Detailed Action
The following action is in response to the communication(s) received on 12/17/2025.
As of the claims filed 12/17/2025:
Claims 1, 6, 21, and 22 have been amended.
Claim 24 has been added.
Claims 2 and 9-20 have been canceled.
Claims 1, 3-8, and 21-24 are now pending.
Claims 1 are independent claims.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/17/2025 has been entered.
Response to Arguments
Applicant’s arguments filed 12/17/2025 have been fully considered, but are not fully persuasive.
Rejections under 35 USC § 101:
Applicant’s arguments have been considered and are persuasive. Thus, the rejection regarding eligibility has been withdrawn.
Rejections under 35 USC § 103:
Applicant asserts that Hanina does not teach the adherence gap prediction (p.27). This is unpersuasive, as Hanina ([col.14 2nd ¶] Criteria other than the adherence rate may also be chosen for inclusion of a patient on the watch list. For example, placement of a patient on the watch list may result if a gap in adherence of m consecutive days was predicted. Here m is greater than or equal to zero and less than or equal to k) teaches the future gap in medication possession, as adherence includes possession of medication as taught by the combined primary art Kapaldo ([0004] An accepted and standard approximate measurement of medical adherence (or “adherence”) is the “proportion of days covered” (PDC), which computes the fraction of days a patient is covered (has effective medication) to treat a condition). Applicant’s argument regarding Foschini not teaching this limitation is moot in view of the response above.
Applicant further asserts that the references lacking the gap prediction results in failing to teach ranking the users by the “urgency measure” (p.28 1st ¶). Examiner respectfully submits that Hanina does teach the gap days as discussed above. Gap days measures how many days the patient has been without the medication, which is indicative of an urgency measure.
Applicant further asserts that Kelly does not disclose the process of evaluating multiple communication channels and choosing the one with the highest probability of prompting the user’s expected action. Examiner respectfully submits that Kelly does teach the limitation of selecting the best time to send the communication ([0004]; [abstract] By providing a reminder prompt generation system that utilizes machine-learning and/or artificial intelligence to determine appropriate reminder times). Determining best channel out of the multiple communication channels is further taught by the combination with the primary art in Kapaldo [0070] and must be read in combination, not in separation. It is reasonable for a person of the ordinary skill in the art to send the most appropriate time (Kelly [0004]) and communication methods (Kapaldo [0070]).
Applicant further asserts that none of the prior arts teach the amended limitation of dispatching content via an API in claim 1 (p.29 last ¶). This is unpersuasive, as Kapaldo does further teach this limitation in [0070], where robotic-based calls or emails initiated by the intervention servers correspond to the automatic construction of the communication to the user which involve an API (e.g., email is an API).
Applicant further asserts that none of the prior arts teach the amended limitation of using gap days for the urgency approach in claim 6 (p. 29 last ¶). This is unpersuasive, as Hanina further teaches this limitation in [col.14 line 7], as m consecutive days of gap in adherence places the patient into the watch list, and thus corresponds to the threshold time interval.
As set forth in the previous office action and as maintained in this office action, the references do teach the recited limitations:
Applicant further asserts that Kapaldo does not teach the dual-model risk prediction. Examiner respectfully submits that the claims do not specifically recite “dual model risk predictions”, rather that it requires an adherence and gap days analysis. Kapaldo does not teach the gap days, but Hanina teaches the gap days ([col.14 2nd ¶], please see office action below).
Applicant further asserts that Hanina does not teach the communication optimization. Examiner respectfully submits that Foschini, via Kapaldo/Hanina/Foschini/Kelly, further teaches the limitation (Foschini [0034], please see office action below).
The argument that Foschini does not teach selecting a specific communication channel has been considered but is moot in view of the new rejection under 35 U.S.C. 103 in view of Kelly (Abstract; [0004]; please see office action below).
Applicant further asserts that the prior art does not teach the dual-model adherence risk structure. Examiner respectfully submits that, as stated above, the claims do not explicitly recite the model to have two distinct predictive models “in tandem.” Rather, the claims recite a method to rank a set of eligible users using predicted gap days, taught by Hanina (e.g. [col.14 2nd ¶] ), and then determining the optimal communication method to send to the user, taught by Foschini (e.g. [0064]).
Applicant’s argument regarding selecting a specific communication channel has been considered but is moot in view of the new rejection under 35 U.S.C. 103 further in view of Kelly ([Abst.]; [0004]).
Applicant’s argument regarding determining the optimal time to send the communication has been considered but is moot in view of the new rejection under 35 U.S.C. 103 further in view of Kelly ([Abst.]; [0002]).
Applicant further asserts that the prior art does not teach using training datasets comprised of time series data representing instances of communication performed using each of the respective communication channels so that each of the plurality of machine learning models is configured to output a likelihood of a particular user performing an expected action based on receiving a communication. This is unpersuasive, as Foschini further teaches these limitations (Foschini [0064]).
Applicant asserts the Office Action has used impermissible hindsight in the combination of Kapaldo/Hanina/Foschini/Kelly. Examiner respectfully submits the analogous endeavors and the motivations for the combination of Kapaldo/Hanina/Foschini/Kelly are provided in the previous and current Office Actions. As currently recited, the claims can be broadly read such that the training to classify the input merely comprises determining a ranking of eligible users, selecting a user based on the ranking, and determining a communication method for outputting the data.
Thus, the claims remain obvious in view of the prior arts.
Claim Objections
Claim 1 is objected to because of the following informalities:
Claim 1 recites “agregate,” which should instead recite “aggregate”.
Appropriate action is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 24 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 24 recites the limitation "a channel-specific application programming interface (API)". It is unclear whether it is referring to the channel-specific application programming interface in claim 1 or a new channel-specific application programming interface.
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, 3-8, 21, 23, and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Kapaldo US 20210241873 A1 (hereinafter Kapaldo) in view of Hanina et al US 11631484 B1 (hereinafter Hanina), further in view of Foschini et al., US 20210151194 A1 (hereinafter Foschini), further in view of Kelly et al., US 20200004583 A1 (hereinafter Kelly).
Regarding Claim 1, Kapaldo teaches:
A computer-implemented method for communicating with users (Kapaldo, abstract, “Artificial Intelligence (AI) based systems and methods are disclosed for implementing patient-specific medical adherence intervention”),
comprising the steps of: receiving user profile data for each of a set of eligible users (Kapaldo [0028] the database 105 may include all or part of any of the data or information described herein, including, for example, the one or more search requests, the one or more transaction details, and the profile information of the user);
for each eligible user from the set of eligible users: providing user profile data for the eligible user as input to a first machine learning based model (Kapaldo [0008] The AI based systems and methods may input patient-specific data, medication related data, and other data);
trained to predict adherence rates; and executing the first machine learning based model to predict an adherence rate for the eligible user (Kapaldo [0008] to determine adherence metrics such as when, how, how many times, and in what combinations of interaction modes, channels, and/or intervals to intervene with specific patients);
the adherence rate representing the rate at which the eligible user performs a predefined action… (Kapaldo [0004] An accepted and standard approximate measurement of medical adherence (or “adherence”) is the “proportion of days covered” (PDC)) (Note: being medically adherent corresponds to performing a predefined action)
wherein at least one of the communication parameters indicates a communication channel selected from a plurality of communication channels used for communicating with users; (Kapaldo [0035] An intervention channel, for example, comprises any of, e.g., a telephone communication, a text message, an in-app communication, or an email, which may be transmitted or otherwise established, e.g., via computer network 120 from server(s)) [0068] Once one or more intervention methods/types are selected (block 24), server(s) 102 may execute intervention algorithm 250.)
Kapaldo does not teach, but Hanina further teaches:
executing a gap days prediction model to dynamically predict future gap days for the eligible user that represent a number of days the eligible user is without a prescription (Hanina [Abstract] A system and method for predictively following up with a user to improve medication adherence. The system includes a medication adherence monitoring apparatus for determining whether a user has taken a medication at a predetermined medication administration time… [col. 14 last ¶] Known models from time series analysis thus may be used to make predictions about future adherence. If time series models are used, the only data required are a patient's past data. Sample data from other members of the population, or from similar existing or past populations aren't required, but may be employed as desired. In addition, a model may be fitted to each patient's data. Since different patients may have different behavioral patterns, this is an advantage to time series models. In this case, the predictive model 400 may preferably comprise an aggregate of predictive models for each patient.
[col.14 2nd ¶] Criteria other than the adherence rate may also be chosen for inclusion of a patient on the watch list. For example, placement of a patient on the watch list may result if a gap in adherence of m consecutive days was predicted. Here m is greater than or equal to zero and less than or equal to k.) (Note: the time series model applying to different behavioral patterns corresponds to the dynamic prediction.)
ranking the set of eligible users based on the predicted adherence rates and the predicted gap days for the eligible user, wherein eligible users with lower adherence rates and higher urgency measures based on the number of days within which a potential gap period is predicted to occur are given a higher priority rank… (Hanina [col 12 line 41] In addition to comparing various historical patient information, patient scores and histories may also be compared across one or more patient populations or sub-populations at step 309. Together with a collection of patient scores for any number of patients in a population or sub population, an individual's updated patient score 303 may be used to rank the patient relative to others in the population, thus giving a sense of the patient's performance relative to the rest of the population... Patient scores may also be aggregated across care providers, institutions, health care systems, etc. to give a profile of adherence of all or some patients associate with a particular institution or provider, etc. This information may also be helpful to provide a snapshot or patient and provider participation with the system.
[col 9 line 63] Alternatively or in addition, the display of the medication adherence monitoring apparatus may be configured to display one or more visualizations that show trends of the patient scores over time and to encourage medication adherence in accordance with at least the ranking of the user in accordance with one or more of the plurality of different combinations.
[col 13 line 43] As noted above, a decision about whether, when, and how to intervene is preferably made by using the patient watch list 106 in conjunction with one or more updated patient profiles 305. Since the system makes adherence predictions for each dose each patient is scheduled to take over the following k days, it is possible to target a proactive intervention to the day (or any number of days or other desired time period) before a patient is predicted to miss a dose.
[col.14 2nd ¶] Criteria other than the adherence rate may also be chosen for inclusion of a patient on the watch list. For example, placement of a patient on the watch list may result if a gap in adherence of m consecutive days was predicted. Here m is greater than or equal to zero and less than or equal to k.)
selecting a subset of users from the set of eligible users based on the priority ranking; (Hanina [abstract] generate a patient adherence score across each of the plurality of different combinations, and ranking a user in accordance with each of the plurality of different combinations. The system further includes a communication apparatus for contacting a user to encourage medication adherence in accordance with at least the ranking of the user in accordance with one or more of the plurality of different combinations.)
and wherein the subset of users is selected based on a weighted agregate of factors including the predicted adherence rate and the urgency measures based on the number of days within which the potential gap period is predicted to occur (Hanina (20) Not only is the method and apparatus presented in accordance with the present invention able to predict future behavior, but is also able to provide a classification system to identify urgency and priority related to a particular patient or group of patients. (12) It should also be noted that it is contemplated in accordance with one or more embodiments of the invention that several sets of weights may be chosen, thus creating several different patient scores based on the same category scores. In this case, each different patient score would, by design, emphasize different aspects of patient behavior.)
for each selected user from the set of selected users…: (Hanina (28) It should be noted that nothing precludes setting k=1 and x=100. In this case, the watch list consists of patients who are predicted to not take all of their next day's medication. A proactive intervention could then be arranged for each patient on this watch list, for each patient whose overall adherence level is below some threshold, or for each patient who meets some other criteria.)
Hanina and Kapaldo are analogous to the present invention because both are from the same field of endeavor of machine learning-based method on communicating with patients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Hanina’s ranking method to Kapaldo’s method of identifying non-adherent patients. The motivation would be to be “giving a sense of the patient's performance relative to the rest of the population” (Hanina [col 12 line 43]).
Kapaldo/Hanina does not teach, but Foschini further teaches:
training a plurality of machine learning models, one for each of a plurality of communication channels, using training datasets comprised of time series data representing instances of communication performed using each of the respective communication channels so that each of the plurality of machine learning models is configured to output a likelihood of a particular user performing an expected action based on receiving a communication; (Foschini [0064] For instance, the technique 700 includes time series event streams being accessed (702), and messages and/or other interventions that were provided to an individual being identified (704). Activities that are intended to be affected by the messages and/or other interventions and that occur after the messages and/or other interventions are provided to the individual can be identified (706). From these messages/interventions and activities, the computer system 100 can determine one or more coefficients that represent impulse signals correlating messages/interventions to the resulting activities (708). For example, the computer system 100 can calculate coefficients such as the Granger causality coefficient and/or Convergent Cross Mapping coefficient, which can indicate the causal effect of the messages/interventions on the activities. The resulting coefficient can be output as the receptivity score (710).) (Note: the receptivity score depends on the received communication, thus corresponding to the recited likelihood of a user performing an expected action.)
wherein training the plurality of machine learning models comprises automatically generating labeled training data (Foschini [0080] Additionally and/or alternatively, the scores described above can be determined using machine learning based approaches. For example, for a given score S, event streams can qualitatively be labeled based on, for example, whether they are perceived as being a high score (S.sub.H) or a low score (S.sub.L). Such labelling may be automatically performed by the computer system)
by performing a time-series causality analysis on historical user communication records and corresponding user event time series data for each communication channel, the causality analysis producing a channel effectiveness metric for each channel and each user, and assigning, based on said metric relative to a significance threshold, a label indicating whether that communication channel caused the user's expected action (Foschini [0064] For instance, the technique 700 includes time series event streams being accessed (702), and messages and/or other interventions that were provided to an individual being identified (704). Activities that are intended to be affected by the messages and/or other interventions and that occur after the messages and/or other interventions are provided to the individual can be identified (706). From these messages/interventions and activities, the computer system 100 can determine one or more coefficients that represent impulse signals correlating messages/interventions to the resulting activities (708). For example, the computer system 100 can calculate coefficients such as the Granger causality coefficient and/or Convergent Cross Mapping coefficient, which can indicate the causal effect of the messages/interventions on the activities. The resulting coefficient can be output as the receptivity score (710).) (Note: calculating the Granger causality coefficient corresponds to performing a time-series causality analysis; the receptivity score corresponds to the label indicating whether that communication channel caused the user's expected action)executing the plurality of trained machine learning models, wherein each of the plurality of machine learning models is dedicated to a particular communication channel, to determine the likelihood of the selected user performing the expected action based on receiving a communication for each communication channel; (Foschini [0034] Interventions can be used to help individuals become healthier and to transition between health/behavioral states.
[0064] For instance, the technique 700 includes time series event streams being accessed (702), and messages and/or other interventions that were provided to an individual being identified (704). Activities that are intended to be affected by the messages and/or other interventions and that occur after the messages and/or other interventions are provided to the individual can be identified (706). From these messages/interventions and activities, the computer system 100 can determine one or more coefficients that represent impulse signals correlating messages/interventions to the resulting activities (708). For example, the computer system 100 can calculate coefficients such as the Granger causality coefficient and/or Convergent Cross Mapping coefficient, which can indicate the causal effect of the messages/interventions on the activities. The resulting coefficient can be output as the receptivity score (710).) [Note: the resulting output coefficient corresponds to an output to a Granger causality model, which depends on a particular intervention (communication channel)]
Foschini and Kapaldo/Hanina are analogous to the present invention because both are from the same field of endeavor of machine learning-based method on communicating with patients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the Granger causality model from Foschini to Kapaldo/Hanina’s method of identifying non-adherent patients. The motivation would be to “indicate the causal effect of the messages/interventions on the activities” (Foschini [0064])
Kapaldo/Hanina/Foschini do not teach, but Kelly further teaches:
and selecting a communication channel with the highest likelihood to result in the selected user performing the expected action based on receiving the communication; (Kelly [Abst.] By providing a reminder prompt generation system that utilizes machine-learning and/or artificial intelligence to determine appropriate reminder times and modalities for providing automated-prompting notifications to users, the users' adherence to scheduled task completions can be significantly increased.
[0004] In general, embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for providing an optimal prompting model/strategy to maximize a user's medication adherence. Certain embodiments utilize machine-learning based models to train a prompting apparatus of most-effective notification strategies for users to maximize the likelihood that the user will take appropriate medication at appropriate times.)
Kelly and Kapaldo/Hanina/Foschini are analogous to the present invention because both are from the same field of endeavor of intervention methods for patients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to implement the notification selection method of Kelly into Kapaldo/Hanina/Foschini’s method of identifying non-adherent patients. The motivation would be to “There is, therefore, a need for systems and methods that consider various environmental and/or patient contexts that may be indicative of the likelihood of task adherence (e.g., medication or treatment adherence).” (Kelly [0002]).
Kapaldo, via Kapaldo/Hanina/Foschini/Kelly, further teaches:
sending the selected user a first communication using the selected communication channel with the highest likelihood to result in the selected user performing the expected action based on receiving the first communication (Kapaldo [0035] An intervention channel, for example, comprises any of, e.g., a telephone communication, a text message, an in-app communication, or an email, which may be transmitted or otherwise established, e.g., via computer network 120 from server(s). [0068] Once one or more intervention methods/types are selected (block 24), server(s) 102 may execute intervention algorithm 250.)
and wherein sending the first communication via the selected communication channel comprises, by a communication engine of the system, invoking a channel-specific application programming interface (API) corresponding to the selected communication channel to automatically construct and dispatch the first communication to the user. (Kapaldo [0070] Intervention component 232 may consider various intervention methods/types, including electronic medical adherence intervention communications as transmitted to or otherwise provided to medical patients. For example, such electronic medical adherence intervention communications ma include any of a phone call by pharmacist, a robotic based call, e.g., initiated by intervention server(s) 102, a text message transmitted from intervention server, an in-app communication transmitted from intervention server(s) 102, an email transmitted by intervention server(s) 102, and/or direct mail as initiated by intervention server(s) 102. ) (Note: in light of the Specification [0041], the API is recited as the various technological means to automatically dispatch a message. Thus, Kapaldo's email communication corresponds to an API. The robotic-based call and the direct mail initiated by the intervention server corresponds to automatically constructing and dispatching the first communication to the user)
Regarding Claim 3, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kapaldo further teaches the plurality of communication channels comprises: a communication channel for sending text messages, a communication channel for leaving voice mail, a communication channel for calling via live agent (Kapaldo [0035] An intervention channel, for example, comprises any of, e.g., a telephone communication, a text message, an in-app communication, or an email, which may be transmitted or otherwise established, e.g., via computer network 120 from server(s)).
Regarding Claim 4, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kapaldo further teaches the computer-implemented method of claim 1, wherein the machine learning based model is a classification based model (Kapaldo [0037] The machine learning programs or algorithms may also include natural language processing, semantic analysis, automatic reasoning, regression analysis, support vector machine (SVM) analysis, decision tree analysis, random forest analysis, K-Nearest neighbor analysis, naïve Bayes analysis, clustering, reinforcement learning, and/or other machine learning algorithms and/or techniques.) [Note: Many of Kapaldo’s listed algorithms and models are known classification-based models].
Regarding Claim 5, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kapaldo further teaches the computer-implemented method of claim 1, wherein the adherence rate for the eligible user represents an estimated percentage days covered for the eligible user, wherein a day is covered if the eligible user is determined to be in possession of an item (Kapaldo [0004] An accepted and standard approximate measurement of medical adherence (or “adherence”) is the “proportion of days covered” (PDC), which computes the fraction of days a patient is covered (has effective medication) to treat a condition.)
Regarding Claim 6, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kelly, via Kapaldo/Hanina/Foschini/Kelly, further teaches determining an optimal time most likely to result in the selected user performing the expected action by executing the gap days prediction model…;
and sending the selected user the first communication at the optimal time most likely to result in the selected user performing the expected action based on receiving the first communication (Kelly [Abst.] By providing a reminder prompt generation system that utilizes machine-learning and/or artificial intelligence to determine appropriate reminder times and modalities for providing automated-prompting notifications to users, the users' adherence to scheduled task completions can be significantly increased.
[0002] Various medication adherence programs exist which sense a patient's activity in his/her home environment and employ rules-based algorithms to decide when is the best time to remind them to take his/her medication.)
Hanina, via Kapaldo/Hanina/Foschini/Kelly, further teaches:
…to identify a potential gap that is likely to happen in the near future for the selected user; … wherein the optimal time is within a threshold time interval of the potential gap identified by executing the gap days prediction model
(Hanina [col.14 line 7] Criteria other than the adherence rate may also be chosen for inclusion of a patient on the watch list. For example, placement of a patient on the watch list may result if a gap in adherence of m consecutive days was predicted. Here m is greater than or equal to zero and less than or equal to k.) (Note: the predicted gap in adherence corresponds to the potential gap that is likely to happen in the future; the m consecutive days of gap in adherence places the patient into the watch list, and thus corresponds to the threshold time interval.)
Regarding Claim 7, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 6 teaches the computer-implemented method of Claim 6 (and thus the rejection of Claim 6 is incorporated. Kapaldo further teaches the computer-implemented method of claim 6, wherein the timing for sending the communication to the selected user is determined based on a predicted gap for the user, wherein a gap indicates a time interval when the user is not in possession of an item (Kapaldo [0065] intervention server(s) 102 determines the probability distribution of the intervention methods/types that maximizes an expected increase in PDC, for a specific patient or group of patients)
Regarding Claim 8, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kapaldo further teaches the computer-implemented method of claim 1, wherein the user profile data includes (1) a communication time series representing communications send to the user and (2) an event time series representing user actions performed by the user (Kapaldo [0038] For example, as shown for FIG. 3, feature data may include anything of relevance, particularly features concerning the patient (302), medical condition (304), insurance coverage (306), patient behaviors (308), time/geo based features (310), and/or medication features (312). Several examples of such feature data are illustrated for FIG. 3… [0049] Database 204 stores result set data regarding tracking data and information regarding medical adherence by patient(s) based on correspondence of the electronic medical adherence intervention communications as described herein.). [Note: See also [0051], [0043], Fig. 2 (251), and Fig. 3 column (308)]
Regarding Claim 21, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kapaldo does not teach, but Hanina further teaches:
The computer-implemented method of claim 1, wherein the gap days prediction model uses historical prescription refill patterns, patient engagement data, and adherence probabilities to predict the specific number of gap days for the eligible user (Hanina [col 8 line 5] It is a data-driven system that preferably comprises two main models that use the data collected from the adherence monitoring device to (1) summarize a patient's characteristics by computing a patient score (based on past behavior), and (2) identify patients who are likely to have an adherence rate below a certain level over some future time period by forecasting which upcoming doses, if any, a patient will miss. The system in accordance with one or more embodiments of the invention may also utilize a machine learning algorithm to profile patients with various electronic monitoring and behavior-based mechanisms (prescription refills, text reports, etc), and including one or more of the automated monitoring systems noted above. The system may also employ different methods for reporting adherence, such as automated determinations, self reporting, suspicious reporting, usability errors or other issues, location of the patient, demographics, and any other basis for categorization of the patient that may provide information as to the risk and need for urgency in an intervention.
[col.14 2nd ¶] Criteria other than the adherence rate may also be chosen for inclusion of a patient on the watch list. For example, placement of a patient on the watch list may result if a gap in adherence of m consecutive days was predicted. Here m is greater than or equal to zero and less than or equal to k.)
Regarding Claim 23, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Hanina, via Kapaldo/Hanina/Foschini/Kelly, further teaches:
The computer-implemented method of claim 1, wherein the predicted gap days are ranked based on the urgency measures, including the proximity of the predicted gap period and the user’s historical adherence trends. (Hanina [col 9 line 53] At step 104, the processing/analysis unit may further determine a “watch list” of patients 106 who may require proactive intervention because they are at increased risk of non-adherence in the near future, and may also include one or more attributes from the patient profile 105 to make such a determination… (8) With the help of a domain knowledge expert 202 (or other store of knowledge, either automated, individual or the like) one or more categories of patient behavior that may be relevant to adherence are determined at step 200. Such categories may be determined in accordance with an expert opinion, or upon analysis of historical adherence correlation data with any number of possible categories of patient behavior… [col.14 2nd ¶] Criteria other than the adherence rate may also be chosen for inclusion of a patient on the watch list. For example, placement of a patient on the watch list may result if a gap in adherence of m consecutive days was predicted. Here m is greater than or equal to zero and less than or equal to k.)
Regarding Claim 24, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kapaldo, via Kapaldo/Hanina/Foschini/Kelly, further teaches:
The computer-implemented method of claim 1, wherein the expected action is picking up a medication from a pharmacy, (Kapaldo [0069] For any given iteration or time period, at block 251, intervention server(s) 102 begins execution of intervention algorithm 250 by accessing or reading data (e.g., from database 201 and/or database 204) regarding the patient or patient group and/or medication type(s). Intervention component 232 considers a successful intervention methods/type where the patient exhibited medical adherence. This may be demonstrated by a patient refilling (or having dispensed) a given medication.
[0005] …insurance companies typically offer incentives to pharmacies, or other such medical providers, for each patient who is adherent. For example, such incentives may be provided at the end of a calendar year or otherwise.) (Note: a patient having been dispensed medication exhibits medical adherence and corresponds to picking up a medication. Thus, having pharmacies provided incentives for each adherent patient corresponds to
and wherein the step of invoking a channel-specific application programming interface (API) corresponding to the selected communication channel to automatically construct and dispatch the first communication to the user comprises the step of constructing the first communication to inform the user to pick up the medication (Kapaldo [0070] Intervention component 232 may consider various intervention methods/types, including electronic medical adherence intervention communications as transmitted to or otherwise provided to medical patients. For example, such electronic medical adherence intervention communications ma include any of a phone call by pharmacist, a robotic based call, e.g., initiated by intervention server(s) 102, a text message transmitted from intervention server, an in-app communication transmitted from intervention server(s) 102, an email transmitted by intervention server(s) 102, and/or direct mail as initiated by intervention server(s) 102.
[0069] Intervention component 232 considers a successful intervention methods/type where the patient exhibited medical adherence. This may be demonstrated by a patient refilling (or having dispensed) a given medication. ) (Note: in light of the Specification [0041], the API is recited as the various technological means to automatically dispatch a message. Thus, Kapaldo's email communication corresponds to an API. The robotic-based call and the direct mail initiated by the intervention server corresponds to automatically constructing and dispatching the first communication to the user; successful intervention is demonstrated by being dispensed the medication; thus, intervention communication corresponds to informing the user to pick up the medication)
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Kapaldo/Hanina/Foschini/Kelly further in view of Chu et al., US 2014024788 W (hereinafter Chu).
Regarding Claim 22, the Kapaldo/Hanina/Foschini/Kelly combination of Claim 1 teaches the computer-implemented method of Claim 1 (and thus the rejection of Claim 1 is incorporated. Kapaldo does not teach, but Hanina further teaches:
The computer-implemented method of claim 1, wherein the gap days prediction model dynamically updates predictions (Hanina [col 15 line 27] Whatever methods are used to create the predictive model, the model may be updated regularly to take into account changes in longer-term patient behavior, including the effect that both proactive and retrospective interventions are having on patients.) (Note: updating based on both proactive and retrospective interventions corresponds to dynamically updating the prediction model)
Kapaldo/Hanina/Foschini/Kelly does not teach, but Chu further teaches:
based on real-time user data, including missed refill alerts and communication interactions (Chu [p.31 ¶1] Entities 60 may use the Monitor option 180 to monitor real time changes in patient medication usage during intervention calls. When an entity 60 makes a missed dose phone call intervention to a patient 1 1 and the patient 1 1 takes the correct dose while on the phone with the entity 60. If the correct dose is taken by the patient 11 from the container 20, the container 20 will send the correct does amount to the server 40 and the server 40 updates the missed dose alert as a correct dose in real time so the entity 60 may easily confirm the correct dose taken while still on the phone with the patient 1 1. The history is also updated in real time.) (Note: the missed dose phone call intervention corresponds to the missed refill alert and communication interaction.)
Chu and Kapaldo/Hanina/Foschini/Kelly are analogous to the present invention because both are from the same field of endeavor of methods of improving prescription adherence of a medical patient. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Chu’s missed dose alert intervention method to Kapaldo/Hanina/Foschini’s method of identifying non-adherent patients. The motivation would be to “to record the interaction in the history and save new inputs, information and/or changes” (Chu [p.30 last ¶]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEP HAN whose telephone number is (703)756-1346. The examiner can normally be reached Mon-Fri 9am-5pm.
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, Kakali Chaki can be reached at (571) 272-3719. 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.
/J.H./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122