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 .
DETAILED ACTION
Response to Amendment
In the Amendment dated 02 October 2025, the following occurred:
Claims 1, 3-5, 9, 11, and 14-17 were amended.
Claims 1-20 are pending.
Information Disclosure Statement
The Information Disclosure Statement (IDS) submitted on 10 September 2025 is in compliance with the provisions of 37 CFR 1.97 and has been fully considered by the Examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1, 9, and 15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1
The claims recite a system and methods for training, testing, and validating systems for continuous monitoring of the human state, and therefore meet step 1.
Step 2A1
The limitations of (Claim 15 being representative) inducing a target state in a subject; recording physiological data comprising at least one of electrocardiogram (ECG) data, electroencephalogram (EEG) data, photoplethysmogram (PPG) data, skin conductance data, and eye gaze data from the subject over a continuous duration greater than or equal to a threshold duration; segmenting the recorded physiological data into a plurality of physiological data windows, each of the plurality of physiological data windows being of a pre-determined duration of less than the threshold duration; labeling each of the plurality of physiological data windows with a ground truth label indicative of the target state; storing the plurality of physiological data windows and the ground truth label…; selecting a training data pair, comprising the plurality of physiological data windows of pre-determined duration, and the ground truth label indicative of the target state; mapping the plurality of physiological data windows to a corresponding plurality of state predictions using the state prediction model; determining a loss for the plurality of state predictions based on a loss function and the ground truth label; and updating parameters of the state prediction model based on the determined loss, wherein updating the parameters of the state prediction model based on the determined loss comprises calculating a gradient of the loss function and adjusting the parameters in the direction that minimizes the loss, as drafted, is a process that, under the broadest reasonable interpretation, falls in the grouping of certain methods of organizing human activity (i.e., managing personal behavior including following rules or instructions).
That is, other than reciting a system and methods implemented by a processor and non-transitory memory (a general-purpose computing device), the claimed invention amounts to managing personal behavior or interaction between people. 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. The Examiner notes that the state prediction model is simple enough to be included in the abstract idea. Accordingly, the claim recites an abstract idea.
Step 2A2
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of a processor (claim 9) and a non-transitory memory (claims 1, 9, and 15) that implement the identified abstract idea. The computing elements are not exclusively described by the applicant and are recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components. See MPEP 2106.05(f). 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.
Step 2B
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 element of using a processor to perform the noted steps amounts to no more than mere instructions to apply the exception using a generic computer component cannot provide an inventive concept (“significantly more”). As such the claim is not patent eligible.
Claims 2-8, 10-14, and 16-20 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide an inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination. Claim 2 merely describes inducing the target state in the subject. Claims 3 and 11 merely describe the threshold duration. Claim 4 merely describes the pre-determined duration. Claims 5 and 12 merely describe filtering the plurality of shorter analysis windows. Claims 6 and 14 merely describe segmenting the recorded physiological data. Claim 7 merely describes predicting a state. Claim 8 merely describes determining a plurality of performance metrics and aggregating the plurality of performance metrics. Claim 10 merely describes administering a cognitive task and adjusting a level of cognitive load. Claim 13 merely describes the pre-determined duration of the plurality of shorter analysis windows. Claim 16 merely describes selecting the training data pair. Claim 17 merely describes the loss function. Claim 18 merely describes determining a state discriminatory power. Claim 19 merely describes validating the updated state prediction model. Claim 20 merely describes the separate validation set of physiological data windows.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5 and 11-13 are rejected under 35 U.S.C. 103 as being unpatentable over Lemos (U.S. 2007/0066916) in view of Jernigan (U.S. 2022/0071535) and Ren at al. (U.S. 2025/0221647), referred to hereinafter as Ren.
REGARDING CLAIM 1
Lemos teaches the claimed method comprising:
recording physiological data […] from a subject in a target state over a continuous duration equal to or greater than a threshold duration; [Claim 1 teaches collecting physiological data from a subject. Para. 0022 teaches a subject in a desired (target) state. Para. 0096 teaches collecting data from a subject over a predetermined time period (a threshold duration).]
Lemos may not explicitly teach
…comprising at least one of electrocardiogram (ECG) data, electroencephalogram (EEG) data, photoplethysmogram (PPG) data, skin conductance data, and eye gaze data…
segmenting the recorded physiological data into a plurality of shorter analysis windows, each analysis window being of a pre-determined duration of less than the threshold duration;
labeling the plurality of shorter analysis windows with a ground truth label indicative of the target state;
detecting in each of the plurality of shorter analysis windows occurrence of one or more of a pre-determined set of manifestations of the target state;
storing the plurality of shorter analysis windows and the ground truth label in non-transitory memory; and
training a state prediction model for real-time state detection using the stored plurality of shorter analysis windows and the stored ground truth label.
However, Jernigan teaches the following:
…comprising at least one of electrocardiogram (ECG) data, electroencephalogram (EEG) data, photoplethysmogram (PPG) data, skin conductance data, and eye gaze data… [Para. 0125 teaches electrocardiogram (ECG) data. Para. 0169 teaches electroencephalogram (EEG) data. Para. 0049 teaches PPG data. Para. 0359 teaches skin conductance data. Para. 0072 teaches eye gaze data.]
segmenting the recorded physiological data into a plurality of shorter analysis windows, each analysis window being of a pre-determined duration of less than the threshold duration; [Para. 0240 teaches adding a segment (shorter analysis window) identifier to each sample of time series data. Para. 0250 teaches a benefit of segment implementation is the ability to perform analysis on windows of data.]
labeling the plurality of shorter analysis windows with a ground truth label indicative of the target state; [Para. 0350 teaches approximating ground truth labels for state. Para. 0377 teaches labeling windows with a ground truth label indicative of a flow experience (the target state).]
detecting in each of the plurality of shorter analysis windows occurrence of one or more of a pre-determined set of manifestations of the target state; [Para. 0005 teaches flow (the target state) occurs at the balance of challenge and skills. If skills are low and challenge is high, anxiety occurs. Para. 0016 teaches detecting breathing data to determine the subject’s mental state.]
storing the plurality of shorter analysis windows and the ground truth label in non-transitory memory. [To train the system, labeled ground truth data is stored (e.g., as training sets) in the memory. Para. 0332 teaches event markers are treated as ground truth labels and are available during training. Para. 0418 teaches windows are stored in the training set.]
training a state prediction model for real-time state detection using the stored plurality of shorter analysis windows and the stored ground truth label. [Para. 0333 teaches training a classifier using the stored windows and the ground truth.]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos to segment the data into windows, label the windows, detect manifestations, store the windows with ground truth labels, and train a model as taught by Jernigan with the motivation of improving compliance (see Jernigan at Para. 0012).
Lemos in view of Jernigan may not explicitly teach
labeling the plurality of shorter analysis windows with a secondary ground truth label indicative of the detected manifestations of the target state, wherein the secondary ground truth label indicative of the detected manifestations of the target state comprises a level or intensity of each of a plurality of manifestations in the predetermined set of manifestations of the target state;
However, Ren teaches the following:
labeling the plurality of shorter analysis windows with a secondary ground truth label indicative of the detected manifestations of the target state, wherein the secondary ground truth label indicative of the detected manifestations of the target state comprises a level or intensity of each of a plurality of manifestations in the predetermined set of manifestations of the target state; [Para. 0027 teaches labeling each of the psychomotor vigilance test sessions (shorter analysis windows of a testing period) with a corrected drowsiness level label (secondary ground truth label) indicative of circadian rhythm (manifestation of the target state).]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan to label the windows with secondary ground truth labels as taught by Ren with the motivation of improving the accuracy of drowsiness level predictions (see Ren at Para. 0045).
REGARDING CLAIM 2
Lemos in view of Jernigan and Ren teaches the claimed method of claim 1.
Jernigan further teaches
inducing the target state in the subject by: administering one or more of a cognitive task, and an audio-visual stimuli to elicit the target state; [Para. 0351 teaches inducing the flow (target) state in the user by administering game-playing (cognitive) tasks.]
and adjusting a level of the target state by varying a complexity of the cognitive task, or adjusting an intensity of the audio-visual stimuli. [Para. 0017 teaches adjusting a level of the mental state (overload, flow, or underload) by altering the difficulty of the task.]
REGARDING CLAIM 3
Lemos in view of Jernigan and Ren teaches the claimed method of claim 1.
Jernigan further teaches
wherein the threshold duration is five minutes. [Para. 0073 teaches a predetermined period of time is five minutes.]
REGARDING CLAIM 4
Lemos in view of Jernigan and Ren teaches the claimed method of claim 1.
Jernigan further teaches
wherein the pre-determined duration of the plurality of shorter analysis windows is 30 seconds; [Para. 0138 teaches the window is 30 seconds.]
REGARDING CLAIM 5
Lemos in view of Jernigan and Ren teaches the claimed method of claim 1.
Cheng further teaches
filtering the plurality of shorter analysis windows based on a plurality of respective secondary ground truth labels indicative of manifestations of the target state. [Para. 0134 teaches adjusting the label associated with each entry in the series of consecutive entries so as to delete (filter) a breathing event (shorter analysis window of the target state) represented by the series of consecutive entries (manifestations).]
REGARDING CLAIM 11
Claim 11 is analogous to Claim 3, thus Claim 11 is similarly analyzed and rejected in a manner consistent with the rejection of Claim 3.
REGARDING CLAIM 12
Claim 12 is analogous to Claim 5, thus Claim 12 is similarly analyzed and rejected in a manner consistent with the rejection of Claim 5.
REGARDING CLAIM 13
Claim 13 is analogous to Claim 4, thus Claim 13 is similarly analyzed and rejected in a manner consistent with the rejection of Claim 4.
Claims 6 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Ren, and Cheng et al. (U.S. 2024/0057964), referred to hereinafter as Cheng.
REGARDING CLAIM 6
Lemos in view of Jernigan and Ren teaches the claimed method of claim 1.
Jernigan further teaches
wherein segmenting the recorded physiological data into the plurality of shorter analysis windows includes selecting a window size… [Para. 0283 teaches requesting (selecting) a window size.]
Lemos in view of Jernigan and Ren may not explicitly teach
…and splitting the recorded physiological data into consecutive analysis windows by a predetermined step duration of less than the pre-determined duration of the plurality of shorter analysis windows
However, Cheng teaches the following:
…and splitting the recorded physiological data into consecutive analysis windows by a predetermined step duration of less than the pre-determined duration of the plurality of shorter analysis windows. [Para. 0116 teaches splitting the recorded physiological data (15 seconds) into consecutive segments (windows) by a predetermined step duration (.016 seconds).]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan and Ren to label the windows with secondary ground truth labels as taught by Cheng with the motivation of gaining insights into the health of the patient (see Cheng at Para. 0035).
REGARDING CLAIM 7
Lemos in view of Jernigan and Ren teaches the claimed method of claim 1.
Lemos in view of Jernigan and Ren may not explicitly teach
predicting a state for each of the plurality of shorter analysis windows using a mathematical model, wherein the mathematical model is configured to map the plurality of shorter analysis windows to a plurality of state predictions.
However, Cheng teaches the following:
predicting a state for each of the plurality of shorter analysis windows using a mathematical model, wherein the mathematical model is configured to map the plurality of shorter analysis windows to a plurality of state predictions. [Para. 0098 teaches producing a sequence of detections. Each detection is representative of a separate prediction made independently by the (mathematical) model.]
Motivation to combine the teaching of Cheng with the teachings of Lemos, Jernigan, and Ren is the same as that used with respect to claim 6 and is therefore reiterated here.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Ren, Cheng, and Sharma et al. (U.S. 2024/0095455), referred to hereinafter as Sharma.
REGARDING CLAIM 8
Lemos in view of Jernigan, Ren, and Cheng teaches the claimed method of claim 7.
Cheng further teaches
determining a plurality of performance metrics for the mathematical model, one for each of the plurality of state predictions, using the ground truth label, wherein the plurality of performance metrics include at least one of precision, recall, F1 score, and accuracy; and [Para. 0111 teaches determining the F1 score and accuracy of the (mathematical) model.]
Lemos in view of Jernigan, Ren, and Cheng may not explicitly teach
aggregating the plurality of performance metrics to produce an aggregate performance metric for the recorded physiological data, wherein the aggregate performance metric is a weighted average of the plurality of performance metrics.
However, Sharma teaches the following:
aggregating the plurality of performance metrics to produce an aggregate performance metric for the recorded physiological data, wherein the aggregate performance metric is a weighted average of the plurality of performance metrics. [Para. 0041 teaches a weighted average of precision and recall (performance metrics).]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan, Ren, and Cheng to produce an aggregate performance metric as taught by Sharma with the motivation of improving accuracy (see Sharma at Para. 0038).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Ren, Teplitzky et al. (U.S. 2020/0176122), referred to hereinafter as Teplitzky.
REGARDING CLAIM 9
Lemos teaches the claimed state prediction model training device comprising: a processor; and a non-transitory memory storing instructions that, when executed by the processor, cause the system to:
record physiological data […] from the subject over a continuous duration equal to or greater than a threshold duration; [Claim 1 teaches collecting physiological data from a subject. Para. 0022 teaches a subject in a desired (target) state. Para. 0096 teaches collecting data from a subject over a predetermined time period (a threshold duration).]
Lemos may not explicitly teach
induce the target state in a subject…;
…comprising at least one of electrocardiogram (ECG) data, electroencephalogram (EEG) data, photoplethysmogram (PPG) data, skin conductance data, and eye gaze data…
segment the recorded physiological data into a plurality of shorter analysis windows, each analysis window being of a pre-determined duration of equal to or less than the threshold duration;
label each of the plurality of shorter analysis windows with a ground truth label indicative of the target state;
detect in each of the plurality of shorter analysis windows occurrence of one or more of a pre-determined set of manifestations of the target state;
store the plurality of shorter analysis windows and the ground truth label in the non-transitory memory;
However, Jernigan teaches the following:
induce the target state in the subject…; [Para. 0351 teaches inducing the flow (target) state in the user.]
…comprising at least one of electrocardiogram (ECG) data, electroencephalogram (EEG) data, photoplethysmogram (PPG) data, skin conductance data, and eye gaze data… [Para. 0125 teaches electrocardiogram (ECG) data. Para. 0169 teaches electroencephalogram (EEG) data. Para. 0049 teaches PPG data. Para. 0359 teaches skin conductance data. Para. 0072 teaches eye gaze data.]
segment the recorded physiological data into a plurality of shorter analysis windows, each analysis window being of a pre-determined duration of equal to or less than the threshold duration; [Para. 0240 teaches adding a segment (shorter analysis window) identifier to each sample of time series data. Para. 0250 teaches a benefit of segment implementation is the ability to perform analysis on windows of data.]
label each of the plurality of shorter analysis windows with a ground truth label indicative of the target state; [Para. 0350 teaches approximating ground truth labels for state. Para. 0377 teaches labeling windows with a ground truth label indicative of a flow experience (the target state).]
detect in each of the plurality of shorter analysis windows occurrence of one or more of a pre-determined set of manifestations of the target state; [Para. 0005 teaches flow (the target state) occurs at the balance of challenge and skills. If skills are low and challenge is high, anxiety occurs. Para. 0016 teaches detecting breathing data to determine the subject’s mental state.]
store the plurality of shorter analysis windows and the ground truth label in the non-transitory memory. [To train the system, labeled ground truth data is stored (e.g., as training sets) in the memory. Para. 0332 teaches event markers are treated as ground truth labels and are available during training. Para. 0418 teaches windows are stored in the training set.]
Motivation to combine the teaching of Jernigan with the teaching of Lemos is the same as that used with respect to claim 1 and is therefore reiterated here.
Lemos in view of Jernigan may not explicitly teach
…during a driving simulation…
label each of the plurality of shorter analysis windows with a secondary ground truth label indicative of the detected manifestations of the target state, wherein the secondary ground truth label indicative of the detected manifestations of the target state comprises a level or intensity of each of a plurality of manifestations in the predetermined set of manifestations of the target state;
However, Ren teaches the following:
…during a driving simulation… [Para. 0004 teaches in-vehicle driver drowsiness detection. Para. 0178 teaches the training data is generated in a simulation.]
label each of the plurality of shorter analysis windows with a secondary ground truth label indicative of the detected manifestations of the target state, wherein the secondary ground truth label indicative of the detected manifestations of the target state comprises a level or intensity of each of a plurality of manifestations in the predetermined set of manifestations of the target state; [Para. 0027 teaches labeling each of the psychomotor vigilance test sessions (shorter analysis windows of a testing period) with a corrected drowsiness level label (secondary ground truth label) indicative of circadian rhythm (manifestation of the target state).]
Motivation to combine the teaching of Ren with the teachings of Lemos and Jernigan is the same as that used with respect to claim 1 and is therefore reiterated here.
Lemos in view of Jernigan and Ren may not explicitly teach
select a training data pair, comprising the plurality of physiological data windows of pre-determined duration, and the ground truth label indicative of the target state;
map the plurality of physiological data windows to a corresponding plurality of state predictions using a state prediction model;
determine a loss for the plurality of state predictions based on a loss function and the ground truth label; and
update parameters of the state prediction model based on the determined loss.
However, Teplitzky teaches the following:
select a training data pair, comprising the plurality of physiological data windows of pre-determined duration, and the ground truth label indicative of the target state; [Para. 0060 teaches receiving training data including physiological data labeled with appropriate classifications.]
map the plurality of physiological data windows to a corresponding plurality of state predictions using a state prediction model; [Para. 0061 teaches mapping the physiological data to multiple corresponding classifications using the model.]
determine a loss for the plurality of state predictions based on a loss function and the ground truth label; and [Para. 0061 teaches determining a loss for the multiple classifications based on a loss function.]
update parameters of the state prediction model based on the determined loss. [Para. 0061 teaches determining which result classification should be weighted more based on a loss function.]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan and Ren to select training data, map the data to classifications, determine a loss, and update parameters as taught by Teplitzky with the motivation of improving the accuracy and speed of medical treatment and alerts for patients (see Teplitzky at Para. 0020).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Ren, Teplitzky, and Mishra Ramanathan et al. (U.S. 2019/0159715), referred to hereinafter as Mishra.
REGARDING CLAIM 10
Lemos in view of Jernigan, Ren, and Teplitzky teaches the claimed method of claim 9.
Jernigan further teaches
adjust a level of cognitive load experienced by the subject by varying a complexity of the cognitive task… [Para. 0017 teaches adjusting a level of the mental state (overload, flow, or underload) by altering the difficulty of the task.]
Lemos in view of Jernigan, Ren, and Teplitzky may not explicitly teach
…a frequency of task stimuli, and a duration for which the cognitive task is performed by the subject.
administer a cognitive task to the subject to elicit the target state, the cognitive task comprising one of an n-back task, a simulated driving task, and a pattern recognition task;
However, Mishra teaches the following:
…a frequency of task stimuli, and a duration for which the cognitive task is performed by the subject. [Para. 0104 teaches a frequency of task stimuli. Para. 0101 teaches varying duration for auditory stimuli.]
administer a cognitive task to the subject to elicit the target state, the cognitive task comprising one of an n-back task, a simulated driving task, and a pattern recognition task; [Para. 0100 teaches a task comprising navigating a moving vehicle (simulated driving).]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan, Ren, and Teplitzky to administer a simulated driving task, and vary frequency and duration of task stimuli as taught by Mishra with the motivation of improving quality of life (see Mishra at Para. 0004).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Ren, Teplitzky, and Sullivan et al. (U.S. 2016/0000349), referred to hereinafter as Sullivan.
REGARDING CLAIM 14
Lemos in view of Jernigan, Ren, and Teplitzky teaches the claimed method of claim 9.
Lemos in view of Jernigan, Ren, and Teplitzky may not explicitly teach
segment the recorded physiological data into the plurality of shorter analysis windows by overlapping consecutive analysis windows by a predetermined step duration of one second.
However, Sullivan teaches the following:
segment the recorded physiological data into the plurality of shorter analysis windows by overlapping consecutive analysis windows by a predetermined step duration of one second. [Para. 0090 teaches a one second overlap.]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the device of Lemos in view of Jernigan, Ren, and Teplitsky to record physiological data with a one second overlap as taught by Sullivan with the motivation of improving the ability to treat life-threatening conditions (see Sullivan at Para. 0010).
Claims 15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Teplitzky, and Eisenhuth et al. (U.S. 2025/0336539), referred to hereinafter as Eisenhuth.
REGARDING CLAIM 15
Lemos teaches the claimed method for training a state prediction model, comprising:
recording physiological data […] from the subject over a continuous duration equal to or greater than a threshold duration; [Claim 1 teaches collecting physiological data from a subject. Para. 0022 teaches a subject in a desired (target) state. Para. 0096 teaches collecting data from a subject over a predetermined time period (a threshold duration).]
Lemos may not explicitly teach
inducing the target state in the subject;
…comprising at least one of electrocardiogram (ECG) data, electroencephalogram (EEG) data, photoplethysmogram (PPG) data, skin conductance data, and eye gaze data…
segmenting the recorded physiological data into a plurality of shorter analysis windows, each analysis window being of a pre-determined duration of equal to or less than the threshold duration;
labeling each of the plurality of shorter analysis windows with a ground truth label indicative of the target state;
and storing the plurality of shorter analysis windows and the ground truth label in the non-transitory memory.
However, Jernigan teaches the following:
inducing the target state in the subject; [Para. 0351 teaches inducing the flow (target) state in the user.]
…comprising at least one of electrocardiogram (ECG) data, electroencephalogram (EEG) data, photoplethysmogram (PPG) data, skin conductance data, and eye gaze data… [Para. 0125 teaches electrocardiogram (ECG) data. Para. 0169 teaches electroencephalogram (EEG) data. Para. 0049 teaches PPG data. Para. 0359 teaches skin conductance data. Para. 0072 teaches eye gaze data.]
segmenting the recorded physiological data into a plurality of shorter analysis windows, each analysis window being of a pre-determined duration of equal to or less than the threshold duration; [Para. 0240 teaches adding a segment (shorter analysis window) identifier to each sample of time series data. Para. 0250 teaches a benefit of segment implementation is the ability to perform analysis on windows of data.]
labeling each of the plurality of shorter analysis windows with a ground truth label indicative of the target state; [Para. 0350 teaches approximating ground truth labels for state. Para. 0377 teaches labeling windows with a ground truth label indicative of a flow experience (the target state).]
storing the plurality of shorter analysis windows and the ground truth label in the non-transitory memory. [To train the system, labeled ground truth data is stored (e.g., as training sets) in the memory. Para. 0332 teaches event markers are treated as ground truth labels and are available during training. Para. 0418 teaches windows are stored in the training set.]
Motivation to combine the teaching of Jernigan with the teaching of Lemos is the same as that used with respect to claim 1 and is therefore reiterated here.
Lemos in view of Jernigan may not explicitly teach
selecting a training data pair, comprising the plurality of physiological data windows of pre-determined duration, and the ground truth label indicative of the target state;
mapping the plurality of physiological data windows to a corresponding plurality of state predictions using the state prediction model;
determining a loss for the plurality of state predictions based on a loss function and the ground truth label;
and updating parameters of the state prediction model based on the determined loss.
However, Teplitzky teaches the following:
selecting a training data pair, comprising the plurality of physiological data windows of pre-determined duration, and the ground truth label indicative of the target state; [Para. 0060 teaches receiving training data including physiological data labeled with appropriate classifications.]
mapping the plurality of physiological data windows to a corresponding plurality of state predictions using the state prediction model; [Para. 0061 teaches mapping the physiological data to multiple corresponding classifications using the model.]
determining a loss for the plurality of state predictions based on a loss function and the ground truth label; and [Para. 0061 teaches determining a loss for the multiple classifications based on a loss function.]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan to select training data, map the data to classifications, and determine a loss as taught by Teplitzky with the motivation of improving the accuracy and speed of medical treatment and alerts for patients (see Teplitzky at Para. 0020).
Lemos in view of Jernigan and Teplitzky may not explicitly teach
updating parameters of the state prediction model based on the determined loss, wherein updating the parameters of the state prediction model based on the determined loss comprises calculating a gradient of the loss function and adjusting the parameters in the direction that minimizes the loss.
However, Eisenhuth teaches the following:
updating parameters of the state prediction model based on the determined loss, wherein updating the parameters of the state prediction model based on the determined loss comprises calculating a gradient of the loss function and adjusting the parameters in the direction that minimizes the loss. [Para. 0071 teaches calculating the gradient of the loss function. This process includes updating one or more parameters.]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan and Teplitzky to calculate the gradient of the loss function and adjust the parameters as taught by Eisenhuth with the motivation of improving the processing of health data (see Eisenhuth at Para. 0023).
REGARDING CLAIM 17
Lemos in view of Jernigan, Teplitzky, and Eisenhuth teaches the claimed method of claim 15.
Eisenhuth further teaches
wherein the loss function comprises one of a mean squared error function or across-entropy loss function. [Para. 0071 teaches loss function such as mean squared error and cross entropy loss.]
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Teplitzky, Eisenhuth, and Ren.
REGARDING CLAIM 16
Lemos in view of Jernigan, Teplitzky, and Eisenhuth teaches the claimed method of claim 15.
Lemos in view of Jernigan, Teplitzky, and Eisenhuth may not explicitly teach
wherein selecting the training data pair further comprises filtering the plurality of physiological data windows based on secondary ground truth labels associated with detected manifestations of the target state, and wherein the secondary ground truth label is indicative of a level or intensity of the detected manifestations of the target state.
However, Ren teaches the following:
wherein selecting the training data pair further comprises filtering the plurality of physiological data windows based on secondary ground truth labels associated with detected manifestations of the target state, and wherein the secondary ground truth label is indicative of a level or intensity of the detected manifestations of the target state. [Para. 0027 teaches labeling each of the psychomotor vigilance test sessions (shorter analysis windows of a testing period) with a corrected drowsiness level label (secondary ground truth label) indicative of circadian rhythm (manifestation of the target state).]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan, Teplitzky, and Eisenhuth to filter the physiological data as taught by Ren with the motivation of improving the accuracy of drowsiness level predictions (see Ren at Para. 0045).
Claims 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Lemos in view of Jernigan, Teplitzky, Eisenhuth, and Jain et al. (U.S. 2017/0245759), referred to hereinafter as Jain.
REGARDING CLAIM 18
Lemos in view of Jernigan, Teplitzky, and Eisenhuth teaches the claimed method of claim 15.
Lemos in view of Jernigan, Teplitzky, and Eisenhuth may not explicitly teach
determining a state discriminatory power of the state prediction model by comparing predictions generated for a first plurality of physiological data windows acquired while a first state was induced in the subject with predictions generated for a second plurality of physiological data windows acquired while a second state was induced in the subject.
However, Jain teaches the following:
determining a state discriminatory power of the state prediction model by comparing predictions generated for a first plurality of physiological data windows acquired while a first state was induced in the subject with predictions generated for a second plurality of physiological data windows acquired while a second state was induced in the subject. [Para. 0145 teaches a system that monitors physiological data. Para. 0312 teaches a discriminative multi-class classifier (e.g., an emotional state classifier) is built from extracted feature representations from the processed local facial regions of the patients in the reference database. Discriminative classifiers are trained on data from a wide range of patients with n-fold cross-validation.]
Therefore, it would have been prima facie obvious to one of ordinary skill in the art of computerized healthcare, before the effective filling date of the invention, to modify the method of Lemos in view of Jernigan, Teplitzky, and Eisenhuth to compare predictions as taught by Jain with the motivation of improving patient safety (see Jain at Para. 0005).
REGARDING CLAIM 19
Lemos in view of Jernigan, Teplitzky, and Eisenhuth teaches the claimed method of claim 15.
Lemos in view of Jernigan, Teplitzky, and Eisenhuth may not explicitly teach
validating the updated state prediction model by comparing a set of state predictions against a separate validation set of data windows and associated ground truth labels.
However, Jain teaches the following:
validating the updated state prediction model by comparing a set of state predictions against a separate validation set of data windows and associated ground truth labels. [Para. 0189 teaches validating by comparing the heart rate recovery against prior heart rate recovery data, e.g., a baseline heart rate recovery.]
Motivation to combine the teaching of Jain with the teachings of Lemos, Jernigan, Teplitzky, and Eisenhuth are the same as that used with respect to claim 18 and are therefore reiterated here.
REGARDING CLAIM 20
Lemos in view of Jernigan, Teplitzky, Eisenhuth, and Jain teaches the claimed method of claim 19.
Jain further teaches
wherein the separate validation set of physiological data windows is derived from a different continuous recording session of data from the subject or a different subject. [Para. 0189 teaches validating by comparing the heart rate recovery against prior heart rate recovery data, e.g., a baseline heart rate recovery for the patient.]
Response to Arguments
Rejection under 35 U.S.C. § 101
Regarding the rejection of Claims 1-20, the Examiner has considered the Applicant’s arguments; however, the arguments are not persuasive. Any arguments inadvertently not addressed are unpersuasive for at least the following reasons. Applicant argues:
Regardless of whether the claims involve “a person’s interaction with a computer,” the approach of amended claim 15 recites a specific technical method for training machine learning models using physiological data, not managing human behavior or organizing human activity.
Regarding (a), the Examiner respectfully disagrees. MPEP 2106. 04(a)(2)(II) states that a claimed invention is directed to certain methods of organizing human activity if the identified claim elements contain limitations that encompass fundamental economic principles or practices, commercial or legal interactions, or managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions). The Examiner submits that the identified claim elements represent a series of rules or instructions that a person or persons, with or without the aid of a computer, would follow to monitor human states. Furthermore, the Examiner submits that healthcare itself inherently represents the organization of human activity. Applicant has not pointed to anything in the claims that fall outside of this characterization. Applicant’s assertion that amended claim 15 recites a specific technical method for training machine learning models is not reflected in the claims, as machine learning is not recited. Because the claim elements fall under a series of rules or instructions that a person or persons would follow to monitor human states, the claimed invention is directed to an abstract idea.
…amended claim 15 addresses the following technical problem identified in the specification: the “dynamic and variable nature of physiological manifestations of underlying psychophysiological states” that makes accurate human state detection challenging.
Regarding (b), the Examiner respectfully disagrees. MPEP 2106.04(d)(1) and MPEP 2106.05(a) indicates that a practical application may be present where the claimed invention provides a technical solution to a technical problem. See, e.g., DDR Holdings, LLC. v. Hotels.com, L.P., 773 F.3d 1245, 1259 (Fed. Cir. 2014) (finding that claiming a website that retained the “look and feel” of a host webpage provided a technological solution to the problem of retention of website visitors by utilizing a website descriptor that emulated the “look and feel” of the host webpage, where the problem arose out of the internet and was thus a technical problem). Here, the Applicant’s argued problem is not a technological problem caused by the computer. The problem of the dynamic and variable nature of physiological manifestations of underlying psychophysiological states was not a problem cause by the computer, it is a problem that existed and/or exists regardless of whether a computer is involved in the process. At best, Applicant’s identified problem is a human/medical problem and the Applicant is using a computer for it’s intended purpose of performing calculations faster/more efficiently. Because no technological problem is present, the claims do not provide a practical application.
Amended claim 15 integrates any abstract idea into a practical application because it provides “an improvement in the functioning of a computer, or an improvement to other technology or technical field… improvements in technology beyond computer functionality may demonstrate patent eligibility, and “[c]onsideration of improvements is relevant to the eligibility analysis regardless of the technology of the claimed invention.”
Regarding (c), the Examiner respectfully disagrees. MPEP 2106.04(d)(1) states that a practical application may be present where the claimed invention improves another technology. See also MPEP 2106.05(a)(II). Applicant’s claim is confined to a general-purpose computer (see Spec. Para. 0101) and does not recite “another technology.” Because no other technology is recited in the claim, the claim cannot improve another technology (see, e.g., MPEP 2106.05(I)(A)(i) describing an example of an improvement to another technology where the abstract idea implemented on a computer improved the claimed additional element of a rubber molding machine).
This technological improvement is analogous to the patent-eligible improvement recognized in the recent Appeals Review Panel Decision on Request for Rehearing in Application No. 16/319,040. See Ex parte Desjardins…
Regarding (d), the Examiner respectfully disagrees. Desjardins is inapplicable to applicant’s invention because Applicant is not claiming improvements to machine learning; the claims are merely using a model as a tool. Initially, the claims do not even recite machine learning, so the argument fails on its face. Even assuming arguendo that machine learning is claimed, there is no training, retraining, parameter adjustment, or anything else in the claim that describes an improvement to ML within the meaning of Desjardins.
…amended claim 15 requires "mapping the plurality of physiological data windows to a corresponding plurality of state predictions using the state prediction model," determining loss based on a loss function and ground truth labels, and updating parameters of the state prediction model based on the determined loss by "calculating a gradient of the loss function and adjusting the parameters in the direction that minimizes the loss." This represents a non-conventional arrangement of elements that provide a technical improvement in human state prediction technology.
Regarding (e), the Examiner respectfully disagrees. There are no elements present in the claims beyond the general-purpose computer. The state prediction model (which is not at all defined in the claim) is part of the abstract idea.
Rejection under 35 U.S.C. § 103
Regarding the rejection of Claims 1-20, the Examiner has considered the Applicant’s arguments; however, these arguments are moot given the new grounds of rejection as necessitated by amendment.
Conclusion
Prior art made of record though not relied upon in the present basis of rejection are noted in the attached PTO 892 and include:
Ptaszek et al. (U.S. 2025/0339103) which discloses an apparatus and method for generating clinical decision support.
Gupta et al. (U.S. 2025/0143627) which discloses methods and systems for multi-class classification of seizure.
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 CAMRYN B LEWIS whose telephone number is (703)756-1807. The examiner can normally be reached Monday - Friday, 11:00 am - 8:00 pm 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, Robert W Morgan can be reached on 571-272-6773. 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.
/CAMRYN B LEWIS/
Examiner, Art Unit 3683
/JASON S TIEDEMAN/Primary Examiner, Art Unit 3683
Prosecution Insights