Prosecution Insights
Last updated: October 04, 2026
Application No. 18/562,210

SYSTEM AND METHOD FOR COMPLIANCE PREDICTION BASED ON DEVICE USAGE AND PATIENT DEMOGRAPHICS

Final Rejection §103
Filed
Nov 17, 2023
Priority
May 20, 2021 — provisional 63/191,235 +1 more
Examiner
PAULS, JOHN A
Art Unit
3683
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
ResMed
OA Round
4 (Final)
49%
Grant Probability
Moderate
5-6
OA Rounds
10m
Est. Remaining
76%
With Interview

Examiner Intelligence

Grants 49% of resolved cases
49%
Career Allowance Rate
422 granted / 860 resolved
-2.9% vs TC avg
Strong +27% interview lift
Without
With
+27.4%
Interview Lift
resolved cases with interview
Typical timeline
3y 9m
Avg Prosecution
23 currently pending
Career history
886
Total Applications
across all art units

Statute-Specific Performance

§101
29.1%
-10.9% vs TC avg
§103
34.9%
-5.1% vs TC avg
§102
10.0%
-30.0% vs TC avg
§112
21.1%
-18.9% vs TC avg
Black line = Tech Center average estimate • Based on career data from 860 resolved cases

Office Action

§103
DETAILED ACTION Status of Claims This action is in reply to the communication filed on 21 July, 2026. Claims 1, 2, 7, 20, 26, 28, 48 and 59 have been amended. Claim 60 has been added. Claims 1, 2, 5, 7, 11, 12, 14, 15, 17, 19, 20, 22, 24, 26, 28, 47, 48, 59 and 60 are currently pending and have been examined. 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 . Claim Rejections - 35 USC § 103 The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. Claims 1, 2, 5, 7, 11, 12, 14, 15, 17, 19, 24, 26, 28, 47 and 60 are rejected under 35 U.S.C. 103 as being unpatentable over Levings et al.: (US PGPUB 2017/0209657 A1) in view of Englehard et al.: (US PGPUB 2015/0100335 A1) in view of Stenzler et al.: (US PGPUB 2014/0156296 A1) and in view of Sudharsan: (US PGPUB 2015/0006462 A1). The Levings reference has a common assignee with the instant application. Based upon the earlier effectively filed date of the reference, it constitutes prior art under 35 U.S.C. 102(a)(1). CLAIMS 1, 26, 28 and 60 Levings discloses a respiratory therapy system that includes the following limitations: A method of predicting compliance with a respiratory treatment regimen for a patient, (Levings Abstract); the method comprising: collecting operational data and usage data from a respiratory pressure therapy device providing a supply of pressurized air at positive pressure through a user interface to the patient during a sleep session; (Levings 0033, 0087 – 0099, 0171 – 0185); predicting compliance with the treatment based on inputting operational data, usage data and demographic data to a machine learning compliance prediction model having a compliance prediction output, wherein the machine learning model is trained from the operational data, usage data, demographic data and compliance data of a population of patients using respiratory pressure therapy devices; (Levings 0040, 0196, 0197, 0199, 0205, 0210, 0218, 0221, 0260 – 0264). Levings discloses a respiratory therapy system and method that includes collecting operational data and usage data from a respiratory therapy device used by a patient, and patient demographics, and uses a trained machine learning model, such as a neural network, to predict future compliance with the regimen. The model is trained on historical operational, usage, demographic and compliance data from a population of therapy device users. Levings further teaches the following limitations: determining a type of usage data of operational data that negatively contributes to the predicted compliance; modifying the respiratory treatment regimen based on the determined type of usage data or operational data to increase predicted compliance with the treatment; (Levings 0039 – 0041, 0205, 0271 – 0276); and communicating with the respiratory pressure therapy device to change operation of the respiratory pressure therapy device in supplying pressurized air to the patient based on the determined type of operational data in response to the modification of the respiratory treatment regimen; (Levings 0040, 0204, 0205, 0232, 0249, 0250). Levings teaches modifying the treatment regimen to converge on an “optimal” therapy based on the device usage history or other changes to the patient’s profile. For example, the system may determine what actions to take “If leak is high”, or other conditions, and transmit control commands to the device. With respect to the following limitations: a compliance prediction output for each of a plurality of days of the treatment; displaying the predicted compliance for each of the plurality of days to show drops of the predicted compliance between days; (Englehard 0015, 0016, 0023, 0024, 0162 – 0166, 0169 – 0171, 0173, 0175, Figure 29, Figure 30). Levings disclose generating a prediction of future compliance after each treatment session, but does not expressly disclose generating and displaying a prediction for each of a plurality of days. Englehard discloses a patient adherence monitoring system that includes detecting usage of a medical device, providing the data to an external device for analysis and display on a user interface. In particular, Englehard predicts a patient’s future adherence to a treatment protocol based on a patient’s historical adherence. (The terms adherence and compliance have the same meaning in this context.) The level of adherence for past, current or future time periods, such as a day in a month, are displayed in a user interface on a client device including drops or improvements from day-to-day. Therefore, it would have been obvious to one of ordinary skill in the art, at the time the invention was filed, to have modified the respiratory therapy system of Levings to have included predicting and displaying treatment compliance for a plurality of days, in accordance with the teachings of Englehard, in order to manage patient compliance trends. With respect to the following limitations: display the predicted compliance as a plot on a graph; (Stenzler 0013, 0021 – 0032) The combination of Levings/Englehard disclose generating and displaying a prediction of future compliance after each treatment session for each of a plurality of days, but does not disclose a plot on a graph. Stenzler discloses a medication adherence monitoring and scoring system that includes tracking and scoring a user’s daily adherence to taking their medication. The adherence score for a plurality of time periods, such as a day in a month, are displayed in a user interface on a client device. The graph allows a user to identify drops or improvements in compliance from day-to-day. Therefore, it would have been obvious to one of ordinary skill in the art, at the time the invention was filed, to have modified the respiratory therapy system of Levings/Englehard to have included displaying treatment compliance for a plurality of days as a plot on a graph, in accordance with the teachings of Stenzler, in order to provide intuitive visual displays of patient compliance trends. With respect to the following limitations: determining whether a drop of the predicted compliance between days is greater than a threshold representing a sharp drop; communicating to a user device associated with the patient to engage the patient to comply with the treatment when the drop of the predicted compliance is greater than the threshold; (Sudharsan 0007, 0027, 0043, 0045, 0051 – 0054, 0060 - 0064). The combination of Levings/Englehard/Stenzler discloses generating and displaying a graph of a predicted compliance values for each of a plurality of days, and communicating to a user device associated with the patient to engage the patient to comply with the treatment, but does not disclose determining a drop between days greater than a threshold, and engaging the patient based on the drop. Sudharsan discloses a system and method for managing medication adherence that includes calculating, on a daily basis, a value indicating a user’s medical compliance or adherence to a prescribed regimen, and comparing the value to a threshold. The compliance value provides an indication regarding a significant trend in a rise or drop in medical compliance, and provides a notification. For example, the threshold may be set for a level where clinical intervention may be necessary. Medical adherence is calculated for successive days, and the variation in adherence over the successive days is determined. A rise or drop over a threshold amount on successive days will trigger a notification for intervention. Therefore, it would have been obvious to one of ordinary skill in the art, at the time the invention was filed, to have modified the respiratory therapy system of Levings/Englehard/Stenzler to have included determining if a drop in adherence between days exceeds a threshold, and engaging the user, in accordance with the teachings of Sudharsan, in order to intervene for a patient who is not maintaining a stable regimen. With respect to CLAIM 26, Levings teaches A non-transitory computer program product comprising instructions which, when executed by a computer, cause the computer to carry out: the method of Claim 1 (Levings 0121, 0135). With respect to CLAIM 28, Levings teaches A system comprising: a respiratory pressure therapy device including a transmitter and an air control device a patient database a network; and a compliance analysis engine (Levings 0040, 0196, 0197, 0199, 0205, 0210, 0218, 0221, 0260 – 0264). Claim 28 recites system components for executing the method of Claim 1 including a RPT device including a transmitter and flow control, patient database, network and compliance engine. Levings discloses a respiratory therapy system and method that includes the recited components for collecting device operational data and various other data including patient demographics, and uses a trained model, such as a neural network, to predict compliance. The model is trained on historical data from a population of therapy device users. CLAIMS 2, 5, 7, 11, 12, 14, 15, 17, 19 and 47 The combination of Levings/Englehard/Stenzler/Sudharsan discloses the limitations above relative to Claims 1 and 28. Additionally, Levings discloses the following limitations: sending the compliance prediction to a user device operated by a health care provider associated with the patient or sending the compliance prediction to the user device operated by the patient; (Levings 0200 – 0203); classifying the patient based on a plurality of classifications of the population of patients wherein the machine learning compliance prediction model includes an output based on the classification of the patient; (Levings 0218); wherein the treatment regimen has a predetermined period of days; (Levings 0171, 0186 – 0193, 0196); collecting physiological data from a health monitor, wherein the collected physiological data is input to the machine learning compliance prediction model to determine the prediction; wherein the health monitor includes at least one sensor, the at least one sensor selected from one of the group of an audio sensor, a heart rate sensor, a respiratory sensor, a ECG sensor, a photoplethysmography (PPG) sensor, an infrared sensor, an activity sensor, a radio frequency sensor, a SONAR sensor, an optical sensor, a doppler radar motion sensor, a thermometer, an impedance sensor, a piezoelectric sensor, a photoelectric sensor, or a strain gauge sensor; (Levings 0201); wherein the machine learning compliance prediction model analyzes environmental data related to the patient in determining the prediction; (Levings 0210, 0211); wherein the machine learning compliance prediction model analyzes demographic data related to the patient in determining the prediction; (Levings 0210, 0211); further comprising deriving at least one of duration of usage of the respiratory therapy device, leaks of the interface, AHI, or mask type from the collected operational data; (Levings 0186 – 0191); collecting patient input data from a survey, and wherein the machine learning compliance prediction model analyzes the patient input data in determining the prediction; (Levings 0200, 0212); a display coupled to the compliance analysis engine, wherein the display displays the compliance prediction of the patient; (Levings 0144). Levings expressly discloses the features recited in the cited paragraphs. Claim 24 is rejected under 35 U.S.C. 103 as being unpatentable over Levings et al.: (US PGPUB 2017/0209657 A1) in view of Englehard et al.: (US PGPUB 2015/0100335 A1) in view of Stenzler et al.: (US PGPUB 2014/0156296 A1) and in view of Sudharsan: (US PGPUB 2015/0006462 A1) in view of Levine et al.: (US PGPUB 2003/0011646 A1). CLAIM 24 The combination of Levings/Englehard/Stenzler/Sudharsan discloses the limitations above relative to Claim 19. With respect to the following limitations: displaying information relating to a last contact attempt with the patient; (Levine 0153). Levings discloses transmitting electronic messages to the patient, but does not disclose displaying the last contact attempt. Levine discloses a clinical management system that includes listing patient messages sent by the provider to the patient, including which messages have been read or not read. Therefore, it would have been obvious to one of ordinary skill in the art, at the time the invention was filed, to have modified the respiratory therapy system of Levings to have included a list of messages by date, in accordance with the teachings of Levine, in order to manage patient compliance. Claim 59 is rejected under 35 U.S.C. 103 as being unpatentable over Levings et al.: (US PGPUB 2017/0209657 A1) in view of Englehard et al.: (US PGPUB 2015/0100335 A1) in view of Stenzler et al.: (US PGPUB 2014/0156296 A1) and in view of Sudharsan: (US PGPUB 2015/0006462 A1) in view of Applebaum et al.: (US PGPUB 2022/0051773 A1). CLAIM 59 The combination of Levings/Englehard/Stenzler/Sudharsan discloses the limitations above relative to Claim 1. With respect to the following limitations: determining a shap value for each type of usage data and each type of operational data; based on the shap values, determining the contribution of each type of usage data and operational data on the predicted compliance with the treatment; wherein the determining a type of usage data or operational data that negatively contributes to the predicted compliance is determined from the shap values; (Applebaum 0006 – 0009, 0014, 0021, 0022, 0025, 0041, 0047, 0048, 0050). Levings discloses a predictive compliance model that uses weighted feature values, or parameters, as inputs; and that has been trained “according to conventional predictor training methods”. (@ 0260 – 0264) The weighting of the parameters may be increased or decreased, based on their importance (i.e. the contribution on the predicted compliance), according to a predefined schedule. Levings does not disclose the use of shap values to determine the contribution each data element makes to the compliance prediction. Initially, Examiner asserts that shap values are old and well known. For example, shap values may be used as a feature selection technique to reduce the dimensionality of the input data in order to make the prediction using fewer processing resources “according to conventional predictor training methods”. Nonetheless, whether shap values may be an Officially Noticed fact or not, Examiner relies on Appelbaum for these features. Applebaum discloses a system and method for managing a patient’s therapy regimen including a machine learning trained model or classifier for predicting future compliance, and adjusting the therapy regimen to improve compliance. In particular, Appelbaum discloses the use of Shapely Additive Explanation values – i.e. shap values – to determine the importance of each data element, and which data element most adversely affects the prediction. Therefore, it would have been obvious to one of ordinary skill in the art, at the time the invention was filed, to have modified the respiratory therapy system of Levings to have included determining shap values of input data, in accordance with the teachings of Applebaum, in order select the data elements having the greatest predictive power. Claims 20, 22 and 48 are rejected under 35 U.S.C. 103 as being unpatentable over Levings et al.: (US PGPUB 2017/0209657 A1) in view of Englehard et al.: (US PGPUB 2015/0100335 A1) in view of Stenzler et al.: (US PGPUB 2014/0156296 A1) and in view of Sudharsan: (US PGPUB 2015/0006462 A1) in view of Official Notice. CLAIMS 20, 22 and 48 The combination of Levings/Englehard/Stenzler/Sudharsan discloses the limitations above relative to Claims 1 and 47. With respect to the following limitations: wherein the compliance prediction is displayed in a calendar showing a period of the respiratory treatment regimen; wherein the calendar shows past days of usage of the respiratory therapy device in compliance with a usage threshold; displaying an icon indication identifying a day of a compliance prediction of the patient completing the treatment regimen in a day of a calendar showing other days of a period for completing the treatment regimen; wherein the days of the period for completing the treatment regimen are distinguishable graphically; (Englehard Figure 30, 0171 - 0176). Levings does not disclose calendar displays. Englehard discloses displaying a calendar on the user interface of a client device for each day of a user selected treatment period, for example, one month as disclosed (i.e. a period/projected compliance period for completing the treatment regimen). The calendar shows past, current and future days, (i.e. a calendar showing other days of a period for completing the treatment), and various levels of smiley/frowny face (i.e. an indication of compliance prediction) indicating compliance for each past day, or an indication of a compliance prediction for each future day. The calendar shows past usage in compliance with a treatment protocol that determines the amount and timing of treatments (i.e. a usage threshold). Therefore, it would have been obvious to one of ordinary skill in the art, at the time the invention was filed, to have modified the respiratory therapy system of Levings to have included a calendar view of compliance and compliance predictions, in accordance with the teachings of Englehard, in order to manage patient compliance over a period of time. With respect to the following limitations: accepting a selection of missing one or more days of using the respiratory pressure therapy device; and displaying the icon indication identifying a new day of predicted completion of the treatment regimen and showing a new set of days of a modified period for completing treatment regimen, in response to accepting the selection indication of missing one or more days. The claims require identifying a new day for completing the treatment regimen and a new set of days of a modified period for completing the treatment regimen, in response to selecting a day where use of the device was missed. The combination of Levings/Englehard/Stenzler/Sudharsan discloses displaying a treatment period and end day on a calendar, but does not disclose modifying a regimen treatment period, and day of completion on the calendar, based on a missed day. Nonetheless, Examiner takes Official Notice that modifying a period of days and an end day for completing a treatment, based on having missing days of treatment, is old and well known. For example, project management techniques that graphically chart the start date, end date and period of time for performing a particular project task are old and well-known – i.e. GANTT Charts. These techniques track task progress on a daily basis and automatically adjust the time period and end data for a task when daily milestones are not met. It would have been obvious to one of ordinary skill in the art, at the time the invention was filed, to have modified the respiratory therapy system of Levings/Englehard/Stenzler/Sudharsan to have included GANTT Chart techniques including modifying a regimen’s completion date and period in a calendar view based on having days of missed activity, in accordance with the Official Notice taken, in order to manage patient compliance over a period of time. Response to Arguments Applicant's arguments filed 21 July, 2026 with respect to the U.S.C. §103 Rejections have been fully considered but they are not persuasive. The U.S.C. §103 Rejection Applicant asserts that the prior art of record does not disclose a graphical plot over a treatment period to show drops in predictions, or communicating with the patient to engage the patient. Examiner agrees. However, on further search and consideration, a new grounds of rejection in view of Stenzler/Sudharsan is presented herein. Applicant asserts that the art of record does not teach modifying an end day and treatment period on a calendar based on missing days. Examiner agrees. Nonetheless, these project management techniques are notoriously old and well known such as GANTT Charts. CONCLUSION The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US PGPUB 2007/0023039 A1 to Ishizaki et al. discloses a system and method for monitoring respiratory therapy compliance and graphing daily compliance measures. US PGPUB 2011/0112857 A1 to Yurko et al. discloses a system and method for monitoring medical device usage compliance and graphing daily compliance measures together with a warning threshold. US PGPUB 2016/0026773 A1 to Chu et al. discloses a system and method for monitoring medication compliance and graphing daily compliance measures. 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 of a general nature or relating to the status of this application or concerning this communication or earlier communications from the Examiner should be directed to John A. Pauls whose telephone number is (571) 270-5557. The Examiner can normally be reached on Mon. - Fri. 8:00 - 5:00 Eastern. If attempts to reach the examiner by telephone are unsuccessful, the Examiner’s supervisor, Robert Morgan can be reached at (571) 272-6773. Official replies to this Office action may now be submitted electronically by registered users of the EFS-Web system. Information on EFS-Web tools is available on the Internet at: http://www.uspto.gov/patents/process/file/efs/guidance/index.jsp. An EFS-Web Quick-Start Guide is available at: http://www.uspto.gov/ebc/portal/efs/quick-start.pdf. Alternatively, official replies to this Office action may still be submitted by any one of fax, mail, or hand delivery. Faxed replies should be directed to the central fax at (571) 273-8300. Mailed replies should be addressed to “Commissioner for Patents, PO Box 1450, Alexandria, VA 22313-1450.” Hand delivered replies should be delivered to the “Customer Service Window, Randolph Building, 401 Dulany Street, Alexandria, VA 22314.” /JOHN A PAULS/Primary Examiner, Art Unit 3683 Date: 15 September, 2026
Read full office action

Prosecution Timeline

Show 1 earlier event
Apr 22, 2025
Non-Final Rejection mailed — §103
Jul 22, 2025
Response Filed
Oct 22, 2025
Final Rejection mailed — §103
Jan 22, 2026
Request for Continued Examination
Feb 13, 2026
Response after Non-Final Action
Mar 11, 2026
Non-Final Rejection mailed — §103
Jul 21, 2026
Response Filed
Sep 17, 2026
Final Rejection mailed — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12738358
ARTIFICIAL INTELLIGENCE-DRIVEN PREDICTIVE TOOL FOR DIGITAL PLATFORMS
2y 8m to grant Granted Sep 15, 2026
Patent 12725710
CONVERSATIONAL SERVICES FOR ARTIFICIAL INTELLIGENCE HEALTH SUPPORT
1y 8m to grant Granted Sep 01, 2026
Patent 12718947
SYSTEMS, METHODS, AND DEVICES FOR DETECTING VIRAL RESPIRATORY ILLNESS IN PRESYMPTOMATIC AND ASYMPTOMATIC INFECTED PERSONS
2y 8m to grant Granted Aug 25, 2026
Patent 12718044
SYSTEMS AND METHODS FOR STORAGE AND TRANSFER OF SMART PACKAGING METADATA
2y 10m to grant Granted Aug 25, 2026
Patent 12712063
SYSTEMS AND METHODS FOR TRIAGING PATIENTS
2y 10m to grant Granted Aug 18, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

5-6
Expected OA Rounds
49%
Grant Probability
76%
With Interview (+27.4%)
3y 9m (~10m remaining)
Median Time to Grant
High
PTA Risk
Based on 860 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month