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 .
Notice to Applicant
This communication is in response to Amendments filed on 05/18/2026.
Claims 1-13, 28-30, 38 and 40-42 are currently pending in the application.
Limitations appearing inside of {} are intended to indicate the limitations not taught by said prior art(s)/combinations.
Response to Amendment
The amendment to the claims filed on 05/18/2026 have been entered. Claims 1, 13, and 28 have been amended. Claims 14-27, 31-37, 39, 43-99 were previously canceled. No new matter has been introduced.
Response to Arguments
Applicant’s arguments, see Remarks, filed 05/18/2026, with respect to the rejection of claims under 35 USC §101 have been fully considered and are persuasive. The rejection of claims 1-13,28-30,38 and 40-42 under 35 USC §101 are withdrawn in view of the amended claims because the claims are not directed towards an abstract idea. Specifically, independent claim 1 recites “performing interpolation” and “lateral displacements are based on point data” and “determining using the point data, spinal mobility features” which are not considered mental processes. The independent claim and all dependent claims are not directed towards a judicial exception/abstract idea (Step 2A Prong 1: NO).
Applicant’s arguments, see Remarks, filed 05/18/2026, with respect to the rejection(s) of claim(s) 1-13,28-30,38 and 40-42 under 35 USC §§102 and 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Delp (US 20210315486 A1) in view of Whitehead (2014), as cited in the IDS.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 6, 12, 38, 40, and 41 are rejected under 35 U.S.C. 103 as being unpatentable over “Delp” (Delp et al., US 20210315486 A1) in view of “Whitehead” (J.C. Whitehead, et al., "A Clinical Frailty Index in Aging Mice: Comparisons with Frailty Index Data in Humans," J Gerontol a Biol Sci Med Sci 2014 June:69(6):621-632.), as cited in the Information Disclosure Statement (filed on 01/30/2024).
1. (Currently Amended) Delp teaches a computer-implemented method comprising:
receiving, at one or more processors (processor 405; ¶[0043]), video data representing a video capturing movements of a subject (motion evaluation;¶[0030]. Process 100 trains (105) a model to evaluate keypoint trajectories identified from images (e.g., frames of a video); ¶[0031]. image capture device (e.g., webcam, camera, etc.) for recording images of a user performing a set of motions; ¶[0039]);
determining, by the one or more processors, point data tracking movements, for a duration of the video, of a set of body parts of the subject (evaluate motion based on keypoint trajectories; ¶[0049]);
determining, by the one or more processors, at least one gait measurement of the subject, wherein determining at least one gait measurement comprises performing interpolation on a set of lateral displacements (step width is interpreted as a set of lateral displacements in: Evaluation scores in accordance with several embodiments of the invention include, but are not limited to, a gait deviation index (GDI), stride lengths, O.sub.2 expenditure, maximum hip flexion, step width, muscle activity, muscle fiber length, joint loads, and other motion evaluation scores. ¶[0035]; perform gait checkups; ¶[0040]),
wherein the lateral displacements (step width; ¶[0035]) are based on the point data of the set of body parts (Process 100 feeds the extracted keypoints trajectories to the trained model to generate (115) evaluation scores to evaluate the motion in the video;¶[0035]), to generate interpolated data representing {lateral} displacements at time points between video frames of the video data (missing values can be imputed (e.g., using linear interpolation); ¶[0075]);
determining, using the point data, spinal mobility features of the subject for a duration of the video (Evaluation engines … can be used to evaluate a timed trajectory of keypoints in images of an individual to provide a quantitative score for the individual's motions; ¶[0053]; Delp further teaches “deriving time series” which may, for example, be calculated as a difference between coordinates (i.e., key points) of body parts, where the difference between coordinates is interpreted as “features”: “processing the training data includes deriving time series that can be helpful for improving the performance of the CNN. Derived time series in accordance with certain embodiments of the invention can include a time series that is simply the difference between the x-coordinate of the left ankle and the x-coordinate of the right ankle throughout time. In some embodiments, derived time series include an approximation the angle formed by the left ankle, left knee, and left hip. In numerous embodiments, time series can be derived separate for opposite sides (e.g., right and left sides) of the body”; ¶[0074])); and
processing, using at least one machine learning model (evaluation engines can include one or more models, such as (but not limited to) convolutional neural networks, support vector regression, ridge regression, and random forests; ¶[0053]), at least the spinal mobility features and the at least one gait measurement (generating features of a user's motion, such as (but not limited to) step length, cadence, and peak knee flexion; ¶[0073]) to determine a visual {frailty} score for the subject (a set of motion parameters, such as (but not limited to) Gait Deviation Index (GDI), Gross Motor Function Classification System (GMFCS), stride length, and gait asymmetry; ¶[0039]. outputs can include performance and/or injury risk metrics; ¶[0052]. scoring an individual’s gait, ¶[0069]).
Delp teaches a visual gait-based scoring, however Delp does not explicitly disclose a visual frailty score.
However, Whitehead, a similar field of endeavor of machine vision based gait analysis (Ethovision analysis software; [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]. According to Ethovision manufacture, Noldus, “EthoVision XT uses advanced deep learning technology to accurately detect and track rodent body points” https://noldus.com/ethovision-xt), teaches a visual frailty score for the subject (Videotapes of open-field behavior were analyzed; eight-item frailty index score for each mouse; Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include a visual frailty score as taught by Whitehead to the invention of Delp. The motivation to do so would be to obtain a simple, noninvasive quantification of frailty for use in acute, longitudinal and comparative studies.
6. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. Delp further teaches further comprising:
processing the video data to determine pose estimation data tracking, during the duration of the video (The OpenPose algorithm is described in greater detail in “Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields,” by Cao et al., the disclosure of which is incorporated herein in its entirety; ¶[0078]),
a location of at least twelve body parts of the subject (One skilled in the art will recognize that a different number of keypoints and/or keypoints at different body parts can be used without departing from the spirit of the invention; Delp, ¶[0032]; (x, y) coordinates of 18 different body parts; ¶[0078]);
determining, using the pose estimation data, features for the subject (process the training data by filtering extracted keypoint trajectories;¶[0072]. processing the training data includes generating features of a user's motion, such as (but not limited to) step length, cadence, and peak knee flexion; ¶[0073] ); and
processing, using the at least one machine learning model, the features to determine the visual frailty score (Process 800 trains (820) a model to predict a quantitative motion evaluation score based on the extracted multivariate time series; ¶[0080]).
12. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. The Delp further teaches further comprising:
determining, using the video data, gait measurements of the subject for the duration of the video (CNNs, SVRs, RRs) for predicting a set of motion parameters, such as (but not limited to) Gait Deviation Index (GDI), Gross Motor Function Classification System (GMFCS), stride length, and gait asymmetry ;Delp, ¶[0039]); and
Whitehead further teaches processing, using the at least one machine learning model, the gait features to determine the visual frailty score for the subject (Ethovision analysis software; Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]); See Table 1, System and Parameter: “Physical/musculoskeletal, Gait disorders”; Potential Deficits: “uncoordinated gait”; Videotapes of open-field behavior were analyzed; eight-item frailty index score for each mouse; Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]).
38. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. Delp further teaches further comprising:
processing the video data to determine gait measurements for the subject for the duration of the video (Joint analysis engines …can be used to analyze the images of an individual to identify the positions of an individual's joints and their movements over a sequence of images or frames of a video; Delp, ¶[0048]; the evaluated motion is gait; ¶[0085]);
processing the video data to determine behavior data identifying portions of the video where the subject exhibits a predetermined behavior (Delp teaches gait analysis for scoring gait, e.g., gait deficit index (GDI) and other motions: “received inputs include (but are not limited to ) videos of a user walking and/or otherwise performing a set of motions”; Delp ¶[0069], where “performing a set of motions” may be interpreted as behavior data. However the nature of the “set of motions” is not explicitly disclosed)
Whitehead further teaches behavior data ((g) rearing frequency (number of occurrences/10 min), Whitehead, [§Methods. Quantification of frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]) ; and further teaches
processing, using the at least one machine learning model, the spinal mobility features, the gait measurements (See Whitehead, Table 1, System and Parameter: “Physical/musculoskeletal, Gait disorders”; Potential Deficits: “uncoordinated gait”)) and the behavior data (rearing, [§Methods. Quantification of frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]) to determine the visual frailty score (Videotapes of open-field behavior were analyzed; eight-item frailty index score for each mouse; Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include behavior data as taught by Whitehead to the invention of Delp. The motivation to do so would be to provide a robust estimate of frailty by including more parameters based on readily apparent sigs of clinical deterioration.
40. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. Delp further teaches further comprising: determining a physical condition of the subject using the visual frailty score (the predicted motion evaluation scores can be used as a part of a diagnostic tool for predicting or detecting the early onset of medical conditions such as cerebral palsy or Parkinson's disease. It is expected that, even if the predicted GDI is not perfectly correlated with the “true” GDI, it could theoretically be more predictive of such medical conditions because of the way that the evaluation engines are trained and the ability of such models to identify characteristics that may not be readily visible to a medical professional. In numerous embodiments, outputs from a process can include a diagnosis for a disease. Diagnoses in accordance with numerous embodiments of the invention can include (but are not limited to) the current state of a disease, the rate of progression of a disease, and a future state of a disease.; Delp, ¶[0084]).
41. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 40. Whitehead further teaches wherein the physical condition is frailty (eight-item frailty index score; Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2])).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include frailty condition as taught by Whitehead to the invention of Delp. The motivation to do so would be to examine vulnerability where frail individuals have higher mortality and use more health care services than do fit people.
Claims 2, 7, 10, and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Delp in view of Whitehead and further in view of “Heikkinen” (Heikkinen T,et al.. Rapid and robust patterns of spontaneous locomotor deficits in mouse models of Huntington's disease. PLoS One. 2020 Dec 28;15(12):e0243052. doi: 10.1371/journal.pone.0243052. PMID: 33370315; PMCID: PMC7769440.).
2. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. Delp further teaches wherein determining the spinal mobility features of the subject for the duration of the video comprises:
determining a plurality of spinal measurements (Such keypoints can include (but are not limited to) elements of bones, muscles, joints, organs, and derivatives. One skilled in the art will recognize that a different number of keypoints and/or keypoints at different body parts can be used without departing from the spirit of the invention; Delp, ¶[0032]),
each spinal measurement of the plurality of spinal measurements corresponding to one video frame of the video data (Keypoint trajectories can be extracted using a number of methods including (but not limited to) OpenPose, CNNs, image processing algorithms, and/or manual annotations. In some embodiments, processes use the OpenPose algorithm to extract 2D body landmark positions (such as knees, ankles, nose, etc.) in each frame of the video; Delp, ¶[0078]); and
determining the spinal mobility features using the plurality of spinal measurements (Delp teaches “deriving time series” which is interpreted as “features” because it may, for example, be calculated as a difference between coordinates (i.e., key points) of body parts, where the difference between coordinates is interpreted as features: processing the training data includes deriving time series that can be helpful for improving the performance of the CNN. Derived time series in accordance with certain embodiments of the invention can include a time series that is simply the difference between the x-coordinate of the left ankle and the x-coordinate of the right ankle throughout time. In some embodiments, derived time series include an approximation the angle formed by the left ankle, left knee, and left hip. In numerous embodiments, time series can be derived separate for opposite sides (e.g., right and left sides) of the body; ¶[0074]).
The example provided by Delp includes an angle formed by joints in the leg, and may not necessarily be interpreted as “spinal measurements”, although the spinal mobility may be involved.
However, Heikkinen, a similar field of endeavor of vision-based kinematic analysis of locomotion, teaches plurality of spinal measurements (body posture and joint angles (i.e., spinal measurements per specification ) were determined, Heikkinen, [§Materials and Methods, Measuring individual components of a complex spontaneous behavior, p5, ¶1]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include spinal measurements as taught by Heikkinen to the combined invention of Delp and Whitehead. The motivation to do so would be provide a more robust analysis.
7. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. Whitehead further teaches further comprising:
{determining body features for the subject, the body features corresponding to at least one of a length of the subject, a width of the subject, and a distance between rear paws of the subject;}
processing, using the at least one machine learning model, the body features to determine the visual frailty score (Videotapes of open-field behavior were analyzed; eight-item frailty index score for each mouse; Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]; and See Table 1,“Gait Disorders” as part of the clinical assessment).
The combination does not explicitly disclose determining body features for the subject, the body features corresponding to at least one of a length of the subject, a width of the subject, and a distance between rear paws of the subject.
However, Heikkinen teaches determining body features for the subject, the body features corresponding to at least one of a length of the subject, a width of the subject, and a distance between rear paws of the subject (See at least Heikkinen Table 3 exhibits :Parameter: Step Width; Definition: The distance between forepaws or hindpaws when both are touching the ground during stance, perpendicular to midline).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include body features as taught by Heikkinen to the combined invention of Delp and Whitehead. The motivation to do so would be to include specific details regarding frailty analysis of a subject with paws.
10. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. Delp further teaches wherein determining spinal mobility features of the subject for a duration of the video comprises:
determining a first set of video frames representing gait movements by the subject (the input comprises videos of patients walking; Delp, ¶[0070]);
determining a first set of spinal mobility features for the first set of video frames (processing the training data includes generating features of a user's motion, such as (but not limited to) step length, cadence, and peak knee flexion; Delp, ¶[0073]);
determining a second set of video frames representing non-gait movements by the subject (Whitehead lists non-gait movements: (a) total distance moved in 10 minutes(cm); (b) maximal distance moved between bouts of inactivity(cm); (c) total duration of movement (seconds); (d) percent of total time spent moving; (e) the change in direction per unit distance moved, called meander (degrees/cm; from 0° to 180°); (f) the average velocity of movement over 10 minutes (cm/s); and (g) rearing frequency (number of occurrences/10 min); Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2])); and
{determining a second set of spinal mobility features for the second set of video frames;
wherein the spinal mobility features include the first set of spinal mobility features and the second set of spinal mobility features.}
The combination does not explicitly disclose determining a second set of spinal mobility features for the second set of video frames; wherein the spinal mobility features include the first set of spinal mobility features and the second set of spinal mobility features.
However, Heikkinen further teaches determining a second set of spinal mobility features for the second set of video frames (body posture and joint angles, and properties of limb trajectories during swing phase (i.e., features) were determined, Heikkinen, [§Materials and Methods, Measuring individual components of a complex spontaneous behavior, p5, ¶1]; body posture and joint angles, and properties of limb trajectories during swing phase (i.e., features) were determined, Heikkinen, [§Materials and Methods, Measuring individual components of a complex spontaneous behavior, p5, ¶1]); and
wherein the spinal mobility features include the first set of spinal mobility features and the second set of spinal mobility features (we measured 79 parameters of gait, body posture and fine motor movements; Heikkinen, [§Introduction, p3, ¶1])
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include a second set of spinal mobility features as taught by Heikkinen to the combined invention of Delp and Whitehead. The motivation to do so would be to measure quantitative changes in the complex adaptive movement because they provide signs of aging which may be useful in a frailty index.
28. (Currently amended) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1.
{wherein the set of body parts comprises one or more of: the nose, base of neck, mid spine, left hind paw, right hind paw, base of tail, middle of tail and tip of tail determining, using the point data, features for the subject;} and
processing, using at least the one machine learning model, the features to determine the visual frailty score (Ethovision analysis software is used to detect and track rodent body parts/features … eight-item frailty index score for each mouse; Whitehead, [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2])
The combination does not explicitly disclose wherein the set of body parts comprises one or more of: the nose, base of neck, mid spine, left hind paw, right hind paw, base of tail, middle of tail and tip of tail determining, using the point data, features for the subject; and
However, Heikkinen teaches wherein the set of body parts comprises one or more of: the nose, base of neck, mid spine, left hind paw, right hind paw, base of tail, middle of tail and tip of tail determining, using the point data, features for the subject (two-dimensional marker data of 22 selected markers of each stride (bilaterally: iliac crest, hip, knee, ankle, heel, hindpaw, shoulder, elbow, wrist and forepaw as well as single points of the chin and tail tip, middle, and base) were first referenced to the left iliac crest marker; Heikkinen, [§Materials and Methods, Data analysis, p5, ¶2], and additionally teaches processing, using at least one machine learning model, features: The movement of 24 points on each mouse were analyzed from the videos (Simi Reality Motion Systems, Unterschleissheim, Germany), and the trajectories of markers (see Table 2 for details) were analyzed by customized scripts; Heikkinen, [§Materials and Methods, Fine motor skill and gait analysis, p4, ¶1]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include body parts as taught by Heikkinen to the combined invention of Delp and Whitehead. The motivation to do so would be to gain a comprehensive perspective on the spatio-temporal features of mouse gait.:
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Delp in view of Whitehead and further in view of “Tanka” (Tanaka S. et al. Four factors underlying mouse behavior in an open field. Behav Brain Res. 2012 Jul 15;233(1):55-61. doi: 10.1016/j.bbr.2012.04.045. Epub 2012 May 2. PMID: 22569582; PMCID: PMC3866095.).
8. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. The combination does not explicitly teach further comprising:
determining a number of times a rearing event occurs during the duration of the video; determining a rearing length for each rearing event; processing, using the at least one machine learning model, the number times the rearing event occurs and the rearing length for each rearing event to determine the visual frailty score.
However, Tanka, a similar field of endeavor of video analysis of rat behavior in an open field test, teaches determining a number of times a rearing event occurs during the duration of the video; determining a rearing length for each rearing event; processing, using the at least one machine learning model, the number times the rearing event occurs and the rearing length for each rearing event to determine the visual frailty score (Raw data were transformed into the location of the animal (in x-y coordinates), whether holepoking or rearing occurred (events), and the duration of each event (time); Tanka, [§2.2, ¶1])
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include frequency and duration of rearing behavior as taught by Tanka to the combined invention of Delp and Whitehead. The motivation to do so would be because rearing may represent both inspective and diversive exploration of an environment, the frequency and duration of which may indicate frailty or aging in rodents.
Claims 9, 29, and 30 are rejected under 35 U.S.C. 103 as being unpatentable over Delp in view of Whitehead and further in view of “Pereira” (Pereira, T.D. et al. Quantifying behavior to understand the brain. Nat Neurosci 23, 1537–1549 (2020). https://doi.org/10.1038/s41593-020-00734-z)
9. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. Whitehead further teaches further comprising: {processing, using the at least one machine learning model, the video data to determine ellipse-fit data for the subject for the duration of the video; determining, using the ellipse-fit data, features for the subject processing},
using the at least one machine learning model, the features to determine the visual frailty score (Ethovision analysis software; [§Methods. Quantification of Frailty with a performance-based eight-item frailty index, p622, col 2, ¶2]).
The combination does not explicitly disclose further comprising: processing, using the at least one machine learning model, the video data to determine ellipse-fit data for the subject for the duration of the video; determining, using the ellipse-fit data, features for the subject processing, using the at least one machine learning model, the features to determine the visual frailty score .
However, Pereira, a similar field of endeavor of vision-based animal tracking for and pose estimation for understanding behavior, teaches further comprising: processing, using the at least one machine learning model, the video data to determine ellipse-fit data for the subject for the duration of the video; determining, using the ellipse-fit data, features for the subject (See Pereira Fig 1 exhibits ellipse tracking and features for pose estimation of a animals and insects; Pose estimation CNNs [§Animal pose estimation, p1539, col 1, ¶1]); and
PNG
media_image1.png
713
810
media_image1.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include ellipse fitting as taught by Pereira to the combined invention of Delp and Whitehead. The motivation to do so would be to find the major and minor axes of an ellipse encircling the animal (Fig. 1b). This is a conveniently universal description, as most animals with a central nervous system share a similar body plan, in which a spinal or ventral nerve cord forms a line at the center of an elongated body.
29. (Previously Presented) The combination of Delp and Whitehead teaches the computer-implemented method of claim 1. The combination does not explicitly disclose further comprising: processing the video data using an additional machine learning model to identify a likelihood of the subject exhibiting a grooming behavior for a plurality of video frames of the video data; and determining the visual frailty score using the likelihood of the subject exhibiting the grooming behavior.
However, Pereira teaches processing the video data using an additional machine learning model (Given user-provided examples of times when particular behaviors are (or are not) occurring, these methods derive classification criteria using specific features (for example, body-part positions or speeds) extracted from the raw data (Fig. 3b). Popular toolkits use decision trees (or random forest ensembles)66–68 to learn potentially complex or abstract classifiers from animal tracking features. These methods leverage data to avoid the tedious and potentially flawed manual design of classification criteria, in addition to providing measures of robustness to overfitting through standard statistical techniques such as cross-validation; Pereira, [§Quantifying the dynamics of behavior. Animal behavior, as defined by humans, p1542, col 2, ¶2]) to identify a likelihood (Pereira teaches methods for identifying the likelihood that a subject is exhibiting grooming behaviors: “For behaviors involving highly periodic movements, such as locomotion or grooming, spectral features can provide an effective representation by expressing the behavioral feature in the time-frequency space”, or “correlation structure between posture coordinates”, “principal component analysis”, or “nonlinear dimensionality reduction on the coordinates or pairwise features, such as variational auto-encoders”; [§Box 2, p1542]) of the subject exhibiting a grooming behavior for a plurality of video frames of the video data (“behavioral states, such as ‘ walking’ or ‘grooming’… machine learning to classify these states from video data or features derived from tracking (Box 2) Pereira, [§Quantifying the dynamics of behavior, p1542, col 1, ¶1]); and
determining the visual frailty score using the likelihood of the subject exhibiting the grooming behavior (“Interpretation of the behavioral clusters will depend on the application”; Pereira, [§Animal behavior, as defined by the data, p1544, col 1, ¶1]).
PNG
media_image2.png
233
403
media_image2.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include grooming behavior tracking as taught by Pereira to the combined invention of Delp and Whitehead. The motivation to do so would be to capture highly periodic movements such as grooming which capture dynamics of muscle control.
30. (Previously Presented) The combination of Delp and Whitehead teach the computer-implemented method of claim 1. The combination does not explicitly disclose further comprising: processing the video data using an additional machine learning model to identify a likelihood of the subject exhibiting a predetermined behavior for a plurality of video frames of the video data; and determining the visual frailty score using the likelihood of the subject exhibiting the predetermined behavior.
However, Pereira teaches further comprising: processing the video data using an additional machine learning model to identify a likelihood of the subject exhibiting a predetermined behavior for a plurality of video frames of the video data (“For behaviors involving highly periodic movements, such as locomotion or grooming, spectral features can provide an effective representation by expressing the behavioral feature in the time-frequency space”, or “correlation structure between posture coordinates”, “principal component analysis”, or “nonlinear dimensionality reduction on the coordinates or pairwise features, such as variational auto-encoders”; [§Box 2, p1542]); and determining the visual frailty score using the likelihood of the subject exhibiting the predetermined behavior (“Interpretation of the behavioral clusters will depend on the application”; Pereira, [§Animal behavior, as defined by the data, p1544, col 1, ¶1]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include predetermined behavior tracking as taught by Pereira to the combined invention of Delp and Whitehead. The motivation to do so would be to capture highly periodic movements which capture dynamics of muscle control.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Delp in view of Whitehead and further in view of “Broom” (Broom L, et al. A translational approach to capture gait signatures of neurological disorders in mice and humans. Sci Rep. 2017 Jun 12;7(1):3225. doi: 10.1038/s41598-017-03336-1. PMID: 28607434; PMCID: PMC5468293.)
13. (Currently amended) The combination of Delp and Whitehead teaches the computer-implemented method of claim 12. The combination does not explicitly disclose further comprising: determining, using the point data a plurality of stance phases and a plurality of swing phases represented in the video data; determining, based on the plurality of stance phases and the plurality of swing phases, a plurality of stride intervals represented in the video data; and determining, using the point data, the gait measurements based on each stride interval of the plurality of stride intervals .
However, Broom, a similar field of endeavor of capturing gait signatures of mice, teaches determining, using the point data (placement of the paw on the runway was captured by assigning a pixel (space) to a video frame (time); Broom [§Methods, Behavioral data collection, p23, ¶2]),
a plurality of stance phases and a plurality of swing phases represented in the video data; determining, based on the plurality of stance phases and the plurality of swing phases, a plurality of stride intervals represented in the video data; and determining, using the point data, the gait measurements based on each stride interval of the plurality of stride intervals (We obtained spatial (stride length) and temporal gait measurements (stance and swing duration, cadence, swing speed) that are known to be speed dependent from high speed video recordings; Broom, [§Results, p2, ¶1]; For each paw, the start and end of the swing phase with the corresponding paw location was marked. From these parameters we calculated stride velocity, stride length, stance, duration, swing duration, stride duration, cadence, swing speed, and base width; Broom, [§Methods, Behavioral data collection, p13, ¶1]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include calculating the stance swing and stride as taught by Broom to the combined invention of Delp and Whitehead. The motivation to do so would be to accurately tracking rat walking.
Claim 42 is rejected under 35 U.S.C. 103 as being unpatentable over Delp in view of Whitehead, and further in view of “Veld” (Veld et al. Fried phenotype of frailty: cross-sectional comparison of three frailty stages on various health domains. BMC Geriatr. 2015 Jul 9;15:77. doi: 10.1186/s12877-015-0078-0. PMID: 26155837; PMCID: PMC4496916.)
Regarding claim 42, The combination of Delp and Whitehead teaches the computer-implemented method of claim 40. The combination does not explicitly disclose wherein the physical condition is a pre-frailty condition
However, Veld, a similar field of endeavor of investigating frailty, teaches wherein the physical condition is a pre-frailty condition (Veld, [p 3, §Methods: Fried frailty criteria; Col 2, ¶2]; Persons with a score of 1 or 2 are at intermediate risk for adverse outcomes or are considered to be pre-frail).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include pre-frail as a physical condition as taught by Veld to the combined invention of Delp and Whitehead. The motivation to do so would be to investigate factors that vary between different stages of frailty that may be clinically relevant.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Lencioni (Lencioni, T. et al. Human kinematic, kinetic and EMG data during different walking and stair ascending and descending tasks. Sci Data 6, 309 (2019). https://doi.org/10.1038/s41597-019-0323-z) would have been relied upon for teaching interpolation.
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 CHANDHANA PEDAPATI whose telephone number is (571)272-5325. The examiner can normally be reached M-F 8:30am-6pm (ET).
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, Chan Park can be reached at 5712727409. 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.
/CHANDHANA PEDAPATI/Examiner, Art Unit 2669
/JOHN B STREGE/Primary Examiner, Art Unit 2669
Prosecution Insights