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 Applicant’s communication filed on May 27, 2025.
Claims 1, 3, 5, 9, 13 and 18 have been amended and are hereby entered.
Claim 2 has been canceled.
Claims 1, 3-5, 8-9 and 11-21 are currently pending and have been examined.
Priority
Acknowledgment is made of Applicant’s claim for priority under 35 U.S.C. § 371 of International Application No. PCT/US2020/053059, filed September 28, 2020, which claims the benefit of U.S. Provisional Application No. 62/906,939, filed September 27, 2019.
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 May 27, 2025 has been entered.
Claim Objections
Claim 1 is objected to because of the following informalities: The limitation “the intervention-response relationship produced by” (line 14) should read “intervention-response relationship is produced by”. Appropriate correction is required.
Claim Rejections - 35 USC § 112(a)
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 3-5, 8-9 and 11-21 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 recites “using a self-supervised model” in line 19. There is no support in the Applicant’s description stating that the model may be a self-supervised model, nor anything describing the use of a self-supervised model. Therefore, Applicant’s specification does not contain sufficient support for the claimed subject matter.
Claims 13 and 18 recites substantially similar limitations to those in claim 1 and is rejected on the same basis as stated above. Claims 2, 3-5, 8-9, 11-12, 14-17 and 19-21 are further rejected as being dependent on a rejected base claim.
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, 3-5, 8-9 and 11-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1 analysis:
Claims 1 and 13 are each directed to a method and Claim 18 is directed to a system. Therefore, all claims fall into one of the four statutory categories. (Step 1: Yes, the claims fall into one of the four statutory categories).
Step 2A analysis - Prong one:
The substantially similar independent method and system claims, taking claim 1 as exemplary, recite the following limitations: receiving and storing in a memory an initial speech sample of a human patient; administering an initial dose of pain-relieving drugs to the human patient; after administering the initial dose, receiving and storing in the memory a first response speech sample of the human patient; administering a second dose of pain-relieving drugs to the human patient; after administering the second dose, receiving and storing in the memory a second response speech sample of the human patient; analyzing, with a processing device the initial speech sample, the first response speech sample, and the second response speech sample to produce an intervention-response relationship for the human patient, the intervention-response relationship produced by extracting objective speech-response features from the initial speech sample, first response speech sample, and second response speech sample and mapping a speech-pain gradient according to the extracted objective speech-response features using a self-supervised model; calibrating the initial dose of pain-relieving drugs according to the intervention-response relationship for the human patient to produce a personalized dose of pain-relieving drugs; and administering the personalized dose of pain-relieving drugs according to the intervention-response relationship.
The examiner is interpreting the above bolded limitations as additional elements as further discussed below. The remaining un-bolded limitations are interpreted as a series of steps describing managing personal behavior or relationships or interactions between people including following rules or instructions and are thus are grouped as certain methods of organizing human activity which are abstract ideas. The un-bolded limitations, as drafted, recite a process that, under the broadest reasonable interpretation, covers certain methods of organizing human activity (i.e., managing personal behavior including following rules or instructions) but for recitation of generic computer components. That is, other than reciting implementing the method by a processing device (computer) and self-supervised model, the claimed invention amounts to managing personal behavior or interaction between people. For example, but for the processing device, memory and model, this claim encompasses a person listening to a patient speak before and after administering a dose of drugs, deciding if the patient is in more, less or the same amount of pain than before the drug administration, and determining a next dose in the manner described in the identified abstract idea, supra. The Examiner notes that certain “method[s] of organizing human activity” includes a person’s interaction with a computer (see MPEP 2106.04(a)(2)(II)). If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “certain methods of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. (Step 2A – Prong 1: Yes, the claims are abstract).
Step 2A analysis - Prong two:
Claims 1, 13 and 18 recite additional elements beyond the abstract idea. Claims 1, 13 and 18 recite a processing device and a self-supervised model. Claims 1 and 13 further recite storing data in a memory. Claim 13 further recites calibrating an automated therapeutic device. Claim 18 further recites an intervention administering device.
This judicial exception is not integrated into a practical application. In particular, the claims recite a processing device, a self-supervised model, storing data in a memory, calibrating an automated therapeutic device, and an intervention administering device which are recited at a high-level of generality (i.e., as a generic processor performing generic computer functions) such that it amounts to no more than mere instructions to apply the exceptions using a generic computer component. For example, Applicant’s specification explains that the processing device represents one or more general-purpose processing devices that executes processing logic in instructions for performing the operations and steps discussed (see Applicant’s spec. para 48). Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Therefore, Claims 1, 13 and 18 are directed to an abstract idea without practical application. (Step 2A – Prong 2: No, the additional claimed elements are not integrated into a practical application).
Step 2B analysis:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using a processing device, a self-supervised model, a memory, an automated therapeutic device, and an intervention administering device to perform the noted steps amounts to no more than mere instructions to apply the exception using a generic computer component. This has been re-evaluated under the “significantly more” analysis and determined to be insufficient to provide significantly more. 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. The collective functions appear to be implemented using conventional computer systemization. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”). See MPEP2106.05(I)(A).
Applicant describes embodiments of the disclosure at a very high level to include the use of an intervention administering device/computer system which includes the use of a wide variety of machine learning models/techniques, processing devices, memories, data storage devices, computer-readable medium, device displays, input/output devices, etc. (see Applicant’s Spec. paras 33, 46-52).
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of a processing device, a memory, an automated therapeutic device and an intervention administering device to perform all of the steps discussed above amount to no more than mere instructions to apply the exceptions using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. (Step 2B: No, the claims do not provide significantly more).
Dependent Claims 3-5, 8-9, 11-12, 14-17 and 19-21 further define the abstract idea that is presented in independent Claims 1, 13 and 18 and are further grouped as certain methods of organizing human activity and are abstract for the same reasons and basis as presented above. Further, Claims 9, 15 and 19-21 recite additional elements beyond the abstract idea. Claims 9 and 15 recite a patient-controlled analgesia (PCA) device. Claim 19 recites an audio input device. Claims 20-21 recites an output device. These additional elements are recited at a high level of generality such that they amount to no more than mere instructions to apply the exception using generic computer components. For example, as noted above, the Applicant’s specification indicates the use of known drug administration devices and input/output devices. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims do not recite additional elements that integrate the judicial exception into a practical application when considered both individually and as an ordered combination. Therefore, the dependent claims are also directed to an abstract idea.
Thus, Claims 1, 3-5, 8-9 and 11-21 are rejected under 35 U.S.C. 101 as being directed to abstract ideas without significantly more.
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.
Claims 1-5, 9 and 11-21 are rejected under 35 U.S.C. 103 as being unpatentable over Rosenbek et al. (US 20170119302) in view of Srivastava et al. (US 20180193652), further in view of Gfeller at al. (US 20210056980).
Regarding Claim 1, Rosenbek discloses the following limitations:
A method for assessing a response of a human patient to a therapeutic intervention, the method comprising:
receiving and storing in a memory an initial speech sample of a human patient; (Rosenbek discloses collecting (receiving) speech sample from subjects (an initial speech sample of a human patient) for determining baseline acoustic measures and storing the baseline acoustic measures in a memory (storing in a memory - para 48) – paras 37, 48; FIG. 1 & 2A)
administering an initial dose of…drugs to the human patient; (Rosenbek discloses methods that can be used to monitor a change in a neurological or other disease in a subject (the human patient), and/or to monitor effects of specific drugs, surgical treatments or rehabilitative efforts (administering an initial dose of drugs). – paras 32, 94-95)
after administering the initial dose, receiving and storing in the memory a first response speech sample of the human patient; (Rosenbek discloses receiving speech samples (a first response speech sample). The identification device is an analytical tool that includes an interface, a processor and a memory (storing in the memory) and receives input via the interface, one or more speech samples from a subject (S210 of FIG. 2B). The subject systems can be used to monitor therapy. In one embodiment a subject's adherence and performance on a particular treatment/rehabilitation program can be monitored via continued use of the subject systems. By monitoring adherence to a treatment, this implies the speech samples may occur after the treatment/therapy has occurs (after administering the initial dose), in order to determine the patients state. – paras 32, 48, 94; FIG. 2B)
administering a second dose of…drugs to the human patient; (Rosenbek discloses methods that can be used to monitor a change in a neurological or other disease in a subject (the human patient), and/or to monitor effects of specific drugs, surgical treatments or rehabilitative efforts. In addition, monitoring speech/language changes over periods of time can help determine whether or not a particular treatment (drugs/rehabilitation exercise) (administering a second dose of drugs) is slowing down the progression of the disease. – paras 32, 94-95) (Examiner interprets the monitoring of drug treatment over periods of time as disclosed by Rosenbek to mean that the drug is administered in measured doses over periods of time)
after administering the second dose, receiving and storing in the memory a second response speech sample of the human patient; (Rosenbek discloses receiving one or more speech samples from a subject and that the user may produce speech samples that correspond to a scheduled time, day, week, or month that repeats at a predetermined frequency (receiving and storing in the memory a second response speech sample of the human patient). The subject systems can be used to monitor therapy. In one embodiment a subject's adherence and performance on a particular treatment/rehabilitation program can be monitored via continued use of the subject systems. By monitoring adherence to a treatment, this implies the speech samples may occur after the treatment/therapy has occurs (after administering the second dose), in order to determine the patients state. – paras 48, 54, 94; FIG. 2B)
and analyzing, with a processing device the initial speech sample, the first response speech sample, and the second response speech sample to produce an intervention-response relationship for the human patient, (Rosenbek discloses that the identification device (a processing device) compares (analyzing) the baseline acoustic measures (the initial speech sample) with the speech samples (the first response speech sample, and the second response speech sample) (S230 of FIG. 2B). The processor can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (produce an intervention-response relationship for the human patient) (S240 of FIG. 2B). – paras 32, 48, 94; FIG. 2A-2B)
the intervention-response relationship produced by extracting objective speech-response features from the initial speech sample, first response speech sample, and second response speech sample… (Rosenbek discloses determining a health state of the subject based upon the results of comparing the identified acoustic measures (extracting objective speech-response features) from the baseline acoustics (the initial speech sample) with the speech samples (first response speech sample, and second response speech sample) or by tracking the rate of change in specific baseline acoustic measures. – para 48; FIG. 2B)
calibrating the initial dose of…drugs according to the intervention-response relationship for the human patient to produce a personalized dose of pain-relieving drugs; (Rosenbek discloses methods that can be used to monitor effects of specific drugs, surgical treatments or rehabilitative efforts. The processor 202 can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (the intervention-response relationship) (S240 of FIG. 2B). The model that outputs the diagnosis and treatment plan, which can include the use of specific drugs, after the health state S240 is determined, is iteratively trained (calibrating the initial dose of drugs patient to produce a personalized dose of pain-relieving drugs – para 133). – paras 32, 48, 94, 133; FIG. 2B) (Examiner notes that this iterative training, as disclosed by Rosenbek, is in effect calibrating the treatment plan to be provided to the patient based upon the patients’ health state from the speech analysis)
and administering the personalized dose of pain-relieving drugs according to the intervention-response relationship. (Rosenbek discloses that the methods provided herein can be used to monitor effects of specific drugs (administering the personalized dose of pain-relieving drugs). – paras 32, 94-95) (Examiner notes that in monitoring effects of drugs, the drugs must be administered)
Rosenbek does not disclose the following limitations met by Srivastava:
pain-relieving drugs (Srivastava teaches an implantable neuromodulator device (IND) which may be configured as a therapeutic device for treating or alleviating the pain. In some examples, the IND 112 may include a drug delivery system such as a drug infusion pump that can deliver pain medication (the pain reliever) to the patient, such as morphine sulfate or ziconotide, among others. – para 47)
and mapping a speech-pain gradient according to the extracted objective speech-response features…; (Srivastava teaches that the closed-loop control of the electrostimulation may be further based on the type of the pain, such as chronic or acute pain. In an example, the pain analyzer circuit 220 may trend the signal metric over time (mapping a speech-pain gradient) to compute an indication of abruptness of change of the signal metrics, such as a rate of change of vocal expression metrics (according to the extracted objective speech-response features). The pain episode may be characterized as acute pain if the signal metric changes abruptly (e.g., the rate of change of the signal metric exceeding a threshold), or as chronic pain if the signal metric changes gradually (e.g., the rate of change of the signal metric falling below a threshold). The controller circuit 312 may control the therapy unit 250 to deliver, withhold, or otherwise modify the pain therapy in accordance with the pain type. Speech motor slowness such as slower syllable pronunciation, or an increased variability of accuracy in syllable pronunciation, may indicate intensity or duration of pain (mapping a speech-pain gradient). – paras 82-83, 100)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate pain medication and generating a trend of signal metrics over time to indicate intensity or duration of pain to further adjust the pain therapy as taught by Srivastava in order to provide an efficient way of managing appropriate pain therapy (see Srivastava para 7).
Rosenbek and Srivastava do not disclose the following limitations met by Gfeller:
using a self-supervised model; (Gfeller teaches self-supervised audio representation learning. More particularly, systems and methods which use unlabeled training data to train a machine-learned model using self-supervised learning to reconstruct portions of an audio signal or to estimate the distance between two portions of an audio signal. – paras 1,22)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the machine learning techniques as disclosed by Rosenbek to incorporate a self-supervised machine learning model as taught by Gfeller in order to have the capability to deploy the systems and methods on a mobile device where no explicit labeling of the data is available (see Gfeller para 37).
Regarding Claim 3, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations: -
monitoring a response of the human patient to the calibrated initial dose of…drugs by receiving and analyzing one or more additional response speech samples for objective indicia…; (Rosenbek discloses that the monitoring of effects of specific drugs, surgical treatments or rehabilitative efforts (monitoring a response of the human patient to the calibrated initial dose of…drugs) includes receiving and analyzing one or more speech samples (receiving and analyzing one or more additional response speech samples) from a subject (S210 of FIG. 2B). The speech samples can be collected at a predetermined frequency or scheduled time; they may be taken at specified intervals. The trimmed WAV files were analyzed using the ITU-T P.56 standard, Method B (“Objective measurement of active speech level,” ITU-T Recommendation P.56, 2011), to measure the active speech level (ASL) which measured the signal level in active (non-silence) regions of speech (analyzing one or more additional response speech samples for objective indicia). – paras 32, 48, 54, 116; FIG. 2B)
and recalibrating the personalized dose of…drugs responsive to the analyzing the one or more additional response speech samples. (Rosenbek discloses determining the health state of the subject by comparing (analyzing) the acoustic measures from the one or more speech samples (the one or more additional response speech samples) with the baseline acoustic measures. Results derived using overtrained models may be accurate for the particular dataset employed in the experiment but grossly misleading for the greater population of talkers in general. Generalization may be tested by splitting a dataset into test data and training data (which may be further split to include a validation set for iterative training or feature selection). The model that outputs the diagnosis and treatment plan, which can include the use of specific drugs, after the health state S240 is determined, is iteratively trained. This iterative training is in effect calibrating the therapeutic intervention to be provided to the patient based upon the health state from the speech analysis. The recalibration occurs when new speech samples are received (recalibrating the personalized dose of drugs). – paras 32, 42, 48, 54, 133; FIG. 2B)
Rosenbek does not disclose the following limitations met by Srivastava:
analyzing one or more additional response speech samples for objective indicia of pain; (Srivastava teaches analyzing the recorded speech signal to generate a plurality of speech features to generate a pain score (objective indicia of pain) to provide objective pain assessment. FIG. 5 shows that the process of analyzing vocal expression may be repeated (analyzing one or more additional response speech samples). – paras 7, 15, 42, 95; FIG. 5)
pain-relieving drugs (Srivastava teaches an implantable neuromodulator device (IND) which may be configured as a therapeutic device for treating or alleviating the pain. In some examples, the IND 112 may include a drug delivery system such as a drug infusion pump that can deliver pain medication (the pain reliever) to the patient, such as morphine sulfate or ziconotide, among others. – para 47)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate the systems and methods of objective pain assessment and the use of pain medication as taught by Srivastava in order to improve pain therapy efficacy (see Srivastava para 42).
Regarding Claim 4, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
further comprising: administering the recalibrated personalized dose of pain-relieving drugs to the human patient. (Rosenbek discloses methods that may be used to monitor effects of specific drugs (administering the recalibrated personalized dose of pain-relieving drugs), surgical treatments or rehabilitative efforts. – paras 32, 94-95)
Regarding Claim 5, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
wherein administering the personalized dose of pain-relieving drugs comprises setting at least one of an initial loading dose, a demand dose, a lockout interval, an infusion rate, or an administration time limit for the pain-relieving drugs. (Srivastava teaches a drug delivery system such as a drug infusion pump that can deliver pain medication to the patient. The process includes computer-implemented generation of recommendations or an alert to the system user regarding pain medication (e.g., medication dosage and time for taking a dose), electrostimulation therapy, or other pain management regimens. In some examples, the IND 112 may include a drug delivery system (a demand dose) such as a drug infusion pump (an infusion rate) that can deliver pain medication (the pain-relieving drugs.) to the patient, such as morphine sulfate or ziconotide, among others. – paras 47, 56, 74, 85-87, 106; FIG. 2) (Examiner interprets providing a dosage as being a demand dose, and using an infusion pump would include an infusion rate and is therefore being interpreted as an infusion rate)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified iteratively training a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate adaptively adjusting drug dosage as taught by Srivastava in order to provide an efficient way of managing appropriate pain therapy (see Srivastava para 7).
Regarding Claim 9, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
wherein the pain reliever is administered by a patient-controlled analgesia (PCA) device. (Srivastava teaches a drug delivery system, such as an intrathecal drug delivery pump that may be surgically placed under the skin, which may be programmed to inject medication or biologics through a catheter to the area around the spinal cord. Other examples of drug delivery system may include a computerized patient-controlled analgesia pump (a patient-controlled analgesia (PCA)) that may deliver the prescribed pain medication to the patient such as via an intravenous line. – para 74)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified monitoring therapy efficacy as disclosed by Rosenbek to incorporate delivery of pain therapy via a patient-controlled analgesia pump as taught by Srivastava in order to provide an efficient way of managing appropriate pain therapy, thereby providing the appropriate dosage to the patient based upon the pain levels determined by the speech (see Srivastava para 7).
Regarding Claim 11, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
further comprising receiving additional objective data for the human patient; wherein the intervention-response relationship is further produced by analyzing the additional objective data for objective indicia…in the human patient. (Rosenbek discloses a screening system that can monitor for a respiratory disease. In one embodiment, a similar system as described with respect to FIG. 5 can be used, where the screening for respiratory diseases can be accomplished by using cough as a biomarker. For the respiratory diseases, cough can be found (receiving additional objective data) and analyzed (analyzing the additional objective data). This may be accomplished via an automatic speech recognition-based analysis. In further embodiments, the acoustic analysis can be performed to quantify metrics (by analyzing the additional objective data for objective indicia in the human patient) including, but not limited to fundamental frequency characteristics, intensity, articulatory characteristics, speech/voice quality, prosodic characteristics, and speaking rate. Once the information from the speech/cough analysis is obtained, comparators 512 can be used to reach a diagnostic decision. The decision provides information indicative of a likelihood and type of disease. A base line of cough data for respiratory-type infections can be created by obtaining cough samples from a variety of sources. Additional respiration data related to a cough can be analyzed along with the speech data can be used determine the health state with an output that is the treatment response (the intervention-response relationship is further produced by analyzing the additional objective data). – paras 80, 82, 84, 94; FIG. 5)
Rosenbek does not disclose the following limitations met by Srivastava:
analyzing…for objective indicia of pain in the human patient. (Srivastava teaches analyzing the recorded speech signal to generate a plurality of speech features to generate a pain score (objective indicia of pain in the human patient) to provide objective pain assessment. FIG. 5 shows that the process of analyzing (analyzing) vocal expression may be repeated to manage pain of a patient. – paras 7, 15, 42, 95; FIG. 5)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate the systems and methods of objective pain assessment as taught by Srivastava in order to improve pain therapy efficacy (see Srivastava para 42).
Regarding Claim 12, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
wherein the additional objective data comprises at least one of: a video sample of the human patient; a facial scan of the human patient; eye movement of the human patient; a thermal sample of the human patient; a writing sample of the human patient; a heart rate of the human patient; or respiration data of the human patient. (Rosenbek discloses a screening system that can monitor for a respiratory disease. In one embodiment, a similar system as described with respect to FIG. 5 can be used, where the screening for respiratory diseases can be accomplished by using cough as a biomarker (respiration data). For the respiratory diseases, cough can be found (receiving additional objective data) and analyzed (analyzing the additional objective data). This may be accomplished via an automatic speech recognition-based analysis. In further embodiments, the acoustic analysis can be performed to quantify metrics including, but not limited to fundamental frequency characteristics, intensity, articulatory characteristics, speech/voice quality, prosodic characteristics, and speaking rate. Once the information from the speech/cough analysis is obtained, comparators 512 can be used to reach a diagnostic decision. The decision provides information indicative of a likelihood and type of disease. A base line of cough data for respiratory-type infections can be created by obtaining cough samples from a variety of sources. – paras 80, 82, 84, 94; FIG. 5)
Regarding Claim 13, Rosenbek discloses the following limitations:
A method for calibrating an automated therapeutic device, the method comprising:
receiving and storing in a memory an initial sample of objective data from a human patient; (Rosenbek discloses collecting (receiving) speech sample from subjects (an initial speech sample of objective data from a human patient) for determining baseline acoustic measures and storing the baseline acoustic measures in a memory (storing in a memory - para 48) – paras 37, 48; FIG. 1 & 2A)
receiving and storing in the memory a first response sample of objective data after administering a dose of…drugs; (Rosenbek discloses receiving speech samples (a first response sample of objective data). The identification device is an analytical tool that includes an interface, a processor and a memory (storing in the memory) and receives input via the interface, one or more speech samples from a subject (S210 of FIG. 2B). The subject systems can be used to monitor therapy. In one embodiment a subject's adherence and performance on a particular treatment/rehabilitation program can be monitored via continued use of the subject systems. By monitoring adherence to a treatment, this implies the speech samples may occur after the treatment/therapy has occurs (after administering a dose of drugs), in order to determine the patients state. – paras 32, 48, 94; FIG. 2B)
analyzing, with a processing device, the initial sample and the first response sample to produce an intervention-response relationship according to objective indicia…in the initial sample and first response sample, (Rosenbek discloses that the identification device (a processing device) compares (analyze) the baseline acoustic measures (the initial speech sample) with the speech samples (first response speech sample) (S230 of FIG. 2B). The processor can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (produce an intervention-response relationship for the human patient according to objective indicia in the initial speech sample and first response speech sample) (S240 of FIG. 2B). – paras 32, 48, 94; FIG. 2A-2B)
wherein the intervention-response relationship is produced by extracting objective response features from the initial sample and first response sample (Rosenbek discloses determining a health state of the subject based upon the results of comparing the identified acoustic measures (extracting objective response features) from the baseline acoustics (the initial sample) with the speech samples (first response sample) or by tracking the rate of change in specific baseline acoustic measures. – para 48; FIG. 2B)
calibrating the automated therapeutic device according to the intervention-response relationship to produce a personalized dose of pain-relieving drugs, (Rosenbek discloses methods that can be used to monitor effects of specific drugs, surgical treatments or rehabilitative efforts. The processor 202 can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (the intervention-response relationship.) (S240 of FIG. 2B). The processor 202 can then output a diagnosis. Results derived using overtrained models may be accurate for the particular dataset employed in the experiment but grossly misleading for the greater population of talkers in general. Generalization may be tested by splitting a dataset into test data and training data (which may be further split to include a validation set for iterative training or feature selection). The model that outputs the diagnosis and treatment plan, which can include the use of specific drugs, after the health state S240 is determined, is iteratively trained. This iterative training is in effect calibrating the therapeutic intervention to be provided to the patient based upon the health state from the speech analysis (calibrating the automated therapeutic device to produce a personalized dose of pain-relieving drugs – para 133). – paras 32, 48, 94, 133; FIG. 2B)
and administering the personalized dose of pain-relieving drugs according to the intervention-response relationship. (Rosenbek discloses that the methods provided herein can be used to monitor effects of specific drugs (administering the personalized dose of pain-relieving drugs). – paras 32, 94-95) (Examiner notes that in monitoring effects of drugs, the drugs must be administered)
Rosenbek does not disclose the following limitations met by Srivastava:
pain-relieving drugs (Srivastava teaches an implantable neuromodulator device (IND) which may be configured as a therapeutic device for treating or alleviating the pain. In some examples, the IND 112 may include a drug delivery system such as a drug infusion pump that can deliver pain medication (pain-relieving drugs) to the patient, such as morphine sulfate or ziconotide, among others. – para 47)
produce an intervention-response relationship according to objective indicia of pain (Srivastava teaches analyzing the recorded speech signal to generate a plurality of speech features to generate a pain score (objective indicia of pain) to provide objective pain assessment. FIG. 5 shows that the process of analyzing vocal expression may be repeated to manage pain of a patient. – paras 7, 15, 42, 94-95; FIG. 5)
and mapping a speech-pain gradient according to the extracted objective response features…; (Srivastava teaches that the closed-loop control of the electrostimulation may be further based on the type of the pain, such as chronic or acute pain. In an example, the pain analyzer circuit 220 may trend the signal metric over time (mapping a speech-pain gradient) to compute an indication of abruptness of change of the signal metrics, such as a rate of change of vocal expression metrics (according to the extracted objective response features). The pain episode may be characterized as acute pain if the signal metric changes abruptly (e.g., the rate of change of the signal metric exceeding a threshold), or as chronic pain if the signal metric changes gradually (e.g., the rate of change of the signal metric falling below a threshold). The controller circuit 312 may control the therapy unit 250 to deliver, withhold, or otherwise modify the pain therapy in accordance with the pain type. Speech motor slowness such as slower syllable pronunciation, or an increased variability of accuracy in syllable pronunciation, may indicate intensity or duration of pain (mapping a speech-pain gradient). – paras 82-83, 100)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate the use of pain medication, objective pain assessment and generating a trend of signal metrics over time to indicate intensity or duration of pain to further adjust the pain therapy as taught by Srivastava in order to improve pain therapy efficacy (see Srivastava para 42).
Rosenbek and Srivastava do not disclose the following limitations met by Gfeller:
using a self-supervised model (Gfeller teaches self-supervised audio representation learning. More particularly, systems and methods which use unlabeled training data to train a machine-learned model using self-supervised learning to reconstruct portions of an audio signal or to estimate the distance between two portions of an audio signal. – paras 1,22)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the machine learning techniques as disclosed by Rosenbek to incorporate a self-supervised machine learning model as taught by Gfeller in order to have the capability to deploy the systems and methods on a mobile device where no explicit labeling of the data is available (see Gfeller para 37).
Regarding Claim 14, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
calibrating the automated therapeutic device comprises setting at least one of an initial loading dose, a demand dose, a lockout interval, an infusion rate, or an administration time limit for the pain-relieving drug. (Srivastava teaches a drug delivery system such as a drug infusion pump that can deliver pain medication to the patient. The process includes computer-implemented generation of recommendations or an alert to the system user regarding pain medication (e.g., medication dosage and time for taking a dose), electrostimulation therapy, or other pain management regimens. In some examples, the IND 112 may include a drug delivery system (a demand dose) such as a drug infusion pump (an infusion rate) that can deliver pain medication (the pain-relieving drugs.) to the patient, such as morphine sulfate or ziconotide, among others. – paras 47, 56, 74, 85-87, 106; FIG. 2) (Examiner interprets providing a dosage as being a demand dose, and using an infusion pump would include an infusion rate and is therefore being interpreted as an infusion rate)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified iteratively training a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate adaptively adjusting drug dosage as taught by Srivastava in order to provide an efficient way of managing appropriate pain therapy (see Srivastava para 7).
Regarding Claim 15, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
wherein the automated therapeutic device comprises a patient-controlled analgesia (PCA) device; (Srivastava teaches a drug delivery system, such as an intrathecal drug delivery pump that may be surgically placed under the skin, which may be programmed to inject medication or biologics through a catheter to the area around the spinal cord. Other examples of drug delivery system may include a computerized patient-controlled analgesia pump (a patient-controlled analgesia (PCA)) that may deliver the prescribed pain medication to the patient such as via an intravenous line. – para 74)
and analyzing the initial sample and the first response sample comprises analyzing an objective pain level of the human patient in response to the PCA device administering a pain reliever. (Srivastava teaches a pain analyzer circuit may generate a pain score using signal metrics of facial or vocal expression extracted from the sensed information. The pain score may be output to a user or a process. The system may additionally include a neurostimulator that can adaptively control the delivery of pain therapy (the PCA device administering a pain reliever) by automatically adjusting stimulation parameters based on the pain score. The pain analyzer circuit includes a speech processor which may be configured to analyze the recorded voice or speech, and generate a vocal expression metric from the recorded voice or speech. Patient with chronic pain may present with impaired cognitive function, emotional and psychological distress, depression, and motor control impairment. Chronic pain can directly or indirectly result in abnormality in speech motor control. The speech processor 223 may process the recorded voice or speech by performing one or more of speech segmentation, transformation, feature extraction, and pattern recognition. Speech motor slowness such as slower syllable pronunciation, or an increased variability of accuracy in syllable pronunciation, may indicate intensity or duration of pain (analyzing an objective pain level of the human patient in response). – abstract; paras 7, 62, 74, 100; FIGs. 2, 3)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified monitoring therapy efficacy as disclosed by Rosenbek to incorporate delivery of pain therapy via a patient-controlled analgesia pump as taught by Srivastava in order to provide an efficient way of managing appropriate pain therapy, thereby providing the appropriate dosage to the patient based upon the pain levels determined by the speech (see Srivastava para 7).
Regarding Claim 16, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
further comprising: after calibrating the automated therapeutic device, receiving a second response sample of objective data; (Rosenbek discloses monitoring effects of specific drugs, surgical treatments or rehabilitative efforts that includes receiving and analyzing one or more speech samples from a subject (receiving a second response sample of objective data) (S210 of FIG. 2B). The processor 202 can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (the intervention-response relationship) (S240 of FIG. 2B). The processor 202 can then output a diagnosis. The model that outputs the diagnosis and treatment plan, which can include the use of specific drugs, after the health state S240 is determined, is iteratively trained. This iterative training is in effect calibrating the therapeutic intervention to be provided to the patient based upon the health state from the speech analysis (after calibrating the automated therapeutic device). – paras 32, 48, 94, 133; FIG. 2B)
analyzing the second response speech sample to produce an updated intervention-response relationship according to objective indicia…in the second response sample; (Rosenbek discloses that the monitoring of effects of specific drugs, surgical treatments or rehabilitative efforts includes receiving and analyzing one or more speech samples (analyzing the second response speech sample) from a subject (S210 of FIG. 2B). The speech samples can be collected at a predetermined frequency or scheduled time; they may be taken at specified intervals. The trimmed WAV files were analyzed using the ITU-T P.56 standard, Method B (“Objective measurement of active speech level,” ITU-T Recommendation P.56, 2011), to measure the active speech level (ASL) which measured the signal level in active (non-silence) regions of speech (according to objective indicia). The processor 202 can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (to produce an updated intervention-response relationship) (S240 of FIG. 2B). – paras 32, 48, 54, 116; FIG. 2B)
and recalibrating the automated therapeutic device according to the updated intervention response relationship to produce a recalibrated personalized dose of pain-relieving drugs. (Rosenbek discloses monitoring effects of specific drugs, surgical treatments or rehabilitative efforts. The processor 202 can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (the intervention-response relationship.) (S240 of FIG. 2B). The processor 202 can then output a diagnosis. Results derived using overtrained models may be accurate for the particular dataset employed in the experiment but grossly misleading for the greater population of talkers in general. Generalization may be tested by splitting a dataset into test data and training data (which may be further split to include a validation set for iterative training or feature selection). The model that outputs the diagnosis and treatment plan, which can include the use of specific drugs, after the health state S240 is determined, is iteratively trained. This iterative training is in effect calibrating the therapeutic intervention to be provided to the patient based upon the health state from the speech analysis (recalibrating the automated therapeutic device to produce a recalibrated personalized dose of pain-relieving drugs). – paras 32, 48, 94, 133; FIG. 2B)
Rosenbek does not disclose the following limitations met by Srivastava:
objective indicia of pain (Srivastava teaches analyzing the recorded speech signal to generate a plurality of speech features to generate a pain score (objective indicia of pain) to provide objective pain assessment. FIG. 5 shows that the process of analyzing vocal expression may be repeated to manage pain of a patient. – paras 7, 15, 42, 94-95; FIG. 5)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate the systems and methods of objective pain assessment as taught by Srivastava in order to improve pain therapy efficacy (see Srivastava para 42).
Regarding Claim 17, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
wherein the objective data comprises at least one of a speech sample, a video sample, a facial scan, eye movement data, a thermal sample, a writing sample, heart rate data, or respiration data. (Rosenbek discloses monitoring effects of specific drugs, surgical treatments or rehabilitative efforts that includes receiving and analyzing one or more speech samples from a subject (the objective data comprises a speech sample) (S210 of FIG. 2B). A person's speech can include other vocal behaviors such as cough or laugh. In one embodiment, a similar system as described with respect to FIG. 5 can be used, where the screening for respiratory diseases can be accomplished by using cough as a biomarker (respiration data). For the respiratory diseases, cough can be found (the objective data comprises respiration data) and analyzed. In further embodiments, the acoustic analysis can be performed to quantify metrics including, but not limited to fundamental frequency characteristics, intensity, articulatory characteristics, speech/voice quality, prosodic characteristics, and speaking rate. Once the information from the speech/cough analysis is obtained, comparators 512 can be used to reach a diagnostic decision. – paras 19, 48, 82,84, 94; FIG. 5)
Regarding Claim 18, Rosenbek discloses the following limitations:
A system for administering a therapeutic intervention to a human patient, the system comprising:
…and a processing device configured to: receive an initial speech sample of the human patient; (Rosenbek discloses using a processor (a processing device) for collecting (receive) speech sample from subjects (an initial speech sample of the human patient) for determining baseline acoustic measures and storing the baseline acoustic measures in a memory. – paras 37, 48; FIG. 1 & 2A)
…administer an initial dose of…drugs to the human patient; (Rosenbek discloses methods that can be used to monitor a change in a neurological or other disease in a subject (the human patient), and/or to monitor effects of specific drugs, surgical treatments or rehabilitative efforts (administering an initial dose of drugs). – paras 32, 94-95)
receive a first response speech sample of the human patient after administering the initial dose; (Rosenbek discloses receiving speech samples (a first response speech sample). The identification device is an analytical tool that includes an interface, a processor and a memory and receives input via the interface, one or more speech samples from a subject (receive a first response speech sample of the human patient) (S210 of FIG. 2B). The subject systems can be used to monitor therapy. In one embodiment a subject's adherence and performance on a particular treatment/rehabilitation program can be monitored via continued use of the subject systems. By monitoring adherence to a treatment, this implies the speech samples may occur after the treatment/therapy occurs (after administering the initial dose), in order to determine the patients state. – paras 32, 48, 94; FIG. 2B)
analyze the initial speech sample and the first response speech sample to produce an intervention-response relationship for the human patient according to objective indicia…in the initial speech sample and first response speech sample; (Rosenbek discloses that the identification device (a processing device) compares (analyze) the baseline acoustic measures (the initial speech sample) with the speech samples (first response speech sample) (S230 of FIG. 2B). The processor can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (produce an intervention-response relationship for the human patient according to objective indicia in the initial speech sample and first response speech sample) (S240 of FIG. 2B). – paras 32, 48, 94; FIG. 2A-2B)
wherein the intervention-response relationship is produced by extracting objective speech-response features from the initial speech sample and first response speech sample (Rosenbek discloses determining a health state of the subject based upon the results of comparing the identified acoustic measures (extracting objective speech-response features) from the baseline acoustics (the initial speech sample) with the speech samples (first response speech sample) or by tracking the rate of change in specific baseline acoustic measures. – para 48; FIG. 2B)
calibrate the initial dose of…drugs according to the intervention-response relationship to produce a personalized dose of…drugs. (Rosenbek discloses methods that can be used to monitor effects of specific drugs, surgical treatments or rehabilitative efforts. The processor 202 can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (according to the intervention-response relationship) (S240 of FIG. 2B). The model that outputs the diagnosis and treatment plan, which can include the use of specific drugs, after the health state S240 is determined, is iteratively trained (calibrate the initial dose of drugs to produce a personalized dose of pain-relieving drugs – para 133). – paras 32, 48, 94, 133; FIG. 2B) (Examiner interprets that this iterative training, as disclosed by Rosenbek, is in effect calibrating the treatment plan to be provided to the patient based upon the patients’ health state from the speech analysis)
and administer the personalized dose of pain-relieving drugs according to the intervention-response relationship. (Rosenbek discloses that the methods provided herein can be used to monitor effects of specific drugs (administering the personalized dose of pain-relieving drugs). – paras 32, 94-95) (Examiner notes that in monitoring effects of drugs, the drugs must be administered)
Rosenbek does not disclose the following limitations met by Srivastava:
an intervention administering device (Srivastava teaches a therapy circuit/unit (an intervention administering device) that may include a drug delivery system such as a computerized patient-controlled analgesia pump that may deliver the prescribed pain medication to the patient such as via an intravenous line. – paras 47, 62, 74; FIG. 2, item 250; FIG. 3)
cause the intervention administering device to administer an initial dose of pain-relieving drugs to the human patient; (Srivastava teaches a therapy circuit/unit (the intervention administering device) that may include a drug delivery system such as a computerized patient-controlled analgesia pump that may deliver the prescribed pain medication to the patient such as via an intravenous line (cause the intervention administering device to administer an initial dose of pain-relieving drugs to the human patient). – paras 47, 62, 74; FIG. 2, item 250; FIG. 3)
objective indicia of pain (Srivastava teaches analyzing the recorded speech signal to generate a plurality of speech features to generate a pain score (objective indicia of pain) to provide objective pain assessment. FIG. 5 shows that the process of analyzing vocal expression may be repeated to manage pain of a patient. – paras 7, 15, 42, 94-95; FIG. 5)
and mapping a speech-pain gradient according to the extracted objective speech-response features…; (Srivastava teaches that the closed-loop control of the electrostimulation may be further based on the type of the pain, such as chronic or acute pain. In an example, the pain analyzer circuit 220 may trend the signal metric over time (mapping a speech-pain gradient) to compute an indication of abruptness of change of the signal metrics, such as a rate of change of vocal expression metrics (according to the extracted objective speech-response features). The pain episode may be characterized as acute pain if the signal metric changes abruptly (e.g., the rate of change of the signal metric exceeding a threshold), or as chronic pain if the signal metric changes gradually (e.g., the rate of change of the signal metric falling below a threshold). The controller circuit 312 may control the therapy unit 250 to deliver, withhold, or otherwise modify the pain therapy in accordance with the pain type. Speech motor slowness such as slower syllable pronunciation, or an increased variability of accuracy in syllable pronunciation, may indicate intensity or duration of pain (mapping a speech-pain gradient). – paras 82-83, 100)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate pain medication and generating a trend of signal metrics over time to indicate intensity or duration of pain to further adjust the pain therapy as taught by Srivastava in order to provide an efficient way of managing appropriate pain therapy (see Srivastava para 7).
Rosenbek and Srivastava do not disclose the following limitations met by Gfeller:
using a self-supervised model (Gfeller teaches self-supervised audio representation learning. More particularly, systems and methods which use unlabeled training data to train a machine-learned model using self-supervised learning to reconstruct portions of an audio signal or to estimate the distance between two portions of an audio signal. – paras 1,22)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the machine learning techniques as disclosed by Rosenbek to incorporate a self-supervised machine learning model as taught by Gfeller in order to have the capability to deploy the systems and methods on a mobile device where no explicit labeling of the data is available (see Gfeller para 37).
Regarding Claim 19, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
further comprising an audio input device configured to receive the initial speech sample and the first response speech sample. (Rosenbek discloses an input to the identification device 200 (an audio input device) which can include a microphone, which is connected to the device in such a manner that a speech sample can be recorded into the device 200 (configured to receive). Alternately, a speech sample can be recorded on another medium and copied (or otherwise transmitted) to the device 200. Once the speech sample is input to the device 200, the processor of the computer or mobile device can provide the processor 202 of the device 200 and perform the identification procedures to determine the health state of the subject. The one or more speech samples may be received in this way. – paras 48, 50, 64; FIG. 2A-2B, 5)
Regarding Claim 20, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
further comprising an output device configured to request the human patient to elicit the initial speech sample and the first response speech sample. (Rosenbek discloses the identification device 200 can be located at the testing site of a patient. In one such embodiment, the identification device 200 can be part of a computer or mobile device such as a smartphone. The interface 201 (an output device) can include a user interface such as a graphical user interface (GUI) provided on a screen or display. An input to the identification device 200 can include a microphone, which is connected to the device in such a manner that a speech sample can be recorded into the device 200. The screening app on the phone may prompt the user (request the human patient to elicit) to record a sample of their speech (the initial speech sample and the first response speech sample). – paras 48, 50-51; FIG. 2A-2B)
Regarding Claim 21, Rosenbek, Srivastava and Gfeller teach all the limitations above and further teach the following limitations:
the output device provides a selected model speech sample to the human patient; (Rosenbek discloses that a speech sample can be recorded by the phone through the phone's microphone. The screening app on the phone may prompt the user to record a sample of their speech and/or request a sample already stored in the phone's memory (provides a selected model speech sample), which may provide the memory of the identification device when the screening app and baseline acoustic measures are stored entirely on the phone. The screening app can perform the steps to determine the health state of the subject. The user interface can prompt the user with exactly what to say as part of the selected model speech sample to be analyzed by the processor. – paras 48, 50-51, 54; FIG. 2A-2B)
and the processing device is configured to analyze the initial speech sample and the first response speech sample based on the selected model speech sample. (Rosenbek discloses that once the speech sample is input to the device 200, the processor of the computer or mobile device can provide the processor 202 of the device 200 and perform the identification procedures (the processing device is configured to analyze) to determine the health state of the subject. In an embodiment, a speech sample (the initial speech sample and the first response speech sample) can be recorded by the phone through the phone's microphone. The screening app on the phone may prompt the user to record a sample of their speech and/or request a sample already stored in the phone's memory (the selected model speech sample), which may provide the memory 203 of the identification device 200 when the screening app and baseline acoustic measures are stored entirely on the phone. The screening app can perform the steps to determine the health state of the subject. The subject systems can be used to monitor therapy. In one embodiment a subject's adherence and performance on a particular treatment/rehabilitation program can be monitored via continued use of the subject systems. – paras 32, 48, 50-51, 94; FIG. 1, 2A-2B)
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Rosenbek et al. (US 20170119302) in view of Srivastava et al. (US 20180193652), in view of Gfeller at al. (US 20210056980), further in view of Berisha et al. (US 20220338804) (Applicant admitted prior art).
Regarding Claim 8, Rosenbek and Srivastava teach all the limitations above and further teach the following limitations:
and the method further comprises providing a personally calibrated dose of…drugs according to the intervention-response relationship. (Rosenbek discloses methods that can be used to monitor effects of specific drugs, surgical treatments or rehabilitative efforts. The processor 202 can determine a health state of the subject based upon the results of the comparison or by tracking the rate of change in specific baseline acoustic measures (according to the intervention-response relationship) (S240 of FIG. 2B). The processor 202 can then output a diagnosis. Results derived using overtrained models may be accurate for the particular dataset employed in the experiment but grossly misleading for the greater population of talkers in general. Generalization may be tested by splitting a dataset into test data and training data (which may be further split to include a validation set for iterative training or feature selection). The model that outputs the diagnosis and treatment plan, which can include the use of specific drugs, after the health state S240 is determined, is iteratively trained. This iterative training is in effect calibrating the therapeutic intervention to be provided to the patient based upon the health state from the speech analysis (providing a personally calibrated dose of drugs – para 133). – paras 32, 48, 94, 133; FIG. 2B)
pain-relieving drugs (Srivastava teaches an implantable neuromodulator device (IND) which may be configured as a therapeutic device for treating or alleviating the pain. In some examples, the IND 112 may include a drug delivery system such as a drug infusion pump that can deliver pain medication (the pain reliever) to the patient, such as morphine sulfate or ziconotide, among others. – para 47)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate pain medication as taught by Srivastava in order to provide an efficient way of managing appropriate pain therapy (see Srivastava para 7).
Rosenbek and Srivastava do not teach the following limitations met by Berisha:
administering the initial dose of pain-relieving drugs to the human patient comprises administering a dose of the pain-relieving drugs according to normative data from other human patients; (Berisha teaches Table 1 which illustrates common concentrations which have been previously determined for opioid-naive patients across large populations (see para 6) (pain-relieving drugs). The traditional approach for programming and setting the PCA device (administering a dose of the pain-relieving drugs) relies on normative data from tables like Table 1 (according to normative data from other human patients) (see para 7). Traditionally, the pump is programmed via normative data for different patient populations or through subjective assessment of the patient's pain scores (see para 37). – Applicant’s Spec. paras 6-7, 37, 39; Table 1; FIG. 1)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified a model which outputs a health state of a subject by including the use of specific drugs as disclosed by Rosenbek to incorporate normative drug concentration data for different patient populations as taught by Berisha because one of ordinary skill in the art would have recognized that applying a well-known “traditional” technique to a known drug administration device (i.e., a PCA device) would have yielded predictable results and resulted in an improved system.
Response to Arguments
Regarding rejections under 35 USC § 112(b) to Claims 3-4 and 13-17, Applicant’s arguments have been fully considered and are persuasive. The rejection has been withdrawn in light of latest amendments.
Regarding rejections under 35 USC § 101 to Claims 1, 3-5, 8-9 and 11-21, Applicant’s arguments have been fully considered and are not persuasive. The rejection has been updated in light of latest amendments. Applicant argues:
(a) Independent claims 1, 13, and 18 have been amended to recite the limitations of dependent claim 2 such that they recite the limitation "administering the personalized dose of pain-relieving drugs according to the intervention-response relationship." Notably, this limitation does not recite, nor is it identified by the Office Action as reciting any of the judicial exceptions to patentable subject matter. In upholding the §101 rejection of claims 1, 13, and 18, the Office Action further states that "the claims may be interpreted to recite a practical application of the abstract idea and overcome the 101 rejection if and only if the independent claims are amended to recite limitations that administer the specific treatments described in the respective claims." Office Action at 44. Accordingly, independent claims 1, 13, and 18 have been amended such that they now recite an administration step for the specific treatment described (i.e. the personalized dose of pain-relieving drugs). With these amendments, the independent claims now provide a practical application of the abstract idea such that they overcome the §101 rejections to the claims because they recite a particular treatment or prophylaxis for a disease or medical condition. Dependent claims 8, 11-12, 14-17, and 19-21 each depend from, either directly or indirectly, and necessarily incorporate each and every limitation of independent claims 1, 13 or 18. (see Remarks p. 9).
Regarding (a), Examiner respectfully disagrees. Upon further analysis of the claimed invention Examiner found the claims to be ineligible under 35 USC § 101. The limitations regarding the administration of a personalized dose of pain-relieving drugs is not particular nor specific enough to provide a practical application via a particular treatment or prophylaxis. Examiner notes that 1) “pain -relieving drugs” encompasses a wide category of drugs and is therefore not particular and that 2) the “personalized dose” is not recited in such a way that requires, e.g., a change in how the drug is administered or the dosage/amount that is administered in a specific or particular way. Therefore, the claims do not provide a particular treatment or prophylaxis and thus do not provide a practical application. See MPEP 2106.04(d)(2).
Regarding rejections under 35 USC § 103 to Claims 1, 3-5, 8-9 and 11-21, Applicant’s arguments have been fully considered and are persuasive regarding the newly added limitations regarding the self-supervised model (see p. 10 of remarks). Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection necessitated by Applicant’s amendments is made in view of Gfeller at al. (US 20210056980), as per the rejection above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KIMBERLY VANDER WOUDE whose telephone number is (703)756-4684. The examiner can normally be reached M-F 9 AM-5 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, PETER H CHOI can be reached at (469) 295-9171. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/K.E.V./Examiner, Art Unit 3681
/PETER H CHOI/Supervisory Patent Examiner, Art Unit 3681