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 .
Response to Arguments
Applicant's arguments filed 5/4/26 have been fully considered but they are not persuasive.
With regards to the 101 arguments, Applicant argues the abstract ideas cannot be performed in the mind because “These models cannot be practically performed in the human mind.”. The human mind can perform the claimed abstract idea such as taking in data and making a classification or determination; thus, the broad argument is not persuasive. Further as discussed in both Eichler and O’Donovan the analysis that those models and the current model are trying to replace have traditionally been performed by medical professionals mentally, such as examining a person’s facial paralysis taking in the through the eyes the occurrence and mentally related determinations.
Applicants next argue that it recites a technological improvement. However, this is not persuasive. The claims are not directed to an improvement of a particular sensor such as a new camera or microphone. Applicants argue the improvement is in the “assessment” processing by a (i) “first” model(s), (ii) “second” model(s), (iii) determining a neurological event and (iv) issuing an alert. The first three are part of the abstract idea, therefore arguing the improvement is in the abstract idea itself the model which is not persuasive. The fourth step is part of the extra solution activity, more specifically post solution activity of outputting a result. To the extent the applicants are arguing elements which are not particularly claimed this is improper (for one example, there is no recitation of “raw” data) it merely recites “data corresponding to one or more symptoms”.
Applicants next argue that the interpretation of receiving and the generating an output are “contrary” to the holistic approach. The claim elements were considered individually and in combination during the analysis. The “additional elements” were deemed to be insignificant extra-solution activity as discussed in MPEP 2106.04(d) and 2106.05(g). Therefore, this argument is not persuasive.
Applicants merely recite that “to the extent the analysis proceeds to Step 2B” its not well known, routine and conventional (WRC). Examiner disagrees as discussed in the rejection; the conclusory statement is not persuasive.
With regards to Applicants 102 arguments against Eichler, Applicant argument can be summarized as “Eichler does not disclose the noted two-stage machine learning pipeline with per-symptom-trained second-stage ML models”; first by arguing that Eichler uses a “single stage” architecture. More specifically Applicant is arguing that there is no “first” models for extraction and “second” models for severity score. Examiner disagrees.
Applicant argues that Eichler discloses extracting relevant feature data in figs. 2-4 using elements such as landmarks etc. but not using ML models (see second argument moved discussed before discussion of the severity scores because that argument is tied to later discussion of per symptom basis). Examiner notes landmark detection is known to be done with machine learning models for computer vision (see Kim in pertinent prior art section of conclusion section), even though the reference may not word for word recite that its computer vision/ML. However, in order to more explicitly show this and other elements a secondary reference O’Donovan has been provided for this element.
With regards to the discussion that the outputs of 190 are not “severity scores” and that the MLCs are “not trained per-symptom to score the severity of a particular symptom”, Examiner disagrees. Examiner notes that reviewing the respective figures 5-7 and associated paragraphs of Eichler; as well as the tables and figs. 14-16 (and associated discussion) which further discuss specific applications of the classifiers discussed ([0066] including “A real-world example implementation of the disclosed technique now follows.”). The tables and 14-16 discuss specific applications of the MLCs to each of a variety of different categories (the categories are the equivalent to a “symptom”) to determine a score, see for example table 5 which recites outputting a category score (“severity score”) related directly to that that symptom/category facial palsy (aka facial paralysis) in table 5 and recites the MLC trained specifically for that symptom/category. The MLC’s of the tables are specific examples of the integration of the more generic discussion earlier of MLCs discussed in figs. 5-6, which more explicitly recite determining “scores”. Also, Applicants are seemingly implying that the “rubric” is not a severity score, but the category scores are determinations of the severity. For example, score 0 for normal –> score 3 for complete facial paralysis (Fig. 14) with intermediary scores 1 and 2 for in between severities (minor and partial respectively). Thus, this is not persuasive. Examiner also notes that O’Donovan also discloses applying a symptom/category specific ML scorer for different symptoms/categories (see citations below). For the above reasons the arguments are not persuasive.
With regards to applicants mention of “individual scores for various subtests” related to per symptom ML models see the discussion above; with regards to the last element “that receives, as input, symptom values that were themselves generated by a separate first-stage ML model from extracted biological features.” Examiner notes this is not what is claimed. The first ML models seem to be recited for “extracting” the biological features, not for the determining the “symptom values” (Examiner notes the 112b on the clarity issue between the “biological features” and “symptom values”). To the extent the element argues is not claimed, in response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). For the above reasons this is not persuasive.
With regards to the arguments discussion of “prompting” the user to perform a task. First of note the claims are directed to the use of a computer implemented method and a system, thus if the patient/user is prompted by medical professional/another user it still fulfills the claim language as it is not the computer method or system performing the prompting. Regardless, contrary to Applicants argument, the Eichler reference explicitly recites it can be done without prompting (see citation below in the rejection). The cited portion recites the measurements can be done with prompting, without prompting or a hybrid version combining elements of with and without prompting. Thus, for the reasons above reasons the arguments are not persuasive.
With regards to the discussion of “generating” based on the spatial pattern of the left side and right side, Examiner does not find this persuasive (also Examiner notes the 112a rejection below). The Eichler reference discloses using a determination of category score per arm and per leg (see for example Tables 6-7). The various categories are combined to determine a “total score” and related “neurological event” thus it is incorporating the scores and associated asymmetry into the final decision. Examiner also notes that O’Donovan also discloses applying receiving scores from symptom specific ML and using them together to make a determination of a neurological event. For the above reasons the arguments are not persuasive.
The remaining arguments/discussion relies on the arguments discussed above and are not persuasive for the same reasons.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 101 see the analysis below.
Step 1
The invention claimed in claims 1-20 are directed to statutory subject matter as the claims recite a CRM apparatus and a system apparatus.
Step 2A, Prong 1
Regarding Claims 1 and 13, the recited steps of “extracting. . . biological features”, “assigning” symptom values, “determining” a severity score based on the symptom values, “generating” a prediction of a neurological even based on the symptom severity scores asymmetry, and “triggering” an alert based on the prediction are directed to a mental process of performing concepts in the human mind (including by a human using the aid of pen and paper). For example, this limitation simply amounts to the mental process of a clinician reviewing data (such as images, audio, motion etc.) and performing a mental analysis (or with pen and paper) extracting biological features such as user mentally noticing landmarks in the images/calculating a droop degree (eye position, mentally performing what’s occurring in O’Donovan fig. 3b, Examiner notes that doctors performed the NIHSS categories mentally see Tables 1-12 in Eichler etc.), assigning values (same as the biological features see applicants [0066]), using values to mentally determine “severity” scores (mentally making a determination of the severity of for example the facial palsy/paralysis; or motor skills of dragging one foot as opposed to other) and based on the severity scores making a prediction if the patient is suffering a stroke and if it is determined they are suffering a stroke then determining an alert is necessary such as calling upon assistance etc. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, then it falls within the “Mental Processes” grouping of abstract ideas.
Step 2A, Prong 2
Regarding Claims 1 and 13, the judicial exception is not integrated into a practical application. The claims include the additional elements of “receiving” data and “generating” a display for the alert. The step of “receiving . . .” the data amounts to insignificant, extra-solution activity in that the it is data gathering (or in an alternative interpretation this also includes the steps of “assigning”). The step of “generating . . .” the display for the alert is extra solution as merely outputting a result. The processor (i.e., “processor”, “computer processor”, “cloud-computing device”, “mobile device”, “user device”) in computing steps are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of determining outputs from inputs) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Step 2B
Regarding Claims 1 and 13, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As with step 2A, Prong 2 above, the additional elements of “receiving” data and “generating” a display for the alert. The step of “receiving . . .” the data amounts to insignificant, extra-solution activity in that the it is data gathering (or in an alternative interpretation this also includes the steps of “assigning”). The step of “generating . . .” the display for the alert is extra solution as merely outputting a result. The processor (i.e., “processor”, “computer processor”, “cloud-computing device”, “mobile device”, “user device”) in computing steps are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of determining outputs from inputs) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Additionally, per the Berkheimer requirement, the camera/audio, display, processing device and data storage: (1) Eichler see citations below; (2) O’Donovan see citations below; (3) US 20180140203 – Cited in IDS dated 8/2/23 – see [0038], [0041]-[0044], [0053]-[0054], Figs. 1-3; (4) US20180177451 - Cited in IDS dated 8/2/23 – see [0040]-[0041], [0049], [0054]-[0055], [0069], [0071] Figs. 1A-B. As such the elements are shown to be WRC.
The claim limitations when viewed individually and in combination therefore do not amount to significantly more than the abstract idea itself. The claims are therefore ineligible.
Claims 2-12, 14-20 only further define the data gathering (insignificant, extra-solution activity) or further define elements of the model (i.e., only further define the mental process). Therefore, the claims do not include any additional elements that show integration into a practical application and do not include any additional elements that amount to significantly more than the abstract idea. The claims are ineligible.
Claim Rejections - 35 USC § 112
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 1-20 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.
Claims 1 and 13 recite “wherein the type of the at least one neurological event is determined based at least in part on a spatial pattern of severity scores across left-side and right-side body regions of the subject” however, there does not appear to be support for this. The most relevant sections of the specification seem to be [0046] reciting “using one or more and/or a combination of the severity scores/indications associated with each experienced symptom, the engine 106 may be configured to determine a type of neurological disorder being experienced by the subject 102.” and similarly in [0057], [0068]. As such, there is support for the determination of type “based on” the “severity scores” generically but not “based at least in part on a spatial pattern of severity scores across left-side and right-side body regions of the subject. . .”. For the above reason the claim does not support in the written description and is new matter. The claims depending from this claim share this issue and are likewise rejected for the same reasons.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1 and 13 recites “extracting, using one or more first machine learning models executed by the at least one processor, one or more biological features from the data received from the one or more sensors, . . . generating the one or more symptom values from the one or more biological features;”, however this causes confusion because when reading the claims in view of the specification [0054] (using Pg Pub for paragraph numbers) which recites “extract one or more feature values (e.g., biological, neurological, etc.) 210 associated with the received data and provide such feature values 210” and [0066] (using Pg Pub for paragraph numbers) which states “assign one or more symptom values to the detected symptoms. These may include one or more feature vector values 210 shown in FIG. 2 .” it appears the claimed “biological features” are synonymous with the “symptom values”. Thus, it is unclear if the “biological features” and the “assigned symptom values” are different things or merely a recitation of the same features/values. For the above reason the claim does not clearly define the metes and bounds of the claim and is indefinite. The claims depending from this claim share this issue and are likewise indefinite.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 1-9, 11-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20220044821 to Eichler et al. in view of US 20210202090 to O'Donovan et al. (hereinafter O’Donovan).
Regarding Claim 1, an interpretation of Eichler discloses a computer-implemented method for diagnosing a neurological event in a subject (abstract), comprising:
receiving, using at least one processor and without prompting the subject to perform a task, data corresponding to one or more neurological symptoms neurological symptoms associated with the subject, the data detected by one or more sensors ([0005], [0032] including “The processor is configured to receive clinical measurement data pertaining to the subject. The clinical measurement data is acquired from at least one sensor that is configured to sense at least one of image data, sound data, movement data, and tactile data pertaining to the subject. The processor is configured to extract from the clinical measurement data, potential stroke features”, [0040], [0051]-[0052] including “the extraction of clinical measurement data by the acquisition units may be with user intervention (e.g., prompting the subject to perform instructions, such as raising hands, speaking, etc.), be without user intervention (e.g., automatic), or be a hybridizes between (partial) user intervention and (partial) user non-intervention.”, Figs. 1-4), including at least one of the following sensors: one or more sensors positioned directly on the subject, one or more sensors being positioned away from the subject, and any combination thereof, the one or more sensors including at least a video sensor and an audio sensor, the at least one processor being communicatively coupled to the one or more sensors ([0005], [0032], [0035], [0044]-[0045], Figs. 1-4, 8);
assigning, using the at least one processor, one or more values to the one or more detected symptoms ([0037], [0047] including “configured and operative to extract potential stroke features (e.g., attributes and their corresponding value) from the clinical measurement data”, [0048]-[0050], Figs. 3-8), wherein the assigning further comprises
extracting, using one or more analysis executed by the at least one processor, one or more biological features from the data received from the one or more sensors ([0047]-[0050] including “The extraction of potential stroke features from different types of clinical measurement data”, [0070], Figs. 2-4, 13), the one or more biological features comprising at least one of one or more facial landmarks extracted from video data ([0044], [0048]-[0049], Figs. 2-4 see also [0054], [0192], Tables 1-12), and
determining, using the at least one processor, a severity score for each of the one or more symptoms ([0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 7, 14, 16), the severity scores being determined using one or more second machine learning models ([0057], [0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 5-6, 14, 16 see also [0043]; more than 2 tables include recitations that they use “MLC” (aka machine learning classifier) to determine score for that particular “symptom”/subtest/category based on features. For example, Table 3 regards Horizontal eye movement (a gaze deficit) and Table 5 regards Facial palsy), the one or more second machine learning models including a plurality of machine learning models each trained, on a per-symptom basis, to score a degree of severity of a corresponding one of facial paralysis ([0054], [0057], [0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 5-6, 14, 16 see also [0043]; The reference discloses a plurality of “MLC” (aka machine learning classifier) and also per the Tables more than 2 tables include recitations that they use an MLC to determine score for that particular “symptom”/subtest/category based on symptom specific features. For example, Table 3 regards Horizontal eye movement (a gaze deficit) and Table 5 regards Facial palsy), gaze deficit ([0057], [0066], [0071], Tables 1-12, Figs. 5-6, 14, 16 see also [0043]), the one or more second machine learning models receiving the one or more extracted features/values as input ([0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 14, 16 see also [0043], [0057]; tables include recitations that they use “MLC” (aka machine learning classifier) to determine score for subtest/category based on features);
generating, using the at least one processor, a prediction that the subject is experiencing at least one neurological event and at least a type of the at least one neurological event using a combination of the determined severity scores corresponding to the one or more symptoms ([0032] including “The systems of the disclosed technique are configured and operative to provide an indication of a stroke as soon (i.e., immediate, in real-time) as it is detected (i.e., estimated at a high likelihood, i.e., over a threshold probability).”, [0072], [0074], [0076], [0078] including “After quantifying each category of the NIHSS, the total score can define the stroke severity” Figs. 17A-B, 19 see also [0002], [0042], [0077]; stroke severity score includes “no stroke” option thus a determination of whether or not the user is suffering from a stroke), wherein the type of the at least one neurological event is determined based at least in part on a spatial pattern of severity scores across left-side and right-side body regions of the subject ([0032], [0060, [0072], [0074], [0076], [0078] including “After quantifying each category of the NIHSS, the total score can define the stroke severity”, Tables 1-12, Figs. 17A-B, 19 see also [0002], [0042], [0077]; taking in severity scores (scores) and determining a type and brain location);
triggering, using the at least one processor, a generation of one or more alerts based on the prediction ([0042] including “systems 101 1, and 101 2 are configured and operative to alert the user, the user's relatives, and medical professionals, as will be detailed hereinbelow.”, [0075]-[0076], Figs. 17A-B, 19); and
generating, using the at least one processor, one or more user interfaces for displaying the one or more alerts ([0037], [0042] including “systems 101 1, and 101 2 are configured and operative to alert the user, the user's relatives, and medical professionals, as will be detailed hereinbelow.”, [0075]-[0076], Figs. 7, 17A-B, 19).
While Eichler discloses using a plurality of machine learning algorithms to gather the extracted biological features and determine severity scores etc. an interpretation of Eichler may not explicitly disclose that extracting one or more biological features from the data received from the one or more sensors, is specifically done using one or more first machine learning models executed by the at least one processor, and generating the one or more symptom values from the one or more biological features; the severity scores being determined using one or more second machine learning models that are different from the one or more first machine learning models, the one or more second machine learning models receiving the one or more assigned symptom values as input
However, in the same field of endeavor (medical devices), O’Donovan teaches extracting one or more biological features from the data received from the one or more sensors, is specifically done using one or more first machine learning models executed by the at least one processor ([0064]-[0065], [0119], [0121] including “the pose estimator 708 may employ OpenPose, available from Carnegie Mellon University, to detect both pose and limb movement”, [0178]-[0179], Tables 3-4, Fig. 7 see also [0107], [0147], [0192]; Discloses one or more models for “extracting” biological features. Examiner notes that OpenPose applies ML model if more information is required on OpenPose please see the conclusion sections additional references), and
generating the one or more symptom values from the one or more biological features ([0066]-[0067], [0122]-[0123], Figs. 7, 10 see also [0107], [0148], [0178]-[0179], [0192], Tables 3-4);
the severity scores being determined using one or more second machine learning models that are different from the one or more first machine learning models ([0116], [0119], [0128]-[0129], [0142]-[0143], [0148], Figs. 7, 10 see also [0192]; pose estimator etc. models are different from the scorer models.), the one or more second machine learning models receiving the one or more assigned symptom values as input ([0116], [0119], [0128], [0142]-[0143], [0148], Figs. 7, 10 see also [0192]; For example, pose estimator extracts data using ML, limb velocity determines additional information. the scorer models receives “assigned” data such as derived data from the limb velocity).
It would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention to have modified the data gathering and determination of a neurological event such as a stroke as recited by Eichler to include using ML models for determining biological features, assigning “symptom” values and using the symptom values to determine severity scores using symptom specific ML models as recited by O’Donovan because it improves diagnostic accuracy by providing a supplemental reference for comparison of a medical professionals determination ([0052]). Separately and additionally, It would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention to have modified the data gathering and determination of a neurological event such as a stroke as recited by Eichler to be combined with using ML models for determining biological features, assigning “symptom” values and using the symptom values to determine severity scores using symptom specific ML models as recited by O’Donovan because it is merely combining prior art elements (recited previously in this paragraph) according to known methods to yield predictable results, of determining a stroke based on the combined process of the elements from the Eicher and Donovan.
Regarding Claim 2, an interpretation of Eichler further discloses wherein the at least one neurological event includes a stroke (abstract, [0042]).
Regarding Claim 3, an interpretation of Eichler further discloses wherein the one or more sensors include at least one of the following: a medical sensor ([0005], [0032] including “The processor is configured to receive clinical measurement data pertaining to the subject. The clinical measurement data is acquired from at least one sensor that is configured to sense at least one of image data, sound data, movement data, and tactile data pertaining to the subject. The processor is configured to extract from the clinical measurement data, potential stroke features”, [0040] including “blood pressure measurement device”, [0045] including “movement sensors”, Figs. 1-4).
Regarding Claim 4, an interpretation of Eichler further discloses wherein the one or more symptoms include at least one of the following: one or more symptoms determined based on one or more physiological responses from the subject ([0054], [0060], Figs. 1-4, Tables 1-12 see also [0055]-[0057]).
Regarding Claim 5, an interpretation of Eichler further discloses wherein the one or more physiological responses include at least one of the following: one or more facial landmarks ([0054], [0069]-[0070] including “a graph of an amalgamated position of right facial landmarks as well as a graph of an amalgamated position of left facial landmarks that are related to smiling of a subject of FIG. 11, and their interrelationship”, Figs. 1-4, Tables 1-12 see also [0055]-[0057]).
Regarding Claim 6, an interpretation of Eichler further discloses wherein the one or more symptoms include at least one of the following: facial paralysis ([0054], [0069]-[0070] including “a graph of an amalgamated position of right facial landmarks as well as a graph of an amalgamated position of left facial landmarks that are related to smiling of a subject of FIG. 11, and their interrelationship”, Figs. 1-4, Tables 5 see also [0004], [0055]-[0057]).
Regarding Claim 7, an interpretation of Eichler further discloses wherein the one or more biological parameters include at least one of the following: a blood pressure ([0040] including “a blood pressure measurement device (not shown) may be used as to acquire clinical measurement blood pressure data (not shown).”).
Regarding Claim 8, an interpretation of Eichler further discloses wherein the type of the at least one neurological event includes at least one of the following: an ischemic stroke ([0060] including “determined stroke type and its probability PT”, [0074]-[0075] including “information pertaining to the stroke type (ischemic. . .”).
Regarding Claim 9, an interpretation of Eichler further discloses wherein the receiving includes at least one of the following: receiving the data resulting from actively requiring the subject to perform an action ([0051]-[0052], [0066]-[0067] including “acquired from subject during a user interaction prompt of system”, [0072], Tables 1-12, Figs. 10-11).
Regarding Claim 11, an interpretation of Eichler further discloses wherein at least one of the receiving, the assigning, the determining, the generating the prediction, the triggering, and the generating the one or more user interfaces is performed in substantially real time ([0032] including “The systems of the disclosed technique are configured and operative to provide an indication of a stroke as soon (i.e., immediate, in real-time) as it is detected (i.e., estimated at a high likelihood, i.e., over a threshold probability).”, [0072]).
Regarding Claim 12, an interpretation of Eichler further discloses wherein the generating the one or more user interfaces includes arranging one or more graphical objects corresponding to the one or more symptoms, the prediction, the one or more alerts, in the one or more user interfaces in a predetermined order ([0061], [0074], [0076], Figs. 17A-B, 19).
Regarding Claim 13, an interpretation of Eichler discloses a system for diagnosing a neurological event in a subject (abstract) comprising:
at least one programmable processor ([0032], [0035]-[0036], [0038], Figs. 1-3, 8);
one or more sensors communicatively coupled to the at least one programmable processor, the one or more sensors including at least a video sensor and an audio sensor and being arranged at least one of directly on the subject, away from the subject, and any combination thereof ([0005], [0032], [0035], [0044]-[0045], Figs. 1-4, 8; Examiner notes that “being arranged at least one of directly on . . . away from . . . or any combination” discloses all variations of placement either the device is on or not on the person to sense them); and
a non-transitory machine-readable medium storing instructions that, when executed by the at least one programmable processor ([0032], [0035]-[0036], [0038]-[0039], [0054] Figs. 1-3, 8), cause the at least one programmable processor to perform operations comprising:
receiving, without prompting the subject to perform a task, data corresponding to one or more neurological symptoms associated with the subject, detected by the one or more sensors, ([0005], [0032] including “The processor is configured to receive clinical measurement data pertaining to the subject. The clinical measurement data is acquired from at least one sensor that is configured to sense at least one of image data, sound data, movement data, and tactile data pertaining to the subject. The processor is configured to extract from the clinical measurement data, potential stroke features”, [0040], [0051]-[0052], Figs. 1-4; Examiner notes that “at least one of the following sensors: one or more sensors positioned directly on the subject, one or more sensors being positioned away from the subject, or any combination” covers any sensor that senses the user), the at least one programmable processor being communicatively coupled to the one or more sensors ([0005], [0032], [0035], Figs. 1-4, 8);
assigning one or more values to the one or more detected symptoms ([0037], [0047] including “configured and operative to extract potential stroke features (e.g., attributes and their corresponding value) from the clinical measurement data”, [0048]-[0050], Figs. 3-4, 7-8)
wherein the assigning further includes extracting, using one or more analysis, one or more biological features from the data received from the one or more sensors ([0047]-[0050] including “The extraction of potential stroke features from different types of clinical measurement data”, [0070], Figs. 2-4, 13), the one or more biological features comprising at least one of one or more facial landmarks extracted from video data ([0044], [0048]-[0049], Figs. 2-4 see also [0054], [0192], Tables 1-12), and
determining a severity score for each of the one or more symptoms ([0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 7, 14, 16), the severity scores being determined using one or more second machine learning models ([0057], [0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 5-6, 14, 16 see also [0043]; more than 2 tables include recitations that they use “MLC” (aka machine learning classifier) to determine score for that particular “symptom”/subtest/category based on features. For example, Table 3 regards Horizontal eye movement (a gaze deficit) and Table 5 regards Facial palsy), the one or more second machine learning models including a plurality of machine learning models each trained, on a per-symptom basis, to score a degree of severity of a corresponding one of facial paralysis ([0054], [0057], [0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 5-6, 14, 16 see also [0043]; The reference discloses a plurality of “MLC” (aka machine learning classifier) and also per the Tables more than 2 tables include recitations that they use an MLC to determine score for that particular “symptom”/subtest/category based on symptom specific features. For example, Table 3 regards Horizontal eye movement (a gaze deficit) and Table 5 regards Facial palsy), gaze deficit ([0057], [0066], [0071], Tables 1-12, Figs. 5-6, 14, 16 see also [0043]), the one or more second machine learning models receiving the one or more extracted features/values as input ([0066], [0071] including “individual scores for various subtests”, Tables 1-12, Figs. 14, 16 see also [0043], [0057]; tables include recitations that they use “MLC” (aka machine learning classifier) to determine score for subtest/category based on features);
generating a prediction that the subject is experiencing at least one neurological event and at least a type of the at least one neurological event using a combination of the determined severity scores corresponding to the one or more symptoms ([0032] including “The systems of the disclosed technique are configured and operative to provide an indication of a stroke as soon (i.e., immediate, in real-time) as it is detected (i.e., estimated at a high likelihood, i.e., over a threshold probability).”, [0072], [0074], [0076], [0078] including “After quantifying each category of the NIHSS, the total score can define the stroke severity” Figs. 17A-B, 19 see also [0002], [0042], [0077]; stroke severity score includes “no stroke” option thus a determination of whether or not the user is suffering from a stroke), wherein the type of the at least one neurological event is determined based at least in part on a spatial pattern of severity scores across left-side and right-side body regions of the subject ([0032], [0060, [0072], [0074], [0076], [0078] including “After quantifying each category of the NIHSS, the total score can define the stroke severity”, Tables 1-12, Figs. 17A-B, 19 see also [0002], [0042], [0077]; taking in severity scores (scores) and determining a type and brain location);
triggering a generation of one or more alerts based on the prediction ([0042] including “systems 101 1, and 101 2 are configured and operative to alert the user, the user's relatives, and medical professionals, as will be detailed hereinbelow.”, [0075]-[0076], Figs. 17A-B, 19); and
generating one or more user interfaces for displaying the one or more alerts ([0037], [0042] including “systems 101 1, and 101 2 are configured and operative to alert the user, the user's relatives, and medical professionals, as will be detailed hereinbelow.”, [0075]-[0076], Figs. 7, 17A-B, 19).
An interpretation of Eichler may not explicitly disclose that extracting one or more biological features from the data received from the one or more sensors, is specifically done using one or more first machine learning models, and generating the one or more symptom values from the one or more biological features; the severity scores being determined using one or more second machine learning models that are different from the one or more first machine learning models, the one or more second machine learning models receiving the one or more assigned symptom values as input
However, in the same field of endeavor (medical devices), O’Donovan teaches extracting one or more biological features from the data received from the one or more sensors, is specifically done using one or more first machine learning models ([0064]-[0065], [0119], [0121] including “the pose estimator 708 may employ OpenPose, available from Carnegie Mellon University, to detect both pose and limb movement”, [0178]-[0179], Tables 3-4, Fig. 7 see also [0107], [0147], [0192]; Discloses one or more models for “extracting” biological features. Examiner notes that OpenPose applies ML model if more information is required on OpenPose please see the conclusion sections additional references), and
generating the one or more symptom values from the one or more biological features ([0066]-[0067], [0122]-[0123], Figs. 7, 10 see also [0107], [0148], [0178]-[0179], [0192], Tables 3-4);
the severity scores being determined using one or more second machine learning models that are different from the one or more first machine learning models ([0116], [0119], [0128]-[0129], [0142]-[0143], [0148], Figs. 7, 10 see also [0192]; pose estimator model etc. models are different from the scorer models.), the one or more second machine learning models receiving the one or more assigned symptom values as input ([0116], [0119], [0128], [0142]-[0143], [0148], Figs. 7, 10 see also [0192]; For example, pose estimator extracts data using ML, limb velocity determines additional information. the scorer models receives “assigned” data such as derived data from the limb velocity).
It would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention to have modified the data gathering and determination of a neurological event such as a stroke as recited by Eichler to include using ML models for determining biological features, assigning “symptom” values and using the symptom values to determine severity scores using symptom specific ML models as recited by O’Donovan because it improves diagnostic accuracy by providing a supplemental reference for comparison of a medical professionals determination ([0052]). Separately and additionally, It would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention to have modified the data gathering and determination of a neurological event such as a stroke as recited by Eichler to be combined with using ML models for determining biological features, assigning “symptom” values and using the symptom values to determine severity scores using symptom specific ML models as recited by O’Donovan because it is merely combining prior art elements (recited previously in this paragraph) according to known methods to yield predictable results, of determining a stroke based on the combined process of the elements from the Eicher and Donovan.
Regarding Claim 14, an interpretation of Eichler wherein the at least one neurological event includes a stroke (abstract, [0042]).
Regarding Claim 15, an interpretation of Eichler further discloses wherein the one or more sensors include at least one of the following: an audio sensor ([0005], [0032] including “The processor is configured to receive clinical measurement data pertaining to the subject. The clinical measurement data is acquired from at least one sensor that is configured to sense at least one of image data, sound data, movement data, and tactile data pertaining to the subject. The processor is configured to extract from the clinical measurement data, potential stroke features”, Figs. 1-4).
Regarding Claim 16, an interpretation of Eichler further discloses wherein the one or more symptoms include at least one of the following: one or more symptoms determined based on one or more physiological responses from the subject ([0054], [0060], Figs. 1-4, Tables 1-12 see also [0055]-[0057]).
Regarding Claim 17, an interpretation of Eichler further discloses wherein the one or more physiological responses include at least one of the following: one or more facial landmarks ([0054], [0069]-[0070] including “a graph of an amalgamated position of right facial landmarks as well as a graph of an amalgamated position of left facial landmarks that are related to smiling of a subject of FIG. 11, and their interrelationship”, Figs. 1-4, Tables 1-12 see also [0055]-[0057]).
Regarding Claim 18, an interpretation of Eichler further discloses wherein the one or more symptoms include at least one of the following: facial paralysis ([0054], [0069]-[0070] including “a graph of an amalgamated position of right facial landmarks as well as a graph of an amalgamated position of left facial landmarks that are related to smiling of a subject of FIG. 11, and their interrelationship”, Figs. 1-4, Tables 5 see also [0004], [0055]-[0057]).
Regarding Claim 19, an interpretation of Eichler further discloses wherein the one or more biological parameters include at least one of the following: a blood pressure ([0040] including “a blood pressure measurement device (not shown) may be used as to acquire clinical measurement blood pressure data (not shown).”).
Regarding Claim 20, an interpretation of Eichler further discloses wherein the type of the at least one neurological event includes at least one of the following: an ischemic stroke ([0060] including “determined stroke type and its probability PT”, [0074]-[0075] including “information pertaining to the stroke type (ischemic. . .”).
Claim Rejections - 35 USC § 103
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Eichler in view of O’Donovan in further view of US 20210106238 to Strasser et al. (hereinafter Strasser) US 10638938 to Tzvieli et al. (hereinafter Tzvieli)
Regarding Claim 10, an interpretation of Eichler further discloses continuously monitoring the subject using the one or more sensors, wherein the continuously monitoring is performed without prompting the subject to perform the task ([0040], [0042], [0047], [0051]-[0052], [0072] including “continuously tracks a detected and ongoing stroke condition in real-time (i.e., real-time diagnosis)”);
determining, one or more new symptom measurements ([0074], Fig. 17B; receives additional sensor data adds new symptom values based on new sensing modality);
updating, using the at least one processor, the determined severity score for each of the one or more symptoms, and the generated prediction, in response to the one or more new measurements ([0042] including “systems 100 1 and 100 2 to monitor, detect, and alert to changing trends in the clinical measurement data (e.g., speech irregularities get progressively worse, etc.), so as to facilitate early estimation and detection of a stroke condition before it occurs (upcoming stroke event).”, [0066], [0071], [0074] Figs. 14, 16, 19 see also [0040], [0053], [0072]-[0073], tables 1-12; when clinical data is gathered it generates the respective scores);
triggering, using the at least one processor, a generation of one or more updated alerts based on the updated prediction ([0042] including “systems 101 1, and 101 2 are configured and operative to alert the user, the user's relatives, and medical professionals, as will be detailed hereinbelow.”, [0075]-[0076], Figs. 17A-B, 19; the alert is based on current prediction); and
generating, using the at least one processor, one or more updated user interfaces for displaying the one or more updated alerts ([0037], [0042] including “systems 101 1, and 101 2 are configured and operative to alert the user, the user's relatives, and medical professionals, as will be detailed hereinbelow.”, [0075]-[0076], Figs. 7, 17A-B, 19; the alert interface is based on current prediction).
an interpretation of Eichler may not explicitly disclose determining, based on the continuous monitoring, one or more new symptom values and updating severity scores based on the new symptom values.
However, in the same field of endeavor (medical diagnostic system), O’Donovan teaches stroke determination based on a sensed values continuously ([0103]-[0105], [0118] see also [0106]-[0107], [0192]) determining based on the continuous monitoring one or more new symptom values ([0103]-[0105], [0118] see also [0106]-[0107], [0192]) updating severity scores based on the new symptom values ([0103]-[0105], [0118] see also [0106]-[0107], [0192]). O’Donovan further discloses
It would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention to have modified the data gathering and determination of a neurological event such as a stroke as recited by Eichler to include continuously gathering data, updating symptom values and updating severity scores using the symptom values as recited by O’Donovan because it improves diagnostic accuracy by providing a supplemental reference for comparison of a medical professionals determination ([0052]). Separately and additionally, It would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention to have modified the data gathering and determination of a neurological event such as a stroke as recited by Eichler to the specifically be combined with continuously gathering data, updating symptom values and updating severity scores using the symptom values by O’Donovan because it is merely combining prior art elements (recited previously in this paragraph) according to known methods to yield predictable results, of determining a stroke based on the combined process of the elements from the Eicher and Donovan.
While Eichler discloses the data extract can be done on frames of a video within a time range ([0048]) and O’Donovan discloses continuously gathering data and determining information “ over a period of time represented by the sequence of video frames” ([0084]-[0085]), an interpretation of Eichler in view of O’Donovan may not explicitly disclose comprises performing repeated data-acquisition windows of a predetermined window duration recurring throughout an ongoing monitoring session.
However, in the same field of endeavor (medical devices), Tzvieli teaches performing repeated data-acquisition windows of a predetermined window duration recurring throughout an ongoing monitoring session (Col 24:18-33 including “a computer may receive a stream of measurements, taken while the user wears an HMS with coupled cameras and/or other sensors during the day, and periodically evaluate measurements that fall within a sliding window of a certain size.”, Col 264:36 including “Time series analysis may involve various forms of processing involving segmenting data”; claims recites gathering data continuously, thus the windows are subsets of the continuously gathered data. The sliding window is a recurring set time window which recurs throughout the larger the gathered data. Furthermore, the reference also discloses data segmentation or breaking down a large set of time series data into a series of equal time segments).
It would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention to have modified the continuous data gathering and determination of a stroke as recited by Eichler in view of O’Donovan to include having recurring periods of windowed acquired data as recited by Tzvieli because it is merely combining using known methods the prior art element of gathering data/windowing subsets of data from a stream (from Tzvieli) with the known prior art element of data gathering and stroke analysis with data extraction and neuroglial event detection using ML models (by Eichler in view of O’Donovan) to predictably make a determination of whether or not a stroke has occurred. Phrased differently it is merely combining prior art elements according to known methods to yield predictable results.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US 20210202090 see Abstract, Fig. 8A
US 20170007167 Figs. 1, 5, 7
Gines Hidalgo Martinez, OpenPose: Whole-Body Pose Estimation, 2019, May, Carnegie Mellon University, https://publications.ri.cmu.edu/openpose-whole-body-pose-estimation
Taehyung Kim et al. Detecting Facial Region and Landmarks at Once via Deep Network. Sensors (Basel). 2021 Aug 9;21(16):5360. doi: 10.3390/s21165360. PMID: 34450804; PMCID: PMC8401714.
NIH, NIH Stroke Scale, https://www.ninds.nih.gov/health-information/stroke/assess-and-treat/nih-stroke-scale#toc-how-to-use-the-nih-stroke-scale, viewed on 8/13/26
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAMES R MOSS whose telephone number is (571)272-3506. The examiner can normally be reached Monday - Friday (9:30 am - 5:30 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, Unsu Jung can be reached at (571)272-8506. 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.
/James Moss/Examiner, Art Unit 3792
Prosecution Insights