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 .
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.
Notice to Applicant
Claims 1 – 20 are pending.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1 – 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The independent claims include the limitation:
encoding, using a modality of specific encoders, the plurality of electrocardiogram signals and the plurality of electronic health records to generate encoded representations
Websters define “encoding” as to convert from one system of communication to another. However, some of these conversions are purely data transformations while other conversions are from a signal to a wave. In the limitation, it is not clear whether or not the encoding performs statutory conversions.
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 – 5, 7 – 15, and 17 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zimmerman, U.S. Pre-Grant Publication 2022/ 0384045 in view of Krishnaiahsetty et al. U.S. Pre-Grant Publication 2017/ 0169128 and Raghu et al., “Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series”
As per claim 1,
Zimmerman teaches an apparatus for generating a diagnostic label, wherein the apparatus comprises:
at least a processor (figure 1, #100); and
a memory communicatively connected to the at least a processor (figure 1, #100),
wherein the memory containing instructions configuring the at least a processor to
(figure 1, #132):
receive a plurality of electrocardiogram signals from a user (figure 3 and paragraph 135 - 137);
receive a plurality of electronic health records from the user (paragraphs 232 - 235 EMR/ EHR),
wherein the plurality of electronic health records includes a plurality of metadata (paragraph 142 where metadata is data about data - demographics, paragraph 204 xml),
encode, using a modality of specific encoders, the plurality of electrocardiogram signals and the plurality of electronic health records to generate encoded representations model (paragraphs 237 - 244, 267 composite model);
generate, using multimodal representations derived from the projected representations, at least a diagnostic label (paragraph 193 risk score - paragraph 262, 328 - 330 output).
Zimmerman does not explicitly teach:
a memory communicatively connected to the at least a processor,
wherein the memory containing instructions configuring the at least a processor to:
receive a plurality of electronic health records from the user,
wherein the plurality of electronic health records includes a plurality of metadata,
wherein the plurality of metadata:
identifies at least a source of the plurality of electronic health records; and
indicates at least a temporal datum associated with the plurality of electronic health records;
project, using the at least a processor, the encoded representations into a joint embedding space to generate projected representations; and
However, Krishnaiahsetty further teaches the apparatus comprising
a memory communicatively connected to the at least a processor (figure 1 #102, paragraphs 132, 133),
wherein the memory containing instructions configuring the at least a processor to (paragraphs 132, 133):
receive a plurality of electronic health records from the user (paragraph 130),
wherein the plurality of electronic health records includes a plurality of metadata (paragraph 90),
wherein the plurality of metadata:
identifies at least a source of the plurality of electronic health records (Paragraph 90, device); and
indicates at least a temporal datum associated with the plurality of electronic health records (paragraph 90, start time, end time);
It would have been obvious to one of ordinary skill in the art before the effective filing date to add these features into Zimmerman. One of ordinary skill in the art before the effective filing date would have added these features into Zimmerman with the motivation to mark multimedia files with file-marks (Krishnaiahsetty, Abstract).
Zimmerman in view of Krishnaiahsetty do not explicitly teach:
a memory communicatively connected to the at least a processor,
wherein the memory containing instructions configuring the at least a processor to:
project, using the at least a processor, the encoded representations into a joint embedding space to generate projected representations; and
However, Raghu further teaches:
a memory communicatively connected to the at least a processor (B.2.4. COMPUTE DETAILS),
wherein the memory containing instructions configuring the at least a processor (B.2.4. COMPUTE DETAILS) to:
project, using the at least a processor, the encoded representations into a joint embedding space to generate projected representations (B.2.1. MODEL ARCHITECTURE); and
It would have been obvious to one of ordinary skill in the art before the effective filing date to add these features into Zimmerman in view of Krishnaiahsetty. One of ordinary skill in the art before the effective filing date would have added these features into Zimmerman in view of Krishnaiahsetty with the motivation to operate a contrastive pre-training strategy to learn representations of multimodal time series (Raghu, Abstract).
As per claims 2, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 1 as described above.
Zimmerman in view of Krishnaiahsetty do not explicitly teach however, Raghu further teaches the apparatus wherein the plurality of electrocardiogram signals are processed using an ResNet-based encoder (4.2. Experimental Setup).
It would have been obvious to one of ordinary skill in the art before the effective filing date to add these features into Zimmerman in view of Krishnaiahsetty for the reasons as described above.
As per claims 3, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 1 as described above.
Zimmerman further teaches the apparatus wherein the plurality of electronic health records comprise unstructured text data, the unstructured text data comprising one or more of ECG reports and echocardiography (ECHO) reports (paragraph 293 unstructured paragraph 122 ECG report).
As per claims 4, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 3 as described above.
Zimmerman in view of Krishnaiahsetty do not explicitly teach however, Raghu further teaches the apparatus wherein projecting the encoded representations into the joint embedding space comprises:
aligning, using a fine-grained space, the plurality of electrocardiogram signals with structured electronic health records (3.2.2. COMPONENT LOSS – second loss term); and
aligning, using a coarse-grained space, the plurality of electrocardiogram signals with unstructured text (3.2.1. GLOBAL LOSS).
It would have been obvious to one of ordinary skill in the art before the effective filing date to add these features into Zimmerman in view of Krishnaiahsetty for the reasons as described above.
As per claims 5, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 1 as described above.
Zimmerman in view of Krishnaiahsetty do not explicitly teach however, Raghu further teaches the apparatus
wherein the at least a processor is further configured to compare, using multi-modal contrastive learning, the projected representations, wherein the multi-modal contrastive learning compares the projected representations by applying a loss function to maximize similarity between related representations (6. Conclusion).
It would have been obvious to one of ordinary skill in the art before the effective filing date to add these features into Zimmerman in view of Krishnaiahsetty for the reasons as described above.
As per claims 6, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 1 as described above.
further teaches the apparatus wherein generating the at least a diagnostic label further comprises:
comparing the multimodal representations to similar multimodal representations from other users; and
applying at least an algorithm to identify one or more abnormalities.
As per claims 7, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 1 as described above.
Zimmerman further teaches the apparatus wherein the at least a source comprises a diagnostic system, wherein the plurality of electronic health records is imported from the diagnostic system (paragraph 44).
As per claims 8, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 1 as described above.
Zimmerman further teaches the apparatus wherein memory further instructs the processor to generate a diagnostic report as a function of the diagnostic label (paragraph 194 report based on risk score).
As per claims 9, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 8 as described above.
Zimmerman further teaches the apparatus wherein generating the diagnostic report comprises:
generating, using the at least a processor, graphical data that visualizes representation clusters (paragraph 139 model using clustering – paragraph 143 data into the model); and
displaying, using at least a graphical user interface, the diagnostic report (paragraph 194 output a report).
As per claims 10, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 9 as described above.
Zimmerman further teaches the apparatus wherein the representation clusters comprise groupings of data points that exhibit similarity in electrocardiogram-derived features (paragraph 139 model using clustering).
As per claims 11,
Zimmerman in view of Krishnaiahsetty and Raghu teach a method for generating a diagnostic label apparatus of claim 1 as described above in claim 1.
As per claims 12, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 11 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 2.
As per claims 13, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 11 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 3.
As per claims 14, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 13 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 4.
As per claims 15, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 11 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 5.
As per claims 17, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 11 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 7.
As per claims 18, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 11 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 8.
As per claims 19, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 18 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 9.
As per claims 20, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 19 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 10.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Zimmerman, U.S. Pre-Grant Publication 2022/ 0384045 in view of Krishnaiahsetty et al. U.S. Pre-Grant Publication 2017/ 0169128 and Raghu et al., “Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series” as applied above to claims 1 and 11, and further in view of Albert et al., U.S. Pre-Grant Publication 2014/ 0276162.
As per claims 6, Zimmerman in view of Krishnaiahsetty and Raghu teaches the apparatus of claim 1 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu do not explicitly teach, however Albert further teaches the apparatus wherein generating the at least a diagnostic label further comprises:
comparing the multimodal representations to similar multimodal representations from other users (paragraph 45 pattern recognition algorithm and paragraph 54 - compared with other ECG data in the database or cloud, taking into account data input by the user regarding the condition and status of the user ); and
applying at least an algorithm to identify one or more abnormalities (paragraph 45).
It would have been obvious to one of ordinary skill in the art before the effective filing date to add these features into Zimmerman in view of Krishnaiahsetty and Raghu. One of ordinary skill in the art before the effective filing date would have added these features into Zimmerman in view of Krishnaiahsetty and Raghu with the motivation to process, distribute, and analyze medical data (Albert, Abstract).
As per claims 16, Zimmerman in view of Krishnaiahsetty and Raghu teaches the method of claim 11 as described above.
Zimmerman in view of Krishnaiahsetty and Raghu further teaches the method as described above in claim 6.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Wagner et al Pub. No.: US 2022/0189636 Disclosed systems, methods, and computer readable media can diagnose a health condition based on patient time series data.
Anand et al Pub. No.: US 2024/0046109 An apparatus and method for expanded cohort application of machine-learning classifier methods based on a seed data set.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Neal R Sereboff whose telephone number is (571)270-1373. The examiner can normally be reached M - T, M - F 8AM - 6PM.
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 Morgan can be reached at (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.
/NEAL SEREBOFF/
Primary Examiner
Art Unit 3626
Prosecution Insights