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 .
Status of the Claims
Claims 1-20 are currently pending.
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 a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Step 1
Claims 1-20 are within the four statutory categories. Claims 1-13 are drawn to a method for mapping medical text to an ontology, which is within the four statutory categories (i.e. process). Claims 14-17 are drawn to a system for mapping medical text to an ontology, which is within the four statutory categories (i.e. machine). Claims 18-20 are drawn to a non-transitory medium for mapping medical text to an ontology, which is within the four statutory categories (i.e. manufacture).
Prong 1 of Step 2A
Claim 1, which is representative of the inventive concept, recites: A computer-implemented method comprising:
receiving one or more clinical notes associated with a patient, wherein each of the one or more clinical notes includes unstructured text;
for each of the one or more clinical notes:
extracting, using a neural network, one or more text spans from the unstructured text, each of the one or more text spans identifying a respective input phrase in the unstructured text and comprising a word or a group of consecutive words in the unstructured text, wherein extracting the one or more text spans comprises classifying, using the neural network, each text span into one of a plurality of categories, and labeling each text span with the category into which it is classified to generate a labeled text span;
for each of the one or more text spans, matching, using a text matcher, the text span with a respective output ontology entity from an ontology, the respective output ontology entity relating to a clinical condition of the patient, wherein the ontology (i) comprises a set of ontology entities that represent clinical terms and (ii) specifies relationships between the clinical terms; and
outputting data defining the one or more text spans and the respective output ontology entity for each of the one or more text spans.
The underlined limitations as shown above, given the broadest reasonable interpretation, cover the abstract ideas of a mental process and/or a certain method of organizing human activity because they recite a process that could be practically performed in the human mind (i.e. observations, evaluations, judgments, and/or opinions – in this case, the limitations of receiving patient clinical notes including unstructured text, extracting text spans identifying a phrase from the unstructured text by classifying each text span into one of a plurality of categories and labeling each text span with a category, matching the text span with an ontology entity from an ontology, the ontology entities representing clinical terms and specifying relationships between clinical terms are reasonably interpreted as evaluations, judgments, and/or opinions that a human user could perform mentally) or using a pen and paper, but for the recitation of generic computer components, and/or managing personal behavior or relationships or interactions between people (i.e. social activities, teaching, and following rules or instructions – in this case, the limitations of receiving patient clinical notes including unstructured text, extracting text spans identifying a phrase from the unstructured text by classifying each text span into one of a plurality of categories and labeling each text span with a category, matching the text span with an ontology entity from an ontology, the ontology entities representing clinical terms and specifying relationships between clinical terms are reasonably interpreted as following rules or instructions to analyze the contents of a medical record), e.g. see MPEP 2106.04(a)(2). Any limitations not identified above as part of the abstract ideas are deemed “additional elements,” and will be discussed in further detail below.
Furthermore, the abstract ideas for Claims 14 and 18 is identical as the abstract ideas for Claim 1, because the only difference between Claims 1, 14, and 18 is that Claim 1 recites a method, whereas Claim 14 recites a system, and Claim 18 recites a non-transitory computer storage media.
Dependent Claims 2-13, 15-17, and 19-20 include other limitations, for example Claims 2, 15, and 19 recite aggregating clinical conditions related to the ontology entities and generating a patient summary organizing the clinical conditions, Claim 3 recites the contents of the unstructured text, Claims 4-7 recite types of neural network and their functions, Claims 8-10 recite identifying and selecting alternatives for the input phrase, Claims 11-12, 16-17, and 20 recite grouping, categorizing, and ranking the clinical conditions, and Claim 13 recites a type of text matcher, but these only serve to further narrow the abstract ideas, and a claim may not preempt abstract ideas, even if the judicial exception is narrow, e.g. see MPEP 2106.04, and/or do not further narrow the abstract idea and instead only recite additional elements, which will be further addressed below. Hence dependent Claims 2-13, 15-17, and 19-20 are nonetheless directed towards fundamentally the same abstract ideas as independent Claims 1, 14, and 18.
Prong 2 of Step 2A
Claims 1, 14, and 18 are not integrated into a practical application because the additional elements (i.e. the non-underlined limitations above – in this case, the neural network and the output of the data defining the text span and the respective ontology entity) amount to no more than limitations which:
amount to mere instructions to apply an exception – for example, the recitation of the neural network which is presumably executed on some type of computing device, which amounts to merely invoking a computer as a tool to perform the abstract idea, e.g. see pgs. 15-17 of the as-filed Specification, and MPEP 2106.05(f);
generally link the abstract idea to a particular technological environment or field of use – for example, the claim language of the received data being clinical notes, the ontology entity relating to a clinical condition of a patient and the ontology including clinical terms and their relationships, which amounts to limiting the abstract idea to the field of healthcare, e.g. see MPEP 2106.05(h); and/or
add insignificant extra-solution activity to the abstract idea – for example, the recitation of outputting the data defining the text span and the respective ontology entity, which amounts to an insignificant application, see MPEP 2106.05(g).
Additionally, dependent Claims 2-13, 15-17, and 19-20 include other limitations, but these limitations also amount to no more than mere instructions to apply an exception (e.g. the types of neural networks recited in dependent Claims 4-7), generally linking the abstract idea to a particular technological environment or field of use (e.g. the types of classifications recited in dependent Claim 6, the types of condition categories recited in dependent Claim 12), and/or do not include any additional elements beyond those already recited in independent Claims 1, 14, and 18, and hence also do not integrate the aforementioned abstract ideas into a practical application.
Hence Claims 1-20 do not include additional elements that integrate the judicial exceptions into a practical application.
Step 2B
Claims 1, 14, and 18 do not include additional elements that are sufficient to amount to “significantly more” than the judicial exception because the additional elements (i.e. the non-underlined limitations above – in this case, the neural network and the output of the data defining the text span and the respective ontology entity), as stated above, are directed towards no more than limitations that amount to mere instructions to apply the exceptions, generally link the abstract ideas to a particular technological environment or field of use, and/or add insignificant extra-solution activity to the abstract ideas, wherein the additional elements comprise limitations which:
amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields, as demonstrated by:
The present Specification expressly disclosing that the additional elements are well-understood, routine, and conventional in nature:
Pgs. 15-17 of the as-filed Specification discloses that the additional elements (i.e. the computing devices that execute the functions of the neural network and the outputting of the data defining the text span and the respective ontology entity) comprise a plurality of different types of generic computing systems that are configured to perform generic computer functions (i.e. extracting and outputting data) that are well-understood, routine, and conventional activities previously known to the pertinent industry (i.e. healthcare);
Relevant court decisions: The following are examples of court decisions demonstrating well-understood, routine and conventional activities, e.g. see MPEP 2106.05(d)(II):
Storing and retrieving information in memory, e.g. see Versata Dev. Group, Inc. v. SAP Am., Inc. – similarly, the current invention requires storing clinical notes such that they may subsequently be retrieved in order to ultimately output the extracted text spans and the respective ontology entity;
Electronically scanning or extracting data from a physical document, e.g. see Content Extraction and Transmission, LLC v. Wells Fargo Bank – similarly, the current invention recites scanning a clinical note documents, and parsing text spans from the clinical note document;
Dependent Claims 2-13, 15-17, and 19-20 include other limitations, but none of these limitations are deemed significantly more than the abstract ideas because the additional elements recited in the aforementioned dependent claims similarly amount to mere instructions to apply the exceptions (e.g. the types of neural networks recited in dependent Claims 4-7), generally linking the abstract ideas to a particular technological environment or field of use (e.g. the types of classifications recited in dependent Claim 6, the types of condition categories recited in dependent Claim 12), and/or the limitations recited by the dependent claims do not recite any additional elements not already recited in independent Claims 1, 14, and 18, and hence do not amount to “significantly more” than the abstract ideas.
Hence, Claims 1-20 do not include any additional elements that amount to “significantly more” than the judicial exceptions.
Thus, taken alone, the additional elements do not amount to significantly more than the abstract ideas identified above. Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually, and there is no indication that the combination of elements improves the functioning of a computer or improves any other technology, and their collective functions merely provide conventional computer implementation.
Therefore, whether taken individually or as an ordered combination, Claims 1-20 are nonetheless rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
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.
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 1-2, 13-15, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Devarakonda (US 2015/0356270) in view of Peri (US 2021/0118574), further in view of Heinze (US 2014/0337044).
Regarding Claim 1, Devarakonda teaches the following: A computer-implemented method comprising:
receiving one or more clinical notes associated with a patient, wherein each of the one or more clinical notes includes unstructured text (The system includes electronic medical records (EMRs) that include structured and unstructured data, e.g. see Devarakonda [0014].);
for each of the one or more clinical notes:
extracting one or more text spans from the unstructured text, each of the one or more text spans identifying a respective input phrase in the unstructured text and comprising a word or a group of consecutive words in the unstructured text (The system extracts candidate medical concepts from an EMR, the EMR containing structured and unstructured data, e.g. see Devarakonda [0015], wherein the data in the EMR includes various data items such as words, e.g. see Devarakonda [0023].);
for each of the one or more text spans, matching, using a text matcher, the text span with a respective output ontology entity from an ontology, the respective output ontology entity relating to a clinical condition of the patient (The system maps the candidate medical concepts from the EMR to a list of standardized medical concepts (i.e. an ontology entity comprising data relating to a clinical condition of the patient) utilizing an ontology such as the Unified Medical Language System (UMLS), e.g. see Devarakonda [0015]-[0016], and groups the highest ranking candidate medical problems utilizing a grouping module, e.g. see Devarakonda [0020].), wherein the ontology (i) comprises a set of ontology entities that represent clinical terms and (ii) specifies relationships between the clinical terms (The UMLS contains medical terms, e.g. see Devarakonda [0015]-[0016], and further the system identifies relationship data between medical data, e.g. see Devarakonda [0017].); and
outputting data defining the one or more text spans and the respective output ontology entity for each of the one or more text spans (The system maps medical problems to preferred names and outputs a list of the preferred names, e.g. see Devarakonda [0037]-[0038] and [0041].).
But Devarakonda does not teach and Peri teaches the following:
wherein the extracting is performed using a neural network (The system includes neural networks that extract information from unstructured documents such as lab reports and clinician notes, e.g. see Peri [0076].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of healthcare to modify Devarakonda to incorporate the neural networks to extract data as taught by Peri in order to enable the transformation of unstructured text to information represented in vectors, e.g. see Peri [0076].
But the combination of Devarakonda and Peri does not teach and Heinze teaches the following:
wherein extracting the one or more text spans comprises classifying, using the neural network, each text span into one of a plurality of categories, and labeling each text span with the category into which it is classified to generate a labeled text span (The system includes a grammatical analysis system implemented using machine learning, e.g. see Heinze [0031], wherein the grammatical analysis system receives input text from documents, wherein the input text includes words, numbers, punctuations, and white or blank spaces to be annotated and parsed to identify syntactic categories for the input, e.g. see Heinze [0032]-[0036].); and
wherein the matching is performed on the labeled text span (The data that has been annotated (i.e. the labeled text span) is subsequently mapped (matched) to various code data by an ontology map application algorithm, e.g. see Heinze [0037]-[0038].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of healthcare to modify the combination of Devarakonda and Peri to incorporate the categorization and labeling of the text prior to the matching and then performing the matching using the labeled text as taught by Heinze in order to enable the system to handle special words or phrasings that may need normalizing and to ensure the accuracy of the language processing, e.g. see Heinze [0008] and [0033]-[0034].
Regarding Claim 2, the combination of Devarakonda, Peri, and Heinze teaches the limitations of Claim 1, and Devarakonda further teaches the following: The method of claim 1, further comprises:
aggregating one or more clinical conditions related to one or more output ontology entities matched to one or more text spans in the one or more clinical notes (The UMLS contains standardized medical terms (i.e. ontology entities) having concept unique identifiers (CUIs) relating to medical disorders (i.e. clinical conditions), e.g. see Devarakonda [0015].); and
generating a patient summary that organizes the aggregated clinical conditions (The system generates a final list mapping medical problems to preferred names and outputs the list of the preferred names as part of a clinical summary, e.g. see Devarakonda [0003], [0037]-[0038], and [0041].).
Regarding Claim 13, the combination of Devarakonda, Peri, and Heinze teaches the limitations of Claim 1, and Devarakonda further teaches the following:
The method of claim 1, wherein the text matcher is a graph-based text matcher (The system groups the highest ranking candidate medical problems, wherein the grouping maybe a graph of grouped problems, e.g. see Devarakonda [0020], Fig. 1.).
Regarding Claims 14 and 18, the limitations of Claims 14 and 18 are substantially similar to those claimed in Claim 1, with the sole difference being that Claim 1 recites a method, whereas Claim 14 recites the functions of a system executed by a computer, and Claim 18 recites a non-transitory computer storage media whose functions are executed by a computer. Specifically pertaining to Claim 14 and 18, Examiner notes that Devarakonda teaches a system and a computer program product including a computer readable storage media, e.g. see Devarakonda [0042]-[0043] and [0048], and hence the grounds of rejection provided above for Claim 1 are similarly applied to Claims 14 and 18.
Regarding Claims 15 and 19, the limitations of Claims 15 and 19 are substantially similar to those claimed in Claim 2, with the sole difference being that Claim 2 recites a method, whereas Claim 15 recites the functions of a system executed by a computer, and Claim 19 recites a non-transitory computer storage media whose functions are executed by a computer. Specifically pertaining to Claim 15 and 19, Examiner notes that Devarakonda teaches a system and a computer program product including a computer readable storage media, e.g. see Devarakonda [0042]-[0043] and [0048], and hence the grounds of rejection provided above for Claim 2 are similarly applied to Claims 15 and 19.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over the combination of Devarakonda, Peri, and Heinze in view of Jackson (US 2011/0022412).
Regarding Claim 3, the combination of Devarakonda, Peri, and Heinze teaches the limitations of Claim 1, but does not teach and Jackson teaches the following:
The method of claim 1, wherein the unstructured text includes one or more of an abbreviation, a spelling error, language ambiguity, or hand-written text (The system includes a medical record that includes unstructured form, for example an image of a handwritten note saying that a patient has a condition (i.e. hand-written text) and/or other information, for example an indication of a test date of “Jan. 1, 2009” and a dosage of “40 mg” (i.e. “Jan.” comprising an abbreviation for “January” and “mg” comprising an abbreviation for “milligrams”), e.g. see Jackson [0025].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of healthcare to modify the combination of Devarakonda, Peri, and Heinze to incorporate the handwritten notes and abbreviations as taught by Jackson in order to enable the system to handle data from a variety of sources, e.g. see Jackson [0003] and [0005].
Claims 4-7 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Devarakonda, Peri, and Heinze in view of Chaballout (US 2021/0313022).
Regarding Claim 4, the combination of Devarakonda, Peri, and Heinze teaches the limitations of Claim 1, but does not teach and Chaballout teaches the following:
The method of claim 1, wherein the neural network is a multi-task encoder-only transformer neural network (The system includes electronic health records (EHR) that are analyzed utilizing natural language processing (NLP) tools, e.g. see Chaballout [0028] and [0030], wherein the NLP tool includes a bidirectional encoder representation (BERT) (i.e. a multi-task encoder-only transformer neural network), e.g. see Chaballout [0044].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of healthcare to modify the combination of Devarakonda, Peri, and Heinze to incorporate the multi-task encoder-only transformer neural network as taught by Chaballout in order to automatically objectively analyze the medical records and avoid misclassification of medical codes, e.g. see Chaballout [0003].
Regarding Claim 5, the combination of Devarakonda, Peri, Heinze, and Chaballout teaches the limitations of Claim 4, and Chaballout further teaches the following:
The method of claim 4, wherein the multi-task encoder-only transformer neural network is configured to perform a multi-class classification task (The NLP tools perform text classification, wherein the text classification is used to associate medical coding to healthcare reports, e.g. see Chaballout [0030], wherein the medical coding may be in the form of ICD-10 diagnosis code or CPT service codes that include approximately 70,000 codes each, e.g. see Chaballout [0026] and [0045]. That is, the text classification operation comprises a determination of (i.e. a multi-class classification task) whether the text corresponds to a diagnosis and/or service.).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of healthcare to modify the combination of Devarakonda, Peri, and Heinze to incorporate the multi-class classification task as taught by Chaballout in order to automatically objectively analyze the medical records and avoid misclassification of medical codes, e.g. see Chaballout [0003].
Regarding Claim 6, the combination of Devarakonda, Peri, Heinze, and Chaballout teaches the limitations of Claim 5, and Chaballout further teaches the following:
The method of claim 5, wherein the multi-class classification task is to classify one or more words in an input phrase into one of a plurality of categories including (i) problem, (ii) body part, (iii) qualifier, and (iv) procedure (The text classification is used to associate medical coding to healthcare reports, e.g. see Chaballout [0030], wherein the medical coding may be in the form of ICD-10 diagnosis (i.e. problem) code or CPT service (i.e. procedure) codes that include approximately 70,000 codes each, e.g. see Chaballout [0026] and [0045]. That is, the text classification operation determines whether the text corresponds to a diagnosis (i.e. a problem) and/or service (i.e. a procedure).).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of healthcare to modify the combination of Devarakonda, Peri, and Heinze to incorporate the types of classification tasks as taught by Chaballout in order to automatically objectively analyze the medical records and avoid misclassification of medical codes, e.g. see Chaballout [0003].
Regarding Claim 7, the combination of Devarakonda, Peri, Heinze, and Chaballout teaches the limitations of Claim 4, and Chaballout further teaches the following:
The method of claim 4, wherein the multi-task encoder-only transformer neural network is a Bidirectional Encoder Representations from Transformers (BERT) neural network (The NLP tools used to perform the analysis includes a bidirectional encoder representation (BERT) (i.e. a multi-task encoder-only transformer neural network), e.g. see Chaballout [0044].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of healthcare to modify the combination of Devarakonda, Peri, and Heinze to incorporate the BERT as taught by Jackson in order to automatically objectively analyze the medical records and avoid misclassification of medical codes, e.g. see Chaballout [0003].
Claims 8-10, 16-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Devarakonda, Peri, and Heinze in view of Kitamura (US 2022/0188513), further in view of Atallah (US 2021/0397792).
Regarding Claim 8, the combination of Devarakonda, Peri, and Heinze teaches the limitations of Claim 1, but does not teach and Kitamura teaches the following: The method of claim 1, wherein, for each of the one or more text spans, matching, using the text matcher, the text span with the respective ontology entity from the ontology comprises:
dividing the respective input phrase identified by the text span into a plurality of components (The system divides sentences contained in an input document into words (i.e. components), e.g. see Kitamura [0091].);
for each of the plurality of components, generating a set of component alternatives, wherein the component alternatives in the set (i) are ontology entities from the ontology and (ii) represent different ways to refer to a same concept that the component refers to, and wherein each component alternative in the set is associated with a component cost that represents a similarity in meaning between the component alternative and the component (The system identifies synonym vectors (i.e. component alternatives) for the words and sentences, e.g. see Kitamura [0092]-[0094], wherein the synonyms are chosen from topics (i.e. an ontology), for example words relating to music, e.g. see Kitamura [0086] and [0101], Fig. 5, and wherein the synonym vectors represent similar meanings, e.g. see Kitamura [0092]-[0094].);
generating, from the component alternatives generated for the plurality of components, a plurality of alternative writings for the respective input phrase identified by the text span, each alternative writing is associated with a phrase cost computed based on the costs of the component alternatives (The generated synonyms include synonyms for words and sentences, and the synonyms are determined based on similarities (i.e. costs), e.g. see Kitamura [0092]-[0094].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of content recognition to modify the combination of Devarakonda, Peri, and Heinze to incorporate the alternative determination steps as taught by Kitamura in order to ensure the consistency and quality of the proposed content, e.g. see Kitamura [0003]-[0004].
But the combination of Devarakonda, Peri, Heinze, and Kitamura does not teach, and Atallah teaches the following:
selecting, from the ontology, the respective output ontology entity that matches with an alternative writing that has a minimum phrase cost among the plurality of alternative writings (The system selects synonyms that exceed a similarity threshold, e.g. Atallah [0063]-[0064] and [0073].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of content recognition to modify the combination of Devarakonda, Peri, Heinze, and Kitamura to incorporate the selecting synonyms that exceed the similarity threshold as taught by Atallah in order to ensure that the synonyms chosen have high enough similarity to an input to be included, e.g. see Atallah [0063].
Regarding Claim 9, the combination of Devarakonda, Peri, Heinze, Kitamura, and Atallah teaches the limitations of Claim 8, and Kitamura further teaches the following:
The method of claim 8, wherein for each of the plurality of components, generating a set of component alternatives comprises: applying one or more transformations to the component, wherein the one or more transformations include at least one of (i) correcting the component, (ii) finding a synonym of the component (The system determines synonyms for the words and sentences, e.g. see Kitamura [0092]-[0094].), or (ii) stemming the component.
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of content recognition to modify the combination of Devarakonda, Peri, Heinze, and Atallah to incorporate the alternative determination steps as taught by Kitamura in order to ensure the consistency and quality of the proposed content, e.g. see Kitamura [0003]-[0004].
Regarding Claim 10, the combination of Devarakonda, Peri, Heinze, Kitamura, and Atallah teaches the limitations of Claim 8, and Atallah further teaches the following: The method of claim 8, wherein generating, from the component alternatives generated for the plurality of components, the plurality of alternative writings for the respective input phrase identified by the text span comprises:
applying one or more transformations to the component alternatives generated for the plurality of components, wherein the one or more transformations include one or more of combining the component alternatives, adding a word to the component alternatives, dropping a word in the component alternatives (The system removes (i.e. drops) words that are below a similarity threshold, e.g. see Atallah [0069].), or changing an order of the component alternatives.
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the art of content recognition to modify the combination of Devarakonda, Peri, Heinze, and Kitamura to incorporate dropping words that do not meet the similarity threshold as taught by Atallah in order to ensure that the synonyms chosen have high enough similarity to an input to be included, e.g. see Atallah [0063].
Regarding Claims 16-17 and 20, the limitations of Claims 16-17 and 20 are substantially similar to those claimed in Claims 8-9, with the sole difference being that Claims 8-9 recite a method, whereas Claims 16-17 recite the functions of a system executed by a computer, and Claim 20 recites a non-transitory computer storage media whose functions are executed by a computer. Specifically pertaining to Claim 16-17 and 20, Examiner notes that Devarakonda teaches a system and a computer program product including a computer readable storage media, e.g. see Devarakonda [0042]-[0043] and [0048], and hence the grounds of rejection provided above for Claim 8-9 are similarly applied to Claims 16-17 and 20.
Claims 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Devarakonda, Peri, and Heinze in view of Syed-Mahmood (US 2020/0185084).
Regarding Claim 11, the combination of Devarakonda, Peri, and Heinze teaches the limitations of Claim 2, and Devarakonda further teaches the following: The method of claim 2, wherein aggregating one or more clinical conditions related to one or more output ontology entities matched to one or more text spans in the one or more clinical notes comprises:
grouping the one or more clinical conditions into one or more groups, wherein the one or more clinical conditions in each group are related to a same condition (The system automatically groups the highest ranking candidate medical problems based on a known medical problem classification hierarchy that fall under a broader category of problem classification, e.g. see Devarakonda [0020].),
removing, from the one or more groups, one or more clinical conditions that are ruled out (Certain candidate problems may be removed from the group of candidates, e.g. see Devarakonda [0030].),
grouping the one or more groups into one or more sub-groups that each including clinical conditions related to each other (The group of candidate problems may be narrowed, e.g. see Devarakonda [0020] – that is, the remaining candidates in the narrowed group comprises a sub-group.).
But the combination of Devarakonda, Peri, and Heinze does not teach and Syed-Mahmood teaches the following:
for each of the one or more sub-groups, classifying, using a classification neural network, the clinical conditions in the sub-group into a plurality of condition categories (The system includes a deep neural network based classifier that determines a severity of a condition based on an normality/abnormality score, e.g. see Syed Mahmood [0025] and [0054].); and
ranking the clinical conditions in each condition category according to a severity and recent of the clinical conditions (The system ranks the severity of patient conditions, e.g. see Syed-Mahmood [0025] and [0054].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the healthcare to modify the combination of Devarakonda, Peri, and Heinze to incorporate categorizing patient conditions according to severity as taught by Syed-Mahmood in order to enable medical personnel to focus on more urgent cases, e.g. see Syed-Mahmood [0025].
Regarding Claim 12, the combination of Devarakonda, Peri, Heinze, and Syed-Mahmood teaches the limitations of Claim 11, and Syed-Mahmood further teaches the following:
The method of claim 11, wherein the plurality of condition categories includes one or more of active conditions, historical conditions, procedures, or symptoms (The system determines the severity of a patient condition (i.e. either an active or a historical condition, and/or a symptom) based on a normality/abnormality score, e.g. see Syed-Mahmood [0025] and [0054].).
Furthermore, before the effective filing date, it would have been obvious to one ordinarily skilled in the healthcare to modify the combination of Devarakonda and Peri to incorporate the patient condition categories as taught by Syed-Mahmood in order to enable medical personnel to focus on more urgent cases, e.g. see Syed-Mahmood [0025].
Response to Arguments
Applicant’s arguments, see Remarks, filed July 2, 2025, with respect to the rejections of Claims 1-20 under 35 U.S.C. 101 have been fully considered but are not persuasive.
Applicants allege that the claimed invention is patent eligible because even if it recites an abstract idea, it nonetheless integrates any abstract idea into a practical application because it provides an improvement in the functioning of a computer or an improvement to other technology or technical field, e.g. see pgs. 9-11 of Remarks – Examiner disagrees.
The language cited by Applicant from the as-filed Specification discloses that the execution of the claimed invention results in a more accurate analysis and extraction of terms from the clinical documents. However, even assuming, arguendo, that the claimed invention achieves this result, this nonetheless represents an improvement to the abstract idea of a mental process (e.g. a healthcare provider manually reading and analyzing a healthcare document) and/or a certain method of organizing human activities (e.g. following analysis/extraction rules or instructions in analyzing the healthcare document), and an improvement to an abstract idea itself is not an improvement in technology, e.g. see MPEP 2106.05(a)(II). For example, a healthcare provider reading a clinical document already performs the operation of reading a phrase and categorizing the words of the phrase (e.g. “patient” being a noun versus an adjective) in order to properly interpret the meaning of the phrase. Thus, the amended claim language merely constitutes rules or instructions for operations that are performed on a routine basis mentally when analyzing a clinical document, and is not properly interpreted as an improvement to the functioning of the computer itself and/or an improvement to another technical field.
For the aforementioned reasons, Claims 1-20 are rejected under 35 U.S.C. 101.
Applicant’s arguments, see Remarks, filed July 2, 2025, regarding the rejections of Claims 1-20 under 35 U.S.C. 103 have been considered but are moot because the arguments do not apply to any of the references being used in the current rejection. As stated above, the newly amended claim limitations of independent Claims 1, 14, and 18 have necessitated the new grounds of rejection, and Heinze is now cited to address the newly amended claim limitations.
Conclusion
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 JOHN P GO whose telephone number is (703)756-1965. The examiner can normally be reached Monday-Friday 9am-6pm PST.
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, PETER H CHOI can be reached at (469)295-9171. 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.
/JOHN P GO/Examiner, Art Unit 3681
/PETER H CHOI/Supervisory Patent Examiner, Art Unit 3681