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, see pages 11-12, filed 05/13/2026, with respect to drawing objections have been fully considered and are persuasive. The drawing objections have been obviated by the amendment to Fig. 3. The drawing objections have been withdrawn.
Applicant’s arguments, see page 12, filed 05/13/2026, with respect to specification objections have been fully considered and are persuasive. The specification objections have been obviated by amendments to the specification. The specification objections have been withdrawn.
Applicant’s arguments, see page 12, filed 05/13/2026, with respect to claim objections have been fully considered and are persuasive. The claim objections have been obviated by amendments to the claims. The claim objections have been withdrawn.
Applicant’s arguments, see pages 12-13, filed 05/13/2026, with respect to 35 U.S.C. 112(a) rejections have been fully considered and are persuasive. The 35 U.S.C. 112(a) rejections have been withdrawn. The Examiner notes that the 35 U.S.C. 112(f) claim interpretation is withdrawn as well.
Applicant’s arguments, see pages 12-13, filed 05/13/2026, with respect to 35 U.S.C. 112(b) rejections have been fully considered and are persuasive. The 35 U.S.C. 112(b) rejections have been obviated by amendments to the claims. The 35 U.S.C. 112(b) rejections have been withdrawn.
Applicant’s arguments, see pages 13-16, filed 05/13/2026, with respect to 35 U.S.C. 101 rejections have been fully considered but they are not persuasive. The Applicant argues that the amended claims are not directed to an abstract idea. The Applicant argues that the present claims, which relate to techniques for using machine learning models to prophylactically predict and prevent attrition, do not recite or relate to a mental process, nor can they be performed mentally. The Applicant cites the August 2025 memorandum (“Reminders on evaluating subject matter eligibility of claims under 35 U.S.C. 101”), and argues that the present claims are not directed to mental processes, at least because several elements of the present claims cannot be performed mentally, including elements such as “predicting a probability of attrition from a medical treatment for the patient based on processing the prediction data using a machine learning (ML) model,” “in response to determining compatibility with one or more healthcare systems, querying the one or more healthcare systems using an identifier of the patient,” “receiving a response from at least one of the one or more healthcare systems indicating how to intervene for the patient,” and “triggering the intervention based on the response.”
This is not found persuasive. The amended claims are still found to be directed to an abstract idea (mental process). The ML model is described at a high level of generality in the Applicant’s specification, such as a suitable ML model (e.g., a random forest ML model) (Par. [0022]) or a logistic progression ML model, a gradient boosting ML model (e.g., light GBM classifier), a fully randomized trees ML model, any suitable supervised ML model (e.g., a trained DNN, regression model, or any other suitable supervised ML model) (Par. [0046]). The involvement of the “ML model” is therefore considered insignificant extra-solution activity in that it amounts to generic computer implementation of the abstract idea [MPEP 2106.04(a)(2)(III)(C)]. The Examiner maintains that “predicting a probability of attrition from a medical treatment for the patient” is a mental process when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(III), the mental process grouping includes observations, evaluation, judgements, and opinions. In this case, a human could mentally predict a probability of attrition from a medical treatment for the patient by observing, evaluating, and making judgements of a patient and their medical treatment. The limitation “determining compatibility with one or more healthcare systems” is a mental process when given its broadest reasonable interpretation. In this case, a human could mentally evaluate or make a judgement as to whether a healthcare system is compatible or not compatible. The limitation “querying the one or more healthcare systems using an identifier of the patient” is considered an additional element, but is considered insignificant pre-solution activity, i.e. mere data gathering [MPEP 2106.05(g)]. The limitation “receiving a response from at least one of the one or more healthcare systems indicating how to intervene for the patient” is also considered an additional element, but is also considered insignificant pre-solution activity, i.e. mere data gathering [MPEP 2106.05(g)]. The limitation “triggering the intervention based on the response” is also considered an additional element, but amounts to merely outputting data, which is insignificant extra-solution activity [MPEP 2106.05(g)]. Please see 35 U.S.C. 101 rejections below.
The Applicant further argues that even if the present claims do recite a judicial exception, pursuant to prong two of Step 2A, the claims are still patent eligible. The Applicant again cites the August Memorandum and argues that the amended claims are eligible because they “reflect an improvement in the functioning of a computer, or an improvement to other technology or technical field,” and further “integrate” the alleged “judicial exception into a practical application of the exception”. The Applicant cites to their Specification at Pars. [0036] and [0038] and argues that as understood by one of ordinary skill in the art, this dynamic compatibility check enables effective and seamless interactivity with various platforms in order to determine how to intervene for a given patient. The Applicant argues this is a clear technical improvement over conventional systems. The Applicant also argues that these improvements are reflected in the present claims.
This is not found persuasive. The amended claims are not found to reflect an improvement in the functioning of a computer, or an improvement to other technology or technical field. The Examiner finds the claims to simply be performing a mental process on a generic computer or using a computer as a tool to perform a mental process [MPEP 2106.04(a)(2)(III)(C) – “A claim that requires a computer may still recite a mental process”].
The Applicant further cites to the August Memorandum and recites the “close call” guidance to make the argument that the present claims at least reflect a “close call”. The Applicant further cites Ex parte Desjardins and argues that the present 35 U.S.C. 101 rejections similarly evaluate the claims at a high level of generality without adequate explanation.
This is not found persuasive. As explained in Examiner’s response to arguments and in the 35 U.S.C. 101 rejections hereinbelow, the Examiner finds the claims to be ineligible under 35 U.S.C. 101. The Examiner therefore does not consider this as a “close call” as defined in the August Memorandum and finds it to be more likely than not (i.e., more than 50%) that the claim is ineligible under 35 U.S.C. 101. With regards to the Ex parte Desjardins case, it is noted that each case turs on its own set of facts. In Desjardins, it was found that claims directed to improvements in how the machine learning model itself operates can be patent-eligible. This is not found to be the case in the present claims. As explained, the ML model is described at a high level of generality in the Applicant’s specification, such as a suitable ML model (e.g., a random forest ML model) (Par. [0022]) or a logistic progression ML model, a gradient boosting ML model (e.g., light GBM classifier), a fully randomized trees ML model, any suitable supervised ML model (e.g., a trained DNN, regression model, or any other suitable supervised ML model) (Par. [0046]). The involvement of the “ML model” is therefore considered insignificant extra-solution activity in that it amounts to generic computer implementation of the abstract idea [MPEP 2106.04(a)(2)(III)(C)]. The Examiner finds the claims to simply be performing a mental process on a generic computer or using a computer as a tool to perform a mental process [MPEP 2106.04(a)(2)(III)(C) – “A claim that requires a computer may still recite a mental process”]. Therefore, the 35 U.S.C. 101 rejections are maintained. Please see 35 U.S.C. 101 rejections hereinbelow.
Applicant’s arguments, see pages 17-18, filed 05/13/2026, with respect to prior art rejections have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. The 35 U.S.C. 103 rejections hereinbelow have been necessitated by the claim amendments.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea (mental process of predicting a probability of attrition from a medical treatment for a patient based on prediction data, and intervening to discourage attrition based on the predicted probability) without significantly more.
Step 1
Independent claims 1, 11, and 16 are directed to a method, an apparatus, and a non-transitory computer-readable medium, and thus meet the requirements for step 1.
Step 2A, Prong 1
Regarding claims 1, 11, and 16, the following steps recite an abstract idea:
“predicting a probability of attrition from a medical treatment for the patient” is a mental process when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(III), the mental process grouping includes observations, evaluation, judgements, and opinions. In this case, a human could mentally predict a probability of attrition from a medical treatment for the patient by observing, evaluating, and making judgements of a patient and their medical treatment.
“determining compatibility with one or more healthcare systems” is a mental process when given its broadest reasonable interpretation. As discussed in MPEP 2106.04(a)(2)(III), the mental process grouping includes observations, evaluation, judgements, and opinions. In this case, a human could mentally evaluate or make a judgement as to whether a healthcare system is compatible or not compatible.
Step 2A, Prong 2
Regarding claims 1, 11, and 16, the claims do not include any additional elements that integrate the abstract idea into a practical application. The following elements do not add any meaningful limitation to the abstract idea:
identifying a plurality of prediction data, the prediction data comprising both: (i) patient medical data comprising a plurality of characteristics relating to a medical history for the patient, and (ii) patient order data comprising a plurality of characteristics relating to an order history for medical items relating to the patient, wherein the patient order data comprises an order interval between orders for the patient – insignificant pre-solution activity, i.e. mere data gathering [MPEP 2106.05(g)]
… based on processing the prediction data using a machine learning (ML) model, wherein the ML model is trained – The ML model is described at a high level of generality in the Applicant’s specification, such as a suitable ML model (e.g., a random forest ML model) (Par. [0022]) or a logistic progression ML model, a gradient boosting ML model (e.g., light GBM classifier), a fully randomized trees ML model, any suitable supervised ML model (e.g., a trained DNN, regression model, or any other suitable supervised ML model) (Par. [0046]). The involvement of the “ML model” is insignificant extra-solution activity in that it amounts to generic computer implementation of the abstract idea [MPEP 2106.04(a)(2)(III)(C)].
… using prior patient medical data and prior patient order data, relating to a plurality of prior patients – insignificant pre-solution activity, i.e. mere data gathering [MPEP 2106.05(g)].
triggering an intervention to prophylactically discourage the attrition from the medical treatment for the patient, based on the predicted probability of the attrition – amounts to merely outputting data, which is insignificant extra-solution activity [MPEP 2106.05(g)].
querying the one or more healthcare systems using an identifier of the patient – insignificant pre-solution activity, i.e. mere data gathering [MPEP 2106.05(g)].
receiving a response from at least one of the one or more healthcare systems indicating how to intervene for the patient – insignificant pre-solution activity, i.e. mere data gathering [MPEP 2106.05(g)].
triggering the intervention based on the response – amounts to merely outputting data, which is insignificant extra-solution activity [MPEP 2106.05(g)].
a memory; and a hardware processor communicatively coupled to the memory -– The memory is described at a high level of generality in the Applicant’s specification, as it is explained that the memory may include one or more memory devices having blocks of memory associated with physical addresses, such as random access memory (RAM), read only memory (ROM), flash memory, or other types of volatile and/or non-volatile memory (Par. [0041]). The processor is also described at a high level of generality in the Applicant’s specification, as it is explained that the processor is representative of a single central processing unit (CPU), multiple CPUs, a single CPU having multiple processing cores, graphics processing units (GPUs) having multiple execution paths, and the like (Par. [0040]). The involvement of the “memory” and “processor” is insignificant extra-solution activity in that it amounts to generic computer implementation of the abstract idea [MPEP 2106.04(a)(2)(III)(C)].
Therefore, the claims are directed to an abstract idea without a practical application.
Step 2B
The additional elements of claims 1, 11, and 16, when considered either individually or in an ordered combination, are not enough to qualify as significantly more than the abstract idea. As discussed above with respect to the integration of the abstract idea into a practical application, the “ML Model”, the “memory”, and the “processor”, along with their associated functions and components, are recited with a high level of generality and simply amount to implementing the abstract idea on a computer. The additional elements that were considered insignificant extra-solution activity have been re-analyzed and do not amount to anything more than what is well-understood, routine, and conventional. Also, simply appending well-understood, routine, and conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception is not indicative of an inventive concept [MPEP 2106.05(d)].
identifying a plurality of prediction data, the prediction data comprising both: (i) patient medical data comprising a plurality of characteristics relating to a medical history for the patient, and (ii) patient order data comprising a plurality of characteristics relating to an order history for medical items relating to the patient, wherein the patient order data comprises an order interval between orders for the patient – MPEP 2106.05(d)(II)(“i. Receiving or transmitting data over a network, e.g., using the Internet to gather data”)
… based on providing the prediction data to a machine learning (ML) model, wherein the ML model is trained to predict the probability – Varghese, et al. (U.S. PGPub No. 2016/0314418) explains that conventional attrition prediction models use machine learning methods with numerous attrition triggers as input databases (Par. [0005]).
… using prior patient medical data and prior patient order data, relating to a plurality of prior patients – MPEP 2106.05(d)(II)(“i. Receiving or transmitting data over a network, e.g., using the Internet to gather data”) and MPEP 2106.05(d)(II)(“iv. Storing and retrieving information in memory”).
triggering an intervention to prophylactically discourage attrition from the medical treatment for the patient, based on the predicted probability of attrition – Varghese, et al. (U.S. PGPub No. 2016/0314418) explains that the HR officer is instantly notified of the employee’s cumulative risk flag and can take immediate remedial action (i.e., intervention) (Par. [0064-0065]).
querying the one or more healthcare systems using an identifier of the patient – MPEP 2106.05(d)(II)(“i. Receiving or transmitting data over a network, e.g., using the Internet to gather data”)
receiving a response from at least one of the one or more healthcare systems indicating how to intervene for the patient – MPEP 2106.05(d)(II)(“i. Receiving or transmitting data over a network, e.g., using the Internet to gather data”)
triggering the intervention based on the response – Varghese, et al. (U.S. PGPub No. 2016/0314418) explains that the HR officer is instantly notified of the employee’s cumulative risk flag and can take immediate remedial action (i.e., intervention) (Par. [0064-0065]).
a memory; and a hardware processor communicatively coupled to the memory -– MPEP 2106.05(d)(II)(“i. Receiving or transmitting data over a network, e.g., using the Internet to gather data”) and MPEP 2106.05(d)(II)(“iv. Storing and retrieving information in memory”).
Therefore, the claims are directed to an abstract idea without a practical application and without significantly more.
Dependent claims
Regarding dependent claims 2, 4-6, 12-14, 17-19, the limitations only further define insignificant extra-solution activity of gathering data.
Regarding dependent claims 8-9, the limitations only further define insignificant extra-solution activity of generic computer implementation of the abstract idea.
Regarding dependent claims 3, 10, 15, and 20, the limitations only further define the abstract idea.
Regarding dependent claim 7, the limitations only further define insignificant extra-solution activity of outputting data.
Therefore, claims 1-20 are unpatentable under 35 U.S.C. 101.
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.
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.
Claims 1-4, 6-13, 15-18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Williams, et al. (U.S. PGPub No. 2022/0273873) and Vdovjak, et al. (U.S. PGPub No. 2014/0039929).
Regarding claim 1, Williams teaches (Fig. 1A, # 106, 116, 156) a computer-implemented method (Abstract; Par. [0023] – the attrition prevention application is a computer application; Par. [0024-0026]), comprising:
(Fig. 1A, # 112, 114; Fig. 2) identifying a plurality of prediction data (Par. [0025]), the prediction data comprising both: (i) (Fig. 2, # 204) patient medical data comprising a plurality of characteristics relating to a medical history for the patient (Par. [0056]; Par. [0060] – patient’s age, weight, gender), and (ii) (Fig. 7) patient order data comprising a plurality of characteristics relating to an order history for medical items relating to the patient, wherein the patient order data comprises an order interval between orders for the patient (Par. [0109] – Historical usage, ordering, complaint, and other data may also be collected as input, yielding an estimated attrition date for patients; Examiner notes that ordering data would be understood to comprise an order interval between orders);
(Fig. 1A, # 106, 116 – ML system, 156 – ML Algorithm) predicting a probability of attrition from a medical treatment for the patient based on processing the prediction data using a machine learning (ML) model (Par. [0004]; Par. [0032] – usage, treatment, and service data contain the crucial variables used to drive an attrition prediction algorithm executed by the attrition prevention engine 106 as well as attrition prevention application 150; Par. [0035] – the ML algorithm may use the data as predictor variables in order to produce a probability value that represents a probability of patient attrition (i.e., a user’s likelihood to abandon use of the drug delivery device)),
wherein (Fig. 1A, # 106, 112 and 114 – prior patient medical data, 116 – ML system, 156 – ML Algorithm; Fig. 2; Fig. 7) the ML model is trained using prior patient medical data and prior patient order data, relating to a plurality of prior patients (Par. [0035] – the ML algorithm may use the data as predictor variables in order to produce a probability value that represents a probability of patient attrition. An example of the set of data collected is shown in Fig. 2 and may be used for the attrition prediction algorithm; Par. [0109] – order data); and
(Fig. 1, # 156) triggering an intervention to prophylactically discourage the attrition from the medical treatment for the patient, based on the predicted probability of the attrition (Par. [0037] – Once the attrition probability and recommendation are stored within the data lake, the ML algorithm 156 is operable to trigger alarms to implement various interventions. The attrition probability may cause ML algorithm 156 to generate different responses), comprising:
(Fig. 1, # 156) receiving a response from at least one of the one or more healthcare systems indicating how to intervene for the patient (Par. [0037] – Alternatively, for a user with a high attrition probability, the in-person assistance from the customer care system 118 initiated by the ML algorithm 156 may include a member of a clinical team reaching out (e.g., calling, emailing, texting, or sending a notification, for example) to the patient to better understand the issues and help with any issues a patient may be having with the drug delivery device 108, controller 134 or another part of the system.); and
(Fig. 1, # 156) triggering the intervention based on the response (Par. [0037] – Alternatively, for a user with a high attrition probability, the in-person assistance from the customer care system 118 initiated by the ML algorithm 156 may include a member of a clinical team reaching out (e.g., calling, emailing, texting, or sending a notification, for example) to the patient to better understand the issues and help with any issues a patient may be having with the drug delivery device 108, controller 134 or another part of the system.).
Williams does not explicitly teach the limitation of instant claim 1, that is wherein in response to determining compatibility with one or more healthcare systems, querying the one or more healthcare systems using an identifier of the patient.
Vdovjak is directed to analogous art and teaches a federated master patient index for autonomous healthcare entities (Title, Abstract). Vdovjak teaches the limitation of instant claim 1, that is wherein (Fig. 6) in response to determining compatibility with one or more healthcare systems, querying the one or more healthcare systems using an identifier of the patient (Par. [0010] – receive an electronically formatted query for a patient from an autonomous healthcare entity in a federation of healthcare entities, wherein the query includes at least an identifier of the entity and a unique patient identifier of the patient generated by the entity; Pars. [0038-0041]; It is noted that being an autonomous healthcare entity in a federation of healthcare entities is viewed as satisfying the compatibility requirement).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have implemented Vdovjak’s method step of determining compatibility and querying using a patient identifier into Williams’ method, because doing so would be an example of applying a known technique to a known method ready for improvement to yield predictable results. Williams teaches (Fig. 1A, # 104) that the stakeholder system may be a computer system or computer environment of a healthcare provider, a healthcare provider network or system, or a guardian of a patient, or the like (Par. [0027]). One of ordinary skill in the art would recognize that such a compatibility check and querying method step, as disclosed in Vdovjak, would be beneficial to have implemented in Williams’ method when the stakeholder system is a healthcare provider network or system. One of ordinary skill in the art would have desired such method steps as disclosed in Vdovjak because it has become more and more common that patients receive care from multiple healthcare providers geographically dispersed at multiple entities (see Par. [0002] of Vdovjak).
Therefore, claim 1 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 2, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 1, as indicated hereinabove. Williams also teaches the limitation of instant claim 2, that is wherein (Fig. 1, # 156) the prediction data further comprises patient intervention data comprising a plurality of characteristics relating to past interventions with the patient (Par. [0039]).
Therefore, claim 2 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 3, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 2, as indicated hereinabove. Williams also teaches the limitation of instant claim 3, that is wherein (Fig. 1, # 156) the ML model is trained to predict the probability further using prior patient intervention data (Par. [0039]).
Therefore, claim 3 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 4, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 2, as indicated hereinabove. Williams also teaches the limitation of instant claim 4, that is wherein the patient medical data comprises (Fig. 1A; Fig. 2, # 202, 204) two or more of: (i) demographic data for the patient, (ii) medical equipment data for the patient, (iii) care provider data for the patient, and (iv) prior diagnosis information for the patient (Par. [0056], [0058], and [0060]).
Therefore, claim 4 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 6, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 2, as indicated hereinabove. Williams also teaches the limitation of instant claim 6, that is wherein the patient order data comprises (Fig. 7) two or more of: (i) statistical information for the order history for the medical items relating to the patient, (ii) information describing the medical items previously ordered by the patient as part of the order history, and (iii) payment history information relating to the order history for medical items relating to the patient (Par. [0109] – historical ordering; It would be well known that historical ordering would include two or more of the items on this list).
Therefore, claim 6 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 7, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 1, as indicated hereinabove. Williams also teaches the limitation of instant claim 7, that is wherein (Fig. 1A) triggering the intervention comprises triggering an automated communication to at least one of: (i) the patient, (ii) a care provider associated with the patient, or (iii) a care facility associated with the patient (Par. [0021]; Par. [0037] – a lower attrition probability may cause the generation of an automated response. A user may receive a push notification in their cloud-connected diabetes management device).
Therefore, claim 7 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 8, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 7, as indicated hereinabove. Williams also teaches the limitation of instant claim 8, that is wherein (Fig. 3, # 308) the automated communication comprises at least one of: (i) an automated telephone call, (ii) a short message service (SMS) message, (iii) a multimedia messaging service message (MMS), or (iv) an e-mail message (Par. [0037] – calling, emailing, texting, sending a notification; Par. [0065]).
Therefore, claim 8 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 9, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 7, as indicated hereinabove. Williams also teaches the limitation of instant claim 9, that is wherein (Fig. 1A; Fig. 3, # 308) the automated communication comprises an electronic communication to the patient (Par. [0037]; Par. [0065]).
Therefore, claim 9 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 10, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 1, as indicated hereinabove. Williams also teaches the limitation of instant claim 10, that is wherein (Fig. 1A, # 156) triggering an intervention to prophylactically discourage attrition from the medical treatment for the patient, based on the predicted probability of attrition comprises:
determining that the predicted probability of attrition exceeds a threshold value, and in response triggering the intervention (Par. [0035]; Par. [0037] – For example, a lower attrition probability may cause generation of an automated response, while a higher attrition probability may cause the ML algorithm 156 to initiate human interaction; This is representative of threshold values for the predicted probability of attrition).
Therefore, claim 10 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 11, Williams teaches (Fig. 1A, # 100) an apparatus (Par. [0024]; Par. [0151] – the various elements of the devices, apparatuses, or systems as previously described with reference to Figs. 1A-9…) comprising:
(Figs. 1A-B, # 146 – memory) a memory (Par. [0043]); and
(Fig. 1A-B, # 134) a hardware processor communicatively coupled to the memory (Par. [0043]), the hardware processor configured to perform operations comprising:
(Fig. 1A, # 112, 114; Fig. 2) identifying a plurality of prediction data (Par. [0025]), the prediction data comprising both: (i) (Fig. 2, # 204) patient medical data comprising a plurality of characteristics relating to a medical history for the patient (Par. [0056]; Par. [0060] – patient’s age, weight, gender), and (ii) (Fig. 7) patient order data comprising a plurality of characteristics relating to an order history for medical items relating to the patient, wherein the patient order data comprises an order interval between orders for the patient (Par. [0109] – Historical usage, ordering, complaint, and other data may also be collected as input, yielding an estimated attrition date for patients; Examiner notes that ordering data would be understood to comprise an order interval between orders);
(Fig. 1A, # 106, 116 – ML system, 156 – ML Algorithm) predicting a probability of attrition from a medical treatment for the patient based on processing the prediction data using a machine learning (ML) model (Par. [0004]; Par. [0032] – usage, treatment, and service data contain the crucial variables used to drive an attrition prediction algorithm executed by the attrition prevention engine 106 as well as attrition prevention application 150; Par. [0035] – the ML algorithm may use the data as predictor variables in order to produce a probability value that represents a probability of patient attrition (i.e., a user’s likelihood to abandon use of the drug delivery device)),
wherein (Fig. 1A, # 106, 112 and 114 – prior patient medical data, 116 – ML system, 156 – ML Algorithm; Fig. 2; Fig. 7) the ML model is trained using prior patient medical data and prior patient order data, relating to a plurality of prior patients (Par. [0035] – the ML algorithm may use the data as predictor variables in order to produce a probability value that represents a probability of patient attrition. An example of the set of data collected is shown in Fig. 2 and may be used for the attrition prediction algorithm; Par. [0109] – order data); and (Fig. 1, # 156) triggering an intervention to prophylactically discourage the attrition from the medical treatment for the patient, based on the predicted probability of the attrition (Par. [0037] – Once the attrition probability and recommendation are stored within the data lake, the ML algorithm 156 is operable to trigger alarms to implement various interventions. The attrition probability may cause ML algorithm 156 to generate different responses), comprising:
(Fig. 1, # 156) receiving a response from at least one of the one or more healthcare systems indicating how to intervene for the patient (Par. [0037] – Alternatively, for a user with a high attrition probability, the in-person assistance from the customer care system 118 initiated by the ML algorithm 156 may include a member of a clinical team reaching out (e.g., calling, emailing, texting, or sending a notification, for example) to the patient to better understand the issues and help with any issues a patient may be having with the drug delivery device 108, controller 134 or another part of the system.); and
(Fig. 1, # 156) triggering the intervention based on the response (Par. [0037] – Alternatively, for a user with a high attrition probability, the in-person assistance from the customer care system 118 initiated by the ML algorithm 156 may include a member of a clinical team reaching out (e.g., calling, emailing, texting, or sending a notification, for example) to the patient to better understand the issues and help with any issues a patient may be having with the drug delivery device 108, controller 134 or another part of the system.).
Williams does not explicitly teach the limitation of instant claim 11, that is wherein in response to determining compatibility with one or more healthcare systems, querying the one or more healthcare systems using an identifier of the patient.
Vdovjak is directed to analogous art and teaches a federated master patient index for autonomous healthcare entities (Title, Abstract). Vdovjak teaches the limitation of instant claim 11, that is wherein (Fig. 6) in response to determining compatibility with one or more healthcare systems, querying the one or more healthcare systems using an identifier of the patient (Par. [0010] – receive an electronically formatted query for a patient from an autonomous healthcare entity in a federation of healthcare entities, wherein the query includes at least an identifier of the entity and a unique patient identifier of the patient generated by the entity; Pars. [0038-0041]; It is noted that being an autonomous healthcare entity in a federation of healthcare entities is viewed as satisfying the compatibility requirement).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have implemented Vdovjak’s processor step of determining compatibility and querying using a patient identifier into Williams’ processor steps, because doing so would be an example of applying a known technique to a known method ready for improvement to yield predictable results. Williams teaches (Fig. 1A, # 104) that the stakeholder system may be a computer system or computer environment of a healthcare provider, a healthcare provider network or system, or a guardian of a patient, or the like (Par. [0027]). One of ordinary skill in the art would recognize that such a compatibility check and querying method step, as disclosed in Vdovjak, would be beneficial to have implemented in Williams’ method when the stakeholder system is a healthcare provider network or system. One of ordinary skill in the art would have desired such method steps as disclosed in Vdovjak because it has become more and more common that patients receive care from multiple healthcare providers geographically dispersed at multiple entities (see Par. [0002] of Vdovjak).
Therefore, claim 11 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 12, Williams, in view of Vdovjak, renders obvious the apparatus of claim 11, as indicated hereinabove. Williams also teaches the limitation of instant claim 12, that is wherein (Fig. 1, # 156) the prediction data further comprises patient intervention data comprising a plurality of characteristics relating to past interventions with the patient (Par. [0039]).
Therefore, claim 12 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 13, Williams, in view of Vdovjak, renders obvious the apparatus of claim 12, as indicated hereinabove. Williams also teaches the limitations of instant claim 13, that is wherein the patient medical data comprises (Fig. 1A; Fig. 2, # 202, 204) two or more of: (i) demographic data for the patient, (ii) medical equipment data for the patient, (iii) care provider data for the patient, and (iv) prior diagnosis information for the patient (Par. [0056], [0058], and [0060]), and
wherein (Fig. 7) the patient order data comprises two or more of: (i) statistical information for the order history for the medical items relating to the patient, (ii) information describing the medical items previously ordered by the patient as part of the order history, and (iii) payment history information relating to the order history for the medical items relating to the patient (Par. [0109] – historical ordering; It would be well known that historical ordering would include two or more of the items on this list).
Therefore, claim 13 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 15, Williams, in view of Vdovjak, renders obvious the apparatus of claim 11, as indicated hereinabove. Williams also teaches the limitation of instant claim 15, that is wherein (Fig. 1A, # 156) triggering the intervention to prophylactically discourage the attrition from the medical treatment for the patient, based on the predicted probability of the attrition comprises:
determining that the predicted probability of the attrition exceeds a threshold value, and in response triggering the intervention (Par. [0035]; Par. [0037] – For example, a lower attrition probability may cause generation of an automated response, while a higher attrition probability may cause the ML algorithm 156 to initiate human interaction; This is representative of threshold values for the predicted probability of attrition).
Therefore, claim 15 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 16, Williams teaches (Fig. 1, # 106) a non-transitory computer-readable medium (Par. [0026] – the attrition prevention engine 106 may be programming instructions embodied in a non-transitory computer readable medium) comprising instructions that, when executed by (Fig. 1A-B, # 134) a processor (Par. [0043]), cause the processor to perform operations comprising:
(Fig. 1A, # 112, 114; Fig. 2) identifying a plurality of prediction data (Par. [0025]), the prediction data comprising both: (i) (Fig. 2, # 204) patient medical data comprising a plurality of characteristics relating to a medical history for the patient (Par. [0056]; Par. [0060] – patient’s age, weight, gender), and (ii) (Fig. 7) patient order data comprising a plurality of characteristics relating to an order history for medical items relating to the patient, wherein the patient order data comprises an order interval between orders for the patient (Par. [0109] – Historical usage, ordering, complaint, and other data may also be collected as input, yielding an estimated attrition date for patients; Examiner notes that ordering data would be understood to comprise an order interval between orders);
(Fig. 1A, # 106, 116 – ML system, 156 – ML Algorithm) predicting a probability of attrition from a medical treatment for the patient based on processing the prediction data using a machine learning (ML) model (Par. [0004]; Par. [0032] – usage, treatment, and service data contain the crucial variables used to drive an attrition prediction algorithm executed by the attrition prevention engine 106 as well as attrition prevention application 150; Par. [0035] – the ML algorithm may use the data as predictor variables in order to produce a probability value that represents a probability of patient attrition (i.e., a user’s likelihood to abandon use of the drug delivery device)),
wherein (Fig. 1A, # 106, 112 and 114 – prior patient medical data, 116 – ML system, 156 – ML Algorithm; Fig. 2; Fig. 7) the ML model is trained using prior patient medical data and prior patient order data, relating to a plurality of prior patients (Par. [0035] – the ML algorithm may use the data as predictor variables in order to produce a probability value that represents a probability of patient attrition. An example of the set of data collected is shown in Fig. 2 and may be used for the attrition prediction algorithm; Par. [0109] – order data); and
(Fig. 1, # 156) triggering an intervention to prophylactically discourage the attrition from the medical treatment for the patient, based on the predicted probability of the attrition (Par. [0037] – Once the attrition probability and recommendation are stored within the data lake, the ML algorithm 156 is operable to trigger alarms to implement various interventions. The attrition probability may cause ML algorithm 156 to generate different responses), comprising:
(Fig. 1, # 156) receiving a response from at least one of the one or more healthcare systems indicating how to intervene for the patient (Par. [0037] – Alternatively, for a user with a high attrition probability, the in-person assistance from the customer care system 118 initiated by the ML algorithm 156 may include a member of a clinical team reaching out (e.g., calling, emailing, texting, or sending a notification, for example) to the patient to better understand the issues and help with any issues a patient may be having with the drug delivery device 108, controller 134 or another part of the system.); and
(Fig. 1, # 156) triggering the intervention based on the response (Par. [0037] – Alternatively, for a user with a high attrition probability, the in-person assistance from the customer care system 118 initiated by the ML algorithm 156 may include a member of a clinical team reaching out (e.g., calling, emailing, texting, or sending a notification, for example) to the patient to better understand the issues and help with any issues a patient may be having with the drug delivery device 108, controller 134 or another part of the system.).
Williams does not explicitly teach the limitation of instant claim 16, that is wherein in response to determining compatibility with one or more healthcare systems, querying the one or more healthcare systems using an identifier of the patient.
Vdovjak is directed to analogous art and teaches a federated master patient index for autonomous healthcare entities (Title, Abstract). Vdovjak teaches the limitation of instant claim 16, that is wherein (Fig. 6) in response to determining compatibility with one or more healthcare systems, querying the one or more healthcare systems using an identifier of the patient (Par. [0010] – receive an electronically formatted query for a patient from an autonomous healthcare entity in a federation of healthcare entities, wherein the query includes at least an identifier of the entity and a unique patient identifier of the patient generated by the entity; Pars. [0038-0041]; It is noted that being an autonomous healthcare entity in a federation of healthcare entities is viewed as satisfying the compatibility requirement).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have implemented Vdovjak’s method step of determining compatibility and querying using a patient identifier into Williams’ method, because doing so would be an example of applying a known technique to a known method ready for improvement to yield predictable results. Williams teaches (Fig. 1A, # 104) that the stakeholder system may be a computer system or computer environment of a healthcare provider, a healthcare provider network or system, or a guardian of a patient, or the like (Par. [0027]). One of ordinary skill in the art would recognize that such a compatibility check and querying method step, as disclosed in Vdovjak, would be beneficial to have implemented in Williams’ method when the stakeholder system is a healthcare provider network or system. One of ordinary skill in the art would have desired such method steps as disclosed in Vdovjak because it has become more and more common that patients receive care from multiple healthcare providers geographically dispersed at multiple entities (see Par. [0002] of Vdovjak).
Therefore, claim 16 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 17, Williams, in view of Vdovjak, renders obvious the non-transitory computer-readable medium of claim 16, as indicated hereinabove. Williams also teaches the limitation of instant claim 17, that is wherein (Fig. 1, # 156) the prediction data further comprises patient intervention data comprising a plurality of characteristics relating to past interventions with the patient (Par. [0039]).
Therefore, claim 17 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 18, Williams, in view of Vdovjak, renders obvious the non-transitory computer-readable medium of claim 17, as indicated hereinabove. Williams also teaches the limitation of instant claim 18, that is wherein the patient medical data comprises (Fig. 1A; Fig. 2, # 202, 204) two or more of: (i) demographic data for the patient, (ii) medical equipment data for the patient, (iii) care provider data for the patient, and (iv) prior diagnosis information for the patient (Par. [0056], [0058], and [0060]), and
wherein (Fig. 7) the patient order data comprises two or more of: (i) statistical information for the order history for the medical items relating to the patient, (ii) information describing the medical items previously ordered by the patient as part of the order history, and (iii) payment history information relating to the order history for the medical items relating to the patient (Par. [0109] – historical ordering; It would be well known that historical ordering would include two or more of the items on this list).
Therefore, claim 18 is unpatentable over Williams, et al. and Vdovjak, et al.
Regarding claim 20, Williams, in view of Vdovjak, renders obvious the non-transitory computer-readable medium of claim 16, as indicated hereinabove. Williams also teaches the limitation of instant claim 20, that is wherein (Fig. 1A, # 156) triggering the intervention to prophylactically discourage the attrition from the medical treatment for the patient, based on the predicted probability of the attrition comprises:
determining that the predicted probability of the attrition exceeds a threshold value, and in response triggering the intervention (Par. [0035]; Par. [0037] – For example, a lower attrition probability may cause generation of an automated response, while a higher attrition probability may cause the ML algorithm 156 to initiate human interaction; This is representative of threshold values for the predicted probability of attrition).
Therefore, claim 20 is unpatentable over Williams, et al. and Vdovjak, et al.
Claims 5, 14, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Williams, et al. (U.S. PGPub No. 2022/0273873) and Vdovjak, et al. (U.S. PGPub No. 2014/0039929), further in view of Dibari, et al. (U.S. PGPub No. 2021/0090733).
Regarding claims 5, 14, and 19, Williams, in view of Vdovjak, renders obvious the computer-implemented method of claim 4, the apparatus of claim 13, and the non-transitory computer-readable medium of claim 18, as indicated hereinabove. Williams does not teach the limitation of instant claims 5, 14, and 19, that is wherein the patient medical data further comprises sentiment analysis generated using natural language processing (NLP) for one or more medical notes relating to the patient.
However, Dibari is directed to method and systems for detecting a mental health condition, where structured and unstructured information is analyzed using natural language processing to extract information including clinical data values and medical concepts pertaining to a user (Abstract, Claim 1). Dibari teaches the limitations of instant claims 5, 14, and 19, that is wherein (Fig. 1, # 125 – NLP sentiment analyzer engine; Fig. 4, # 425) the patient medical data further comprises sentiment analysis generated using natural language processing (NLP) for one or more medical notes relating to the patient (Par. [0017]; Par. [0029-0031] – For example, a patient may be determined to be at-risk if the patient has specific biomarkers associated with depression and the sentiment analyzer determines sentiment as being negative; Par. [0050]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have implemented patient medical data comprising sentiment analysis generated using NLP, as shown in Dibari, into Williams’ modified invention, because doing so is an example of using a known technique to improve similar devices/methods in the same way. One of ordinary skill in the art would have desired implementing medical data comprising sentiment analysis to allow words with strong positive sentiment to be distinguished from words with low positive sentiment in order to produce a sentiment score (Par. [0050] of Dibari). One of ordinary skill in the art would recognize that such a technique could be implemented in Williams’ invention to improve the attrition probability values.
Therefore, claims 5, 14, and 19 are unpatentable over Williams, et al., Vdovjak, et al., and Dibari, et al.
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 MICHAEL TAYLOR HOLTZCLAW whose telephone number is (571)272-6626. The examiner can normally be reached Monday-Friday (7:30 a.m.-5:00 p.m. EST).
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 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.
/MICHAEL T. HOLTZCLAW/Primary Examiner, Art Unit 3796
Prosecution Insights