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 .
Status of Claims
This action is in reply to the application filed on 07/01/25.
Claims 1-20 are currently pending and have been examined.
Continuity/Priority
Status of this application as a Continuation of US Application 18/653,395, filed 05/02/24, is acknowledged. Applicant’s claim to the benefit of and priority to US Provisional Applications 63/550,531 (filed 02/06/24) and 63/467,999 (filed 05/21/23) is acknowledged. Accordingly, a priority date of 05/21/23 has been given to this application.
IDS
The information disclosure statement (IDS) submitted on 10/28/25 have been considered by the examiner. The submission is in compliance with the provisions of 37 CFR 1.97.
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 a judicial exception (an abstract idea) without significantly more.
Step 1
Claims 1-10 are drawn to a method, and Claims 11-20 are drawn to a system, both of which are within the four statutory categories. Claims 1-20 are further directed to an abstract idea on the grounds set out in detail below.
Step 2A Prong 1
Claims 1 and 11 recite implementing the steps of:
analyzing real-time sensor data to generate treatment fidelity data, wherein the treatment fidelity data includes a plurality of indicators of whether the care provider is following a treatment plan for the behavioral treatment session;
detecting, based on the treatment fidelity data, that the care provider has not correctly followed a procedure specified in the treatment plan;
generating a real-time notification prompting the care provider to correctly follow the procedure;
providing and displaying the real-time notification to a care provider during the behavioral treatment session; and
detecting, based on additional real-time sensor data, that the care provider has correctly followed the procedure.
These steps amount to managing personal behavior or relationships or interactions
between people and therefore recite certain methods of organizing human activity. Analyzing sensor data to generate treatment fidelity data to determine a plurality of indicators for whether a care provider is following a treatment plan for a behavioral treatment session; using the treatment fidelity data to determine that the care provider has not correctly followed a specified procedure; generating and providing a notification to display to the care provider to prompt the care provider to correctly follow the procedure; and detecting, based on the additional sensor data, that the care provider has correctly followed the procedure, are personal behaviors and/or interactions between a supervising healthcare provider observing and providing feedback to a second healthcare provider who is delivering a behavioral treatment session to a patient.
Claims 1, 11 are therefore directed to an abstract idea.
Step 2A Prong 2
This judicial exception is not integrated into a practical application because the additional
elements within the claims only amount to:
A. Instructions to Implement the Judicial Exception. MPEP 2106.05(f)
The independent claims additionally recite:
a machine learning model as implementing the step of analyzing the real-time sensor data to generate treatment fidelity data, wherein the treatment fidelity data includes a plurality of indicators of whether the care provider is following a treatment plan for the behavioral treatment session
care provider device as the entity to which a notification is transmitted to prompt the care provider to correctly follow the procedure
a care provider application as a means of outputting the notification to prompt the care provider to correctly follow the procedure
a communication interface; one or more processors; and memory storing instructions that, when executed by the one or more processors to implement the steps of the abstract idea (Claim 11)
The broad recitation of general purpose computing elements at a high level of generality only amounts to mere instructions to implement the abstract idea using computing components as tools. Regarding the machine learning model, the specification does not appear to disclose particulars of this element. Para. [0009] discloses that a first machine learning model may be a multimodal model or language model; Para. [0141] teaches on employing various types of machine learning models such as decision trees or random forests; para. [0142] teaches on another embodiment in which the system may use deep learning models such as feedforward neural networks or LSTM networks; para. [0143] teaches on the system additionally or alternatively using generative models such as VAEs or GANs. While the specification mentions a plurality of different machine learning models, these are all understood to be known forms of machine learning models (e.g., random forests or GANs) being used in their ordinary capacities.
Regarding the care provider device, this is understood to include any of “mobile devices (e.g., smartphones, laptops, tablets), wearable devices (e.g., smartwatches, VR/AR/XR headsets, biometric sensors), other computing devices (e.g., desktop computers, servers), and/or any other devices that may run and interact with corresponding applications” per [0030]). No particulars of the care provider device appear to be disclosed; therefore this element is given its broadest reasonable interpretation as a general purpose computing device such as a smartphone functioning in its ordinary capacity.
Regarding the care provider application, this is understood to amount to software for allowing the respective users of the devices to interact with the system. Para. [0030] discloses “In embodiments, the applications 121, 131, 141 may be one of various web browsers, which may be used interchangeably. Additionally or alternatively, the applications may include various applications that may be native to various operating systems, such as a WINDOWS client application, a MacOS client application, an iOS mobile application, an Android mobile application, etc. The applications 121, 131, 141 may take advantage of various inputs, such as mouse and/or keyboard, touchscreen inputs, voice inputs (e.g., using speech to text software), and/or any other interaction method for inputting data, instructions, selections, and the like”. This is understood to amount to mere instructions to apply the abstract idea using a computer application to facilitate user interactions, data input, selections, and instructions.
Regarding the communication interface; one or more processors; and memory storing instructions that, when executed by the one or more processor, these are understood to be general purpose computing components functioning in their ordinary capacity to implement the steps of the abstract idea. See at least paras. [0025], computing environment/architecture; [0186]-[0187], processor(s); and [0187], [0195], memory storing instructions.
B. Insignificant Extra-Solution Activity. MPEP 2106.05(g)
Claim 1 (and Claim 11) also recite the steps of:
receiving, (via the communication interface) from one or more sensors, real-time sensor data during a behavioral treatment session involving a care provider and a patient, wherein the one or more sensors include at least one of a video sensor, an audio sensor, or an environmental sensor;
receiving (via the communication interface) additional real-time sensor data from the one or more sensors after transmitting the real-time notification
The above limitations only amount to insignificant extra-solution activity in the form of mere data gathering, e.g., obtaining the real-time sensor data from a behavioral treatment session such that the abstract idea (e.g., analyzing data to generate treatment fidelity data, determining whether or not a care provider has correctly followed a procedure based on the received data) can be performed.
These elements are therefore not sufficient to integrate the abstract idea into a practical application. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually.
Claims 1, 11 as a whole, are therefore directed to an abstract idea.
Step 2B
The present claims do not include additional elements that are sufficient to amount to
more than the abstract idea because the additional elements or combination of elements amount to no more than a recitation of:
A. Instructions to Implement the Judicial Exception. MPEP 2106.05(f)
As explained above, claims 1, 11 only recite the aforementioned computing elements as tools for performing the steps of the abstract idea, and mere instructions to perform the abstract idea using a computer is not sufficient to amount to significantly more than the abstract idea. MPEP 2106.05(f).
B. Insignificant Extra-Solution Activity. MPEP 2106.05(g)
Likewise, as explained above, the steps pertaining to receiving, (via a communication interface) from one or more sensors, real-time sensor data during a behavioral treatment session involving a care provider and a patient, wherein the one or more sensors include at least one of a video sensor, an audio sensor, or an environmental sensor; and, receiving (via the communication interface) additional real-time sensor data from the one or more sensors after transmitting the real-time notification, only amount to mere data gathering and accordingly, constitute insignificant extra-solution activity.
C. Well-Understood, Routine and Conventional Activities. MPEP 2106.05(d)
In addition to amounting to insignificant extra-solution activity the elements in Section B
above constitute well-understood, routine and conventional activity. The steps pertaining to receiving, (via the communication interface) from one or more sensors, real-time sensor data during a behavioral treatment session involving a care provider and a patient, wherein the one or more sensors include at least one of a video sensor, an audio sensor, or an environmental sensor; and, receiving (via the communication interface) additional real-time sensor data from the one or more sensors after transmitting the real-time notification, only amount to receiving or transmitting data over a network, which has been previously held to be well understood, routine and conventional when claimed at a high level of generality or as insignificant extra-solution activity. See MPEP 2106.05(d)(II).
Thus, taken alone, the additional elements do not amount to significantly more than the
above-identified judicial exception. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. Their
collective functions merely provide conventional computer implementation.
Depending Claims
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims.
Claims 2 and 12 recite limitations pertaining to further comprising: receiving patient data for the patient which only amounts to insignificant extra-solution activity in the form of mere data gathering and which amounts to transmitting data over a network, which has been previously held to be well understood, routine and conventional when claimed at a high level of generality or as insignificant extra-solution activity. See MPEP 2106.05(d)(II). Claim 2 and 12 also recite limitations pertaining to combining the real-time sensor data with the patient data to generate an integrated data set, which is also certain methods of organizing human activity including managing personal behaviors as a healthcare provider could combine two datasets to create an integrated data set. Claim 2 and 12 also recite wherein analyzing the real-time sensor data using the machine learning model comprises providing the integrated data set as input to the machine learning model, which only amounts to mere instructions to apply the abstract idea on a computer. These limitations are not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 3 and 13 recite limitations pertaining to wherein combining the real-time sensor data with the patient data to generate an integrated data set comprises: ingesting each of the real-time sensor data and the patient data with a corresponding data pipeline from a plurality of data pipelines; generating, by the corresponding data pipeline, metadata based on the ingested data; and integrating the ingested data by performing at least one of: alignment, cross-referencing, or other integration operations based on the metadata. This only further narrows the scope of the respective parent claim, e.g., describing how the sensor data and patient data are combined; this also amounts to mere instructions to apply the abstract idea using a computer (MPEP 2106.05(f)), e.g., using a computer to ingest two types of data, generating metadata, and integrating the ingested data. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 4 and 14 recite limitations pertaining to wherein the treatment fidelity data comprises at least one treatment fidelity score, which further narrows the scope of the respective parent claim. Claims 4 and 14 also recite limitations pertaining to wherein detecting that the care provider has not correctly followed the procedure further comprises detecting that at least one treatment fidelity score is declining over time or has fallen below a predetermined threshold, wherein the real-time notification indicates the at least one treatment fidelity score, which further narrows the scope of the respective parent claim, e.g., describing how the detection of a care provider not correctly following a treatment protocol is made. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 5 and 15 recite limitations pertaining to further comprising adjusting a monitoring frequency for receiving the real-time sensor data based on detecting a change in a patient condition, which is also certain methods of organizing human activities including managing personal behavior, as a healthcare provider could adjust a monitoring frequency of a patient based on detecting a change in the patient’s condition. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 6 and 16 recite limitations pertaining to wherein detecting the change in the patient condition comprises: receiving physiological data from a sensor associated with the patient; and detecting, based on the physiological data, at least one of: an increased heart rate or a change in galvanic skin response. This only further limits the respective parent claim, e.g., describing how the change in patient condition is detected. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 7 and 17 recite limitations pertaining to wherein the machine learning model is a multimodal model configured to process at least two of: image data from the video sensor, audio data from the audio sensor, or environmental data from the environmental sensor. This only further narrows the scope of the abstract idea as set out above and also amounts to mere instructions to apply the abstract idea using a computer (MPEP 2106.05(f)), e.g., using a computer to process two types of data. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 8 and 18 recites limitations pertaining to wherein detecting that the care provider has not correctly followed the procedure comprises: detecting, based on the real-time sensor data, that the patient has engaged in a targeted behavior specified in the treatment plan; and determining, based on analyzing sensor data captured during a predetermined time period after detecting the targeted behavior, that the care provider did not perform a required response specified in the treatment plan for the targeted behavior, which are also certain methods of organizing human activities including managing personal behavior as a healthcare provider could detect that a patient has engaged in a target behavior and determine that the other care provider did not perform a required response specified in the treatment plan. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 9 and 19 recite limitations pertaining to wherein the required response comprises asking a prescribed question, and wherein determining that the care provider did not perform the required response comprises: generating a text transcript from audio data received from the audio sensor during the predetermined time period; and analyzing the text transcript using a language model to determine that the prescribed question was not asked, which are also certain methods of organizing human activities including managing personal behavior as a healthcare provider could identify a treatment response pattern and provide (“transmit”) an indicator of the treatment response pattern to the other (treating) care provider. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Claims 10 and 20 recite limitations pertaining to further comprising: identifying, based on the real-time sensor data, a treatment response pattern indicating a correlation between a specific care provider behavior and a patient outcome; and transmitting an indicator of the treatment response pattern to the care provider device during the behavioral treatment session, which are also certain methods of organizing human activities including managing personal behavior as a healthcare provider could identify a treatment response pattern and provide (“transmit”) an indicator of the treatment response pattern to the other (treating) care provider. This is not sufficient to integrate the judicial exception into a practical application or amount to significantly more than the abstract idea.
Dependent claims 2-10, 12-20 have been given the full two-part analysis including analyzing the additional limitations both individually and in combination. The dependent claims, when analyzed individually, and in combination, are also held to be patent ineligible under 35 U.S.C. 101 as they include all of the limitations of claims 1 or 11 respectively. The additional recited limitations of the dependent claims fail to establish that the claims do not recite an abstract idea because the additional recited limitations of the dependent claims merely further narrow the abstract idea. Beyond the limitations which recite the abstract idea, the claims recite additional elements consistent with those identified above with respect to the independent claims which encompass adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) or amount to insignificant extra-solution activity (e.g., receiving data; which amounts to transmitting data over a network, which has been previously held to be well understood, routine and conventional when claimed at a high level of generality or as insignificant extra-solution activity. See MPEP 2106.05(d)(II)). Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claims 2-10, 12-20 recite additional subject matter which amounts to additional elements consistent with those identified in the analysis of the independent claims above. As discussed above with respect to the independent claims and integration of the abstract idea into a practical application, recitation of these additional elements only amounts to invoking computers as a tool to perform the abstract idea. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation.
Dependent claims 2-10, 12-20, when analyzed as a whole, are held to be patent ineligible under 35 U.S.C. 101 because the additional recited limitation(s) fail(s) to establish that the claim(s) is/are not directed to an abstract idea without significantly more. These claims fail to remedy the deficiencies of their parent claims above, and are therefore rejected for at least the same rationale as applied to their parent claims above, and incorporated herein.
For the reasons stated, Claims 1-20 fail the Subject Matter Eligibility Test and are consequently rejected under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claim(s) 1, 4, 7, 11, 14, 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Toleti et. al. (US Publication 20200381131A1) in view of Martin et. al. (US Publication 20220384038A1) and further in view of Robaina et. al. (US Publication 20230075466A1).
Regarding Claim 1, Toleti discloses:
receiving, from one or more sensors, real-time sensor data during a treatment session involving a care provider and a patient ([0028] teaches on providing continuous monitoring through care of a patient; the intent is to analyze the behavior of the patient and caregiver (e.g., a treatment session involving a care provider and a patient); per [0025] caregivers are understood to include doctors and nurses; [0046] teaches on sensors 110 and microphones 210 continuously monitoring an environment to collect a plurality of event streams 305; Examiner interprets ‘continuously monitoring’ to read on “real-time” data, additionally per [0052] the event streams are understood to in real-time), wherein the one or more sensors include at least one of a video sensor, an audio sensor, or an environmental sensor ([0046] teaches on sensors 110 and microphones 210 continuously monitoring an environment to collect a plurality of event streams 305; [0030] teaches on sensors including optical sensors such as video cameras and audio sensors (microphones));
analyzing the real-time sensor data using a machine learning model to generate treatment fidelity data, wherein the treatment fidelity data includes a plurality of indicators of whether the care provider is following a treatment plan for the treatment session (Para. [0012] broadly teaching on determining compliance with a healthcare protocol (e.g., treatment plan) includes the steps of receiving, by an AI and machine learning subsystem, a plurality of output signals corresponding to an event; the output signals are generated by a plurality of sensors and microphones; a rating is determined via a rating system in operable communication with the AI and machine learning subsystem; the rating is compared to a plurality of defined ratings for a reference pattern; [0042] teaches on one or more sensors including a microphone for monitoring audio between patient and caregiver; [0043] teaches on analysis subsystem receives sensor 110 and microphone 210 output signals; [0046] teaches on sensors 110 and microphone 210 continuously monitoring (e.g., real time data) the environment to generate event streams 305 which are transmitted to analysis subsystem which includes an AI and machine learning subsystem; the analysis subsystem consults an AI-based protocol and compares the signal outputs from the sensors to the AI-based protocol values and performs machine learning from models stored in the database to provide a rating (interpreted as synonymous with “treatment fidelity data”; [0047] teaches on the AI and ML system ranking and rating behaviors and interactions to provide feedback – interpreted as a plurality of indicators for the provider following a treatment plan);
detecting, based on the treatment fidelity data, that the care provider has not correctly followed a procedure specified in the treatment plan ([0024] teaches on using the automated sensor and reasoning system for monitoring protocol adherence (treatment plan) and detecting a “broach of the protocol” (interpreted as a provider not following a specified procedure in the treatment plan); [0031] teaches on an analysis module for anomaly detection; the analysis module utilizes a comparator to compare received sensor data to an acceptable range of values from the pre-defined protocol/acceptable data; a data value outside of the acceptable range indicates anomaly - ;
generating a notification prompting the care provider to correctly follow the procedure [in future interactions] ([0024] teaches on detecting a broach of protocol to “alert a caregiver of the noncompliant breach appropriately”; [0027] teaches on when it is determined that a predefined protocol is not adhered to, the caregiver may be notified by the alert system to modify their behavior in future interactions to ensure a standard of care is realized);
transmitting the notification to a care provider device for display ([0044] teaches on, upon detection of an anomaly by the analysis subsystem, the alert system can generate various types of alerts including SMS messaging, smart watch or similar smart devices; alerts may be visual alerts as known in the arts);
.
Toleti does not explicitly disclose the following, but Martin, which is directed to improvements in interaction analysis between a therapist and a patient, teaches:
behavioral treatment session ([0154] teaches on using CBT (cognitive behavioral therapy) in treatment sessions provided to a patient based on the patient’s presenting condition)
generating a real-time notification prompting the care provider to correctly follow the procedure ([0150] teaches on providing automated feedback to a therapist on the quality of a therapy session such that one or more actions may be taken by the therapist, e.g., alterations to the current therapy session; the feedback may be provided whilst the therapy session is ongoing in real-time/live feedback – if the automated feedback is provided to the therapist, it is interpreted that the notification has necessarily been generated);
transmitting the real-time notification to a care provider device for display via a care provider application during the behavioral treatment session ([0150] teaches on providing automated feedback to a therapist on the quality of a therapy session such that one or more actions may be taken by the therapist, e.g., alterations to the current therapy session; the feedback may be provided whilst the therapy session is ongoing in real-time/live feedback; [0152] teaches on providing the alert in the form of a visual alert, such as a pop-up, text box or other form of message generated by the therapy system; per [0074] the therapy system is interpreted as being accessed via software application such as a web browser software application).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to modify Toleti with these teachings of Martin, so that the notification of Toleti to correctly follow the procedure is a real-time notification which is transmitted to the provider’s device for display during the treatment session (rather than after the session as taught by Toleti) with the motivation of providing real time feedback during the session so that the caregiver could elect to change their current behavior in order to increase the likelihood of the therapy session having an improved outcome (Martin [0150]). It would be obvious to use the system of Toleti in the context of a behavioral treatment session as taught by Martin with the motivation of providing a quality-controlled approach to behavioral health care because ‘therapist drift’ is considered to be one of the biggest factors contributing to poor delivery of treatments, and automated monitoring of therapists’ performance could prevent drift and associated lower improvement rates (Martin [0047])
Toleti/Martin do not teach the following, but Robaina, which is directed to a device for presenting virtual content for healthcare setting applications, teaches:
receiving additional real-time sensor data from the one or more sensors after transmitting the real-time notification ([0311] teaches on the device determining contextual information based on acquired sensor data such as computer vision recognition of people and objects; [0362] teaches on the system “continuously” monitoring objects entering into/exiting the sterile field of the surgeon – interpreted as receiving additional real-time sensor data as [0042] teaches on the device including sensors such as cameras that monitor or image objects in field of view; [0363] provides an example for a set of surgical instruments for an appendectomy; the system identifies a bone curette instrument has been place in the sterile field region which is not in the set of required tools for appendectomy and is interpreted as the care provider not following a treatment procedure; upon detection of the bone curette, an alert is provided to the surgeon that an incorrect instrument (curette) has entered the sterile region and the device shows the phrase “bone curette” in a different color on the surgeon’s display; once the bone curette has been moved to outside of the sterile region, the wearable device removes the phrase “bone curette” from the virtual content display – if the system removes the phrase “bone curette” from the display upon detecting it is no longer present, it is understood that the system has been receiving additional sensor data after transmission of the “bone curette” notification, e.g., as disclosed by [0362] and “continuously” monitoring the environment/sterile field); and
detecting, based on the additional real-time sensor data, that the care provider has correctly followed the procedure ([0363], as cited above, teaches on detecting a wrong instrument (bone curette) in sterile field and provides alert via display to surgeon; once the bone curette has been moved to outside of the sterile region, the wearable device removes the phrase “bone curette” from the virtual content display – if the system removes the phrase “bone curette” from the display upon detecting it is no longer present, it is understood that the system has detected, using the additional sensor data after transmission of the “bone curette” notification, that the procedure has been followed (wrong instrument no longer present).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to further modify Toleti/Martin with these teachings of Robaina, so that after the notification to prompt the care provider to correctly follow the procedure is generated and transmitted to the care provider (as taught by Toleti/Martin), the system would continue receive real-time sensor data and detect that the procedure has been correctly followed, with the motivation of determining that the care provider has provided the correct care to the patient (Robaina [0131]).
Regarding Claim 4, Toleti/Martin/Robaina teach the limitations of Claim 1. Toleti further discloses wherein the treatment fidelity data comprises at least one treatment fidelity score ([0007] teaches on determining a “rating” corresponding to a level of adherence to a healthcare protocol which is interpreted as a treatment fidelity score), wherein detecting that the care provider has not correctly followed the procedure further comprises detecting that at least one treatment fidelity score is declining over time or has fallen below a predetermined threshold ([0031] teaches on defining an acceptable range for detecting anomalies with respect to a pre-defined healthcare protocol; values are compared to the predefined range and data values outside the range are “anomalies” which may may trigger a message, alert or other notification), wherein the real-time notification indicates the at least one treatment fidelity score ([0031] teaches on detecting an anomaly triggering a message, alert or other notification, and [0007] teaches on a rating system determining a rating corresponding to a level of adherence for following a protocol, where the system generates “an alert corresponding to the level of adherence”).
Regarding Claim 7, Toleti/Martin/Robaina teach the limitations of Claim 1. Toleti further discloses wherein the machine learning model is a multimodal model configured to process at least two of: image data from the video sensor, audio data from the audio sensor, or environmental data from the environmental sensor (Para. [0012] broadly teaching on determining compliance with a healthcare protocol (e.g., treatment plan) includes the steps of receiving, by an AI and machine learning subsystem, a plurality of output signals corresponding to an event; the output signals are generated by a plurality of sensors and microphones; per [0030] sensors include both video cameras and audio sensors such as microphones; [0042] teaches on one or more sensors including a microphone for monitoring audio between patient and caregiver; [0043] teaches on analysis subsystem receives sensor 110 and microphone 210 output signals; [0046] teaches on sensors 110 and microphone 210 continuously monitoring (e.g., real time data) the environment to generate event streams 305 which are transmitted to analysis subsystem which includes an AI and machine learning subsystem; the analysis subsystem consults an AI-based protocol and compares the signal outputs from the sensors to the AI-based protocol values and performs machine learning from models stored in the database to provide a rating (interpreted as synonymous with “treatment fidelity data”; if the ML/AI models receive both audio sensor data and image sensor data, it is interpreted as being a multimodal model).
Regarding Claim 11, Toleti/Martin/Robaina teach the limitations of Claim 1. Claim 11 recites substantially similar limitations as Claim 1, and the discussions above with respect to Claim 1 is equally applicable to Claim 11. While the system of Toleti is understood to be implemented via a computer (see at least Figs. 2, 3, 4), no particulars of the computing architecture are explicitly disclosed by Toleti. However, Martin further teaches a communication interface; one or more processors; and memory storing instructions that, when executed by the one or more processors ([0074] teaching on device architecture including one or more processors, memory for storing computer-readable instructions; the processor(s) communicate with other elements via one or more buses, either directly or via one or more interfaces).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to modify Toleti with the specific computer architecture of Martin, with the motivation of implementing a computer-based system for facilitating the interaction of the patient and caregiver using various mobile and/or non-mobile devices (Martin [0070], [0073]).
Regarding Claim 14, Toleti/Martin/Robaina teach the limitations of Claim 4. Claim 14 recites substantially similar limitations as Claim 4, and the discussions above with respect to Claim 4 is equally applicable to Claim 14.
Regarding Claim 17, Toleti/Martin/Robaina teach the limitations of Claim 7. Claim 17 recites substantially similar limitations as Claim 7, and the discussions above with respect to Claim 7 is equally applicable to Claim 17.
Claim(s) 2-3, 12-13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Toleti et. al. (US Publication 20200381131A1) in view of Martin et. al. (US Publication 20220384038A1), further in view of Robaina et. al. (US Publication 20230075466A1)
as applied to Claim 1 and 11 respectively above, and further in view of Evans et. al. (US Publication 20210398676A1)
Regarding Claim 2, Toleti/Martin/Robaina teach the limitations of Claim 1 but does not disclose the following. Evans, which is directed to machine learning algorithms for detecting medical conditions, teaches: further comprising: receiving patient data for the patient ([0005] teaches on receiving patient health data for a patient, where [0030] teaches on patient data including medical record data, dynamic or static data regarding the patient); and combining the real-time sensor data with the patient data to generate an integrated data set, wherein analyzing the real-time sensor data using the machine learning model comprises providing the integrated data set as input to the machine learning model ([0031] teaches on aggregating and combining dissimilar data sources, e.g., real-time patient data with previously collected patient health data, to infer or determine a medical condition state determination in real time; this may be accomplished by integrating the data into a data tensor prior to input into machine learning algorithm; [0031] further teaches on, in some examples, abstracting/converting patient health data into a numerical representation that is conducive to combining with real-time sensor data within the machine learning algorithm).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to modify Toleti/Martin/Robaina with these teachings of Evans, to receive patient data to combine with the real-time sensor data of Toleti/Martin/Robaina, to generate an integrated data set to provide as input to the machine learning model, with the motivation of combining the real-time sensor data and patient data into an integrated single data representation that can be acted upon the machine learning algorithm by combining the multiple data sources and types of data together to evaluate the patient as a whole (Evans [0031]) and to provide output indicating information augmented with considerations to patient history and other relevant patient health data (Evans [0065]).
Regarding Claim 3, Toleti/Martin/Robaina/Evans teach the limitations of Claim 2. Toleti does not disclose, but Evans further teaches wherein combining the real-time sensor data with the patient data to generate an integrated data set comprises: ingesting each of the real-time sensor data and the patient data with a corresponding data pipeline from a plurality of data pipelines ([0030] teaches on receiving patient health data from a computing device storing patient health data/accessing stored patient health data from sources such as EHRs, EMRs, etc. – a pipeline corresponding to the patient health data; [0035] teaches on receiving sensor data – e.g., a pipeline corresponding to the sensor data); generating, by the corresponding data pipeline, metadata based on the ingested data ([0065] teaches on encoding patient health data and using this metadata); and integrating the ingested data by performing at least one of: alignment, cross-referencing, or other integration operations based on the metadata ([0065] teaches on the disclosed system encoding patient health data with one-hot encoding or other reshaping operations such that machine learning models make use of this meta-data in addition to image data – interpreted as reading on “other integration operations”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to further modify Toleti/Martin/Robaina/Evans with these teachings of Evans with the motivation of using both sensor data and encoded patient health data to enable machine learning models to provide output indicating information augmented with considerations to patient history and other relevant patient health data ([0065]).
Regarding Claim 12 and Claim 13, Toleti/Martin/Robaina/Evans teach the limitations of Claim 2 and Claim 13, respectively. Claims 12-13 recite substantially similar limitations as Claims 2-3 respectively, and the discussions above with respect to Claims 2-3 are equally applicable to Claims 12-13.
Claim(s) 5-6, 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Toleti et. al. (US Publication 20200381131A1) in view of Martin et. al. (US Publication 20220384038A1), further in view of Robaina et. al. (US Publication 20230075466A1) as applied to Claim 1 and 11 respectively above, and further in view of Das et. al. (US Publication 20190080056A1)
Regarding Claim 5, Toleti/Martin/Robaina teach the limitations of Claim 1 but do not teach the following. Das, which is directed to systems and methods for remote patient monitoring and event detection, teach: further comprising adjusting a monitoring frequency for receiving the real-time sensor data based on detecting a change in a patient condition ([0049] teaches on receiving sensor signals at one or more sampling rates; [0050] sampling rates may be established based on determined patient condition; a patient may be on a “normal” sampling rate but if a ‘warning type’ patient condition is detected, a relatively higher sampling rate may be selected; [0052] teaches on determining a patient condition based on the one or more sensor signals, e.g., high or low blood pressure, high or low pulse rates or respiration rates, etc.; [0055] teaches on determining patient condition type- e.g., normal, warning or emergency condition; if a ”warning” condition is detected, the process proceeds to block 440, which per [0061] causes an increase in a sampling rate of one or more patient sensors – reference Fig. 4; [0062] teaches on selecting one or more sensors to increase a sampling rate; the system determines which sensors provided the information that were provided to the ML model that output the patient condition that triggered the sample rate increase, e.g., if sensor from a pulse rate sensor and ECG sensor were provided that output a warning type patient condition, the pulse rate sensor and ECG sensor are selected for increased sampling rates; [0074] teaches on the sensors and system providing real- time or near-real-time information).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to further modify Toleti/Martin/Robaina with these teachings of Das, to adjust a monitoring frequency of sensor data based on detecting a change in patient condition, with the motivation of increasing sampling rate and received sensor data to enable a faster response if patient’s condition continues to deteriorate (Das [0063]).
Regarding Claim 6, Toleti/Martin/Robaina/Das teach the limitations of Claim 5. Toleti does not disclose, but Das further teaches, wherein detecting the change in the patient condition comprises: receiving physiological data from a sensor associated with the patient ([0022] teaches on patient sensors 110a-n including any suitable physiological sensors, including pulse rate); and detecting, based on the physiological data, at least one of: an increased heart rate or a change in galvanic skin response ([0022] teaches on physiological sensors for detecting pulse rate (synonymous with heart rate); [0052] teaches on detecting patient condition which may include high pulse rate).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to further modify Toleti/Martin/Robaina/Das with these teachings of Das, to receive physiological sensor data from the patient to detect an increase in heart rate, with the motivation of detecting the patient is experience a patient condition indicative of an abnormal patient state (Das [0025]).
Regarding Claim 15 and Claim 16, Toleti/Martin/Robaina/Evans teach the limitations of Claim 5 and Claim 6, respectively. Claims 15-16 recite substantially similar limitations as Claims 5-6 respectively, and the discussions above with respect to Claims 5-6 are equally applicable to Claims 15-16.
Subject Matter Free of the Prior Art
Claims 8 and 18 are free of the prior art. Claim 8 (representative) requires: wherein detecting that the care provider has not correctly followed the procedure comprises: detecting, based on the real-time sensor data, that the patient has engaged in a targeted behavior specified in the treatment plan; and determining, based on analyzing sensor data captured during a predetermined time period after detecting the targeted behavior, that the care provider did not perform a required response specified in the treatment plan for the targeted behavior.
The closest prior art is understood to include McCarton et. al. (US Publication 20050112534A1), which broadly teaches on methods for treatment of autism spectrum disorders. Paras. [0114] teaches on a therapist evaluating “specific behavioral features” (e.g., targeted behavior) of each individual child which form the basis of the treatment interventions for that child. However, McCarton focuses on methodology of the treatment program itself (e.g., the therapist encourages more appropriate behaviors through positive reinforcements each time she/he is able to elicit those behaviors, para. [0114]) rather than using sensor data for analyzing and determining the therapist did not perform a required response specified in a treatment plan. Katz (US Publication 20100145729A1) teaches on behavioral treatment programs for individuals with autism which uses sensor data to record verbal behavior of an individual with autism and allows a therapist to respond with commands associated with a specific behavioral response (targeted behavior) to record the accuracy of a response or description of a behavior. Katz fails to teach aspects related to using sensor data for analyzing and determining the therapist did not perform a required response specified in a treatment plan, after detecting the targeted behavior.
A search of publicly available prior art fails to yield a reference or combination of references that would make the claimed combination obvious when considered as a whole.
Claims 9-10, 19-20 depend from Claims 8 and 18, respectively, and are therefore also free of the prior art.
Conclusion
In the interest of expediting prosecution, Examiner respectfully requests that Applicant provides citations to relevant paragraphs of specification for support for amendments in future correspondence.
The following relevant prior art not cited is made of record:
US Publication 20190057776A1, teaching on a system, for monitoring a clinical care protocol to determine if a standard of care protocol has been adhered to, and providing a recommendation to the doctor when the standard of care protocol has been deviated from
US Publication 20120239430A1, teaching on system and method to provide metrics regarding a physician’s performance to follow a protocol and provide real-time alerts when performance deviates
US Publication 20230049168A1, teaching on systems and methods for analyzing a telehealth session between a clinician and patient in which a physician is provided with real time feedback for best interacting with the patient
US Publication 20190043501A1, teaching on a patient-centered assistive system for multi-therapy adherence intervention and care management
US Publication 20180174682A1, teaching on system and method for protocol adherence which uses sensor data to detect a breach in healthcare protocol and alert medical personnel during the actual process of care
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANNE-MARIE K ALDERSON whose telephone number is (571)272-3370. The examiner can normally be reached on Mon-Fri 9:00am-5:00pm EST and generally schedules interviews in the timeframe of 2:00-5:00pm 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, Fonya Long, can be reached on 571-270-5096. 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.
/ANNE-MARIE K ALDERSON/Primary Examiner, Art Unit 3682
