T’s 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 .
Claim Objections
Claim 17 is objected to because of the following informalities: “machine learning model” should be amended to read “machine learning framework” to properly refer to the machine learning framework introduced earlier in claim 17. Appropriate correction is required.
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 an abstract idea without significantly more.
At Step 1 of the 101 analysis, all claims are directed to one of the statutory categories of invention.
Claim 1 is rejected in response to the following analysis:
At Step 2A, Prong One, the judicial exceptions are bolded in the copy of claim 1 below:
A method for motor assessment, the method comprising:
receiving first sensed signals in response to a first motor assessment performed using a first test device;
receiving second sensed signals in response to a second motor assessment different than the first motor assessment and performed using the first test device;
extracting features based on a combination of the first sensed signals and the second sensed signals;
providing the extracted features to a machine learning model trained to output a motor assessment based prediction based on the extracted features; and
receiving the motor assessment based prediction from the machine learning model.
As recited, the first and second motor assessments encompass a mental process of evaluation, as does the feature extraction step. Again, providing data to a ML model and receiving a prediction encompasses a mental or mathematical process at the level of detail recited in the claim language.
At Step 2A, Prong Two, the additional elements include receiving data of sensed signals, performing a motor assessment with a test device, and using a machine learning model. The additional elements neither describe a particular machine used to carry out the judicial exceptions, nor give detail as to the nature of the data being processed, the features being extracted, or the resultant prediction. When taken as a whole, a method incorporates some device for motor assessment (is this assessing movement or an engine in a vehicle?), then assesses signals to make a prediction with machine learning. When applying broadest reasonable interpretation, the claim language could encompass any number of processes, since many fields use devices to make assessments, take data, evaluate that data, and use machine learning on processed data to make a prediction. Therefore, the additional elements do not integrate the judicial exceptions into a practical application of the invention.
At Step 2B, the claim as a whole does not amount to significantly more than the judicial exceptions for the reasons given above.
Claim 2 recites performing noise reduction and position normalization for sensed signals. This does not address the issues outlined in the rejection of claim 1, therefore claim 2 is also rejected.
Claims 3 and 4 clarify that the motor assessments include receiving finger tapping input or pronation and supination data. While this narrows the scope of the sensed signals, it does not address the other issues outlined in the rejection of claim 1, therefore these claims are also rejected.
Claims 5 and 6 do little to narrow the scope of the sensed signals and do not address the other issues outlined in the rejection of claim 1, therefore they are also rejected.
Claim 7 does not address the issues outlined in the rejection of claim 1 and is also rejected.
Claim 8 clarifies that the field of use is in the context of patients, but this does little to address the issues outlined in the rejection of claim 1, therefore claim 8 is also rejected.
Claim 9 limits the field to something medical, but this does little to address the issues outlined in the rejection of claim 1, therefore claim 9 is also rejected.
Claim 10 recites producing output which may include repeating portions of the method of claim 1, treating something, or modifying a database. These actions do little to address the issues outlined in the rejection of claim 1, therefore claim 10 is also rejected.
Claim 11 recites a system with a data storage device storing processor-readable instructions, and a processor connected to the device and configured to execute the method of claim 1. The additional elements in claim 11 are encompassed by use of a general-purpose computer, therefore claim 11 is rejected for the same reasons as claim 1.
Claims 12-15 are rejected for the same reasons as claims 3-6, respectively.
Claim 16 recite various sensors which may generate the signals recited in claim 11. This does little to address the issues outlined in the rejection of claim 1, therefore claim 16 is also rejected.
Claim 17 recites a system comprising a test device comprising a processor, an analysis model, and a machine learning framework, all of which are configured to implement the method of claim 1. Claim 17 is therefore rejected for essentially the same reasons as claim 1.
Claims 18-19 are rejected for the same reasons as claims 9-10, respectively.
Claim 20 recites that the machine learning framework may include a first machine learning model which extracts the features recited in claim 17 and a second machine learning model which outputs the action recited in claim 19. At the level of detail recited, this just describes applying a generic technology to the steps previously recited. Furthermore, these limitations to not address the issues outlined in the rejection of claim 1, therefore claim 20 is also rejected.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Miri (US 20230118283 A1) in view of Huo (“A heterogeneous sensing suite for multisymptom quantification of Parkinson’s Disease”).
Regarding claim 1, Miri discloses a method for motor assessment (Abstract: “Embodiments herein disclose computer-implemented methods, computer program products and computer systems for performing neurological diagnostic assessments”), the method comprising:
receiving first sensed signals (biometric activity data) in response to a first motor assessment (¶75: the flow chart is for a neurological diagnostic assessment) performed using a first test device (Fig. 4, element 410);
providing the sensed signals to a machine learning (ML) model trained to output a motor assessment based prediction based on the sensed signals (Fig. 4, 420: biometric activity data provided to ML; from 430, the ML is trained to predict a score); and
receiving the motor assessment based prediction from the machine learning model (the act of providing the data to the ML will result in receiving the predicted score).
Miri does not explicitly disclose receiving second sensed signals in response to a second motor assessment different than the first motor assessment and performed using the first test device. However, Miri teaches performing multiple tests using a smartphone (For example: ¶37: postural tremor; ¶38: muscle baseline tone; ¶39: muscle tone and rigidity during flexion and extension of elbow; ¶40: finger tapping of either hand; ¶41: opening and closing of either hand; ¶42: supination-pronation of either hand; ¶43: foot tapping of either foot), and further teaches that some neurological diseases such as Parkinson’s Disease (PD) can be evaluated by multiple of the above tests (¶28: the Unified Parkinson’s Disease Severity Scale (UPDRS) assesses, among other things, rigidity, finger tapping, hand movements, supination-pronation, toe tapping, tremor, etc.). Therefore, it would have been obvious to one of ordinary skill in the art practicing Miri to receive second sensed signals in response to a second motor assessment different than the first motor assessment and performed using the first test device, and to send some combination of the first and second sensed signals to the ML model to make its assessment. Doing so would incorporate multiple kinds of symptom data relevant to assessing PD.
In light of the above, Miri does not explicitly recite extracting features based on a combination of the first sensed signals and the second sensed signals; and providing the extracted features to a machine learning model trained to output a motor assessment based prediction based on the extracted features.
Huo teaches a wearable sensor system and machine learning algorithms for automated symptomatic assessment of PD (Abstract). Huo teaches that measured data is processed and features are extracted (see pg. 1400, Section C “Data Processing and Feature Extraction”; the whole section discusses how the raw data is filtered and features are extracted). The filtered and extracted data is provided as input to a ML algorithm to make PD predictions (pg. 1401, under Section D “Classification Method”; severity of PD symptoms is quantified based on the extracted features, and to perform this task a ML model is used). Finally, Huo teaches that a ML model can be used to extract features (pg. 1401, first column, the quaternion
q
of an IMU sensor may be estimated using a gradient descent based fusion algorithm based on the measured data; the algorithm described is a kind of ML algorithm).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Huo with the invention of Miri by extracting features based on a combination of the first sensed signals and the second sensed signals; and providing the extracted features to the machine learning model trained to output a motor assessment based prediction based on the extracted features. Doing so would filter out unnecessary data and provide quantities directly related to symptoms of PD to a ML model.
Regarding claim 11, claim 11 recites a system with a data storage device storing processor-readable instructions, and a processor connected to the device and configured to execute the method of claim 1. The additional elements in claim 11 are encompassed by the smartphone disclosed by Miri, therefore claim 11 is rejected for the same reasons as claim 1.
Regarding claim 17, claim 17 recites a system comprising a test device comprising a processor, and analysis model, and a machine learning framework, which system is configured to perform the method of claim 1. The additional elements in claim 17 are encompassed by the smartphone disclosed by Miri, therefore claim 17 is rejected for essentially the same reasons as claim 1.
Regarding claim 2, Miri in view of Huo teaches the limitations of claim 1. Miri does not explicitly teach the limitations of claim 2. However, Huo teaches performing noise reduction on sensed signals (see rejection of claim 1; also see pg. 1400 of Huo, end of first column, where signals were processed using lowpass filters); and extracting features of sensed signals based on the noise reduction (Huo, pg. 1400, under Section C: “Leading up to the feature extraction, the measured signals…were processed as follows: the measured accelerations were filtered”; since the signals are filtered prior to feature extraction, the feature extraction is based on the noise reduction).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Huo with the invention of Miri in view of Huo by causing the extracting features based on the combination of the first sensed signals and the second sensed signals to comprise: performing noise reduction for the first sensed signals and the second sensed signals; and extracting features based on the combination of the first sensed signals and the second sensed signals based on the noise reduction for the first sensed signals and the second sensed signals. Doing so would enable one to filter out unnecessary signals from analysis.
Miri in view of Huo does not explicitly disclose that the extracting features based on the combination of the first sensed signals and the second sensed signals comprises: performing position normalization for the first sensed signals and the second sensed signals; and extracting features based on the combination of the first sensed signals and the second sensed signals based on the noise reduction and the position normalization for the first sensed signals and the second sensed signals.
However, it would have been obvious to one of ordinary skill in the art practicing the invention of Miri in view of Huo to perform the above. Doing so would ensure all signals are set to a common standard (such as by e.g. removing a DC offset in an electrical signal), enabling them to be compared to other signals and/or to a model applied to the signals.
Regarding claims 3 and 12, Miri in view of Huo teaches the limitations of claims 1 and 11, respectively, and further teaches that the first motor assessment or the second motor assessment includes receiving a finger tapping input at the first test device (see ¶40 of Miri and rejection of claim 1).
Regarding claims 4 and 13, Miri in view of Huo teaches the limitations of claim 1, and further teaches that the first motor assessment or the second motor assessment includes receiving a rotation-based input at the first test device, wherein the rotation-based input includes a pronation component and a supination component (see ¶42 of Miri and rejection of claim 1).
Regarding claims 5 and 14, Miri in view of Huo teaches the limitations of claims 1 and 11, respectively, and further teaches that the first sensed signals or the second sensed signals indicate one or more of an area covered, a size, a force, or an impulse (see rejection of claim 1; for a finger tapping test, the sensed signals describe a magnitude (or size) of force. Signals from other of Miri’s tests describe or indicate one or more of a size and a force, and may describe an impulse.).
Regarding claims 6 and 15, Miri in view of Huo teaches the limitations of claims 1 and 11, respectively, and further teaches that the first sensed signals or the second sensed signals indicate one or more of an angular acceleration, an angular velocity, or a change in magnetic field (in ¶42 of Miri, the test of supination-pronation of a hand involves changes in angular acceleration and velocity, and the signals obtained from that test indicate or describe the motion. For example, note that frequency and rhythm data is taken.).
Regarding claim 7, Miri in view of Huo teaches the limitations of claims 1 and 11, respectively, but does not explicitly teach the limitations of claim 7. However, it would have been obvious to one of ordinary skill in the art practicing the invention of Miri in view of Huo to cause the first motor assessment to be performed at a first time and the second motor assessment at a second time different from the first time, because they are different tests and performing them at the same time would be difficult for a user being assessed for a neurological disease such as PD.
Regarding claim 8, Miri in view of Huo teaches the limitations of claim 1, and further teaches that the extracted features identify a patient waveform based on the first motor assessment and the second motor assessment (see at least Fig. 6 of Miri, where a patient waveform is shown; noting from the rejection of claim 1 that Huo teaches using a low pass filter, it follows that Miri in view of Huo would teach identifying a filtered patient waveform. Consider also Fig. 3 of Huo, which shows patient waveforms which have been filtered).
Regarding claim 16, Miri in view of Huo teaches the limitations of claim 11, and further teaches that the first sensed signals or the second sensed signals are generated using one or more sensors selected from a force sensor, a touch sensor, an accelerometer, a gyroscope, or a magnetometer (Miri, ¶67: a multimodal approach to the testing may be applied wherein accelerometer data is included with the microphone data of muscle activity. This data combination “aid[s] the assessment of motor function and neurological examination.”. Note also from ¶32 of Miri that smartphones may have 3D accelerometers.).
Regarding claims 9 and 18, Miri in view of Huo teaches the limitations of claims 1 and 17, respectively, and further teaches that the motor assessment based prediction includes a key biomarker, a medical condition, an inclusion criteria, an exclusion criteria, a disease progression attribute, a disease regression attribute, a disease onset, a disease outcome, a disease trend, or a treatment. (the prediction assesses a medical condition/disease likelihood or severity; see for example Miri, ¶68 where a UPDRS motor score is given).
Regarding claims 10 and 19, Miri in view of Huo teaches the limitations of claims 1 and 17, respectively, and further teaches outputting a trigger action, wherein the trigger action includes modifying a database (Miri, ¶65: “results from each process of the test may be stored in a database”).
Miri in view of Huo does not explicitly teach that the trigger action is output by the machine learning framework, or that the trigger action includes generating an updated motor assessment, triggering a repeat motor assessment, outputting a treatment, or implementing a treatment. However, it would have been obvious to cause the trigger action to include repeating a motor assessment such as if a previous assessment did not obtain high-quality data. Again, it would have been obvious to cause a trigger action to include generating an updated motor assessment in order to update data to a most recent assessment. Additionally, Miri teaches that wrist-worn devices may provide neuromodulation treatment for a tremor, for example (¶33), and it would have been obvious to include that device and to cause the trigger action to include outputting or implementing a treatment in order to, for example, provide neuromodulation treatment for a detected tremor. Finally, it would have been obvious to cause the trigger action to be output by the machine learning framework in order to implement the trigger action autonomously in response to the motor assessment based prediction.
Regarding claim 20, Miri in view of Huo teaches the limitations of claim 19, and further teaches that the machine learning framework includes a first machine learning model configured to extract the extracted features (see rejection of claim 1 and discussion around using gradient descent to estimate
q
) and a second machine learning model configured to output the trigger action (see rejection of claim 19).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Choi (US 20190365287 A1) uses a sensor in an insole to classify gait (Abstract), preprocesses data to remove noise and convert data into a form suitable for analysis (¶13) and performs normalization by resizing pieces of data to have a length corresponding to a unit time (¶40).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ETHAN WESLEY EDWARDS whose telephone number is (571)272-0266. The examiner can normally be reached Monday - Friday, 7:30am-5pm.
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, Andrew Schechter can be reached at (571) 272-2302. 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.
ETHAN WESLEY EDWARDS
Examiner
Art Unit 2857
/E.W.E./ Examiner, Art Unit 2857
/LINA CORDERO/ Primary Examiner, Art Unit 2857
Prosecution Insights