Detailed Action
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. The Amendment filed 5/29/26 has been entered.
3. Claims 1-19 are pending.
4. In view of the amendment, the 101 rejection has been removed.
Claim Rejections - 35 USC § 103
5. 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.
6. Claim(s) 1-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kon et al “Kon” (WO 2020039428 A1) and Shriberg et al “Shriberg” (US 11942194 B2).
(Please see the attached copies of Kon and Shriberg that number paragraphs in the same manner as that used in this Action).
7. Regarding claim 1, Kon shows a computer implemented method for estimating a patient's response to a stimulus perception of a subjective medical test (para 8, 12, 32, 50 show estimating the human subject’s cognitive or emotional response to a stimulus in a given subjective test. Para 49, 63 also show for example estimating the human subject response in an eye blink test to a visual stimulus. Para 43 show it is a psycho-physiological test which is a type of medical test and the human subject would thus be a patient), the method comprising: detecting, using a detector sensor, at least one physiological signal from the patient while the patient is providing a response to the stimulus perception (para 32, 44-45 show detecting the physiological stress signal from the patient using a detector sensor while the patient is responding to the stimulus, and also the blink test in para 49, 63 uses a detector sensor) and estimating, using a computer, the patient's response to the stimulus perception from the at least one physiological signal to generate the estimated patient’s response to the stimulus perception (para 31-32, 65-67 show using a computing device to generate an estimated patient response to the stimulus based on the stress signal), the at least one physiological signal being an input data to a machine learning model trained based on a set of training data (para 20, 32, 34, 44 show the stress signals are input to the trained machine learning model), the set of training data including at least one physiological signal associated to a patient's response (para 20, 35, 60 show the training set includes the stress signal associated with the patient’s response). Kon does not explicitly show that the patent’s response is associated with an estimated of certainty such that output of the trained machine learning model is the estimated level of certainty. Shriberg however does show associating a patient’s response with an estimated level of certainty such that output of the trained machine learning model is the estimated level of certainty (para 57, 202, 224, 229, 352 show the audio response, audiovisual response, and other responses of a patient to a medical testing prompt and estimating a confidence level to it. For example this is done by normalizing and calibrating the reading of the test signal and estimating of level of certainty to the response. Para 227, 230, 270 show the output of a trained machine learning model is the estimated level of certainty). It would have been obvious to a person with ordinary skill in the art before the effective filing date of the claimed invention to associate an estimated level of certainty to a patient’s response such that output of the trained machine learning model is the estimated level of certainty as is shown in Shriberg, in the trained machine learning classifier of signal response estimation of Kon, because it would provide an efficient way to use a trained machine learning model to estimate a patient’s response based on the physiological signal. Estimating the level of certainty would help determine what responses are reasonably indicated by the physiological signal.
8. Regarding claim 2, in addition to that mentioned for claim 1, note the alternative recitation. The input data includes the user response data. Kon para 14, 65 show calculating statistical values of the stress signal data including a standard deviation. Furthermore, Shriberg shows a step of inter and / or intra personal homogenizing the input data or the output of the trained machine learning model (Shriberg para 212, 227, 229 show calibrating and normalizing the user response data over various times and uses as well as among other patients). It would have been obvious to a person with ordinary skill in the art before the effective filing date of the claimed invention to inter or intra personal normalize/homogenize the input data in Kon as is done in Shriberg, because it would provide an efficient way to provide accurate data and minimize anomalies with which to accurately estimate the patient’s response.
9. Regarding claim 3, in addition to that mentioned for claim 2, the step of inter and/or intra personal homogenizing further comprises standardizing the at least one physiological signal, the at least one standardized physiological signal being the input data to the trained machine learning model (as mentioned, Kon para 14, 65 show calculating statistical values of the stress signal data including a standard deviation).
10. Regarding claim 4, in addition to that mentioned for claim 2, the inter and/or intra personal homogenizing further comprises detecting at least one reference physiological signal associated to a reference level of certainty of the patient's response (Shriberg para 126, 229, 350, 352, 425 show a response associated to a benchmark standard certainty level – motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2. Shriberg para 119, 192, 485 further show a response associated with a reference threshold level of confidence – motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2), the at least one reference physiological signal and the reference level of certainty of the patient's response being a set of reference data (Shriberg para 126, 229, 350, 352 show a reference response and benchmark standard level are a set of reference data), and wherein the level of certainty of the patient's response to the stimulus perception is estimated from the at least one physiological signal and from the set of reference data (Shriberg para 126, 229, 350, 352 show the level of certainty of the response is estimated from the response and the reference response and reference level of certainty, and Shriberg para 119, 192, 485 further show a response associated with a reference threshold level of confidence - motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2).
11. Regarding claim 5, in addition to that mentioned for claim 4, the at least one reference physiological signal is an input data to the trained machine learning model (Kon para 20, 32, 34, 44 show the stress signals are input to the trained machine learning model, and this would include any reference stress signal). The motivation to have the reference signal is the same as that mentioned for claim 2, from which claim 4 depends, and now from which claim 5 depends.
12. Regarding claim 6, in addition to that mentioned for claim 4, the at least one reference physiological signal is used to threshold the output data (as mentioned for claim 4, Shriberg para 119, 192, 229, 485 show a response associated with a reference threshold level of confidence – motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2).
13. Regarding claim 7, the physiological signals comprise signals having different modalities, and wherein the method further comprises formatting the physiological signals having different modalities (Kon para 20, 32, 34, 37 show the stress signals have different classes, and Kon para 45, 61, 62 show different format protocols for the different classes of signals).
14. Regarding claim 8, the level of certainty is a category, and estimating the category of certainty further comprises classifying the input data by way of the trained machine learning model to estimate the level of certainty (Shriberg 227, 230, 311, 353 show the confidence level is a score category estimated by classifying the response input data in the trained machine learning model to estimate the confidence level). It would have been obvious to a person with ordinary skill in the art before the effective filing date of the claimed invention to have this in Kon, because it would provide an efficient way to use a trained machine learning model to estimate a patient’s response based on the physiological signal. Classifying the input data by the trained machine learning model to estimate the confidence level would help determine what responses are reasonably indicated by the physiological signal.
15. Regarding claim 9, the level of certainty is a score (Shriberg para 31, 55, 89 show the confidence level is a score) and estimating the score of certainty further comprises regressing the input data by way of the trained machine learning model to estimate the level of certainty (Shriberg para 256, 276, 346, 409 show the using the regression model on the response input data to the trained machine learning model). Motivation to use this in Kon is the same as that mentioned for claim 1.
16. Regarding claim 10, Kon show the subjective medical test is a subjective ophthalmic test (para 49, 63 show the eye blinking test), the stimulus perception is a visual stimulus perception (para 17, 62 show the visual stimulations). Shriberg para 208, 214, 276, 335 also show eye gazing tests in response to visual stimulations.
17. Regarding claim 11, in addition to determining a level of certainty according to claim 1 (see claim 1); please note the alternative recitation of: informing of the estimated level of certainty, and/or weighting a result of the subjective medical test, and/or changing the stimulus perception by taking into account the estimated level of certainty. Shriberg para 134, 141, 227, 229 weights the result of the test, and para 250 for example informs the confidence level via a score. The motivation to use either of these in Kon is the same as that mentioned for claim 1, namely to provide an efficient way to use a trained machine learning model to determine a patient’s response based on the physiological signal.
18. Regarding claim 12, Kon shows a device for a subjective medical test of a patient (para 49, 63 show the device for measuring eye blinking, para 39 shows devices for other subjective medical tests of the human subject, and para 43 show it is a psycho-physiological test which is a type of medical test and the human subject would thus be a patient) comprising a detector configured to detect at least one physiological signal from the patient while the patient is providing a response to a stimulus perception (para 32, 44-45 show detecting the physiological stress signal from the patient using a detector sensor while the patient is responding to the stimulus, and also the blink test in para 49, 63 uses a detector sensor; in general para 39, 49, 63 show the various detectors which then produce some stress signal in response from the patient responding to the test), control unit circuitry configured to estimate the patient's response to a stimulus perception of the subjective medical test to generate the estimated patient's response to the stimulus perception (para 42, 72 show the circuitry to control the medical measuring devices, para 32, 44-45 show detecting the physiological stress signal from the patient while the patient is responding to the stimulus), the response being estimated from at least one physiological signal of the patient while the patient is providing the response to the stimulus perception (para 31-32, 65-67 show estimating a patient response to the stimulus based on the stress signal), the at least one physiological signal being input data to a trained machine learning model (para 20, 32, 34, 44 show the stress signals are input to the trained machine learning model). Kon does not explicitly show that the patent’s response is associated with an estimated level of certainty such that output of the trained machine learning model is the estimated level of certainty. Shriberg however does show associating a patient’s response with an estimated level of certainty such that output of the trained machine learning model is the estimated level of certainty (para 57, 202, 224, 229, 352 show the audio response, audiovisual response, and other responses of a patient to a medical testing prompt and estimating a confidence level to it. For example this is done by normalizing and calibrating the reading of the test signal and estimating of level of certainty to the response. Para 227, 230, 270 show the output of a trained machine learning model is the estimated level of certainty). It would have been obvious to a person with ordinary skill in the art before the effective filing date of the claimed invention to associate an estimated level of certainty to a patient’s response such that output of the trained machine learning model is the estimated level of certainty as is shown in Shriberg, in the trained machine learning classifier of signal response estimation of Kon, because it would provide an efficient way to use a trained machine learning model to estimate a patient’s response based on the physiological signal. Estimating the level of certainty would help determine what responses are reasonably indicated by the physiological signal.
19. Regarding claim 13, Kon shows a test unit circuitry configured to provide a subjective test associated to stimulus perceptions (para 42, 72 show circuitry for the medical test devices that provide the test measurement, para 39, 49, 63 show the subjective medical tests are associated to different stimulations.
20. Regarding claim 14, please note the alternative recitation. Kon para 42 shows the microphone, para 48 shows the blood pressure detector, para 49 shows the temperature detector.
21. Regarding claim 15, Kon show the subjective medical test is a subjective ophthalmic test (para 49, 63 show the eye blinking test, para 17, 62 show the visual stimulations, Shriberg para 208, 214, 276, 335 also show eye gazing tests in response to visual stimulations.
22. Regarding claim 16, in addition to that mentioned for claim 3, the inter and/or intra personal homogenizing further comprises detecting at least one reference physiological signal associated to a reference level of certainty of the patient's response (Shriberg para 126, 229, 350, 352, 425 show a response associated to a benchmark standard certainty level – motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2. Shriberg para 119, 192, 229, 485 further show a response associated with a reference threshold level of confidence – motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2), the at least one reference physiological signal and the reference level of certainty of the patient's response being a set of reference data (Shriberg para 126, 229, 350, 352 show a reference response and benchmark standard level are a set of reference data), and wherein the level of certainty of the patient's response to the stimulus perception is estimated from the at least one physiological signal and from the set of reference data (Shriberg para 126, 3229, 50, 352 show the level of certainty of the response is estimated from the response and the reference response and reference level of certainty, and Shriberg para 119, 192, 485 further show a response associated with a reference threshold level of confidence - motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2).
23. Regarding claim 17, in addition to that mentioned for claim 5, the at least one reference physiological signal is used to threshold the output data (as mentioned for claim 4, Shriberg para 119, 192, 229, 485 show a response associated with a reference threshold level of confidence – motivation to combine this with Kon such that the response would be the physiological signal is the same as that mentioned for claim 2).
24. Regarding claim 18, Kon show the subjective medical test is a subjective ophthalmic test (para 49, 63 show the eye blinking test, para 17, 62 show the visual stimulations, Shriberg para 208, 214, 276, 335 also show eye gazing tests in response to visual stimulations).
25. Regarding claim 19, Kon show the subjective medical test is a subjective ophthalmic test (para 49, 63 show the eye blinking test, para 17, 62 show the visual stimulations, Shriberg para 208, 214, 276, 335 also show eye gazing tests in response to visual stimulations).
Response to Arguments
26. Applicant's arguments filed 5/29/26 have been fully considered but they are not persuasive. Regarding claim 1, Applicant alleges that “The action relies on paragraphs 17, 49, 62, and 63 of Kon to describe … and estimating a level of certainty of the patient’s response to the stimulus perception … generate an estimated level of certainty…” but Applicant incorrectly ascribes the Action’s reliance on Kon for features that indeed the Action brings in Shriberg to show. The Action makes it clear that Kon does not explicitly show that the patent’s response is associated with an estimated of certainty such that output of the trained machine learning model is the estimated level of certainty. Shriberg however does show associating a patient’s response with an estimated level of certainty such that output of the trained machine learning model is the estimated level of certainty (para 57, 202, 224, 229, 352 show the audio response, audiovisual response, and other responses of a patient to a medical testing prompt and estimating a confidence level to it. Para 227, 230, 270 show the output of a trained machine learning model is the estimated level of certainty). Applicant argues that Shriberg shows estimating confidence/certainty levels in the diagnostic outcome of the patient as opposed to a confidence/certainty level of the patient. First of all, the claim language recites estimating the certainty level of the patient’s response, not the certainty level of the patient. With regard to this feature, note that although parts of Shriberg do discuss estimating the level of certainty of the diagnostic outcome as Applicant alleges, nevertheless Shriberg also discusses estimating the level of certainty of the patient’s response itself to the stimulus perception for a variety of tests. The cited paragraphs of Shriberg show this as explained in the Action. Applicant does not address the cited passages.
Note though, that in view of the amendment, the 101 rejection has been removed.
Conclusion
27. THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
28. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
a) Fink (US 11684256 B2) shows measuring a patient response in an ophthalmic test to a visual stimulus.
b) Bostoen (CA 3050225 A1) shows predictive modeling and training devices with biofeedback signal measuring.
29. Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEVEN PAUL SAX whose telephone number is (571)272-4072. The examiner can normally be reached Monday - Friday, 9:30 - 6:00 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, Usmaan Saeed can be reached at 571-272-4046. 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.
/STEVEN P SAX/ Primary Examiner, Art Unit 2146
Prosecution Insights