DETAILED ACTION
Notices to Applicant
This communication is a non-final rejection. Claims 1-20, as filed 01/13/2025, are currently pending and have been considered below.
The application claims domestic benefit to 63/620,226 (01/12/2024). Entitlement to this date, 01/12/2024, is only appropriate where the provisional provides written description support under 112(a) for a claim. The provisional here supports a single-LLM pipeline but not a “multi-agent orchestrator” or “ECG measurements extracted or derived from the raw ECG signals and annotations of cardiac events.” Thus claims 1-20 are not entitled to the filing date of the provisional. The claims are examined with a priority date of 01/13/2025.
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 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.
Claim Objections
Claim 17 is objected to because of the following informalities. The claim recites “a computing device to:…computing metrics” which the Examiner interprets for grammatical correctness to read “a computing device to: …compute metrics.”
Appropriate correction is required.
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, 14, and 17 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 pre-AIA the applicant regards as the invention. Specifically, the term “the healthcare provider” lacks antecedent basis in claims 1 and 17. Similarly, “the LLM” in claim 14 lacks antecedent basis.
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 non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter 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 14-16 are rejected under 35 U.S.C. 101 for being directed to non-statutory subject matter, namely, software per se. The claims recite “a system” with “a data repository,” a multi-agent query processor,” and “a user interface” without reciting any physical components like a physical processor, memory, or display.
Step 1
Claims 1-20 recite(s) subject matter within a statutory category as a process, machine, and/or article of manufacture (with the software per se qualification described above with respect to claims 14-16) with the following features.
1. A method for analyzing pre-processed electrocardiographic (ECG) data, comprising:
receiving an input message regarding health of a subject; (additional element – insignificant extra-solution activity; mere data-gathering)
processing the input message using a multi-agent orchestrator to identify data elements from the pre-processed ECG data, wherein the pre-processed ECG data is associated with historical data, real-time data, or both derived from a plurality of electrographic recorders, and wherein the pre-processed ECG data includes ECG measurements extracted or derived from raw ECG signals and annotations of cardiac events; (abstract idea – mental process because a clinician can mentally review, query, and identify pertinent ECG data; to the extent that the multi-agent orchestrator is non-abstract, it amounts to merely linking the abstract idea to a computer and generally linking to a technical field)
retrieving the identified data elements from a data repository; (additional element – insignificant extra-solution activity; mere data-gathering)
computing metrics corresponding to the input message based on the retrieved data elements; (abstract idea – mental process because a clinician can mentally compute metrics)
generating a response to the input message using a large language model (LLM) or at least one agent to integrate the retrieved data elements and the computed metrics; (abstract idea – mental process because a clinician can mentally review, query, and identify pertinent ECG data; to the extent that the LLM or agent is non-abstract, it amounts to merely linking the abstract idea to a computer and generally linking to a technical field)
presenting the response to the healthcare provider through a user interface. (additional element – insignificant extra-solution activity; mere data output)
Step 2A Prong One
The broadest reasonable interpretation of these steps includes mental processes as described above. Other than reciting generic computer terms like agents, an LLM model, and a data repository, nothing in the claims precludes the italicized portions from practically being performed in the mind by a clinician reviewing patient data, following logic, and creating a report on paper.
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims. For example, claims 2-10 recite particular aspects of how the clinician can think about and monitor the patient is performed but for recitation of generic computer components.
Step 2A Prong Two
This judicial exception is not integrated into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements:
amount to mere instructions to apply an exception. For example, the multi-agent orchestrator and LLM recitations invoke generic computers as a tool to perform the abstract idea, see the list of generic computing devices that can perform the method in applicant’s specification [0062]; MPEP 2106.05(f))
add insignificant extra-solution activity to the abstract idea. For example, receiving and outputting data amounts to mere data gathering and output, recitation of ECG data amounts to selecting a particular data source or type of data to be manipulated, see MPEP 2106.05(g))
generally link the abstract idea to a particular technological environment or field of use such as the multi-agent orchestrator and LLM recitations, see MPEP 2106.05(h))
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. For example, claims 11 and 13 recite a chatbot and prompt engineering which amount to invoking computers as a tool to perform the abstract idea. Claim recites additional limitations which add insignificant extra-solution activity to the abstract idea which amounts to mere data gathering. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, add insignificant extra-solution activity to the abstract idea, and generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, other than the abstract idea per se amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields such as receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i), performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii), electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii), and/or storing and retrieving information in memory, Versata Dev. Group, MPEP 2106.05(d)(II)(iv). The Examiner further notes that using LLMs and multi-agent frameworks were conventional technology as of 9-25-2024 as described in the MAO reference (see the rejection of claim 2, e.g., below).
Dependent claims recite additional subject matter which, as discussed above with respect to integration of the abstract idea into a practical application, amount to invoking computers as a tool to perform the abstract idea. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation.
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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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, 5-10, 12-14, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou (Yuan Zhou et al.; "Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics," arXiv:2410.02026) in view of Hsieh (US20090299204A1).
Regarding claim 1, Zhou discloses: A method for analyzing pre-processed electrocardiographic (ECG) data (“ZODIAC assists cardiologists by extracting clinically relevant characteristics from patient data, detecting significant arrhythmias, and generating preliminary reports for the review and refinement by cardiologists,” Abstract), comprising:
--receiving an input message regarding health of a subject (“cardiologists or their assistants can upload patient data, including monitored metrics and ECG tracings from wearable patches (Steinhubl et al., 2018) or Holters (Kim et al., 2009). This data is routed through AWS API Gateway, triggering AWS Lambda to invoke SageMaker, where ZODIAC is hosted. On AWS SageMaker, ZODIAC generates preliminary reports, including findings and interpretation based on the data, and performs fact-checking to ensure accuracy before finalizing the reports. These reports are then returned to the cardiologists, who can use them as a foundation to finalize their diagnoses, thus enhancing workflow efficiency and improving diagnostic accuracy,” page 7);
--processing the input message using a multi-agent orchestrator to identify data elements from the pre-processed ECG data (“ZODIAC is built on a multi-agent collaboration framework, enabling the processing of patient data across multiple modalities,” Abstract; multiple agents on page 7 and Figure 4),
--wherein the pre-processed ECG data is associated with historical data, real-time data, or both derived from a plurality of electrographic recorders and wherein the pre-processed ECG data includes ECG measurements extracted or derived from raw ECG signals and annotations of cardiac events (patient data from wearable patches or Holters on page 7; “Patient Data is comprised of three sections: (1) Biostatistical information (B) provides background details about the patient such as date of birth, gender, and age group. (2) Metrics (M) summarize cardiological attributes and their corresponding values presented in a tabular format, providing an overview of 24-hour monitored statistics for the patient…AF Burden” page 4), and
--computing metrics corresponding to the input message based on the retrieved data elements (summarizing cardiological attributes such as AF Burden: 12% on page 4);
--generating a response to the input message using a large language model (LLM) or at least one agent to integrate the retrieved data elements and the computed metrics (“ZODIAC generates a patient-specific report by integrating the metrics, tracings, clinical findings, and diagnostic interpretation,” page 4; Figure 2); and
--presenting the response to the healthcare provider through a user interface (showing Clinical Report to Cardiologist in Figure 2).
Zhou does not expressly disclose but Hsieh teaches:
--retrieving the identified data elements from a data repository (“an ECG database for saving web-based data exported from the clinical device,” [0020]);
One of ordinary skill in the art before the effective filing date would have been motivated to expand Zhou’s cardiology report system to include the ECG database of Hsieh because this would “facilitate clinical inquiries and management,” Hsieh [0002].
Additionally, it can be seen that each element is taught by either Zhou or Hsieh. The ECG database of Hsieh does not affect the normal functioning of the elements of the claim which are taught by Zhou. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Zhou with the teachings of Hsieh since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Claims 14 and 17 are substantially similar to claim 1 and are rejected with the same reasoning.
Regarding claims 5 and 20, Zhou discloses: wherein the ECG measurements comprise PR interval, PR segment, QRS complex duration, heart rate variability, R-R intervals, QT intervals, ST interval, ST segment, and data for assessing the cardiac events, or any combination thereof (PR Interval on page 4).
Regarding claim 6, Zhou discloses: wherein the cardiac events comprise arrhythmias and/or any cardiovascular irregularities (significant arrhythmias on page 4).
Regarding claim 7, Zhou discloses: wherein the input message specifies a time period for analysis, a comparison of data across multiple subjects, a comparison of data across multiple studies for a single subject, or any combination thereof (data for a subject over a 24-hour period on page 4).
Regarding claim 8, Zhou discloses: wherein the response comprises insights associated with the input message (various findings in Figure 2).
Regarding claim 9, Zhou discloses: wherein the retrieved data elements and/or the computed metrics include visual representations of ECG data for specific events (ECG tracings; “10-second strip highlighting the highest degree of AV block” on page 4).
Regarding claim 10, Zhou discloses: wherein the response includes textual information, graphical representation, or both (Clinical Report in Figure 2).
Regarding claim 12, Zhou does not expressly disclose but Hsieh teaches: wherein the data repository comprises the pre-processed ECG data and the raw ECG signals associated with the historical data, real-time data, or both and tagged with subject's metadata (waveforms associated with patient in [0046]-[0047]). The motivation to combine is the same as in claim 1.
Regarding claim 13, Zhou discloses: a prompt engineering step to refine the input message for interpretation by the multi-agent orchestrator (“system prompt” for fine-tuning and “in-context learning” on page 6).
Claims 2-3, 11, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou (Yuan Zhou et al.; "Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics," arXiv:2410.02026) in view of Hsieh (US20090299204A1) and MAO (“multi-agent-orchestrator 0.0.15,” https://pypi.org/project/multi-agent-orchestrator/0.0.15/).
Regarding claims 2 and 18, Zhou does not expressly disclose but MAO teaches: performing semantic analysis on the received input message to determine an intent of the input message and to identify data or visualizations required to fulfil the intent; selecting an agent based on the identified data or visualizations required to fulfil the intent of the input message; and receiving an output from the selected agent, the output comprising the identified data elements and/or the computed metrics (“Intelligent intent classification — Dynamically route queries to the most suitable agent based on context and content,” page 2; agent selection, processing, and response output on page 3).
One of ordinary skill in the art before the effective filing date would have been motivated to expand the cardiology report system of Zhou and Hsieh to include the multi-agent orchestration framework of MAO because this would ensure “coherent interactions” across multiple agents (MAO page 2).
Regarding claims 3 and 19, Zhou in combination with Hsieh and MAO teaches: performing semantic analysis on the received input message to determine an intent of the input message and to identify data or visualizations required to fulfil the intent; selecting a plurality of agents based on the identified data or visualizations required to fulfil the intent of the input message; coordinating the execution of the selected plurality of agents in a predetermined sequence; receiving outputs from each of the selected plurality of agents, the outputs comprising the identified data elements and/or the computed metrics; and aggregating the received outputs from the selected plurality of agents into a unified response. Zhou discloses a plurality of agents executed in a predetermined sequence (i.e., metrics to findings agent, tracings to findings agent, findings to interpretation agent on page 5) and generates a synthesized report that integrates their outputs into a single coherent response (page 4).
Regarding claim 11, Zhou does not expressly disclose but MAO teaches: wherein the input message is received via a chatbot interface (“chatbots” on page 3).
Additionally, it can be seen that each element is taught by either Zhou, Hsieh, or MAO. The chatbot interface of MAO does not affect the normal functioning of the elements of the claim which are taught by Zhou and Hsieh. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Zhou and Mao with the teachings of Hsieh since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Zhou (Yuan Zhou et al.; "Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics," arXiv:2410.02026) in view of Hsieh (US20090299204A1) and Gopalakrishnan (US20200022594A1).
Regarding claim 4, Zhou does not expressly disclose but Gopalakrishnan teaches: monitoring real-time pre-processed ECG data stream to detect a critical event; and generating an alert including an actionable insight based on the critical event (“Triggers or alerts may be provided to the user in response to the measured physiological signals and/or parameters. Such triggers or alerts may notify the user to take corrective steps to improve their health or monitor other vital signs or physiological parameters,” [0022]).
One of ordinary skill in the art before the effective filing date would have been motivated to expand the cardiology report system of Zhou and Hsieh to include the real-time monitoring and alerting of Gopalakrishnan because this would allow caregivers to provide timely clinical interventions to improve patient health.
Additionally, it can be seen that each element is taught by either Zhou, Hsieh, or Gopalakrishnan. The ECG database of Hsieh does not affect the normal functioning of the elements of the claim which are taught by Zhou and Gopalakrishnan. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Zhou and Gopalakrishnan with the teachings of Hsieh since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Zhou (Yuan Zhou et al.; "Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics," arXiv:2410.02026) in view of Hsieh (US20090299204A1) and Gao (Dawei Gao et al., "AgentScope: A Flexible yet Robust Multi-Agent Platform", arXiv:2402.14034).
Regarding claim 15, Zhou discloses an insights agent to derive and compute contextual insights related to the input message; an ECG strip agent to generate visual representations of the retrieved ECG data (findings and interpretation agents and for rendering ECG strings, pages 4-5). Zhou does not expressly disclose but Gao teaches:
--wherein the multi-agent query processor comprises: a SQL agent to retrieve structured ECG data from the data repository…and a tool-calling planner for coordinating the execution of the SQL, insights, and ECG strip agents (“9.7 ReAct Agents: Convert Natural Language to SQL Query” including a “ServiceToolkit module,” page 26).
One of ordinary skill in the art before the effective filing date would have been motivated to expand the cardiology report system of Zhou and Hsieh to include the SQL agent of Gao because equipping agents with tools to use an LLM reasoning engine for database tasks this would allow more clinically meaningful queries against a structured SQL database.
Additionally, it can be seen that each element is taught by either Zhou, Hsieh, or Gao. The ECG database of Hsieh does not affect the normal functioning of the elements of the claim which are taught by Zhou and Gao. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Zhou and Gao with the teachings of Hsieh since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Zhou (Yuan Zhou et al.; "Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics," arXiv:2410.02026) in view of Hsieh (US20090299204A1) and Crouse (US20230168955A1).
Regarding claim 16, Zhou does not expressly disclose but Crouse teaches: a validation unit to validate the input message based on predefined rules and data schemas prior to processing the input message (“Additionally, as part of the message subscription, a series of validation rules are declared that will be applied to each incoming message. The validation step must succeed in order for the message to be processed by the declared message handler,” [0014]; “Depending on the specific pipeline declaration, behavior modifying wrappers can be automatically injected around certain components in order to perform tasks like schema and payload validation without forcing developers to re-implement that logic over and over,” [0015]).
One of ordinary skill in the art before the effective filing date would have been motivated to expand the cardiology report system of Zhou and Hsieh to include the input validation of Crouse because this would protect against “invalid or malicious messages” that “would case unexpected, or even problematic results” (Crouse [0012]).
Additionally, it can be seen that each element is taught by either Zhou, Hsieh, or Crouse. The ECG database of Hsieh does not affect the normal functioning of the elements of the claim which are taught by Zhou and Crouse. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Zhou and Crouse with the teachings of Hsieh since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Liu (Chunyu Liu, Yongpei Ma, Kavitha Kothur, Armin Nikpour, Omid Kavehei; "BioSignal Copilot: Leveraging the power of LLMs in drafting reports for biomedical signals" medRxiv 2023.06.28.23291916; doi: https://doi.org/10.1101/2023.06.28.23291916) discloses techniques for using LLMs to draft medical reports, e.g., Fig. 2.
PNG
media_image1.png
378
708
media_image1.png
Greyscale
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA BLANCHETTE whose telephone number is (571)272-2299. The examiner can normally be reached on Monday - Thursday 7:30AM - 6:00PM, 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, Shahid Merchant, can be reached on (571) 270-1360. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JOSHUA B BLANCHETTE/Primary Examiner, Art Unit 3624
Prosecution Insights