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 the Claims
Claims 10, 12-14, and 22-29 are currently pending. Claims 28-29 are added in the Claims filed on February 10, 2026.
Information Disclosure Statement
The information disclosure statement filed June 29, 2026 fails to comply with 37 CFR 1.98(a)(3)(i) because it does not include a concise explanation of the relevance, as it is presently understood by the individual designated in 37 CFR 1.56(c) most knowledgeable about the content of the information, of each reference listed that is not in the English language. It has been placed in the application file, but the information referred to therein has not been considered.
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 10, 12-14, and 22-29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Step 1
Claims 10, 12-14, and 22-29 are within the four statutory categories. Claims 10, 12-14, and 22-29 are drawn to a system for predicting patient stoppage of a therapy, which is within the four statutory categories (i.e. machine).
Prong 1 of Step 2A
Claim 10 recites: A system for predicting patient stoppage of a prescribed treatment that is administered by an automated peritoneal dialysis ("APD") machine, the system comprising:
a memory device comprising
a training data set including treatment data and patient data for a group of patients, the training data also including an indication as to whether the patients stopped treatments or did not stop treatments of a prescribed therapy or program performed by an APD machine,
at least one patient predictive model that is trained using the training data set and configured to output a probability, at least five to seven days in advance, that a patient will at least one of end treatments or reduce a frequency of treatments of a prescribed treatment that is administered by an APD machine, the at least one patient predictive model including inputs of at least (i) counts or frequency of alerts generated by the APD machine, (ii) information related to peritoneal dialysis cycles, (iii) patient blood pressure values, and (iv) patient weight values, and
patient data and previous treatment data for patients that are undergoing prescribed therapies or programs;
an interface device communicatively coupled to the APD machine via a network, the interface device configured to receive the treatment data from the APD machine for a target patient; and
a predictive processor communicatively coupled to the interface device and the memory device, the predictive processor being configured to:
store the treatment data received by the interface device to the memory device,
use the at least one patient predictive model to determine a concern score for the target patient by applying the patient data, the treatment data, and the previous treatment data of the target patient as inputs to the at least one patient predictive model, the concern score being indicative of a probability that the target patient will at least one of end treatments or reduce a frequency of treatments of the prescribed therapy or program performed by the APD machine within at least a next five to seven days, and
cause the concern score to be displayed within a user interface on a clinician device,
wherein the predictive processor trains the at least one patient predictive model using the training data set by
extracting data including (i) counts or frequency of alerts generated by an APD machine, (ii) information related to peritoneal dialysis cycles, (iii) patient blood pressure values, and (iv) patient weight values,
correlating treatment data and patient data to identified patients, and
comparing characteristics of the patients who stopped treatment to characteristics of patients that did not stop treatment to produce modeled patients.
The underlined limitations as shown above, given the broadest reasonable interpretation, cover the abstract idea of a mathematical concept and/or a certain method of organizing human activity because they recite mathematical relationships, formulas, equations, and/or mathematical calculations (in this case, the steps of determining the probability that the patient will end treatments or reduce a frequency of treatments, determining the concern score, and training the patient predictive model including extracting data, correlating data, and comparing data recite at least mathematical relationships and/or calculations), and/or managing personal behavior or relationships or interactions between people (i.e. social activities, teaching, and following rules or instructions, and/or a mental process that a neurologist should follow when testing a patient for nervous system malfunctions – in this case, storing a training data set for a patient predictive model, utilizing the patient predictive model to output a probability that a patient will at least one of end treatments or reduce a frequency of treatments, inputting various inputs into the patient predictive model to obtain the probability, storing patient data and previous treatment data, storing treatment data, using the patient predictive model to determine a concern score for the patient by applying the patient data, the treatment data, and the previous treatment data into the patient predictive model, and displaying the concern score to a clinician recites rules or instructions for a clinician to follow when testing a patient for the particular condition of the patient stopping or reducing treatment), 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 12-14 and 22-29 include other limitations, for example Claim 12 recites identifying and displaying the most significant concern parameters contributing to the concern score, Claim 13 recites storing data that relates medical fluid delivery recommendations to a range of concern scores, Claim 14 recites determining and displaying a recommendation based on the concern score, Claim 22 recites types of therapies and treatment data, Claim 23 recites generating an alert when the concern score exceeds a threshold, Claim 24 recites that the alert is indicative that the patient will end treatments or reduce a frequency of treatments, Claim 25 recites selecting and displaying a recommendation based on the concern score, Claim 26 recites selecting the recommendation based on the concern score, treatment data, and patient data, Claim 27 recites identifying and storing parameters that contribute to the concern score, , and Claim 29 recites a verification data set for validating the patient predictive model, but these only serve 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 dependent Claims 12-14 and 22-29 not addressed above are deemed additional elements to the abstract idea, and will be further addressed below. Hence dependent Claims 12-14 and 22-29 are nonetheless directed towards fundamentally the same abstract idea as independent Claim 10.
Prong 2 of Step 2A
Claim 10 is not integrated into a practical application because the additional elements (i.e. the non-underlined limitations above – in this case, the memory device, the interface device, the network, the predictive processor, the clinician device, the APD machine, the user interface, the training of the patient predictive model, the patient predictive model itself) amount to no more than limitations which:
amount to mere instructions to apply an exception – for example, the recitation of the memory device, the interface device, the network, the predictive processor, the clinician device, the APD machine, the user interface, and the patient predictive model, which amounts to merely invoking a computer or other machinery as a tool to perform the abstract idea, e.g. see [0013], [0062], [0075]-[0076], [0088], [0122], and [00179] of the as-filed Specification, and see MPEP 2106.05(f); and/or
generally link the abstract idea to a particular technological environment or field of use – for example, the claim language of the device being a clinician device and the machine being an ADP machine, which amounts to limiting the abstract idea to the field of dialysis and/or healthcare, see MPEP 2106.05(h).
Additionally, dependent Claims 12-14 and 22-29 include other limitations, but these limitations also amount to no more than generally linking the abstract idea to a particular technological environment or field of use (e.g. the types of data recited in dependent Claims 13, 22, and 29, the recitation of the various types of patient predictive models recited in dependent Claim 28), and/or do not include any additional elements beyond those already recited in independent Claim 10, and hence also do not integrate the aforementioned abstract idea into a practical application.
Step 2B
Claim 10 does not include additional elements that are sufficient to amount to “significantly more” than the judicial exception because the additional elements (i.e. the non-underlined limitations above – in this case, the memory device, the interface device, the network, the predictive processor, the clinician device, the APD machine, the user interface, the patient predictive model itself), as stated above, are directed towards no more than limitations that amount to mere instructions to apply the exception, and/or generally link the abstract idea to a particular technological environment or field of use, wherein the additional elements comprise limitations which:
amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields, as demonstrated by:
The Specification expressly disclosing that the structural additional elements are well-understood, routine, and conventional in nature:
[0013], [0062], [0075]-[0076], [0088], [0122], and [00179] of the as-filed Specification discloses that the additional elements (i.e. the memory device, the interface device, the network, the predictive processor, the clinician device, the APD machine, the user interface, and the patient predictive model itself) comprise a plurality of different types of generic computing systems;
Relevant court decisions: The functional limitations interpreted as additional elements are analogized to the following examples of court decisions demonstrating well-understood, routine and conventional activities, e.g. see MPEP 2106.05(d)(II):
Receiving or transmitting data over a network, e.g. see Intellectual Ventures v. Symantec – similarly, the interface device receives treatment data, and transmits the data to the analytics processor over a network, for example the Internet, e.g. see [00116] and [00121]-[00122] of the present Specification;
Electronic recordkeeping, e.g. see Alice Corp v. CLS Bank – similarly, the current invention merely recites the storing of treatment data, training data, and a predictive model on a database and/or electronic memory;
Storing and retrieving information in memory, e.g. see Versata Dev. Group, Inc. v. SAP Am., Inc. – similarly, the current invention recites storing treatment data, training data, and a predictive model in a database and/or electronic memory, and retrieving the treatment data, training data, and a predictive model from storage in order to determine the probability that the patient will end or reduce treatments and the concern score;
Dependent Claims 12-14 and 22-29 include other limitations, but none of these limitations are deemed significantly more than the abstract idea because the additional elements recited in the aforementioned dependent claims similarly amount to no more than generally linking the abstract idea to a particular technological environment or field of use (e.g. the types of data recited in dependent Claims 13, 22, and 29, the recitation of the various types of patient predictive models recited in dependent Claim 28), and/or do not include any additional elements beyond those already recited in independent Claim 10, and hence do not amount to “significantly more” than the abstract idea.
Thus, taken alone, the additional elements do not amount to significantly more than the abstract idea identified above. Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken 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 conventional computer implementation.
Therefore, whether taken individually or as an ordered combination, Claims 10, 12-14, and 22-29 are nonetheless rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Subject Matter Free From Prior Art
Claims 10, 12-14, and 22-29 are not presently rejected under 35 U.S.C. 102 or 103, and hence would be in condition for allowance if amended to overcome the rejections presented under 35 U.S.C. 101. The following represents Examiner’s characterization of the most relevant prior art references and the differences between the present claim language and the prior art references in view of 35 U.S.C. 102 and/or 103:
With regards to 35 U.S.C. 102 and/or 103, the following represents the closest prior art to the claimed invention, as well as the differences between the prior art and the limitations of the presently claimed invention.
As an initial matter, the claim language of “at least one patient predictive model that is trained using the training data set and configured to output a probability, at least five to seven days in advance, that a patient will at least one of end treatments or reduce a frequency of treatments of a prescribed treatment that is administered by the APD machine” is interpreted in accordance with Applicant’s Remarks filed on September 30, 2025, and in accordance with [0173] of the as-filed Specification, which recites that “the example predictive processor 310d…is configured or trained to predict patient stoppage at least five to seven days in advance, and up to 21 to 30 days in advance.” That is, the aforementioned claim language is interpreted as reciting outputting a probability, wherein the probability predicts that a patient will end or reduce treatments from the APD machine at least five to seven days from when the prediction was made.
Veome (US 2004/0088189) teaches storing patient treatment data including an indication of whether the treatment has been stopped and/or is incomplete. However, Veome does not teach utilizing the stored treatment data as training data to train a predictive model that outputs a probability that the patient will end or reduce treatments at least five to seven days from when the prediction was made, or that the treatments are prescribed treatments administered by an APD machine. Furthermore, Veome does not teach the particular inputs into the predictive model, and/or any of the features pertaining to the determination and display of the concern score.
Hua (US 2010/0205008) teaches the determination and display of a treatment adherence score indicating the probability that the patient will adhere to a treatment regimen or plan, wherein the determination is made using various historical medical data. However, Hua does not teach that the treatment plan is for a treatment administered by an APD machine. Additionally, Hua does not teach that the adherence score comprises a probability that the patient will end or reduce treatments at least five to seven days in advance of when the prediction was made.
Zhou (“Applying machine learning to predict future adherence to physical activity programs,” BMC Medical Informatics and Decision Making (2019) 19:169) teaches utilizing logistic regression and support vector machine methods to design a Discontinuation Prediction Score (DiPS) that comprises a numeric value that quantifies a patient’s likelihood of discontinuing physical activity in the upcoming week. However, as Applicants note, the DiPS score is indicative of a probability of discontinuing physical activity and does not provide any indication of ending or reducing a prescribed treatment administered by an APD machine. Accordingly, Zhou also does not disclose that the parameters input into the algorithms used to determine the DiPS score comprise counts or frequencies of alerts generated by an APD machine, information related to peritoneal dialysis cycles, patient blood pressure, and/or patient weight. Furthermore, Zhou does not teach that the training data used to train the algorithms to determine the DiPS score comprise an indication as to whether the patients stopped or did not stop treatments of a prescribed therapy performed by an APD machine.
Sundar (US 2015/0032465) teaches calculating the probability of adherence to a prescription drug therapy in the form of a Medication Possession Ratio (MPR), wherein the MPR may be for over a period starting six days after the initial start of treatment. However, Sundar teaches that the MPR calculated for the six days after the initial start of treatment is an actual MPR rather than a predicted (i.e. future) MPR, and although Sundar also teaches a predicted MPR, it does not teach how the predicted MPR is obtained/determined beyond using historical/past MPR values. Additionally, Sundar teaches a prediction of the probability that the patient ceases the drug therapy, but this is a separate metric from the MPR, and further Sundar does not teach that this prediction is for the likelihood that the patient ends or reduces treatment at least five to seven days from when the prediction is made. Additionally, the probability of adherence is for adherence to a prescription drug therapy and not a probability relating to treatments administered by an APD machine.
Yu (US 2010/0010427) teaches a prediction model for a patient receiving treatment from an APD machine, wherein the prediction model comprises an alert algorithm that is used to generate medical alerts. However, Yu does not teach that the alerts generated by the alert algorithm comprise predictions of the likelihood of the patient ending or reducing treatments at least five to seven days in advance of when the prediction was made.
The aforementioned references are understood to be the closest prior art. Various aspects of the present invention are known individually, but for the reasons disclosed above, the particular manner in which the elements of the present invention are claimed, when considered as an ordered combination, distinguishes from the aforementioned references and hence the invention recited in Claims 10, 12-14, and 22-29 is not considered to be disclosed by and/or obvious in view of the inventions of the closest prior art references.
Response to Arguments
Applicant’s arguments, see Remarks, filed August 14, 2026, with respect to the rejections of Claims 10, 12-14, and 22-29 under 35 U.S.C. 101 have been fully considered but are not persuasive.
Applicants first allege that the claimed invention is patent eligible because it recites significantly more than an abstract idea, specifically because the claimed limitations as an ordered combination are not a conventional computer implementation of an abstract result, and because the claimed limitations now recite specific operations comprising the training of the patient predictive model, e.g. see pgs. 7-9 of Remarks – Examiner disagrees.
Regarding the consideration of the claimed limitation as an ordered combination, the invention of Bascom is an example of an invention that was deemed eligible because it amounted to significantly more than abstract idea when its additional elements were considered as an ordered combination. Additionally, the invention of Bascom achieved the improvements of decreased susceptibility to hacking, less dependence on local hardware and software, and increase flexibility for the filtering of data, where the aforementioned improvements were achieved as a result of the ordered combination of known elements, specifically the installation of a filtering tool at a specific location, remote from end-users, with customizable filtering features specific to each end user, e.g. see MPEP 2106.05(I)(B). In contrast, the claimed invention recites known, conventional elements (i.e. the memory device, the interface device, the network, the predictive processor, the clinician device, the APD machine, and the user interface) performing known, conventional functions (i.e. receiving data/inputs, storing the data/inputs, transmitting/communicating the data/inputs, processing the data/inputs, and displaying the results of the processing). For example, the fact that the operation of “a model receiving an input” receives an input of a specific type of data (e.g. counts or frequency of alerts generated by an APD machine) does not change the fact that the operation itself is a known, conventional function. That is, the type of data being narrowly claimed is not dispositive of the eligibility of the claimed limitations. Additionally, there is no disclosure of any of the aforementioned elements operating differently when considered as an ordered combination versus when they are considered individually. Hence the claimed invention and the problems it addresses as well as its improvements are distinguished from Bascom and are not patent eligible even when considered as an ordered combination.
Furthermore, regarding the newly amended features defining the training process itself, as shown above, the steps of extracting data, correlating data, and comparing data comprise mathematical relationships and/or calculations, and hence comprise limitations that are part of the abstract idea, and are not properly considered additional elements that amount to significantly more than the abstract idea.
Additionally, Examiner notes that “the novelty of any element or steps in a process, or even of the process itself, is of no relevance in determining whether the subject matter of a claim falls within the 101 categories of possibly patentable subject matter,” and specifically, a finding of a lack of novelty under 35 U.S.C. 102 or obviousness under 35 U.S.C. 103 of a claimed invention does not necessarily indicate that claimed invention is therefore patent eligible. Because they are separate and distinct requirements from eligibility, patentability of the claimed invention under 35 U.S.C. 102 and 103 with respect to the prior art is neither required for, nor a guarantee of, patent eligibility under 35 U.S.C. 101, e.g. see MPEP 2106.05(I).
Regarding Desjardins, the invention of Desjardins recited a specific process for training a machine learning model to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting” encountered in continual learning systems, and hence provided improvements as to how the machine learning model itself operates. In contrast, the claimed invention recites that the patient predictive model is trained with a specific set of training data, and although it now claims the operations comprising the training itself, the Specification does not disclose similar technological improvements to machine learning. For example, [0004] of the as-filed Specification discloses that “the models are configured to provide recommendations to clinicians regarding how patient adherence to one or more prescribed therapies or programs can be improved by addressing potential issues the patient may be experiencing,” [0005] of the as-filed Specification discloses that “the AI patient predictive models are configured to accurately determine a patient’s risk using readily available data without having to access third-party data or other medical data stored in a patient’s medical record,” and [0006] of the as-filed Specification discloses that the system “may enable a clinician and/or the patient to silence some alarms or address alarms in an attempt to limit or avoid patient alarm fatigue.” Hence, the Specification discloses that the problems addressed by the claimed invention comprise problems with patient adherence, patient risk, and alarm fatigue related to medical issues, wherein the claimed invention improves patient adherence, more accurately calculates patient risk, and helps mitigate alarm fatigue. The aforementioned problems are not technological problems because they have existed since long before the advent of any computer technology, and the improvements represent improvements to the abstract idea of a mathematical concept and/or a certain method of organizing human activities, and an improvement to an abstract idea itself is not an improvement in technology, e.g. see MPEP 2106.05(a)(II). Hence, unlike Desjardins, the claimed invention does not address technological problems and/or achieve technological improvements. Therefore, the claimed invention and the problems it addresses as well as its improvements are distinguished from Desjardins.
For the aforementioned reasons, Claims 10, 12-14, and 22-29 are rejected under 35 U.S.C. 101.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure is as follows:
Rao (US 2008/0275731) – teaches a system that calculates the likelihood of patient adherence to a treatment regimen.
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 JOHN P GO whose telephone number is (703)756-1965. The examiner can normally be reached Monday-Friday 9am-6pm Pacific.
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.
/JOHN P GO/Primary Examiner, Art Unit 3681
Prosecution Insights