart failure (Pinhas [0013]-[0014] & [0437], noting prediction of congestive heart failure CHF). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the prediction of a heart attack risk probability as in the combination to also include prediction of a congestive heart failure as in Pinhas in order to allow for prediction of common chronic conditions known to be associated with sleep-related changes in addition to prediction of acute conditions (as suggested by Pinhas [0005]), thereby expanding the breadth of conditions predicted by the system and improving its usefulness.
Claim 17
Molony teaches a system for determining a (Molony Figs. 1 & 13, [0095], [0206], [0218]-[0220], noting a system for predicting a health outcome such as a risk score of heart attack for a user based on data obtained during a sleep session taking place on a bed), the system comprising:
(Molony [0056], [0080], noting various sensors); and
a computer system in communication with the at least one sensor (Molony [0041]-[0042], [0045], noting a processor-based control system that carries out the functions of the invention and is in communication with the sensors):
receive, from the at least one sensor, user data collected by the at least one sensor when a user rests on the bed, the user data associated with the users including at least counts of disruptions per sleep session (Molony [0045], [0205]-[0206], noting the control system receives user data collected by sensors during a sleep session (i.e. when a user rests on a bed system as in [0095]); such data tracks a number of awakenings (i.e. disruptions) during a sleep session per [0100] & [0114]. See also [0176], noting the system tracks a number of times the user removes and/or replaces a sleep apnea mask and other disruptive events like snoring, choking, labored breathing, seizure, etc. that occur during a sleep session for use in determining an interruption score and event score for a sleep session);
determine in-bed-duration data for a sleep session of the user based on analyzing the user data (Molony [0058]-[0059], [0103], noting the system analyzes the sensor data to determine total time in bed (TIB), i.e. in-bed-duration data);
determine, by the computer system, sleep-duration data for the sleep session of the user based on analyzing the user data (Molony [0058]-[0059], [0103], noting the system analyzes the sensor data to determine total sleep time (TST), i.e. sleep-duration data);
determine an in-bed-to-asleep metric for the sleep session of the user based on analysis of the in-bed-duration data and the sleep-duration data (Molony [0113], noting the system determines sleep efficiency (i.e. an in-bed-to-asleep metric) by determining a ratio of total time in bed to total sleep time);
provide the in-bed-to-asleep metric as input to a model that was trained to determine a (Molony [0218]-[0220], noting a determined first parameter (which is a sleep-related parameter per [0208], e.g. sleep efficiency as in [0058]-[0059] & [0113]) is input to a machine learning algorithm trained to output a predicted health outcome such as heart attack risk based on user data); and
perform an action based on the (Molony [0222], noting the system generates a custom message for a user (i.e. performs an action) based on the predicted health outcome).
In summary, Molony teaches a system for determining various sleep-related parameters based on sensor data collected during a sleep session and generating a heart failure risk score based on the determined sleep-related parameters. Molony further teaches that many types of sensor arrangements are contemplated (Molony [0056], [0080]-[0081]). However, in Molony the system is not explicitly disclosed as including a bed having the sensors, and the predicted risk score is not explicitly disclosed as being a probability measurement. However, Pinhas shows an analogous heart failure monitoring system that employs non-contact sensors installed in a patient’s bed to collect sleep and other user data (Pinhas abstract, [0193], [0350], [0437]-[0441]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the sensors of Molony to include sensors of a bed system on which a patient rests as in Pinhas in order to utilize more unobtrusive, non-contact sensors for data collection (as suggested by Pinhas abstract). Pinhas further teaches that predicting health outcomes based on collected sleep data can include predicting a probability or likelihood of the outcome (Pinhas [0293], [0410]-[0411]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the health outcome risk scores of Molony to specifically include probability measurements as in Pinhas in order to allow the system to output quantitative risk measurements indicating how likely a given outcome is, as well as to facilitate alerting a user if a predicted probability exceeds a threshold likelihood that an outcome is imminent so that preventative action may be taken (as suggested by Pinhas [0293]).
Claim 18
Molony in view of Pinhas teaches the system of claim 17, and the combination further teaches wherein: (Molony [0042], [0081], noting a control system (i.e. controller) that carries out the functions of the invention and may be integrated with any component of the system, such as the sensors (i.e. the bed with sensors when considered in the context of the combination with Pinhas)). However, the present combination fails to explicitly disclose that the bed further comprises a controller, i.e. that the computer system controller is integrated with the bed. However, Pinhas further teaches that the entire heart failure monitoring system may be installed in a patient’s bed mattress (Pinhas [0350]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to integrate the computer system controller of the combination into the bed itself as in Pinhas in order to provide an integrated bed system for local data collection, analysis, and display (as suggested by Pinhas [0350]).
Claim 19
Molony in view of Pinhas teaches the system of claim 17, and the combination further teaches wherein the computer system is remote from the bed (Molony [0089], noting the control system may be located in a cloud or remote server, which when considered in the context of the combination with Pinhas, indicates that the computer system could be remote from the bed with the sensors. See also Pinhas [0173]-[0175], noting remote analysis of the sensor data).
Claim 20
Molony teaches a system for determining a (Molony Figs. 1 & 13, [0095], [0206], [0218]-[0220], noting a system for predicting a health outcome such as a risk score of heart attack for a user based on data obtained during a sleep session taking place on a bed), the system comprising:
(Molony [0056], [0080], noting various sensors); and
a computer system in communication with the at least one sensor (Molony [0041]-[0042], [0045], noting a processor-based control system that carries out the functions of the invention and is in communication with the sensors):
receive, from the at least one sensor, user data collected by the at least one sensor when a user rests on the bed, the user data associated with the users including at least counts of disruptions per sleep session (Molony [0045], [0205]-[0206], noting the control system receives user data collected by sensors during a sleep session (i.e. when a user rests on a bed system as in [0095]); such data tracks a number of awakenings (i.e. disruptions) during a sleep session per [0100] & [0114]. See also [0176], noting the system tracks a number of times the user removes and/or replaces a sleep apnea mask and other disruptive events like snoring, choking, labored breathing, seizure, etc. that occur during a sleep session for use in determining an interruption score and event score for a sleep session);
determine in-bed-duration data for a sleep session of the user based on analyzing the user data (Molony [0058]-[0059], [0103], noting the system analyzes the sensor data to determine total time in bed (TIB), i.e. in-bed-duration data);
determine, by the computer system, sleep-duration data for the sleep session of the user based on analyzing the user data (Molony [0058]-[0059], [0103], noting the system analyzes the sensor data to determine total sleep time (TST), i.e. sleep-duration data);
determine an in-bed-to-asleep metric for the sleep session of the user based on analysis of the in-bed-duration data and the sleep-duration data (Molony [0113], noting the system determines sleep efficiency (i.e. an in-bed-to-asleep metric) by determining a ratio of total time in bed to total sleep time);
determine wake after sleep onset data based on analyzing the user data (Molony [0058]-[0059], [0112], noting the system analyzes the sensor data to determine wake-after-sleep onset);
provide the in-bed-duration data and the wake after sleep onset data as input to a model that was trained to determine a (Molony [0218]-[0220], noting a determined first parameter (which is one or more sleep-related parameter per [0208] & [0212], e.g. total time in bed and wake after sleep onset as in [0058]-[0059] & [0208]) is input to a machine learning algorithm trained to output a predicted health outcome such as heart attack risk based on user data); and
perform an action based on the (Molony [0222], noting the system generates a custom message for a user (i.e. performs an action) based on the predicted health outcome).
In summary, Molony teaches a system for determining various sleep-related parameters based on sensor data collected during a sleep session and generating a heart failure risk score based on the determined sleep-related parameters. Molony further teaches that many types of sensor arrangements are contemplated (Molony [0056], [0080]-[0081]). However, in Molony the system is not explicitly disclosed as including a bed having the sensors, and the predicted risk score is not explicitly disclosed as being a probability measurement. However, Pinhas shows an analogous heart failure monitoring system that employs non-contact sensors installed in a patient’s bed to collect sleep and other user data (Pinhas abstract, [0193], [0350], [0437]-[0441]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the sensors of Molony to include sensors of a bed system on which a patient rests as in Pinhas in order to utilize more unobtrusive, non-contact sensors for data collection (as suggested by Pinhas abstract). Pinhas further teaches that predicting health outcomes based on collected sleep data can include predicting a probability or likelihood of the outcome (Pinhas [0293], [0410]-[0411]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the health outcome risk scores of Molony to specifically include probability measurements as in Pinhas in order to allow the system to output quantitative risk measurements indicating how likely a given outcome is, as well as to facilitate alerting a user if a predicted probability exceeds a threshold likelihood that an outcome is imminent so that preventative action may be taken (as suggested by Pinhas [0293]).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Molony and Pinhas as applied to claim 1 above, and further in view of Wexler et al. (US 20210383925 A1).
Claim 5
Molony in view of Pinhas teaches the method of claim 1, but the present combination fails to explicitly disclose wherein the model is a logistic regression model. However, Wexler teaches an analogous machine learning model that predicts user status (e.g. heart failure as in [0019]) based on health-related information (e.g. sleep-related parameters as in [0020]) using logistic regression (Wexler [0030]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the machine learning algorithm of the combination to specifically include a logistic regression model as in Wexler because Wexler shows that logistic regression is a type of machine learning model that is suitable for evaluating health-related information like sleep-related parameters to predict user status like heart failure (as suggested by Wexler [0030]).
Claims 6-8 are rejected under 35 U.S.C. 103 as being unpatentable over Molony and Pinhas as applied to claim 1 above, and further in view of Zhang et al. (US 20080114219 A1).
Claim 6
Molony in view of Pinhas teaches the method of claim 1, showing a machine learning model trained via supervised or unsupervised learning (Molony [0219]). However, the present combination fails to explicitly disclose wherein the model was trained, by the computer system, using feature vectors that were assigned numeric values corresponding to training user data. However, Zhang teaches an analogous predictive model that outputs heart failure probability measurements based on sleep-related parameter inputs that is trained using feature vectors that are assigned numeric values corresponding to training user data (Zhang [0080]-[0081], noting a vector of weighting values corresponding to each feature and derived from historical data is used for the disease state prediction module). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the unspecified training of the algorithm as in the combination to include using feature vectors assigned numeric weights corresponding to training user data as in Zhang in order to allow the predictive model to learn the most accurate and appropriate weighting factors indicative of each input data type’s contribution to the outcome based on historical data (as suggested by Zhang [0081]).
Claim 7
Molony in view of Pinhas and Zhang teaches the method of claim 6, and the combination further teaches wherein the training user data includes at least one of wake time after sleep onset, sleep efficiency, sleep duration, sleep-bout duration, wake time before sleep onset, quantity of sleep disruptions, heartrate, heartrate variability, respiratory rate, or daytime alertness levels (Molony [0219], noting the inputs for the machine learning algorithm include the determined first and second parameters, which include sleep-related parameters like total sleep time (i.e. sleep duration), number of awakenings (i.e. quantity of sleep disruptions), a sleep onset latency (i.e. wake time before sleep onset), etc. per [0208] as well as non-sleep-related parameters like heart rate, heart rate variability, etc. per [0211]. Because the algorithm is trained to correlate these inputs to the output of a predicted health outcome, the training data is also considered to include such data types).
Claim 8
Molony in view of Pinhas and Zhang teaches the method of claim 6, and the combination further teaches wherein the training user data includes demographics information, the demographics information including at least one of weight, age, gender, or body mass index (BMI). (Molony [0219], noting the inputs for the machine learning algorithm can include demographic data, which includes age and gender per [0044]. Because the algorithm is trained to correlate these inputs to the output of a predicted health outcome, the training data is also considered to include such data types)
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Molony and Pinhas as applied to claim 1 above, and further in view of Goldstein et al. (US 20220344018 A1).
Claim 12
Molony in view of Pinhas teaches the method of claim 1, and the combination further teaches that output health scores can be numerical values within a range of 0 to 100 (Molony [0125], [0233]). However, the present combination fails to explicitly disclose wherein: the output from the model is a value between 0 and 1, the method further comprising: multiplying, by the computer system, the value with a numeric factor to generate a score of the risk of cardiac failure.
However, Goldstein teaches that probabilities of medical risk output by a diagnostic model may initially be valued between 0 and 1 and subsequently re-scaled and normalized to a percentage value between 0 and 100 by multiplying the initial value by a factor of 100 (Goldstein [0088]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify risk score of the combination to include an initial value between 0-1 that is then rescaled to a percentage as in Goldstein because this is a known method of normalizing a probability score to a percentage score that better meets principles of clear medical communication (as suggested by Goldstein [0068]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KAREN A HRANEK whose telephone number is (571)272-1679. The examiner can normally be reached M-F 8:00-4:00 ET.
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, Shahid Merchant can be reached on 571-270-1360. 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.
/KAREN A HRANEK/ Primary Examiner, Art Unit 3684