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 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, 6-9, 16, and 19-25 are rejected under 35 U.S.C. 103 as being unpatentable over An et al. (U.S. 2023/0153545, hereinafter “An”) in view of Sizemore et al. (U.S. 2022/0028543, hereinafter “Sizemore”).
Regarding Claim 1, An teaches a computer-implemented method (Abstract and ¶ [0062]), comprising:
receiving, from one or more data systems, a message including unstructured clinical data (fig. 3; ¶ [0063] and [0066]—unstructured raw medical data are received);
applying a machine learning model to identify a first entity and a second entity present in the unstructured clinical data, the first entity and the second entity occupying a same row of the unstructured clinical data or successive rows in a same column of the unstructured clinical data, the machine learning model being trained to determine, based at least on the unstructured clinical data including the first entity, that the second entity is a most likely entity occupying a next position in the same row or a next row in the same column of the unstructured clinical data (¶ [0039] and [0049] – [0051] describe the use of machine learning. Fig. 6 and ¶ [0103] – [0110] describe converting the unstructured data into structured data in a table format. The table includes rows and columns such that a first entity and a second entity are identified that occupy successive columns in the same row or successive rows in the same column, such as entities 2 and 4 that are placed in row 1 of post-processed data 430).
An does not specifically teach:
extracting, from the structured clinical data, a clinically significant data; and
controlling, based at least on the clinically significant data, at least one medical device to perform one or more tasks.
However, Sizemore teaches:
extracting, from clinical data, a clinically significant data (¶ [0047] – [0050]—clinically significant data are identified and extracted from medical records {clinical data}. The data are identified as significant based on a risk score such as a medical conflict or a value that exceeds a threshold); and
controlling, based at least on the clinically significant data, at least one medical device to perform one or more tasks (¶ [0050] – [0051]—a medical device may be controlled based on the risk, such as shutting down a medical device or adjusting operating parameters of a medical device).
All of the claimed elements were known in An and Sizemore and could have been combined by known methods with no change in their respective functions. It therefore would have been obvious to a person of ordinary skill in the art at the time of filing of the applicant’s invention to combine the controlling a medical device based on clinically significant data of Sizemore with the structured clinical data of An to yield the predictable result of extracting, from the structured clinical data, a clinically significant data; and controlling, based at least on the clinically significant data, at least one medical device to perform one or more tasks. One would be motivated to make this combination for the purpose of reducing risk to a patient by identifying potential dangers in clinical data that medical professionals may have missed, as described in Sizemore, ¶ [0002] and [0046].
Regarding Claim 6, An/Sizemore teaches wherein the machine learning model identifies the first entity and the second entity by at least assigning, to each of the first entity and the second entity, a corresponding entity marker (An, ¶ [0103] – [0105]—entities are identified by assigning column names to the entities).
Regarding Claim 7, An/Sizemore teaches wherein the at least one medical device is controlled based on at least one of a header, an organism name, a drug name, a concentration value, and an interpretation value comprising the first entity and/or the second entity (Sizemore, ¶ [0052]—the control may be based on an interpretation value such as blood pressure exceeding a certain value).
Regarding Claim 8, An/Sizemore teaches training, based at least on training data including annotated unstructured clinical data, the machine learning model to learn one or more entity patterns that are present in the annotated unstructured clinical data, the annotated unstructured clinical data including a plurality of entities annotated with a corresponding ground truth entity marker (An, ¶ [0049] – [0050]).
Regarding Claim 9, An/Sizemore teaches wherein the one or more entity patterns include a co-occurrence of the first entity and the second entity in a single row or in successive rows of a single column (An, fig. 6; ¶ [0103] – [0108]).
Regarding Claim 16, An/Sizemore teaches applying one or more second machine learning models to extract, from the structured clinical data, the clinically significant data (Sizemore, ¶ [0048] – [0050]—a second machine learning model extracts the clinically significant data and determines a risk score that is used to initiate an action).
Regarding Claim 19, An/Sizemore teaches wherein the controlling of the at least one medical device includes transmitting, to the at least one medical device, one or more messages to adjust an operational state and/or a functional element of the at least one medical device (Sizemore, ¶ [0050] – [0051]—a medical device can be controlled by shutting down the device or adjusting a parameter. Although Sizemore does not explicitly state that the device is controlled by transmitting a message, the examiner takes official notice that transmitting a message is a well-known method for controlling a computerized device).
Regarding Claim 20, An/Sizemore teaches wherein the one or more messages include one or more instructions, which when executed by a processor associated with the at least one medical device, adjust the operational state and/or the functional element of the at least one medical device (Sizemore, ¶ [0050] – [0051]—a functional element such as radiation levels of an X-ray machine are adjusted. Although Sizemore does not explicitly state the use of instructions executed by a processor associated with the medical device, the examiner takes official notice that these elements are well-known in the art, rendering them obvious).
Regarding Claim 21, An/Sizemore teaches wherein the one or more messages include one or more values, which when applied at the at least one medical device, adjust the operational state and/or the functional element of the at least one medical device (Sizemore, ¶ [0050] – [0051]—parameter values such as radiation levels of an X-ray machine are adjusted, which implies values instructing the device what the parameters should be set to).
Regarding Claim 22, An/Sizemore teaches wherein the at least one medical device comprises an infusion pump including a pumping functional element, and wherein the method comprises generating the one or more messages to adjust a pumping rate of the pumping functional element (Sizemore, ¶ [0046] and [0050] – [0051]—although Sizemore does not name an infusion pump, it describes controlling other medical devices including an MRI and X-ray device. An infusion pump is a well-known medical device, so controlling it is an obvious variation on the teachings of Sizemore).
Regarding Claim 23, An/Sizemore teaches wherein the at least one medical device comprises a dispensing cabinet or a wasting station including one or more receptacles, and wherein the method comprises generating the one or more messages to control access to the one or more receptacles (Sizemore, ¶ [0046] and [0050] – [0051]—although Sizemore does not name a dispensing cabinet or a wasting station, it describes controlling other medical devices including an MRI and X-ray device. A dispensing cabinet and a wasting station are well-known medical devices, so controlling them is an obvious variation on the teachings of Sizemore).
Regarding Claim 24, An teaches a system (fig. 1; ¶ [0035] – [0036]), comprising:
at least one data processor (fig. 1; ¶ [0037] – [0038]); and
at least one memory storing instructions (figs. 1 and 7; ¶ [0039] and [0114]). An and Sizemore teach the instructions, when executed by the at least one data processor, result in operations comprising the method of claim 1, as described for claim 1, above.
Regarding Claim 25, An teaches a non-transitory computer readable medium storing instructions, which when executed by at least one data processor, result in operations (fig. 7; ¶ [0116] and [0125]). An and Sizemore teach the operations comprising the method of claim 1 as described for claim 1, above.
Claims 3-5 are rejected under 35 U.S.C. 103 as being unpatentable over An in view of Sizemore, as applied to claim 1, above, and further in view of Abolhasssani et al. (U.S. 2022/0358336, hereinafter “Abolhasssani”).
Regarding Claim 3, An/Sizemore does not specifically teach generating, based at least on an alignment between the first entity and the second entity in the unstructured clinical data, an entity graph including the first entity and the second entity. However, Abolhasssani teaches generating, based at least on an alignment between a first entity and a second entity in unstructured data, an entity graph including the first entity and the second entity (¶ [0020] and [0026]. Fig. 3 and ¶ [0046] provides a further example and explanation of an entity graph).
All of the claimed elements were known in An/Sizemore and Abolhasssani and could have been combined by known methods with no change in their respective functions. It therefore would have been obvious to a person of ordinary skill in the art at the time of filing of the applicant’s invention to combine the generating an entity graph of Abolhasssani with the unstructured clinical data and first and second entities of An/Sizemore to yield the predictable result of generating, based at least on an alignment between the first entity and the second entity in the unstructured clinical data, an entity graph including the first entity and the second entity. One would be motivated to make this combination for the purpose of improving the speed and accuracy of preparing data without requiring expert knowledge (Abolhasssani, ¶ [0002]).
Regarding Claim 4, An/Sizemore/Abolhasssani teaches generating, based at least on a horizontal alignment between the first entity and the second entity, a horizontal chain of the entity graph to include the first entity and the second entity such that the first entity and the second entity occupy a single row (Abolhasssani, fig. 3; ¶ [0036] and [0046]—the data are arranged in rows and columns. Although the graph is described as generating alignment by columns, rows and columns are interchangeable as a matter of the orientation of data represented in a table, and the terms horizontal and vertical are merely ways that a graph may be represented on paper or on a screen. Abolhasssani therefore teaches the recited graph alignment between entities).
Regarding Claim 5, An/Sizemore/Abolhasssani teaches generating, based at least on a vertical alignment between the first entity and the second entity, a vertical chain of the entity graph to include the first entity and the second entity such that the first entity and the second entity occupy successive rows in a single column (Abolhasssani, fig. 3; ¶ [0036] and [0046]—the data are arranged in rows and columns. The terms horizontal and vertical are merely ways that a graph may be represented on paper or on a screen. Abolhasssani therefore teaches the recited graph alignment between entities).
Allowable Subject Matter
Claims 2, 10-15, and 17-18 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
None of the prior art of record teaches all of the limitations of claim 2, which recites:
2. The method of claim 1, wherein the machine learning model is trained to identify the second entity included in the unstructured clinical data by at least:
determining, based at least on the unstructured clinical data including the first entity, a first probability that the second entity is the most likely entity occupying the next position in the same row or the next row in the same column of the unstructured clinical data,
determining, based at least on the unstructured clinical data including the first entity, a second probability that a third entity is the most likely entity occupying the next position in the same row or the next row in the same column of the unstructured clinical data,
identifying the second entity based at least on a comparison of the first probability and the second probability.
An determines that entities that occupy the next position in rows and columns, but does not determine and compare probabilities in the manner recited by claim 2.
None of the prior art of record teaches all of the limitations of claim 10, which recites:
10. The method of claim 1, wherein the one or more tasks include:
identifying, based at least on the clinically significant data, a stage of a clinical workflow associated with the one or more messages,
determining, based at least on a timestamp associated with the one or more messages, a quantity of time between two or more successive stages of the clinical workflow, and
in response to the quantity of time between the two or more successive stages of the clinical workflow exceeding a threshold value, determining one or more corrective configurations for the at least one medical device.
Sizemore determines an action that can be seen as corrective for a medical device, but does not consider timestamps in messages and does not determine stages of a clinical workflow.
None of the prior art of record teaches all of the limitations of claim 17, which recites:
17. The method of claim 16, wherein the one or more second machine learning models are trained to identify and tag the clinically significant data included in the structured clinical data, and wherein the one or more second machine learning models are further trained to determine that the message associated with the structured clinical data is actionable in response to more than a threshold portion of the structured clinical data being tagged as clinically significant.
Sizemore determines clinically significant data, but does not tag the clinically significant data and does not consider a threshold portion of the structured data as being tagged as clinically significant.
Claims 11-15 and 18 recite allowable subject matter by virtue of their dependence on claims 10 or 17.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. This art includes:
Spandorfer, Adam, et al. (“Deep learning to convert unstructured CT pulmonary angiography reports into structured reports,” European radiology experimental 3.1 (2019): 37) teaches a deep learning system that converts unstructured CT scan reports into structured form, applying labels to entities in the reports
Reisswig (U.S. 2021/0383067) teaches using machine learning to extract a graph structure from text documents, with an example that includes steps in a laboratory process
Giacometti et al. (U.S. 2025/0357012) teaches a context sensitive guidance engine that processes medical information and recommends emergency procedures and equipment to address a medical situation; it can also control medical devices to handle the medical situation
Cwalina et al. (U.S. Patent 12,001,416) teaches systems and methods for parsing unstructured data into database tables, with a mention of machine learning
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAL W SCHNEE whose telephone number is (571) 270-1918. The examiner can normally be reached M-F 7:30 a.m. - 6:00 p.m.
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, Michael Huntley can be reached at 303-297-4307. 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.
/HAL SCHNEE/Primary Examiner, Art Unit 2129
Prosecution Insights