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 .
Status of the Claims
The office action is in response to the claims filed on March 27, 2025, for the application filed on March 27, 2025, which claims priority to Indian Application No. IN202441024609 filed on March 27, 2024. Claims 1 – 15 are currently pending and have been examined as discussed below.
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, 3, 5 – 8, 10, and 12 – 15 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.
Examiners should determine whether a claim satisfies the criteria for subject matter eligibility by evaluating the claim in accordance with the flowchart in MPEP 2016(III).
Eligibility Step 1:
Under Step 1 of the 2019 Revised Patent Subject Matter Eligibility Guidance, it must be determined whether each claim as a whole falls within one of the statutory categories of invention (i.e., a process, machine, manufacture, or composition of matter). See MPEP 2106.03. In the instant application, claims 1 – 7 are directed to a method (i.e., a process); claims 8 – 14 are directed to a clinical decision support tool or system (i.e., a machine); and claim 15 is directed to a non-transitory computer readable medium (i.e., an article of manufacture).
While each one of claims 1 – 15 appears to fall within one or more statutory categories of invention, the Office has determined that the full eligibility analysis is required because there is doubt as to whether the applicant is effectively seeking coverage for a judicial exception itself. The eligibility of each claim is not self-evident at least because each claim as a whole did not appear to clearly improve a technology or computer functionality. To the contrary, each claim as a whole appeared to merely apply one or more judicial exceptions on a computer.
Accordingly, it has been determined that each one of claims 1 – 15 as a whole falls within one or more statutory categories under Step 1, and the Office proceeds with the full eligibility analysis (the Alice/Mayo test described in MPEP 2106(III)) as discussed below.
Eligibility Step 2A, Prong One:
Under Step 2A, Prong One of the 2019 Revised Patent Subject Matter Eligibility Guidance, it must be determined whether each claim is directed to one or more of the judicial exceptions (i.e., an abstract idea, law of nature, or natural phenomenon). See MPEP 2106.04(II)(A)(1). After evaluation, it has been determined that claims 1 – 15 are directed to judicial exceptions because claims 1 – 15 recite an abstract idea. (The Office will not determine that a claim is not directed to a judicial exception under Step 2A, Prong One merely because the claim further recites one or more additional elements beyond the judicial exception.)
Independent claims 1, 8, and 15 are determined to be directed to a judicial exception including abstract ideas (i.e., mental process). Representative claim 8 recites the mental process identified in bold as:
A clinical decision support tool for assisting clinicians in making real time decisions for resuscitation modalities in neonatal shock syndromes, the clinical decision support tool comprising:
a processor (104); and
a memory (202) communicatively coupled to the processor, wherein the memory (202) stores processor instructions, which when executed by the processor (104), cause the processor (104) to:
receive medical data corresponding to a neonate diagnosed with shock;
extract one or more features from the medical data, wherein the one or more features are indicative of perfusion status, possible etiology, type, and severity of shock, in the neonate;
select at least one machine learning model (ML) from a plurality of ML models based on the one or more features;
predict, via at least one ML model, an optimal treatment modality for the neonate, wherein the optimal treatment modality is one of fluid boluses or pressor support; and
assist a clinician to provide the optimal treatment modality to the neonate based on predicting, wherein assisting specifies a number and type of the fluid boluses for the neonate, or a type and dose of the pressor support for the neonate, and wherein the assisting is based on the etiology and severity of shock in the neonate.
Claim 8 recites the combination of limitations identified as “assisting clinicians in making real time decisions for resuscitation modalities in neonatal shock syndromes,” “extract one or more features from the medical data, wherein the one or more features are indicative of perfusion status, possible etiology, type, and severity of shock, in the neonate,” “predict, …, an optimal treatment modality for the neonate, wherein the optimal treatment modality is one of fluid boluses or pressor support,” and “assist a clinician to provide the optimal treatment modality to the neonate based on predicting, wherein assisting specifies a number and type of the fluid boluses for the neonate, or a type and dose of the pressor support for the neonate, and wherein the assisting is based on the etiology and severity of shock in the neonate.” A broadest reasonable interpretation of this combination amounts to determining the optimal treatment modality to the neonate. This activity may be practically performed in the human mind using observation, evaluation, judgment, and opinion, and thus represents an abstract idea falling in the “mental process” grouping.. With the exception of generic computer-implemented steps, there is nothing in the claim itself that forecloses them from being performed by a human, mentally or with tools such as pen and paper. Thus, this activity is an abstract idea in the "mental process" grouping.
Accordingly, claims 1, 8, and 15 are recite judicial exceptions under Step 2A, Prong One.
Dependent claims 3, 5 – 7, 10, and 12 – 14 are directed to one or more judicial exceptions (i.e., abstract idea exceptions) under Step 2A, Prong One of the full eligibility analysis as follows:
Regarding claims 3, 5 – 7, 10, and 12 – 14, each combination of limitations identified in bold as “test the … model on new data to evaluate accuracy and performance of the at least one … model” in claims 3 and 10, “the medical data is received from one or more of electronic health records, bedside monitors, laboratory tests, imaging devices, or wearable sensors” in claims 5 and 12, “the medical data comprises medical history of the neonate, vital signs of the neonate, laboratory results of the neonate, and other related clinical and demographic information of the neonate” in claims 6 and 13, and “the plurality of … models comprises decision trees or random forests, …, gradient boosting” in claims 7 and 14 defines the activity of determining the optimal treatment modality to the neonate. This activity may be practically performed in the human mind using observation, evaluation, judgment, and opinion, and thus represents an abstract idea falling in the “mental process” grouping.. With the exception of generic computer-implemented steps, there is nothing in each of claims 3, 5 – 7, 10, and 12 – 14 themselves that forecloses them from being performed by a human, mentally or with tools such as pen and paper.
Accordingly, claims 3, 5 – 7, 10, and 12 – 14 are recite judicial exceptions under Step 2A, Prong One.
Eligibility Step 2A, Prong Two:
Claims 1, 8, and 15 recite additional limitations beyond the judicial exceptions. Representative claim 8 recites the additional limitations identified in bold as:
A clinical decision support tool for assisting clinicians in making real time decisions for resuscitation modalities in neonatal shock syndromes, the clinical decision support tool comprising:
a processor (104); and
a memory (202) communicatively coupled to the processor, wherein the memory (202) stores processor instructions, which when executed by the processor (104), cause the processor (104) to:
receive medical data corresponding to a neonate diagnosed with shock;
extract one or more features from the medical data, wherein the one or more features are indicative of perfusion status, possible etiology, type, and severity of shock, in the neonate;
select at least one machine learning model (ML) from a plurality of ML models based on the one or more features;
predict, via at least one ML model, an optimal treatment modality for the neonate, wherein the optimal treatment modality is one of fluid boluses or pressor support; and
assist a clinician to provide the optimal treatment modality to the neonate based on predicting, wherein assisting specifies a number and type of the fluid boluses for the neonate, or a type and dose of the pressor support for the neonate, and wherein the assisting is based on the etiology and severity of shock in the neonate.
Claim 8 recites the additional limitations identified in bold as “a clinical decision support tool,” “a processor,” “a memory (202) communicatively coupled to the processor, wherein the memory (202) stores processor instructions, which when executed by the processor (104), cause the processor (104) to,” “receive medical data corresponding to a neonate diagnosed with shock,” and “at least one machine learning model (ML) from a plurality of ML models.”
MPEP 2106.05(a) states: “In determining patent eligibility, examiners should consider whether the claim ‘purport(s) to improve the functioning of the computer itself’ or ‘any other technology or technical field.’… [A]n improvement in the abstract idea itself is not an improvement in technology.” Furthermore, MPEP 2106.05(a)(II) states: “Merely adding generic computer components to perform the method is not sufficient.” In the instant application, claim 1 as a whole does not improve the functioning of the processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models; nor does the claim as a whole improve any other technology or technical field. The processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models are general purpose computer components added post-hoc to the abstract idea of determining the optimal treatment modality to the neonate. The claim as a whole improves exclusively upon the abstract idea itself by using conventional and generic computer technology in the nascent but well known environment of machine learning models for merely automating the manual process of determining the optimal treatment modality to the neonate. See MPEP 2106.05(a) citing Credit Acceptance Corp. v. Westlake Services, 859 F.3d 1044, 1055, 123 USPQ2d 1100, 1108-09 (Fed. Cir. 2017). The claim as a whole represents mere instructions to apply the abstract idea to conventional and generic computer technology recited at a high level of generality. See MPEP 2106.05(f). Regarding the consideration under MPEP 2106.05(g), the limitation of “receive medical data corresponding to a neonate diagnosed with shock” is determined to not add no more than insignificant extra-solution activities to the judicial exception. This limitation represents the well-known pre-solution activity of data necessary data gathering because, when looking at the claim as a whole, this limitation represents an activity incidental to the primary process of the claim as a whole (i.e., determining the optimal treatment modality to the neonate) and thus this limitation is merely nominal or tangential additions to the claim. Regarding the consideration under MPEP 2106.05(h), the additional limitations, individually or in combination, also amount to merely indicating a field of use or technological environment in which to apply the judicial exception. In the instant application, the additional limitations (i.e., the processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models) do no more than link the abstract idea (i.e., determining the optimal treatment modality to the neonate) to the particular technological environment of machine learning models. Thus, the additional limitations fail to add an inventive concept to the claims.
Accordingly, in view of these considerations, the Office has determined that each one of Claims 1, 8, and 15 as a whole does not integrate the abstract idea exception into a practical application under Step 2A, Prong Two, and thus each claim as a whole is directed to a judicial exception under Step 2A.
Dependent claims 3, 5 – 7, 10, and 12 – 14 present additional information in tandem with further details regarding elements and the abstract idea from an associated one of independent Claims 1, 8, and 15 and are therefore directed to an abstract idea for similar reasons as given Under Step 2A, Prong One above. Claims 3, 5 – 7, 10, and 12 – 14 do not recite any additional limitations beyond the abstract idea of determining the optimal treatment modality to the neonate. None of these claims recite additional limitations beyond the judicial exception.
Claims 3, 5 – 7, 10, and 12 – 14 recite the limitations of “test the at least one ML model on new data to evaluate accuracy and performance of the at least one ML model” in claims 3 and 10, “the medical data is received from one or more of electronic health records, bedside monitors, laboratory tests, imaging devices, or wearable sensors” in claims 5 and 12, “the medical data comprises medical history of the neonate, vital signs of the neonate, laboratory results of the neonate, and other related clinical and demographic information of the neonate” in claims 6 and 13, “the plurality of ML models comprises decision trees or random forests, support vector machines (SVMs), gradient boosting, recurrent neural networks (RNNs) or long short-term memory (LSTM), transformers, and Bayesian methods” in claims 7 and 14. Regarding claims 3, 5 – 7, 10, and 12 – 14, at best, each claim as a whole amounts to using a general purpose computer to improve an abstract idea (i.e., determining the optimal treatment modality to the neonate) and having the at least one machine learning model (ML), recited at a high level of generality, without giving any details how the associated functional language is performed. See MPEP 2106.05(f). For example, with respect to claims 4 and 11, the claims do not impose any limits on how the hyperparameters are adjusted and what the hyperparameters are, or how the ML model is optimized to assist the clinician. Thus, each claim as a whole amounts to no more than mere instructions to using the generic computer to improve the abstract idea and merely applying the abstract idea to a generic computer. With further respect to claims 5 – 6 and 12 – 13, the limitations of “the medical data is received from one or more of electronic health records, bedside monitors, laboratory tests, imaging devices, or wearable sensors” and “the medical data comprises medical history of the neonate, vital signs of the neonate, laboratory results of the neonate, and other related clinical and demographic information of the neonate” are determined to not add no more than insignificant extra-solution activities to the judicial exception. These limitations represents the well-known pre-solution activity of necessary data gathering (i.e., gathering the medical data) because, when looking at each claim as a whole, this limitation represents an activity incidental to the primary process of the claim as a whole (i.e., determining the optimal treatment modality to the neonate) and thus this limitation is merely nominal or tangential additions to the claim. See MPEP 2106.05(g). Furthermore, each claim as a whole does no more than an attempt to generally link the judicial exception to a field of use (i.e., machine learning). See MPEP 2106.05(h).
Accordingly, the Office has determined that each one of claims 3, 5 – 7, 10, and 12 – 14 as a whole does not integrate the abstract idea exception into a practical application under Step 2A, Prong Two, and thus each claim as a whole is directed to a judicial exception under Step 2A.
Eligibility Step 2B:
Regarding independent claims 1, 8, and 15 , the Office carries over its identification of the additional elements (and combinations thereof) from Step 2A, Prong Two so as to apply the same additional elements in Step 2B. See MPEP 2106.05(II). The Office further carries over its conclusions from the considerations discussed in MPEP 2106.05(a) through (c), (e) through (h) in Step 2A, Prong Two so as to apply the same considerations in Step 2B.
Under Step 2B of the 2019 Revised Patent Subject Matter Eligibility Guidance, it must be determined whether the claim provides an inventive concept by determining if the claims include additional elements or a combination of elements that are sufficient to amount to significantly more than the judicial exception. After evaluation, there is no indication that an additional element or combination of elements are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, each claim as a whole does not provide an improvement to technology or technical field under MPEP 2106.05(a). Each claim as a whole improves exclusively upon the abstract idea itself by using conventional and generic computer technology in the nascent but well known environment of machine learning models for merely automating the manual process of determining the optimal treatment modality to the neonate. The additional limitations amount to mere instructions to apply an abstract idea under MPEP 2106.05(f) and/or necessary data gathering and/or outputting under MPEP 2106.05(g). Each claim as a whole recites the processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models at a high level of generality, with their functions claimed in a merely generic manner such that each claim as a whole represents the well‐understood, routine, and conventional functions of a computer system (i.e., having the processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models) for determining the optimal treatment modality to the neonate. Evidence that the activity of informing care providers regarding relevant patient data and clinical guidelines, thereby enhancing decision making while maintaining provider autonomy, is a well‐understood, routine, and conventional function is provided by Hill (U.S. Pub. No. 2021/0174963 A1).
Furthermore, looking at the limitations individually or as any ordered combination adds nothing that is not already present when looking at each claim as a whole. There is no indication that the individual elements or combinations of elements amount to an inventive concept.
Therefore, independent claims 1, 8, and 15 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Regarding dependent claims 3, 5 – 7, 10, and 12 – 14, the Office carries over its determination from Step 2A, Prong Two that claims 3, 5 – 7, 10, and 12 – 14 do not further recite additional limitations beyond the judicial exception (i.e., the abstract idea of determining the optimal treatment modality to the neonate) so as to apply the same determination in Step 2B. See MPEP 2106.05(II). The Office further carries over its conclusions from the considerations discussed in MPEP 2106.05(a) through (c), (e) through (h) in Step 2A, Prong Two so as to apply the same considerations in Step 2B. The dependent claims merely present additional abstract information in tandem with further details regarding the elements from the independent claims and are, therefore, directed to an abstract idea for similar reasons as given above. Claims 3, 5 – 7, 10, and 12 – 14 do not recite any additional limitations beyond the abstract idea of determining the optimal treatment modality to the neonate.
Each claim as a whole does not provide an improvement to technology or technical field under MPEP 2106.05(a), but rather only improves the abstract idea itself. Each claim as a whole amounts to mere instructions to apply the abstract idea to generic computer components (i.e., the processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models) under MPEP 2106.05(f). The limitations of “the medical data is received from one or more of electronic health records, bedside monitors, laboratory tests, imaging devices, or wearable sensors” and “the medical data comprises medical history of the neonate, vital signs of the neonate, laboratory results of the neonate, and other related clinical and demographic information of the neonate” are determined to not add no more than insignificant extra-solution activities to the judicial exception. These limitations represent the well-known pre-solution activity of necessary data gathering because they are incidental to the primary process of the claim as a whole (i.e., determining the optimal treatment modality to the neonate) and thus those limitations are merely nominal or tangential additions to the claim. Each claim recites the processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models at a high level of generality, with their functions claimed in a merely generic manner such that each claim as a whole represents the well‐understood, routine, and conventional functions of a computer system (i.e., having the processor, the memory, and the at least one machine learning model (ML) from a plurality of ML models) for determining the optimal treatment modality to the neonate. Evidence that the activity of informing care providers regarding relevant patient data and clinical guidelines, thereby enhancing decision making while maintaining provider autonomy, is a well‐understood, routine, and conventional function is provided by Hill (U.S. Pub. No. 2021/0174963 A1).
Therefore, dependent claims 3, 5 – 7, 10, and 12 – 14 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1 – 2, 5 – 9, and 12 – 15 are rejected under 35 U.S.C. 103(a) as being unpatentable over Hill (U.S. Pub. No. 2021/0174963 A1) in view of NPL Chang, Holder (U.S. Pub. No. 2022/0175324 A1), and NPL Elsayed.
Regarding independent claims 1, 8, and 15, Hill teaches the limitations of representative claim 8 identified in bold as:
A clinical decision support tool for assisting clinicians in making real time decisions for resuscitation modalities in neonatal shock syndromes (Paragraphs [0037] and [0126] – [0127] of Hill. In the instant application, the broadest reasonable interpretation of “a clinical decision support tool for assisting clinicians in making real time decisions for resuscitation modalities in neonatal shock syndromes” reads on the Clinical Decision Support (CDS) knowledge module in Hill (Paragraphs [0037] and [0126] – [0127]) of the Transfusion Appropriateness Algorithm (TAA) that is tailored to neonatal patients and is a real-time algorithm that accounts for a repository of high-quality, evidence-based, tested CDS knowledge modules that may be used to account for any specific transfusion rules data that is applicable to the particular patient/context (e.g., regarding timing of transfusion (i.e., bolus or resuscitation modality), level of severity required before authorizing a transfusion, etc.).), the clinical decision support tool comprising:
a processor (104) (Paragraph [0042] of Hill. In the instant application, the broadest reasonable interpretation of “a processor (104)” reads on the processor in Hill (Paragraph [0042]).) ; and
a memory (202) communicatively coupled to the processor, wherein the memory (202) stores processor instructions, which when executed by the processor (104) (Paragraph [0043] of Hill. In the instant application, the broadest reasonable interpretation of “a memory (202) communicatively coupled to the processor, wherein the memory (202) stores processor instructions, which when executed by the processor (104)” reads on the memory in Hill (Paragraph [0043]) operatively coupled to at least one processor, with the memory storing computer/machine executable components such that the components can be executed by the at least one processor.), cause the processor (104) to:
receive medical data corresponding to a neonate diagnosed with shock (Paragraphs [0009], [0037], and [0126] – [0127] of Hill. In the instant application, the broadest reasonable interpretation of “medical data corresponding to a neonate” reads on the Clinical Decision Support (CDS) knowledge module in Hill (Paragraphs [0009], [0037], and [0126] – [0127]) of the Transfusion Appropriateness Algorithm (TAA) that is tailored to neonatal patients (i.e., neonatal patient data).);
extract one or more features from the medical data, wherein the one or more features are indicative of perfusion status, possible etiology, type, and severity of shock, in the neonate;
select at least one machine learning model (ML) from a plurality of ML models based on the one or more features;
predict, via at least one ML model, an optimal treatment modality for the neonate, wherein the optimal treatment modality is one of fluid boluses or pressor support (Paragraphs [0009], [0037], and [0126] – [0127] of Hill. In the instant application, the broadest reasonable interpretation of “treatment modality for the neonate” reads on the Clinical Decision Support (CDS) knowledge module in Hill (Paragraphs [0009], [0037], and [0126] – [0127]) of the Transfusion Appropriateness Algorithm (TAA) that is tailored to neonatal patients.); and
assist a clinician to provide the optimal treatment modality to the neonate based on predicting, wherein assisting specifies a number and type of the fluid boluses for the neonate, or a type and dose of the pressor support for the neonate, and wherein the assisting is based on the etiology and severity of shock in the neonate (Paragraphs [0009], [0037] – [0038], [0126] – [0127], and [0044] of Hill. In the instant application, the broadest reasonable interpretation of “for the neonate” reads on the Clinical Decision Support (CDS) knowledge module in Hill (Paragraphs [0009], [0037] and [0126] – [0127]) of the Transfusion Appropriateness Algorithm (TAA) that is tailored to neonatal patients.. The broadest reasonable interpretation of “assist a clinician to provide the optimal treatment modality to the neonate based on predicting, wherein assisting specifies a number and type of the fluid boluses …, or a type and dose of the pressor support for the neonate, and wherein the assisting is based on the etiology and severity of shock in the neonate” reads on the activity in Hill (Paragraphs [0038] and [0044]) of assisting the provider in making appropriate clinical decisions, such as determining the type of blood transfusion procedure (e.g., blood transfusion procedures, plasma transfusion procedures, platelet transfusion procedures, and cryoprecipitate transfusion procedures), the amount of blood/blood product for the transfusion procedure, and the recommended timing for performing the transfusion procedure.).
Hill does not appear to explicitly disclose, but NPL Chang teaches the limitation identified in bold as “receive medical data corresponding to a neonate diagnosed with shock” (First Paragraph to Third Paragraph in Second Column on Page 2 of NPL Chang. In the instant application, the broadest reasonable interpretation of “receive medical data corresponding to … diagnosed with shock” reads on the activity in NPL Chang (First Paragraph to Third Paragraph on Page 2) of collecting Electronic Health Record (HER) data of a large regional healthcare system including 4,012 Cardiogenic Shock (CS) patients, 782 hypovolemic shock patients, 16,916 septic shock patients, and 93,581 non-shock patients.).
Hill does not appear to explicitly disclose, but NPL Chang teaches the limitation identified in bold as “extract one or more features from the medical data, wherein the one or more features are indicative of perfusion status, possible etiology, type, and severity of shock, in the neonate” (Third Paragraph in Second Column on Page 2; Last Paragraph in Second Column on Page 2 to First Paragraph in First Column on Page 3; Second Paragraph in Second Column on Page 3; Last Paragraph in Second Column on Page 3 of NPL Chang. In the instant application, the broadest reasonable interpretation of “extract one or more features from the medical data, wherein the one or more features are indicative of perfusion status, possible etiology, type, and severity of shock, in the neonate” reads on the activity in NPL Chang (First Paragraph to Third Paragraph on Page 2) of extracting one or more features from a patient cohort including 4,012 Cardiogenic Shock (CS) patients, 782 hypovolemic shock patients, 16,916 septic shock patients, and 93,581 non-shock patients, with the features including a blood pressure measurement and any ancillary clinical evidence of hypoperfusion (including hypovolemia, medications, arrhythmia, septic shock rather than the onset of cardiogenic shock), types of shock (e.g., CS, septic shock, hypovolemic shock etc.), and CS patients with the highest Troponin levels and Septic shock patients having the highest temperature.).
Hill does not appear to explicitly disclose, but Holder teaches the limitation identified in bold as “select at least one machine learning model (ML) from a plurality of ML models based on the one or more features” (Paragraphs [0101] – [0102] of Holder. In the instant application, the broadest reasonable interpretation of “select at least one machine learning model (ML) from a plurality of ML models based on the one or more features” reads on the activity in Holder (Paragraphs [0101] – [0102]) of generating multiple machine learning models each associated with one or more adverse or non-adverse outcomes.).
Hill does not appear to explicitly disclose, but Holder teaches the limitation identified in bold as “predict, via at least one ML model, an optimal treatment modality for the neonate, wherein the optimal treatment modality is one of fluid boluses or pressor support” (Paragraphs [0101] – [0102] of Holder. In the instant application, the broadest reasonable interpretation of “at least one ML model” reads on the multiple machine learning models in Holder (Paragraphs [0101] – [0102]) each associated with one or more adverse or non-adverse outcomes.).
Hill does not appear to explicitly disclose, but NPL Elsayed teaches the limitation identified in bold as “predict, via at least one ML model, an optimal treatment modality for the neonate, wherein the optimal treatment modality is one of fluid boluses or pressor support” (First Paragraph in First Column on Page 1285; First Paragraph in First Column on Page 1287. In the instant application, the broadest reasonable interpretation of “predict … an optimal treatment modality …, wherein the optimal treatment modality is one of fluid boluses or pressor support” reads on the activities in NPL Elsayed (First Paragraph in First Column on Page 1285; First Paragraph in First Column on Page 1287) of selecting dobutamine after a bolus of volume expander and choosing vasopressor, either norepinephrine, vasopressin, or terlipressin only if there is evidence of heart underfilling.).
Hill does not appear to explicitly disclose, but NPL Chang teaches the limitation identified in bold as “assist a clinician to provide the optimal treatment modality to the neonate based on predicting, wherein assisting specifies a number and type of the fluid boluses for the neonate, or a type and dose of the pressor support for the neonate, and wherein the assisting is based on the etiology and severity of shock in the neonate” (Third Paragraph in Second Column on Page 2; Last Paragraph in Second Column on Page 2 to First Paragraph in First Column on Page 3; Second Paragraph in Second Column on Page 3; Last Paragraph in Second Column on Page 3 of NPL Chang. In the instant application, the broadest reasonable interpretation of “the assisting is based on the etiology and severity of shock in the neonate” reads on the activity in NPL Chang (First Paragraph to Third Paragraph on Page 2) of extracting one or more features from a patient cohort, with the features including a blood pressure measurement and any ancillary clinical evidence of hypoperfusion (including hypovolemia, medications, arrhythmia, septic shock rather than the onset of cardiogenic shock), and CS patients with the highest Troponin levels and Septic shock patients having the highest temperature.).
Therefore, it would have been obvious to one of ordinary skill in the art of medical data mining at the time of filing to modify the clinical decision support tool and method of Hill to: include the activity of receiving medical data corresponding to a neonate diagnosed with shock, and include the activity of extracting one or more features from the medical data, wherein the one or more features are indicative of perfusion status, possible etiology, type, and severity of shock, in the neonate, as taught by NPL Chang (First Paragraph to Third Paragraph in Second Column on Page 2; Last Paragraph in Second Column on Page 2 to First Paragraph in First Column on Page 3; Second Paragraph in Second Column on Page 3; Last Paragraph in Second Column on Page 3), in order to predict clinical outcomes and provide adequate information in a manner to influence patient management and therefore increase chances of improve survival (First Paragraph in First Column on Page 2 of NPL Chang); include the activity of selecting at least one machine learning model (ML) from a plurality of ML models based on the one or more features, as taught by Holder (Paragraphs [0101] – [0102]), in order to provide a comprehensive and accurate monitoring system that takes many types, attributes, features, and/or patterns of fetal data into account when predicting one or more fetal outcomes (Paragraph [0030] of Holder); and include the activity of predicting, via at least one ML model, an optimal treatment modality for the neonate, wherein the optimal treatment modality is one of fluid boluses or pressor support, as taught by NPL Elsayed (First Paragraph in First Column on Page 1285; First Paragraph in First Column on Page 1287), in order to focus on hemodynamic instability in infants with normal cardiac anatomy and integrate different monitoring techniques to understand the underlying pathophysiologic mechanisms and formulate a physiologic-based medical recommendation and approach (Abstract of NPL Elsayed).
Regarding claims 2 and 9, Hill as modified by NPL Chang, Holder, and NPL Elsayed and applied to an associated one of claims 1 and 8 teaches the limitation identified in bold as “train the at least one ML model, wherein the at least one ML model is trained on a dataset of the medical data and the one or more features extracted” (First Paragraph to Sixth Paragraph in First Column on Page 4 of NPL Chang. In the instant application, the broadest reasonable interpretation of “train the at least one ML model, wherein the at least one ML model is trained on a dataset of the medical data and the one or more features extracted” reads on the activity in NPL Chang (First Paragraph to Sixth Paragraph in First Column on Page 4) of training the model on the input feature values measured at 2 and 1 h before the intervention onset time for Cardiogenic Shock (CS) patients and the input feature values (1) measured at 3–12 h before the intervention onset for CS patients; and (2) measured at 1–12 h before the intervention onset for septic/hypovolemic shock patients and non-shock patients.)
Regarding claims 5 and 12, Hill as modified by NPL Chang, Holder, and NPL Elsayed and applied to an associated one of claims 1 and 8 teaches the limitation identified in bold as “the medical data is received from one or more of electronic health records, bedside monitors, laboratory tests, imaging devices, or wearable sensors” (Paragraph [0050] of Hill. In the instant application, the broadest reasonable interpretation of “the medical data is received from one or more of electronic health records, bedside monitors, laboratory tests, imaging devices, or wearable sensors” reads on the patient data in Hill (Paragraph [0050]) including relevant medical history information for a patient, such as information regarding underlying conditions/comorbidities (e.g., chronic anemia, and other relevant comorbidities), past treatments, past procedures/surgeries (e.g., including past transfusion procedures and information regarding type, timing, location, and amount of the transfusions), past diagnosis, family medical history, known allergies, past laboratory tests and associated reports/results, past imaging studies and associated reports/results, blood type, implanted medical devices (IMDs) worn by the patient, and the like, with the medical history information being extracted from one or more EMRs and/or electronic heath records (EHRs) for the patient.).
Regarding claims 6 and 13, Hill as modified by NPL Chang, Holder, and NPL Elsayed and applied to an associated one of claims 1 and 8 teaches the limitation identified in bold as “the medical data comprises medical history of the neonate, vital signs of the neonate, laboratory results of the neonate, and other related clinical and demographic information of the neonate” (Paragraphs [0050] and [0053] of Hill. In the instant application, the broadest reasonable interpretation of “the medical data comprises medical history of the neonate, vital signs of the neonate, laboratory results of the neonate, and other related clinical and demographic information of the neonate” reads on the patient data in Hill (Paragraphs [0050] and [0053]) including relevant medical history information for a patient, such as information regarding underlying conditions/comorbidities (e.g., chronic anemia, and other relevant comorbidities), past treatments, past procedures/surgeries (e.g., including past transfusion procedures and information regarding type, timing, location, and amount of the transfusions), past diagnosis, family medical history, known allergies, past laboratory tests and associated reports/results, past imaging studies and associated reports/results, blood type, implanted medical devices (IMDs) worn by the patient and further including non-clinical information for the respective patients that can be correlated to their need/appropriateness for a transfusion procedure with respect to type, quantity, type and timing (e.g., demographic information for the patient including the patient's age, gender, ethnicity, height/weight, body mass index (BMI), and home location), physician/clinician reports and notes (i.e., regarding the current state of the patient, recommended procedures, clinical orders, behavioral observations, or other practitioner input), blood transfusions for patients grouped by location, by department, by DRG, by severity, by admittance timing, by age, by severity level, by provider, by blood type, or by insurance provider.).
Regarding claims 7 and 14, Hill as modified by NPL Chang, Holder, and NPL Elsayed and applied to an associated one of claims 1 and 8 teaches the limitation identified in bold as “the plurality of ML models comprises decision trees or random forests, support vector machines (SVMs), gradient boosting, recurrent neural networks (RNNs) or long short-term memory (LSTM), transformers, and Bayesian methods” (Paragraphs [0101] – [0102] of Holder. In the instant application, the broadest reasonable interpretation of “the plurality of ML models comprises decision trees or random forests, support vector machines (SVMs), gradient boosting, recurrent neural networks (RNNs) or long short-term memory (LSTM), transformers, and Bayesian methods” reads on the activity in Holder (Paragraphs [0101] – [0102]) of generating of generalized or specialized machine learning applications, including any one or more of deep multilayer perceptrons (MLP), convolutional or deep convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory neural networks (LSTM), artificial neural network (ANN), deep belief networks (DBN), Bayesian networks, autoregressive models, fuzzy-logic systems, hidden Markov models (HMM), Gaussian process models, etc. In one example, the techniques of the disclosure develop prediction models using a Convolutional Neural Network (CNN) and/or a Recurrent Neural Network (RNN) approach based on the Keras Framework with a Tensorflow (Google, Mountain View, Calif.).).
Claims 3 – 4 and 10 – 11 are rejected under 35 U.S.C. 103(a) as being unpatentable over Hill as modified by NPL Chang, Holder, and NPL Elsayed and applied to claims 2 and 9, and further in view of Hong (U.S. Pub. No. 2023/0187067 A1).
Regarding claims 3 and 10, Hill as modified by NPL Chang, Holder, and NPL Elsayed and applied to an associated one of claims 2 and 9 does not appear to explicitly disclose, but Hong teaches the limitation identified in bold as “test the at least one ML model on new data to evaluate accuracy and performance of the at least one ML model” (Paragraphs [0114] – [0115] of Hong. In the instant application, the broadest reasonable interpretation of “test the at least one ML model on new data to evaluate accuracy and performance of the at least one ML model” reads on the activity in Hong (Paragraphs [0114] – [0115]) of testing new models for predictive accuracy in terms of the probability of SIRS onset in the patient by incorporating new patient measurements into the models.)
Therefore, it would have been obvious to one of ordinary skill in the art of medical data mining at the time of filing to modify the clinical decision support tool and method of Hill to: include the activity of testing the at least one ML model on new data to evaluate accuracy and performance of the at least one ML model, as taught by Hong (Paragraphs [0114] – [0115]), in order to predict the onset of Systemic Inflammatory Response Syndrome (SIRS), prior to the appearance of clinical symptoms would enable physicians to initiate therapy in an expeditious manner, thereby improving outcomes (i.e., whether the patients that have non-infectious SIRS or the patients have SIRS that progress to Sepsis) (Paragraph [0024] of Hong).
Regarding claims 4 and 11, Hill as modified by NPL Chang, Holder, and NPL Elsayed and applied to an associated one of claims 2 and 9 teaches the limitation identified in bold as:
optimize the at least one ML model by adjusting hyperparameters, extracting different features from the one or more features, or combining two or more ML models from the plurality of ML models, based on feedback received from the clinician (Paragraphs [0083] and [0114] of Hong. In the instant application, the broadest reasonable interpretation of “optimize the at least one ML model by adjusting hyperparameters, extracting different features from the one or more features, or combining two or more ML models from the plurality of ML models, based on feedback received from the clinician” reads on the activity in Hong (Paragraphs [0083] and [0114]) of optimizing models and parameters to select the best classifier and combining Nearest Neighbors, Linear SVM (support vector machine), RBF SVM (radial basis function support vector machine), Decision Trees, Random Forest (RF), AdaBoost, Naive Bayes, and Logistic Regression (LR) classifiers.); and
deploy at least one ML model optimized in clinical settings to assist the clinician in making informed treatment decisions (Paragraph [0114] of Hong. In the instant application, the broadest reasonable interpretation of “deploy at least one ML model optimized in clinical settings to assist the clinician in making informed treatment decisions” reads on the activity in Hong (Paragraph [0114]) of using the relative Predictive Results of the model as a basis upon which a hospital makes the decision on whether to begin treatment for SIRS or sepsis in an asymptomatic patient.).
Therefore, it would have been obvious to one of ordinary skill in the art of medical data mining at the time of filing to modify the clinical decision support tool and method of Hill to: include the activity of optimizing the at least one ML model by adjusting hyperparameters, extracting different features from the one or more features, or combining two or more ML models from the plurality of ML models, based on feedback received from the clinician, and include the activity of deploying at least one ML model optimized in clinical settings to assist the clinician in making informed treatment decisions, as taught by Hong (Paragraphs [0083] and [0114]), in order to predict the onset of Systemic Inflammatory Response Syndrome (SIRS), prior to the appearance of clinical symptoms would enable physicians to initiate therapy in an expeditious manner, thereby improving outcomes (i.e., whether the patients that have non-infectious SIRS or the patients have SIRS that progress to Sepsis) (Paragraph [0024] of Hong).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VINCENT CAESAR ILAGAN whose telephone number is (703) 756-1639. The examiner can normally be reached Monday - Friday 8:30 am - 6:00pm.
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, Jason B. Dunham, can be reached on (571) 272-8109. 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.
/V.C.I./Examiner, Art Unit 3686
/DEVIN C HEIN/Examiner, Art Unit 3686
Prosecution Insights