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 .
Response to Arguments
Applicant’s arguments in combination with amendments, see Remarks and Claims, filed 02/05/2026, with respect to rejections under 35 USC 102 have been fully considered and are persuasive. The 102 rejections of claims has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Yu reference as detailed below.
Applicant’s arguments in combination with amendments, see Remarks and Claims, filed 02/05/2026, with respect to rejections under 35 USC 101 have been fully considered but they and are not persuasive.
The applicant argues that the amendments clearly tie the claims to the specific architecture used. This argument is fully considered but is not persuasive. As written the claim does not provide any details of the specific architecture, (i.e., number of layers, the language, parameters, training details, etc.). The claim merely provides having more than one model and selecting the model based on time and/or location. As written, the models are pre-trained and are any generic models.
The applicant argues that the claims are not directed toward an abstract idea. This argument is fully considered but is not persuasive. The claim recites obtaining data, and providing prediction. These are concepts performed in mind. The additional limitations such as generating alarm, as recited, are merely outputting the result of the abstract idea. It is noted that the claims do not recite details of the alarm that would provide a specific treatment or step to mitigate the alarm status. As written, the claim merely recites outputting an indication.
For at least the reasons cited above, the 101 rejection is maintained. See detailed rejection below.
Claim Objections
Claim 11 objected to because of the following informalities: Claim 11 recites “an, a critical response unit” which should be amended to “a critical response unit”. Appropriate correction is required.
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 1-23 are rejected under 35 U.S.C. 101 because of the following analysis:
1 – statutory category: Claims 1-11 and 23 recite a system, and therefore, falls under the statutory category of being a thing or products. See MPEP 2106.03. Claim 12-22 recite a series of steps and therefore, falls under the statutory category of being a process. See MPEP 2106.03.
2A – Prong 1: The independent claims 1, 12 and 23 recite a judicial exception by reciting the limitations of “receive, [], current patient data for a patient; obtain a current mean arterial pressure (MAP) value from the current patient data; obtain prior MAP data obtained from the patient during a period of care; use the current MAP value, the prior MAP data, to predict [], whether a hemodynamic event is expected to occur within a window of time []”. These limitations, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in mind or by a person using a pen and paper. Therefore, an abstract idea is involved. In other words, obtaining various data to predict an event are concepts performed in the human mind (including an observation, evaluation, judgment, opinion).
Applying a previously pre-trained model, under its broadest reasonable interpretation, is understood to be the same as using a generic model. wherein, using a generic model is simply applying an abstract idea on a computer. See MPEP 2106.05(f).
Outputting an alert is further considered to be merely outputting the result of an abstract idea.
2A – Prong 2: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as an ordered combination do not amount to significantly more than the abstract idea. The independent claims 1, 12 and 23 recite the additional limitations of “system”, “processor”, “communications module”, “alert module”, “prediction engine”, “memory”, “device”, “display”, etc. The mentioned limitations are recited at a high level of generality and are considered to be data gathering/processing which are mere extra-solution activity. The elements amount to mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.04(d) and 2106.05(f)). Accordingly, each of the additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limitations on practicing the abstract idea.
2B: The emphasized elements cited above do not amount to significantly more than the judicial exception because these limitations are simply appending well-understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’I, 110 USPQ2d 1976 (2014)).
In view of the above, the additional elements individually do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process. Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known to the industry, as discussed in Alice Corp., 573 U.S. at 225, 110 USPQ2d at 1984 (see MPEP § 2106.05(d)).
Claims 2-11 and 13-22 depend on claims 1 and 12. The mentioned dependent claims recite the same abstract idea as the independent claims. Furthermore, these claims only contain recitations that further limit the abstract idea (that is, the claims only recite limitations that further limit the mental process). For example, the dependent claim recites the limitations “graphical user interface”, “monitored site”, “communication network”, “clinical site”, “wide area network”, “client device”, etc., are recited at a high level of generality and are mere extra-solution activity, and recited as performing generic computer functions. i.e., data processing. The elements amount to mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.04(d) and 2106.05(f)).
It is noted that the act of using a pre-trained deep learning model is equivalent to using an equation and falls under the judicial exception of mathematical calculations. Furthermore, the details of the model are recited at a high level of generality and are mere extra-solution activity, and recited as performing generic computer functions. i.e., data processing.
The additional elements individually do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Thus, claims 1-23 are directed to an abstract idea and are therefore rejected.
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.
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, 6, 10-12, 17, and 21-23 are rejected under 35 U.S.C. 103 as being obvious over Buddi et al. (US 2022/0395236) (hereinafter Buddi) in view of Yu et al. (US 20090210373) (hereinafter “Yu”).
Regarding claims 1, 12, and 23, Buddi discloses a system and method for predicting hemodynamic events (Abstract), the system (Fig. 4) comprising: a processor (system processor 40); a communications module coupled to the processor (para. 26: “Housing 18 of hemodynamic sensor 16 encloses… communication circuitry”); an alerts module coupled to the communications module and to the processor, the alerts module for generating and sending alerts (abstract, para. 0024, etc.) and a memory/non-transitory computer readable storage medium (system memory 42), the memory storing one or more trained models (para. 17 discloses selection of risk coefficients and/or hypotension profiling parameters can be accomplished via machine learning) and computer executable instructions for predicting hemodynamic events and generating alerts to be displayed in a user interface (Abstract; para. 33, last sentence: “User interface 54, as illustrated in FIG. 4, also provides sensory alarm 58 to provide warning to medical personnel of a predicted future hypotension event of patient 36”), the computer executable instructions comprising instructions that when executed by the processor cause the system to: receive via the communications module, current patient data (Fig. 6, box 72); obtain a current mean arterial pressure (MAP) value from the current patient data; obtain prior MAP data obtained from the patient during a period of care (para. 62: “changes in MAP with respect to time can be derived by subtracting the average of the MAP over the past five minutes, ten minutes, or other time durations, from the current value of the MAP”, suggesting the use of both current MAP value and past MAP values); use the current MAP value, the past MAP data, a predetermined MAP threshold (Fig. 6, box 70, 74 disclose MAP thresholds), and at least one trained model to predict a hemodynamic event, each trained model corresponding to a prediction interval to determine whether the hemodynamic event is expected to occur within a window of time (para. 42: “The risk coefficients can be determined via training operations (e.g., offline training) using machine learning or other techniques to minimize a cost function that represents the error of the risk score to the true value of training subsets (e.g., aggregations of data from multiple patients) that define hypotension according to a standard MAP threshold for hypotension. That is, risk coefficients utilized by predictive weighting module 50 can be selected via training operations to minimize the error of the predictive risk score determined by hypotension prediction software code 48 as predictive of a future hypotension event”); and output an alert indicative of the hemodynamic event to a device configured to display a graphical user interface comprising the alert (para. 33: ““User interface 54, as illustrated in FIG. 4, also provides sensory alarm 58 to provide warning to medical personnel of a predicted future hypotension event of patient 36”).
Buddi fails to disclose a prediction engine coupled to the communications module and to the processor, the prediction engine comprising a plurality of trained models including at least one trained model corresponding to an operating room (OR) setting and at least one trained model corresponding to an intensive care unit (ICU) setting, wherein each of the plurality of trained models corresponds to a respective window of time.
Yu, from a similar field of endeavor shows that it is known to provide multiple Models [] for the different time frame and the different location (para 0036). 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 disclosure of Buddi with the known teachings of Yu to provide the predictable result of providing different models for different time/locations to improve assessment.
Regarding claims 6 and 17, Buddi as modified by Yu renders obvious the system is remotely coupled to a monitored site via a communication network and the communications module, and the patient data is received via the communication network (para. 34: “Hemodynamic sensor 34 is operatively connected to hemodynamic monitor 10 (e.g., electrically and/or communicatively connected via wired or wireless connection, or both) to provide the sensed hemodynamic data to hemodynamic monitor 10”).
Regarding claims 10 and 21, Buddi as modified by Yu renders obvious the system is embedded in a client device on or near the patient (Fig. 4 depicts sensing system 32 on or near patient 36).
Regarding claims 11 and 22, Buddi as modified by Yu renders obvious the current patient data is obtained from the patient in an intensive care unit (ICU), an operating room (OR), a critical response unit, or an inpatient ward (para. 4, 6-7).
Claim(s) 2 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Buddi in view of Yu and Addison, further in view of Addison et al. (US 2022/0287579) (hereinafter Addison).
Regarding claims 2 and 13, modified Buddi does not disclose the at least one trained model used to predict the hemodynamic event is generated as a deep learning long-short term memory (LSTM) model.
Addison, however, teaches a system continuous non-invasive blood pressure measurement (Abstract) wherein at least a portion of the first sensor data, at least a portion of the second sensor data, and the calculated differential pulse transit time (DPTT) are input into a deep learning AI model to determine continuous non-invasive blood pressure (CNIBP). Exemplary deep learning AI models include LSTM model (para. 12; see also Fig. 9 which depicts blood pressure output 706 from LSTM model 704).
It would have been obvious to one of ordinary skill in the art before the effective filing date of this invention to modify Buddi (as modified by Yu) such that the at least one trained model used to predict the hemodynamic event is generated as a deep learning long-short term memory (LSTM) model. Making this modification would be useful for facilitating continuous non-invasive blood pressure measurement, as taught by Addison.
Claim(s) 3-4 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Buddi in view of Yu and Addison, further in view of Wilson et al. (US 2022/0061676) (hereinafter Wilson), further in view of Liu et al. (US 2021/0125696) (hereinafter Liu).
Regarding claims 3-4 and 14-15, modified Buddi does not teach the LSTM model is generated using longitudinal sequential patient level data collected over time across a monitored period, wherein the LSTM utilizes a sequence of hemodynamic data points in an observation window.
Wilson, however, teaches monitoring blood pressure levels in a patient using machine learning (Abstract) wherein the systolic BP prediction submodel 840 concatenates the systolic blood pressure prediction outputted by the first model trained to process sequential features (e.g., the LSTM model described above) with the systolic blood pressure prediction outputted by the second model trained to process static features (e.g., Dense neural network described above) to generate an aggregate prediction of a patient's rolling systolic blood pressure average, for example their rolling average over a 3-day time period. Similarly, the diastolic blood pressure prediction submodel 845 concatenates the diastolic blood pressure prediction outputted by model trained to process sequential features (e.g., the LSTM model described above) with the diastolic blood pressure prediction outputted by the second model trained to process static features (e.g., Dense neural network) to generate an aggregate prediction of a patient's rolling diastolic blood pressure average, for example their rolling average over a 3-day time period. The concatenation performed by each of the systolic BP prediction submodel 840 and the diastolic BP prediction submodel 845 is further described with reference to FIG. 8C. In practice, the long-term prediction model 830 generates predictions of systolic blood pressure with a mean absolute error (MAE) of 4.3 mmHg and the diastolic blood pressure with an MAE of 3.5 mmHg (para. 112).
Furthermore, Liu teaches method and system for personalized hypertension treatment (Abstract) wherein the adjustment treatment model receives patient input such as longitudinal blood pressure measurements 121 and other patient characteristics 122 and determines an adjustment treatment plan for the patient including the type of medicine(s) 123 and dosage 124. This model may be trained using the adjustment treatment training data. The adjustment treatment model includes a classification model 126 and a regression model 127. The classification model 126 includes feature selection and classification. Training the classification model includes determining based upon the adjustment treatment training data, which are the best features for predicting what type of medicine to use, which might include changing which medicine(s) to use to treat the patient going forward. Various types of models for classification may be used including, for example, multiple linear logistic regression, random forest, support vector machines (SVM), K nearest neighbor classifier (KNN), and longitudinal machine learning methods such as recursive neural network (RNN), long short-term memory (LSTM), and penalized linear mixed effects models (para. 49).
Taking the teachings of Wilson and Liu together, it would have been obvious to one of ordinary skill in the art before the effective filing date of this invention to modify modified Buddi as modified by Yu such that the LSTM model is generated using longitudinal sequential patient level data collected over time across a monitored period, wherein the LSTM utilizes a sequence of hemodynamic data points in an observation window. Making this modification would be useful for generating predictions of systolic blood pressure with a mean absolute error (MAE) of 4.3 mmHg and the diastolic blood pressure with an MAE of 3.5 mmHg, as taught by Wilson, and determining an adjustment treatment plan for the patient, as taught by Liu.
Claims 7-8 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Buddi in view of Yu, further in view of Chaudhuri et al. (US 2020/0178903) (hereinafter Chaudhuri).
Regarding claims 7-8 and 18-19, modified Buddi does not disclose the alert is sent via the communication network to the monitored site to be displayed by a device on or near a monitored patient; the alert is sent via the communication network to a client device used by a caregiver or clinician, the client device being mobile relative to the monitored site.
Chaudhuri, however, teaches a patient monitoring system (Abstract) wherein upon detection of an alarm event by the respective sensing device 3a-3c, an alarm may be generated either by the sensing device 3a-3c (e.g., an auditory alarm via a speaker and/or visual alarm via a display) or the hub 15 (e.g., via speaker 18 and/or display 16), at a mobile device 50 (e.g., via speaker 53 and/or display 52), and/or a network access point (such as a central monitoring station or computer terminal at a nurse's station) (para. 27; Fig. 2).
It would have been obvious to one of ordinary skill in the art before the effective filing date of this invention to modify Buddi as modified by Yu such that the alert is sent via the communication network to the monitored site to be displayed by a device on or near a monitored patient; the alert is sent via the communication network to a client device used by a caregiver or clinician, the client device being mobile relative to the monitored site. Making this modification would be useful for providing an alarm at a mobile device and/or a network access point, such as a central monitoring station or computer terminal at a nurse’s station, as taught by Chaudhuri.
Claim(s) 9 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Buddi in view of Yu, further in view of Lee et al. (US 2004/0236190) (hereinafter Lee).
Regarding claims 9 and 20, modified Buddi does not disclose the communication network is a local area network at a clinical site or a wide area network connectable to one or more local area networks.
Lee, however, teaches network based patient monitor apparatus (Abstract) wherein it is desirable to take advantage of the existing LAN of a hospital for establishing novel network based patient monitor apparatuses so that a medical staff, for example, a nurse or doctor whether locally or remotely located, can immediately know the conditions of a patient by using a computer to retrieve the patient's data from an associated monitor apparatus (para. 5).
It would have been obvious to one of ordinary skill in the art before the effective filing date of this invention to modify Buddi as modified Yu such that the communication network is a local area network at a clinical site such that a nurse or doctor whether locally or remotely located, can immediately know the conditions of a patient by using a computer to retrieve the patient's data from an associated monitor apparatus, as taught by Lee.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SANA SAHAND whose telephone number is (571)272-6842. The examiner can normally be reached M-Th 8:30 am -5:30 pm; F 9 am-3 pm.
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, Jennifer S McDonald can be reached at (571) 270- 3061. 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.
/SANA SAHAND/Examiner, Art Unit 3796
Prosecution Insights